{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qG97kysNGR3z"
      },
      "source": [
        "# **🤖 Data Analysis & Visualization**\n",
        "### Project: E-Commerce Customer Intelligence — Food & Grocery Products\n",
        "**Business Question:** *How can an online food retailer reduce customer churn and optimize product positioning by analyzing review sentiment (qualitative) and rating/helpfulness patterns (quantitative)?*\n",
        "\n",
        "**Dataset:** Amazon Fine Food Reviews + Synthetic Enrichment"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-FyYQK03GR30"
      },
      "source": [
        "## **1.** 📦 Install required packages"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1cRvdI6-GR30",
        "outputId": "02d59df3-0f1c-4337-a12a-bafa1b673f23"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[?25l   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/126.0 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m126.0/126.0 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h✅ All packages installed\n"
          ]
        }
      ],
      "source": [
        "!pip install pandas matplotlib seaborn numpy textblob vaderSentiment -q\n",
        "import nltk\n",
        "nltk.download('punkt', quiet=True)\n",
        "print('✅ All packages installed')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5XDlX-qvGR30"
      },
      "source": [
        "## **2.** ✅ Load & Inspect the Dataset"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LV-WNmj1GR30"
      },
      "source": [
        "### *a. Initial setup*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "By19FKc1GR31",
        "outputId": "a04a260f-c704-4255-d786-1eaa4b39b9ee"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "✅ Setup complete\n",
            "   Output folders ready: artifacts/py/figures | artifacts/py/tables\n"
          ]
        }
      ],
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "import random\n",
        "import json\n",
        "from pathlib import Path\n",
        "from textblob import TextBlob\n",
        "from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer\n",
        "\n",
        "pd.set_option('display.max_colwidth', 100)\n",
        "plt.style.use('seaborn-v0_8-whitegrid')\n",
        "random.seed(42)\n",
        "np.random.seed(42)\n",
        "\n",
        "# Output folders for Hugging Face app\n",
        "ART_DIR = Path('artifacts')\n",
        "PY_FIG  = ART_DIR / 'py' / 'figures'\n",
        "PY_TAB  = ART_DIR / 'py' / 'tables'\n",
        "for p in [PY_FIG, PY_TAB]:\n",
        "    p.mkdir(parents=True, exist_ok=True)\n",
        "\n",
        "print('✅ Setup complete')\n",
        "print(f'   Output folders ready: {PY_FIG} | {PY_TAB}')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0k7bV6WSGR31"
      },
      "source": [
        "### *b. Load the enriched dataset from Notebook 1*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 347
        },
        "id": "ttRbbwaSGR31",
        "outputId": "e3ec8123-1341-4b02-d16a-72513e92e068"
      },
      "outputs": [
        {
          "output_type": "error",
          "ename": "FileNotFoundError",
          "evalue": "[Errno 2] No such file or directory: 'food_reviews_enriched.csv'",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
            "\u001b[0;32m/tmp/ipykernel_16835/3710694340.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'food_reviews_enriched.csv'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf'✅ Dataset loaded: {df.shape[0]:,} rows × {df.shape[1]} columns'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf'\\nColumns: {list(df.columns)}'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36mread_csv\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)\u001b[0m\n\u001b[1;32m   1024\u001b[0m     \u001b[0mkwds\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkwds_defaults\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1025\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1026\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1027\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1028\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m    618\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    619\u001b[0m     \u001b[0;31m# Create the parser.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 620\u001b[0;31m     \u001b[0mparser\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mTextFileReader\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    621\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    622\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mchunksize\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0miterator\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, f, engine, **kwds)\u001b[0m\n\u001b[1;32m   1618\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1619\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhandles\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mIOHandles\u001b[0m \u001b[0;34m|\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1620\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_engine\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mengine\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1621\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1622\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas/io/parsers/readers.py\u001b[0m in \u001b[0;36m_make_engine\u001b[0;34m(self, f, engine)\u001b[0m\n\u001b[1;32m   1878\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0;34m\"b\"\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1879\u001b[0m                     \u001b[0mmode\u001b[0m \u001b[0;34m+=\u001b[0m \u001b[0;34m\"b\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1880\u001b[0;31m             self.handles = get_handle(\n\u001b[0m\u001b[1;32m   1881\u001b[0m                 \u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1882\u001b[0m                 \u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/pandas/io/common.py\u001b[0m in \u001b[0;36mget_handle\u001b[0;34m(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)\u001b[0m\n\u001b[1;32m    871\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencoding\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;34m\"b\"\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    872\u001b[0m             \u001b[0;31m# Encoding\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 873\u001b[0;31m             handle = open(\n\u001b[0m\u001b[1;32m    874\u001b[0m                 \u001b[0mhandle\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    875\u001b[0m                 \u001b[0mioargs\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmode\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'food_reviews_enriched.csv'"
          ]
        }
      ],
      "source": [
        "df = pd.read_csv('food_reviews_enriched.csv')\n",
        "print(f'✅ Dataset loaded: {df.shape[0]:,} rows × {df.shape[1]} columns')\n",
        "print(f'\\nColumns: {list(df.columns)}')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "UgkWA8UjGR32"
      },
      "source": [
        "### *c. View first few lines*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "eYq3npz3GR32",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "c55c2bd6-d8b4-431e-cb52-d307a127cb98"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "   product_id  rating                            review_title  \\\n",
            "0  B002TMV3E4       4                         Good but pricey   \n",
            "1  B001TY6T6K       1  The other reviewer is totally right!!!   \n",
            "2  B000LKZTSC       4                       Good tea, bad bag   \n",
            "3  B004K30HO2       2                    Not very good for me   \n",
            "4  B005K4Q1VI       2             Tastes like hot sugar water   \n",
            "\n",
            "                                                                                           review_text  \\\n",
            "0  I love coffee and admit that I am particular when it comes to good coffee.  I was not expecting ...   \n",
            "1  You can get these SOOOOOOOOOOOOO much cheaper at wholesale clubs.  I get the 24/20oz(yes 20oz!) ...   \n",
            "2  I love this tea. It has a mild flavor and no caffeine. The only problem is that the string comes...   \n",
            "3  The basic problem with this product is that unless you load a VERY small amount of coffee in the...   \n",
            "4  This hot chocolate tastes like hot sugar water with a pinch of coco in it. Although, even the su...   \n",
            "\n",
            "   helpful_votes  total_votes         user_id     timestamp reviewer_name  \\\n",
            "0              1            3   A37D5847LN3WQ  1.290470e+09   Wildcat Fan   \n",
            "1              4            5  A3UPXR0I04EO4W  1.272067e+09       LuvLeaf   \n",
            "2              1            1  A2VZV78X2V3RPE  1.270685e+09  Steve in STL   \n",
            "3              0            0  A1AV9FXFHM50WM  1.331510e+09    Chief Mike   \n",
            "4              2            3  A3A2M1Z8HO7RZ5  1.321229e+09      K. Jones   \n",
            "\n",
            "  sentiment_label  sentiment_score  is_synthetic product_name category  \n",
            "0        Positive            0.310         False          NaN      NaN  \n",
            "1        Positive            0.130         False          NaN      NaN  \n",
            "2        Positive            0.112         False          NaN      NaN  \n",
            "3         Neutral           -0.061         False          NaN      NaN  \n",
            "4        Negative           -0.128         False          NaN      NaN  \n"
          ]
        }
      ],
      "source": [
        "print(df.head())"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "f0nvuIx_GR32"
      },
      "source": [
        "### *d. Run a quality check on the dataset*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "fbNDr7RYGR32",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "a5ba9269-4ae2-42d3-8760-023074e1c35e"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "🔍 Quality Check Report for: food_reviews_enriched\n",
            "===================================\n",
            "\n",
            "📏 Shape: (560, 14)\n",
            "\n",
            "🔠 Column Types:\n",
            "product_id          object\n",
            "rating               int64\n",
            "review_title        object\n",
            "review_text         object\n",
            "helpful_votes        int64\n",
            "total_votes          int64\n",
            "user_id             object\n",
            "timestamp          float64\n",
            "reviewer_name       object\n",
            "sentiment_label     object\n",
            "sentiment_score    float64\n",
            "is_synthetic          bool\n",
            "product_name        object\n",
            "category            object\n",
            "\n",
            "❓ Missing Values:\n",
            "product_id           0\n",
            "rating               0\n",
            "review_title         0\n",
            "review_text          0\n",
            "helpful_votes        0\n",
            "total_votes          0\n",
            "user_id             60\n",
            "timestamp           60\n",
            "reviewer_name       60\n",
            "sentiment_label      0\n",
            "sentiment_score      0\n",
            "is_synthetic         0\n",
            "product_name       500\n",
            "category           500\n",
            "\n",
            "📋 Duplicate Rows: 0\n",
            "\n",
            "📊 Summary Statistics:\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "        product_id      rating         review_title  \\\n",
              "count          560  560.000000                  560   \n",
              "unique         245         NaN                  490   \n",
              "top     B001LG945O         NaN  Positive experience   \n",
              "freq            28         NaN                   30   \n",
              "mean           NaN    3.035714                  NaN   \n",
              "std            NaN    1.427613                  NaN   \n",
              "min            NaN    1.000000                  NaN   \n",
              "25%            NaN    2.000000                  NaN   \n",
              "50%            NaN    3.000000                  NaN   \n",
              "75%            NaN    4.000000                  NaN   \n",
              "max            NaN    5.000000                  NaN   \n",
              "\n",
              "                                                                                                review_text  \\\n",
              "count                                                                                                   560   \n",
              "unique                                                                                                  541   \n",
              "top     Exceptional product. Fresh, well packaged and exactly as described. The flavour profile is compl...   \n",
              "freq                                                                                                      3   \n",
              "mean                                                                                                    NaN   \n",
              "std                                                                                                     NaN   \n",
              "min                                                                                                     NaN   \n",
              "25%                                                                                                     NaN   \n",
              "50%                                                                                                     NaN   \n",
              "75%                                                                                                     NaN   \n",
              "max                                                                                                     NaN   \n",
              "\n",
              "        helpful_votes  total_votes        user_id     timestamp  \\\n",
              "count      560.000000   560.000000            500  5.000000e+02   \n",
              "unique            NaN          NaN            490           NaN   \n",
              "top               NaN          NaN  AQQLWCMRNDFGI           NaN   \n",
              "freq              NaN          NaN              3           NaN   \n",
              "mean         4.989286     6.442857            NaN  1.294008e+09   \n",
              "std         11.757382    14.087903            NaN  4.511952e+07   \n",
              "min          0.000000     0.000000            NaN  1.090973e+09   \n",
              "25%          0.000000     0.000000            NaN  1.268633e+09   \n",
              "50%          1.000000     1.000000            NaN  1.304770e+09   \n",
              "75%          3.000000     5.000000            NaN  1.328486e+09   \n",
              "max        100.000000   133.000000            NaN  1.351210e+09   \n",
              "\n",
              "             reviewer_name sentiment_label  sentiment_score is_synthetic  \\\n",
              "count                  500             560       560.000000          560   \n",
              "unique                 486               3              NaN            2   \n",
              "top     Steven A. Peterson        Positive              NaN        False   \n",
              "freq                     3             339              NaN          500   \n",
              "mean                   NaN             NaN         0.161468          NaN   \n",
              "std                    NaN             NaN         0.238170          NaN   \n",
              "min                    NaN             NaN        -1.000000          NaN   \n",
              "25%                    NaN             NaN         0.007750          NaN   \n",
              "50%                    NaN             NaN         0.158500          NaN   \n",
              "75%                    NaN             NaN         0.300000          NaN   \n",
              "max                    NaN             NaN         0.988000          NaN   \n",
              "\n",
              "                 product_name   category  \n",
              "count                      60         60  \n",
              "unique                      6          6  \n",
              "top     Organic Matcha Powder  Beverages  \n",
              "freq                       10         10  \n",
              "mean                      NaN        NaN  \n",
              "std                       NaN        NaN  \n",
              "min                       NaN        NaN  \n",
              "25%                       NaN        NaN  \n",
              "50%                       NaN        NaN  \n",
              "75%                       NaN        NaN  \n",
              "max                       NaN        NaN  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-60c20d9f-d277-4238-9440-6ae818bfc282\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>product_id</th>\n",
              "      <th>rating</th>\n",
              "      <th>review_title</th>\n",
              "      <th>review_text</th>\n",
              "      <th>helpful_votes</th>\n",
              "      <th>total_votes</th>\n",
              "      <th>user_id</th>\n",
              "      <th>timestamp</th>\n",
              "      <th>reviewer_name</th>\n",
              "      <th>sentiment_label</th>\n",
              "      <th>sentiment_score</th>\n",
              "      <th>is_synthetic</th>\n",
              "      <th>product_name</th>\n",
              "      <th>category</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>560</td>\n",
              "      <td>560.000000</td>\n",
              "      <td>560</td>\n",
              "      <td>560</td>\n",
              "      <td>560.000000</td>\n",
              "      <td>560.000000</td>\n",
              "      <td>500</td>\n",
              "      <td>5.000000e+02</td>\n",
              "      <td>500</td>\n",
              "      <td>560</td>\n",
              "      <td>560.000000</td>\n",
              "      <td>560</td>\n",
              "      <td>60</td>\n",
              "      <td>60</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>unique</th>\n",
              "      <td>245</td>\n",
              "      <td>NaN</td>\n",
              "      <td>490</td>\n",
              "      <td>541</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>490</td>\n",
              "      <td>NaN</td>\n",
              "      <td>486</td>\n",
              "      <td>3</td>\n",
              "      <td>NaN</td>\n",
              "      <td>2</td>\n",
              "      <td>6</td>\n",
              "      <td>6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>top</th>\n",
              "      <td>B001LG945O</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Positive experience</td>\n",
              "      <td>Exceptional product. Fresh, well packaged and exactly as described. The flavour profile is compl...</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>AQQLWCMRNDFGI</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Steven A. Peterson</td>\n",
              "      <td>Positive</td>\n",
              "      <td>NaN</td>\n",
              "      <td>False</td>\n",
              "      <td>Organic Matcha Powder</td>\n",
              "      <td>Beverages</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>freq</th>\n",
              "      <td>28</td>\n",
              "      <td>NaN</td>\n",
              "      <td>30</td>\n",
              "      <td>3</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>3</td>\n",
              "      <td>NaN</td>\n",
              "      <td>3</td>\n",
              "      <td>339</td>\n",
              "      <td>NaN</td>\n",
              "      <td>500</td>\n",
              "      <td>10</td>\n",
              "      <td>10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>NaN</td>\n",
              "      <td>3.035714</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>4.989286</td>\n",
              "      <td>6.442857</td>\n",
              "      <td>NaN</td>\n",
              "      <td>1.294008e+09</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.161468</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>NaN</td>\n",
              "      <td>1.427613</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>11.757382</td>\n",
              "      <td>14.087903</td>\n",
              "      <td>NaN</td>\n",
              "      <td>4.511952e+07</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.238170</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>NaN</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>1.090973e+09</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>-1.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>NaN</td>\n",
              "      <td>2.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>1.268633e+09</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.007750</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>NaN</td>\n",
              "      <td>3.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>1.304770e+09</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.158500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>NaN</td>\n",
              "      <td>4.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>3.000000</td>\n",
              "      <td>5.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>1.328486e+09</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.300000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>NaN</td>\n",
              "      <td>5.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>100.000000</td>\n",
              "      <td>133.000000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>1.351210e+09</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0.988000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-60c20d9f-d277-4238-9440-6ae818bfc282')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-60c20d9f-d277-4238-9440-6ae818bfc282 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-60c20d9f-d277-4238-9440-6ae818bfc282');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "summary": "{\n  \"name\": \"quality_check(df, 'food_reviews_enriched')\",\n  \"rows\": 11,\n  \"fields\": [\n    {\n      \"column\": \"product_id\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          245,\n          \"28\",\n          \"560\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"rating\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 197.0112524760018,\n        \"min\": 1.0,\n        \"max\": 560.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          3.0357142857142856,\n          3.0,\n          560.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"review_title\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          490,\n          \"30\",\n          \"560\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"review_text\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          541,\n          \"3\",\n          \"560\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"helpful_votes\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 194.87949605136967,\n        \"min\": 0.0,\n        \"max\": 560.0,\n        \"num_unique_values\": 7,\n        \"samples\": [\n          560.0,\n          4.989285714285714,\n          3.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"total_votes\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 195.24322381689282,\n        \"min\": 0.0,\n        \"max\": 560.0,\n        \"num_unique_values\": 7,\n        \"samples\": [\n          560.0,\n          6.442857142857143,\n          5.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"user_id\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          490,\n          \"3\",\n          \"500\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"timestamp\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 584351482.8763152,\n        \"min\": 500.0,\n        \"max\": 1351209600.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          1294007788.8,\n          1304769600.0,\n          500.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"reviewer_name\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          486,\n          \"3\",\n          \"500\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"sentiment_label\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          3,\n          \"339\",\n          \"560\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"sentiment_score\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 197.94751782876892,\n        \"min\": -1.0,\n        \"max\": 560.0,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          0.16146785714285714,\n          0.1585,\n          560.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"is_synthetic\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          2,\n          \"500\",\n          \"560\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"product_name\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          6,\n          \"10\",\n          \"60\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"category\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 4,\n        \"samples\": [\n          6,\n          \"10\",\n          \"60\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "👀 Sample Rows:\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "     product_id  rating                         review_title  \\\n",
              "453  B00016UX0K       1            Guess I'm in the Minority   \n",
              "341  B000G6RYNE       3                      Too Much Flavor   \n",
              "177  B001EO5ZMY       2                         Disappointed   \n",
              "86   B000FDKQC4       2          Bitter and a disappointment   \n",
              "332  B002GWMCIS       1  Chocolate Raspberry Flavored Coffee   \n",
              "\n",
              "                                                                                             review_text  \\\n",
              "453  I was looking for a good sweet and sour sauce for chicken and based on the reviews, I took a cha...   \n",
              "341  These things are just too darn cheesy. If you like a lot of flavor, you'll love these. Otherwise...   \n",
              "177  I've been drinking this tea for the past 8 or 10 years, usually buying a box or two when visitin...   \n",
              "86   I bought these at my local grocery store. I wish I would have read the review on here first. The...   \n",
              "332  This is the worst flavored coffee I have ever tried.  There is no aroma or flavor of Chocolate/R...   \n",
              "\n",
              "     helpful_votes  total_votes         user_id     timestamp  \\\n",
              "453              2           15  A3E3YJO2V3YZUM  1.295482e+09   \n",
              "341              0            1   AYBYYDVV5ABJE  1.251245e+09   \n",
              "177              1            9  A3E81HFGNME65J  1.245456e+09   \n",
              "86               0            0  A3AKRFTAPS05AH  1.327795e+09   \n",
              "332              1            1   A777YVRDEG1UI  1.320883e+09   \n",
              "\n",
              "                reviewer_name sentiment_label  sentiment_score  is_synthetic  \\\n",
              "453              Lidgemeister        Positive            0.178         False   \n",
              "341                  retrodog         Neutral            0.000         False   \n",
              "177                     suave         Neutral           -0.034         False   \n",
              "86   LivingOurLoveSong &#60;3        Positive            0.205         False   \n",
              "332        RedCrystal Peacock        Negative           -0.480         False   \n",
              "\n",
              "    product_name category  \n",
              "453          NaN      NaN  \n",
              "341          NaN      NaN  \n",
              "177          NaN      NaN  \n",
              "86           NaN      NaN  \n",
              "332          NaN      NaN  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-517fdfed-84c0-4c84-8613-0c2f7a5e7e53\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>product_id</th>\n",
              "      <th>rating</th>\n",
              "      <th>review_title</th>\n",
              "      <th>review_text</th>\n",
              "      <th>helpful_votes</th>\n",
              "      <th>total_votes</th>\n",
              "      <th>user_id</th>\n",
              "      <th>timestamp</th>\n",
              "      <th>reviewer_name</th>\n",
              "      <th>sentiment_label</th>\n",
              "      <th>sentiment_score</th>\n",
              "      <th>is_synthetic</th>\n",
              "      <th>product_name</th>\n",
              "      <th>category</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>453</th>\n",
              "      <td>B00016UX0K</td>\n",
              "      <td>1</td>\n",
              "      <td>Guess I'm in the Minority</td>\n",
              "      <td>I was looking for a good sweet and sour sauce for chicken and based on the reviews, I took a cha...</td>\n",
              "      <td>2</td>\n",
              "      <td>15</td>\n",
              "      <td>A3E3YJO2V3YZUM</td>\n",
              "      <td>1.295482e+09</td>\n",
              "      <td>Lidgemeister</td>\n",
              "      <td>Positive</td>\n",
              "      <td>0.178</td>\n",
              "      <td>False</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>341</th>\n",
              "      <td>B000G6RYNE</td>\n",
              "      <td>3</td>\n",
              "      <td>Too Much Flavor</td>\n",
              "      <td>These things are just too darn cheesy. If you like a lot of flavor, you'll love these. Otherwise...</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>AYBYYDVV5ABJE</td>\n",
              "      <td>1.251245e+09</td>\n",
              "      <td>retrodog</td>\n",
              "      <td>Neutral</td>\n",
              "      <td>0.000</td>\n",
              "      <td>False</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>177</th>\n",
              "      <td>B001EO5ZMY</td>\n",
              "      <td>2</td>\n",
              "      <td>Disappointed</td>\n",
              "      <td>I've been drinking this tea for the past 8 or 10 years, usually buying a box or two when visitin...</td>\n",
              "      <td>1</td>\n",
              "      <td>9</td>\n",
              "      <td>A3E81HFGNME65J</td>\n",
              "      <td>1.245456e+09</td>\n",
              "      <td>suave</td>\n",
              "      <td>Neutral</td>\n",
              "      <td>-0.034</td>\n",
              "      <td>False</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>86</th>\n",
              "      <td>B000FDKQC4</td>\n",
              "      <td>2</td>\n",
              "      <td>Bitter and a disappointment</td>\n",
              "      <td>I bought these at my local grocery store. I wish I would have read the review on here first. The...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>A3AKRFTAPS05AH</td>\n",
              "      <td>1.327795e+09</td>\n",
              "      <td>LivingOurLoveSong &amp;#60;3</td>\n",
              "      <td>Positive</td>\n",
              "      <td>0.205</td>\n",
              "      <td>False</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>332</th>\n",
              "      <td>B002GWMCIS</td>\n",
              "      <td>1</td>\n",
              "      <td>Chocolate Raspberry Flavored Coffee</td>\n",
              "      <td>This is the worst flavored coffee I have ever tried.  There is no aroma or flavor of Chocolate/R...</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>A777YVRDEG1UI</td>\n",
              "      <td>1.320883e+09</td>\n",
              "      <td>RedCrystal Peacock</td>\n",
              "      <td>Negative</td>\n",
              "      <td>-0.480</td>\n",
              "      <td>False</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-517fdfed-84c0-4c84-8613-0c2f7a5e7e53')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-517fdfed-84c0-4c84-8613-0c2f7a5e7e53 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-517fdfed-84c0-4c84-8613-0c2f7a5e7e53');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "repr_error": "0"
            }
          },
          "metadata": {}
        }
      ],
      "source": [
        "def quality_check(df, name='df'):\n",
        "    print(f'\\n🔍 Quality Check Report for: {name}')\n",
        "    print('===================================')\n",
        "    print(f'\\n📏 Shape: {df.shape}')\n",
        "    print(f'\\n🔠 Column Types:')\n",
        "    print(df.dtypes.to_string())\n",
        "    print(f'\\n❓ Missing Values:')\n",
        "    print(df.isnull().sum().to_string())\n",
        "    print(f'\\n📋 Duplicate Rows: {df.duplicated().sum()}')\n",
        "    print(f'\\n📊 Summary Statistics:')\n",
        "    display(df.describe(include='all'))\n",
        "    print(f'\\n👀 Sample Rows:')\n",
        "    display(df.sample(5, random_state=42))\n",
        "\n",
        "quality_check(df, 'food_reviews_enriched')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "hAXAm2sSGR32"
      },
      "source": [
        "## **3.** 🛠️ Data Preparation"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xxwKCoHUGR32"
      },
      "source": [
        "### *a. Clean and type-fix columns*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "7YVpW5gAGR32",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7797487d-b6ce-436f-8df4-5f32c1056f75"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "✅ Data preparation complete\n",
            "   Total reviews  : 560\n",
            "   Real reviews   : 500\n",
            "   Synthetic      : 60\n",
            "   Unique products: 245\n"
          ]
        }
      ],
      "source": [
        "df['rating']          = pd.to_numeric(df['rating'], errors='coerce').fillna(3).astype(int)\n",
        "df['sentiment_score'] = pd.to_numeric(df['sentiment_score'], errors='coerce').fillna(0.0)\n",
        "df['helpful_votes']   = pd.to_numeric(df['helpful_votes'], errors='coerce').fillna(0).astype(int)\n",
        "df['is_synthetic']    = df['is_synthetic'].fillna(False).astype(bool)\n",
        "df['sentiment_label'] = df['sentiment_label'].astype(str).str.capitalize()\n",
        "\n",
        "# Add helpfulness ratio (how useful was this review to others?)\n",
        "if 'total_votes' in df.columns:\n",
        "    df['total_votes'] = pd.to_numeric(df['total_votes'], errors='coerce').fillna(0).astype(int)\n",
        "    df['helpfulness_ratio'] = np.where(\n",
        "        df['total_votes'] > 0,\n",
        "        (df['helpful_votes'] / df['total_votes']).round(3),\n",
        "        0.0\n",
        "    )\n",
        "\n",
        "print('✅ Data preparation complete')\n",
        "print(f'   Total reviews  : {len(df):,}')\n",
        "print(f'   Real reviews   : {(~df[\"is_synthetic\"]).sum():,}')\n",
        "print(f'   Synthetic      : {df[\"is_synthetic\"].sum():,}')\n",
        "print(f'   Unique products: {df[\"product_id\"].nunique():,}')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FkK0Vi6HGR32"
      },
      "source": [
        "### *b. Separate real and synthetic reviews*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "wYZ2XSWxGR32",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "b00cf0bf-b69a-456d-d03b-a752db08d473"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Real reviews     : 500\n",
            "Synthetic reviews: 60\n",
            "Name column used : product_id\n"
          ]
        }
      ],
      "source": [
        "df_real      = df[df['is_synthetic'] == False].copy()\n",
        "df_synthetic = df[df['is_synthetic'] == True].copy()\n",
        "\n",
        "# Use product_name if available, otherwise product_id as label\n",
        "name_col = 'product_name' if ('product_name' in df.columns and df['product_name'].notna().sum() > len(df_synthetic)) else 'product_id'\n",
        "\n",
        "print(f'Real reviews     : {len(df_real):,}')\n",
        "print(f'Synthetic reviews: {len(df_synthetic):,}')\n",
        "print(f'Name column used : {name_col}')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "XFj06izOGR33"
      },
      "source": [
        "## **4.** 📊 Data Visualizations"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "e5yKCKciGR33"
      },
      "source": [
        "### *a. Setup output folders*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "FvVrFHHeGR33",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "fcc51daa-7b64-4e98-9c2c-4a69c6370c44"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "✅ Output folders:\n",
            "   /content/artifacts/py/figures\n",
            "   /content/artifacts/py/tables\n"
          ]
        }
      ],
      "source": [
        "print('✅ Output folders:')\n",
        "print(f'   {PY_FIG.resolve()}')\n",
        "print(f'   {PY_TAB.resolve()}')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uBKJ5ptyGR33"
      },
      "source": [
        "### *b. Rating & sentiment overview*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Ys5U1rYZGR33",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 575
        },
        "outputId": "be620d44-b87c-4b7b-e9e9-51daa230673c"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/tmp/ipykernel_1475/285524268.py:22: UserWarning: Glyph 11088 (\\N{WHITE MEDIUM STAR}) missing from font(s) Liberation Sans.\n",
            "  plt.tight_layout()\n",
            "/tmp/ipykernel_1475/285524268.py:23: UserWarning: Glyph 11088 (\\N{WHITE MEDIUM STAR}) missing from font(s) Liberation Sans.\n",
            "  plt.savefig(PY_FIG / 'rating_sentiment_overview.png', dpi=150, bbox_inches='tight')\n",
            "/usr/local/lib/python3.12/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 11088 (\\N{WHITE MEDIUM STAR}) missing from font(s) Liberation Sans.\n",
            "  fig.canvas.print_figure(bytes_io, **kw)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1300x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "📊 Saved: rating_sentiment_overview.png\n"
          ]
        }
      ],
      "source": [
        "fig, axes = plt.subplots(1, 2, figsize=(13, 5))\n",
        "fig.suptitle('Rating & Sentiment Overview — Food Reviews', fontsize=14, fontweight='bold')\n",
        "\n",
        "rc = df['rating'].value_counts().sort_index()\n",
        "bars = axes[0].bar(rc.index, rc.values,\n",
        "    color=['#e74c3c','#e67e22','#f1c40f','#2ecc71','#27ae60'], edgecolor='white', width=0.7)\n",
        "axes[0].set_title('Rating Distribution', fontweight='bold')\n",
        "axes[0].set_xlabel('Star Rating')\n",
        "axes[0].set_ylabel('Number of Reviews')\n",
        "axes[0].set_xticks([1,2,3,4,5])\n",
        "axes[0].set_xticklabels(['1⭐','2⭐','3⭐','4⭐','5⭐'])\n",
        "for bar in bars:\n",
        "    axes[0].text(bar.get_x()+bar.get_width()/2, bar.get_height()+0.5,\n",
        "                 str(int(bar.get_height())), ha='center', va='bottom', fontsize=10)\n",
        "\n",
        "sc = df['sentiment_label'].value_counts()\n",
        "axes[1].pie(sc, labels=sc.index, autopct='%1.1f%%', startangle=90,\n",
        "    colors=[{'Positive':'#27ae60','Neutral':'#f39c12','Negative':'#e74c3c'}.get(s,'grey') for s in sc.index],\n",
        "    textprops={'fontsize':11})\n",
        "axes[1].set_title('Sentiment Breakdown (TextBlob)', fontweight='bold')\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.savefig(PY_FIG / 'rating_sentiment_overview.png', dpi=150, bbox_inches='tight')\n",
        "plt.show()\n",
        "print('📊 Saved: rating_sentiment_overview.png')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RfzGx0AsGR33"
      },
      "source": [
        "### *c. Sentiment score distribution by rating*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "iMMf7Z8CGR33",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 563
        },
        "outputId": "036807e8-9225-481a-9ed3-5e06a1696dcf"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/tmp/ipykernel_1475/2785659891.py:5: MatplotlibDeprecationWarning: The 'labels' parameter of boxplot() has been renamed 'tick_labels' since Matplotlib 3.9; support for the old name will be dropped in 3.11.\n",
            "  bp = axes[0].boxplot(groups, labels=['1⭐','2⭐','3⭐','4⭐','5⭐'], patch_artist=True)\n",
            "/tmp/ipykernel_1475/2785659891.py:20: UserWarning: Glyph 11088 (\\N{WHITE MEDIUM STAR}) missing from font(s) Liberation Sans.\n",
            "  plt.tight_layout()\n",
            "/tmp/ipykernel_1475/2785659891.py:21: UserWarning: Glyph 11088 (\\N{WHITE MEDIUM STAR}) missing from font(s) Liberation Sans.\n",
            "  plt.savefig(PY_FIG / 'sentiment_score_analysis.png', dpi=150, bbox_inches='tight')\n",
            "/usr/local/lib/python3.12/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 11088 (\\N{WHITE MEDIUM STAR}) missing from font(s) Liberation Sans.\n",
            "  fig.canvas.print_figure(bytes_io, **kw)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1300x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "fig, axes = plt.subplots(1, 2, figsize=(13, 5))\n",
        "fig.suptitle('Sentiment Score Analysis', fontsize=14, fontweight='bold')\n",
        "\n",
        "groups = [df[df['rating']==r]['sentiment_score'].dropna() for r in [1,2,3,4,5]]\n",
        "bp = axes[0].boxplot(groups, labels=['1⭐','2⭐','3⭐','4⭐','5⭐'], patch_artist=True)\n",
        "for patch, color in zip(bp['boxes'], ['#e74c3c','#e67e22','#f1c40f','#2ecc71','#27ae60']):\n",
        "    patch.set_facecolor(color); patch.set_alpha(0.7)\n",
        "axes[0].set_title('Sentiment Score by Star Rating', fontweight='bold')\n",
        "axes[0].set_xlabel('Star Rating'); axes[0].set_ylabel('TextBlob Score')\n",
        "axes[0].axhline(y=0, color='black', linestyle='--', alpha=0.4)\n",
        "\n",
        "df['sentiment_score'].plot(kind='hist', bins=30, ax=axes[1], color='#9b59b6', edgecolor='white', alpha=0.85)\n",
        "axes[1].axvline(x=0, color='black', linestyle='--', alpha=0.6, label='Neutral')\n",
        "axes[1].axvline(df['sentiment_score'].mean(), color='red', linestyle='--', alpha=0.7,\n",
        "                label=f'Mean ({df[\"sentiment_score\"].mean():.2f})')\n",
        "axes[1].set_title('Sentiment Score Distribution', fontweight='bold')\n",
        "axes[1].set_xlabel('-1.0 = Very Negative  →  +1.0 = Very Positive')\n",
        "axes[1].legend()\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.savefig(PY_FIG / 'sentiment_score_analysis.png', dpi=150, bbox_inches='tight')\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cT5dFtfMGR33"
      },
      "source": [
        "### *d. Sample of products per sentiment level for visualizations (same approach as class)*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "6tbUXM2aGR33",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "68a961c1-0448-4d7d-ed38-5f2976923d36"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Synthetic products available: ['SYN001', 'SYN002', 'SYN003', 'SYN004', 'SYN005', 'SYN006']\n",
            "Top real product IDs        : ['B001LG945O', 'B006N3IG4K', 'B001RVFDOO', 'B003VXFK44', 'B005K4Q1VI']\n"
          ]
        }
      ],
      "source": [
        "# Sample 5 synthetic products per sentiment (they have product names we can display)\n",
        "sampled_products = df_synthetic[name_col].unique().tolist()\n",
        "\n",
        "# Also sample some real product IDs for comparison\n",
        "top_real = df_real['product_id'].value_counts().head(10).index.tolist()\n",
        "\n",
        "print(f'Synthetic products available: {sampled_products}')\n",
        "print(f'Top real product IDs        : {top_real[:5]}')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "YEs1RAjKGR33"
      },
      "source": [
        "### *e. Sentiment breakdown per synthetic product*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "xSxQkm_aGR33",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 489
        },
        "outputId": "f0c38165-ec24-4b0a-c056-e0a2d90e752a"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1100x500 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABEEAAAHqCAYAAADrglBeAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAj8ZJREFUeJzs3Xd8jef/x/H3yU7sUUoitohKKiS1R5OoWdEaRdHWpmhpbUqtUpRWaaqoDrVTLbWpaq3agtg7iJEYkZA4Ob8/fHP/hISIkOh5PR8Pj5/c47o+931u31/PO9d13SaLxWIRAAAAAADAf5xNRhcAAAAAAADwLBCCAAAAAAAAq0AIAgAAAAAArAIhCAAAAAAAsAqEIAAAAAAAwCoQggAAAAAAAKtACAIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAKzSsWPHNHDgQNWvX1++vr566aWXVK1aNXXq1EkbN258JjWsWLFCkydPTrKtf//+8vDwkL+//zOp4UkkV39yEq/p/j9ly5aVv7+/+vXrp2PHjj2Dih9eX1rv+fP0mWVGFy5c0MiRI9WoUSNVrFhRL730kipVqqR33nlHf/zxxzOpYdOmTZo8ebKuX79ubJs8ebI8PDzk5eX1zPry8PBIlz7ube/eP15eXqpTp47Gjh2rq1evpktfqRESEmLUcPbs2afaV2hoqCZPnvzU+wHw/LLL6AIAAHjW9u7dq7Zt2yo2NlaOjo4qWbKkbGxsdPDgQf3111/asGGDPv/8czVq1Oip1WCxWDR69GhFRESoR48exvYSJUqocuXKyps371PrOz2kVP/D2Nra6pVXXjF+vn79usLCwrR48WKtXr1av/76qwoXLvy0SkYmdPbsWTVr1kyRkZGys7NTqVKl5OjoqEOHDmnLli3asmWLzpw5oy5dujzVOr766ivt2rVLb7zxhrJnz/7M+ypUqJAqV678VPrz8/OTnd3d/+SPiIjQ8ePHNXPmTK1bt04LFy5UtmzZnkq/GWXWrFlaunSpXnnlFbm5uWV0OQAyIUIQAIDVmTp1qmJjY5U3b179+uuvypcvnyQpPDxcb731li5duqRp06Y91RBk7969ioiIeGB7hw4d1KFDh6fWb3pJqf6HcXR01KxZs5Js27hxo9q1a6ebN29q0aJF6t27dzpWiczu+++/V2RkpBwdHRUSEqISJUpIkq5evao2bdro8OHDmjlzptq1aycHB4enUsPFixe1e/fup9J2avtq3LixGjdu/FT6/Oqrr5Q7d27j54ULF2rQoEE6efKk5s2b91z8701qxcXFaf369RldBoBMjukwAACrc/LkSUmSq6urEYAk/jxx4kQFBwfryy+/THLO8ePH1atXL1WuXFlly5ZV/fr1NWfOnCTHJE6LeOedd3T27Fl17NhRPj4+qlixosaPHy+z2Wwc17x5c+O8e6dSJDe14t52jxw5opYtW8rb21u1a9fWH3/8IYvFosmTJ6ty5cp6+eWXNWDAAMXFxWVI/Y+rcuXKsrW1lSTdvHkz2VrWrFmjWrVqqVmzZo91PZL0119/qVWrVipXrpwqVKigpk2bavny5Y+s6+DBg/Lx8ZGHh4e+/vprY/uyZctUv359eXl5qUGDBlq6dGmKbURGRmrUqFHy9/dX2bJl9corr6hdu3ZJplu9+eabD/SxcuVKY+rAZ599ZmzfsWOHPDw89NJLL+nmzZup/rxS0qdPH3l4eKhx48Y6ceKE2rdvb5w/evToJ36Gkvvc7pf4bzFbtmxGACJJOXPm1JgxYzRlyhT99NNPsrW11dSpU437cuHChSTtDBw4UB4eHqpSpYru3LljTAcJDAxUVFSUevfuLV9fX5UvX14DBw7UrVu3JN2dNlK9enVZLBZJUkBAQLJTUm7duqVPPvlEFStWlI+PjwYMGKDY2Ngkx1y8eFGDBg1S9erVVbZsWQUEBOibb77RnTt3HtlXStNhIiMjNXLkSNWqVUtly5ZV9erV9dlnn+natWsp3tNHadq0qbJmzSrp7tQR6f+nq5QpU0bHjh3Tm2++KS8vL0VHR0uS4uPjNXPmTAUFBenll1+Wj4+P3nzzTc2ePVsJCQlJ2j948KDefvtteXt7q0aNGpo0aVKyz2JK15zS1JnY2FhNnDhRr732msqWLavKlStr4MCBRhgbEhKSpOa2bds+k+k3AJ4/jAQBAFidF154QSdOnNDevXs1fvx4tWrVSgULFpR0d+j4/U6cOKHmzZvrxo0byp07tzw9PRUWFqZhw4YpOjpaHTt2THL8jRs31K5dO9nb28vZ2VlXrlzRd999p2zZsqlz584qUaKE3NzcjP84T+30lxs3bqhLly7KmjWrEhISdPr0afXt21fHjx/X7NmzlTVrVkVGRiokJET58uVTr169MlX9ydm8ebPxBalixYoP7I+MjNSAAQNUsGBBubu7P9b1rFq1Sj179pTFYlHJkiUVHx+v0NBQffjhh7K1tdVrr72WbE2RkZHq2rWrYmJiFBQUpO7du0u6O2qld+/eslgsypkzp3LkyKGBAwfK1dX1gTauXLmiZs2aKTw8XPb29sYX940bN2rTpk0aM2aMGjduLD8/P+3fv1/79u0zzt22bZskyWQyafv27cb2xC+sL730krJkyWJsf9TnlZLE8CkqKkrt27dXlixZlC1bNkVEROiHH35QQkKCBg8e/Fj3/GGfW3ISQ8jLly9r4MCBat++vYoXL25c50svvWQc+8Ybb2jy5MlKSEjQ2rVr9fbbbxv7/v77b0lS/fr1jakfknT79m11795dERERypYtm86dO6dFixbJzs5Ow4cPV6FChVSiRAkdPXpUklS+fHk5OjomqdFkMmnIkCHatWuXXFxcdPXqVYWEhMje3l7Dhw83rvett97SuXPnlDVrVpUpU0aHDh3SpEmTFBERoWHDhqWqr3vduHFDLVu21MmTJ+Xs7KwyZcroyJEjmjVrlrZs2aK5c+fK2dk5xfNTYrFYjODC3t4+yT6z2azBgwfr6tWr8vT0NI7v0aOH/vzzT0ky/i3t379f+/fv14EDBzRq1ChJd5/7d955R1evXpWDg4Pc3Nw0Z84c5cmT57HrvFd8fLzatWunnTt3yt7eXqVLl9aZM2e0aNEibdy40fjfvJdeekn79++XdPf5yZ49u5ycnJ6obwD/PYwEAQBYnRYtWki6+x/33333nV599VUFBASoT58+Wrp0qW7fvp3k+AkTJujGjRtydXXVqlWrtGDBAk2ZMkWSNGXKlCQLHErS/v37Va9ePf3xxx9atWqVEbD89ttvku5Oebl36PusWbM0fvz4R9a9f/9+tWnTRr/99ptGjhwpSbpz545++uknLV26VMuWLVOxYsUk3V20NLPVf/v2bb377rvGnzfffFMdOnRQ1qxZ1aNHj2RDicOHD6tdu3b67bffNGHChMe6npkzZ8rGxkY+Pj5aunSpli9frlKlShk1Jyc+Pl49evTQuXPn5OfnZ9xnSfr222+NAGTp0qX65Zdf9MMPPxijGe41ceJEhYeHy8nJSYsWLdKiRYu0bt06+fn5yWKxaOTIkYqJiTFCt8SAQ5L+/fdfZcmSRZUqVVJYWJgxQmbv3r2SlGRdFenRn9ejXLhwQQ0bNtSSJUu0Zs0alS9fXpI0b94847fqj/sMJfe5Jadp06ZGGLNo0SLVr19f1apV0wcffKAFCxboxo0bxrEFChRQpUqVJElr1qwxth84cEAXL16UJL3++utJ2r948aIKFiyo1atXa9WqVfL29pYk/f7777JYLGrcuLHat29vHD9u3LgHno24uDiZTCajjbJly0qSlixZYozq+Pbbb40AZOnSpZo/f77mzZsnW1tbzZ07V8ePH09VX/f67rvvdPLkSdnb22vBggWaP3++fv31Vzk4OOjgwYNatGhRiuc+zC+//KKYmBhJyQePLi4uWr16tebPn6+sWbNqyZIlRgAycuRILV26VCtXrjSuZeHChUZYN2fOHGPB1W+//Va//PKLli9fbvSXViEhIdq5c6ckKTg4WAsXLtTy5cuVJ08eXbhwQdOnT1e1atXUr18/45x+/fpp1qxZmX59JQDPHiEIAMDqNGjQQGPHjlX+/PmNbWfPntXvv/+ujz76SP7+/tq8ebOkuyFD4m+ZAwMDjUUEa9asqezZsys2NlZbt25N0r6NjY3xm/GsWbOqRo0aRh9Pws7OzghwatasaWwPCAhQ3rx55eDgoCpVqkiSzp8/n+nqN5vN2rx5s/Fn//79SkhIUJYsWXT58uVk31ZhY2OjNm3aGD8/zvXMnTtXBw4c0Ny5c422Eofep7SeyYgRI7R9+3YVLlxYX3/9dZJ1KBJDiNq1a+uFF16QJPn4+Dzw9pCEhAStXLnSODaxT0dHR7377ruS7v6W/99//5Wvr69MJpMuX76sc+fO6erVqzp8+LAxLcVsNmvXrl1J+r9/tNKTfl73nu/g4KC33npL0t0v/0eOHEnzM3Tv55aSChUq6JtvvlGRIkWMbZcuXdKKFSs0ePBg1apVK8mUozfffFPS3dEyiQHJX3/9JUlyd3fXyy+//EAfnTt3lslkkr29vWrXri3p7tSKK1euPPrm6G5Y2qlTJ6ONOnXqSJJiYmIUGRkpScY6FJUqVVKBAgUkSaVLl1apUqVksVi0YcOGVPV1r7Vr10qSfH19VbJkSUlSkSJFNHPmTAUHBxth1aP07NnTCB7r1q1rjF4pV66cgoKCHji+TZs2RjAlyZg+9uKLL6pp06bG9i5dushkMiWpdc+ePZKkwoULG/9blDt3bjVs2DD1F56MxPbd3d1VrVo1o93g4GAFBwcbnysApAbTYQAAVqlx48Zq1KiRdu/ere3bt2vbtm3asmWL4uLidPnyZX3wwQdas2aN4uLijPUDfvjhB/3www8PtBUeHp7k57x58xpz7iUZQ8HvH2HyuHLnzm0M7c6ZM6ex/d4wJ0eOHEn6unr1aqap38XFxfhCn9je3r171a9fP82ZM0d79+7VwoULZWPz/7+jyZkzZ5JaHud6Tp48qcmTJ2vr1q26fPmy8Vt7SUn+nuj8+fOaN2+epLsBwL1TFa5evWqsAVGoUKEk5xUqVMj48ifdnRqRODLi3i/3kpJMDTl79qxq1aqlUqVK6dChQwoNDZWtra0sFov8/PyML7nbt2/XSy+9pDNnzsjW1lYVKlRI0uaTfl558uRJ8oaQe6f3XLx4MU3P0P2f28PUrFlTNWvW1IEDB/Tvv/9qx44d+ueffxQTE6Po6Gj1799f3t7ecnd3V+3atZUtWzbduHFD69ev1+uvv26EIPePAkl07xuH7p2WkXhNqZFSG4nPRGLouGbNmmTXFLn//qTGmTNnJMkY2ZMouSl7D5M4vUq6O/2lSJEiqlevnjp37pzsYrP3v1ElcaSTu7u7EXpIUvbs2ZUjRw5dvXrVuL7EtVru/zfysClRqZHSvUgc2QMAj4MQBABgtWxsbFS+fHmVL19enTp10tWrV9WvXz+tX79e165d0+7du4158dLdL0L3/0e4pAe+7N0/z/7eLw5P4t52723z3t/a3t/XvV/2M7r++zk6OsrPz0/du3fXgAEDjLUx7v1ic/+aB6m9nujoaLVr107h4eGytbXVSy+9pGzZsuno0aO6dOlSsvUkJCSoXLlyOnz4sM6fP6/g4GBjXZV7+42Pj3/gvJTcuz7F/T8n3lc/Pz8dOnRIe/fuNRbR9PX1lZeXl+zt7bVjxw75+PhIksqUKfPUP697F7G0sbFJ0zOUlrUqypQpozJlyujdd99VbGysRo4cqYULFyo+Pl4bN26Uu7u7nJycVL9+fc2bN09r1qxR9erVjREyKYUgKf27eRyPaiPxHuXPn9+YknavtKyJkdhmcoHd49i8eXOSt8M8SkpraNz/nN277f57cv+/kUct0muxWIw2Ev8N3L9fevi/NQBILUIQAIBVOXv2rNasWaOjR4+qS5cuSX7rmTNnTrVv394Y2h4dHW2Mvrh165YCAgKSzDl/HjwP9d/7BTpxekFKUns9a9asMX47PXz4cGMYf5cuXYz1De73wgsvaPbs2Zo2bZq+/PJLzZw5U02aNJG7u7ty5cole3t7xcfHP/Bb/cSFLu+tMXG0wpEjR5LsO3bsmPH3xFEifn5++vnnnxUaGqro6Gg5OTnJ29tbDg4OKlu2rPbs2WOsh3D/eiDp4cqVK4qOjjY+h3un0eTPn/+pPUORkZFavny5jhw5ojfffPOB8Ktbt25auHChJBlrk0h3F0idN2+e/v77b61bt05ms1lly5ZV0aJF06WutChYsKBOnjypcuXK6auvvkqXNt3c3HT8+HFjFESipUuXKiIiQoULF1ZgYGC69PUwhQsX1vHjx3Xs2LEkYUVUVJQuX74s6f+f5RdeeEGHDx9+YCrWvc99ontHWl2/ft0YxXb69OkHjnVzc9OJEyce+Lf3119/6ejRo8qdO7feeOONtF8kAKvCmiAAAKtisVg0duxYLViwQJ9++mmSV03Gx8dryZIlku7+Btzb21u2traqWrWqpLuLjSZ+SQ8PD1enTp3Ut2/fZP8D/1HuHb2RlqHyj9NPZq4/Li7OWODRZDIlO5Xg/n5Tcz33/mY6V65cku4uIJr4etro6OgHfsPu4OAgOzs7tWvXTgUKFFBcXJxGjx5t7E+chrB27VqdO3dOkrRu3TodPnw4STs2NjbGIq+rV682gpCbN29qxowZku5OYUls797FUcPCwowARLo7IuT27dtGGJDcQpZPKiEhwVigMy4uzujLxcVFpUqVemrPkIODgyZMmKA5c+Zo2LBhSdZpsVgsWrx4sfFzuXLljL/7+PioaNGiunnzphE4pDQKJDXufZYTP9fHlbgOy99//22EFjdu3ND777+vjz76yFg49HH6CggIkHT31ciJbzw5e/ashgwZos8//zxN9zwt6tatK+nuVJfEZ0O6uyBu4r+hxHVSEp/l8PBwI2w8e/as8b+r90pcO0WSsYZOZGRksgv6Jt6L8PBwY1Hca9euGfcicZpdenyWAP77GAkCALAqhQoVUqdOnRQcHKwNGzaoVq1aKlq0qBwcHHTixAljcc5OnToZo0R69+6tzZs369y5c6pTp46KFy+uI0eOKDo6Wq+88soD6z6kxr3nvPXWWypWrJh+/PHHdLjCB2WW+hPfDpPozp07On78uLFA5XvvvZfki9GTXE/OnDnl4uKimJgY9e3bV8WKFdPBgwfVrl07BQcH69q1a2rcuLE+++yzB9p3cnJSr1691LdvX/3555/666+/VLNmTbVt21abNm3StWvX1LBhQxUuXFhHjx6Vt7e3MSXj3hq3bNmi8PBwNWnSRB4eHjpz5oyioqJkb2+vESNGGEFHnjx5VLx4ceNL7b1rPvj6+uq7777T5cuXk10PJD3kzJlTc+fO1bp16xQVFWV8eXz33XeNqRFP4xnKmjWr+vXrp6FDh2r//v0KCAhQiRIl5OLiotOnTxvTll5//fUH1sF48803NWHCBJ0/f162trZPtPDmvSNIunfvrsKFC+v7779/rDY6d+6s5cuX69KlS2rUqJE8PDx08uRJRUVFqXjx4ipduvRj99WxY0etWLFCZ86cUcuWLVW6dGkdPXpUMTExKlGiRKoWnk0PjRo10rJly/TXX39pyJAhmj17tm7cuGGM9ujUqZPKlCkjSWrSpImmTZummJgYde/eXSVLltSpU6fk4eGRZD0gSfL391eOHDl07do1DR8+XEuXLtXx48fl5eWldevWJTm2SZMm+vXXX7Vnzx598MEHKl26tM6ePaurV6/qhRdeMF5j7e7uLhsbGyUkJGj48OGaO3euRo8ebbx2GQAkRoIAAKxQr169NG3aNAUEBChbtmw6fPiw9u3bJ0dHRwUGBmratGnGWhCSVKJECc2fP1+BgYGysbFRaGiocuTIoQ4dOig4ODjJbx9T67XXXlPjxo2VJUsW3bhx46nOdc8s9d//dpgdO3bIxsZGVatW1ZQpU1I9zSI115MnTx5NmTJFHh4eio+PV3R0tMaMGaNevXopKChIjo6OunLlSorX3qhRI+OtL6NHj1ZcXJxeffVVjRgxQq6uroqPj5fZbNbEiRPl6+v7wPl58+bVwoUL1bp1a+XJk0dhYWGyWCwKDAzUnDlz5O/vn+T4e7/k3/v38uXLGwvFenp6pnqx0ceRJUsWTZ8+XS4uLrpy5YrxpbJHjx7GMU/jGZLuBmi//PKLGjZsqHz58unYsWPas2ePEhISVK1aNY0fP17jxo174LygoCCjz8qVKz/Ra1C9vb3Vvn175ciRQzExMYqNjU2yOG9q5M2bVwsWLFBQUJBcXFwUGhoqe3t7vfXWW/rpp5+Mz+1x+sqRI4fmzp2rt956Szlz5tSBAweUJUsWvffee5o7d65cXFzSfM2Pw8bGRlOmTFGfPn1UsmRJHTt2TJGRkapQoYK++OILffTRR8ax+fLl0/Tp0/XSSy/JZDLp2rVr6ty5s/H2oXtlyZJFs2bN0ksvvSTp7oiRdu3aJXmNcCIHBwfNnDlTHTp00IsvvqhDhw7JxsbGCEfy5ctn9N+/f3/lyZNH8fHxioqKSnbxVwDWzWR50tWWAAAA8Nzp37+/fv31V7m6uj7wm/fM7ty5cwoICFBCQoLGjh2rxo0bZ3RJAIDnBCNBAAAA8NyIj4/XmDFjlJCQoLx586pevXoZXRIA4DnCmiAAAAB4LjRv3lwnT540FjTu1atXkreMAADwKIQgAAAAeC6YzWbFxMTI3d1d7dq1M159DABAarEmCAAAAAAAsAqsCQIAAAAAAKwCIQgAAAAAALAKrAkCq3fnzh1du3ZNjo6OsrEhFwQAAACA501CQoJu376tHDlyyM4u5aiDEARW79q1azp58mRGlwEAAAAAeEJFihRRnjx5UtxPCAKrl/hqPXd3d2XJkiWDqwEeZDabdfjwYZUqVUq2trYZXQ7wAJ5RZGY8n8jseEaR2T0vz2hsbKxOnjz5yFenE4LA6iVOgXFycpKLi0sGVwM8yGw2S5JcXFwy9f/jgfXiGUVmxvOJzI5nFJnd8/aMPmqJAxZAAAAAAAAAVoEQBAAAAAAAWAVCEAAAAAAAYBUIQQAAAAAAgFUgBAEAAAAAAFaBEAQAAAAAAFgFQhAAAAAAAGAVCEEAAAAAAIBVIAQBAAAAAABWgRAEAAAAAABYBUIQAAAAAABgFQhBAAAAAACAVSAEAQAAAAAAVoEQBACeA87OzhldAvBQPKPIzHg+kdnxjCKzs7e3z+gS0o3JYrFYMroIICPFxMQoLCxMnp6ecnFxyehyAAAAACBTSbhzRxaTSba2thldSopS+73O7hnWBGRqN36cppiDoRldBgAAAABkGnZuhZXz409kNpszupR0QQgC/M+di+dlOXY4o8sAAAAAADwlrAkCAAAAAACsAiEIAAAAAACwCoQgAAAAAADAKhCCAAAAAAAAq0AIAgAAAAAArAIhCAAAAAAAsAqEIAAAAAAAwCoQggAAAAAAAKtACAIAAAAAAKwCIchTsnXrVnl4eOj27dsZXQoAAAAAAJBkl9EFPI9Onjyp4OBgbdy4UdeuXVP27Nnl4+Ojrl27qkyZMmlq8/vvv1ebNm1kZ5f+H8nZs2cVEBAge3t7mUymJPsaNmyozz77LN37vN/kyZM1ZcoU2dvbS5JMJpMKFCigN954Qx07dpStre0Ttb9//35du3ZNVapUSY9yAQAAAAD/QYQgjyksLEytW7dWy5YtFRISorx58yo8PFwzZsxQixYt9PPPP8vb2/ux2oyMjNTYsWPVqlWrpxKCJPrtt99UvHjxp9b+o3h7e2v+/PmSpISEBO3bt0/du3eXjY2NOnXq9ERtL1q0SC4uLoQgAAAAAIAUMR3mMQ0fPlw1a9bUxx9/rBdeeEEmk0lubm4aOnSoevfunWyIcfbsWXl4eOjYsWPGtvHjx6tNmza6fPmyatSoIYvFIl9fX4WEhEiSli1bpqCgIJUrV04BAQGaN2+ecW7//v01YsQIffbZZ3rllVdUqVIlfffdd090XW3atNG4ceP0+uuvG4FEeHi4unTpoooVK8rPz099+/ZVdHS0cc7mzZv11ltvycfHR9WrV9eUKVNS3Z+NjY28vb3VsmVLrVq1ytg+a9YsBQYGysfHR/Xq1Uuyb8+ePWrevLl8fHxUsWJFDRo0SLdu3dKIESP0yy+/aObMmapdu7Yk6fTp02rfvr0qVqyoihUrqnfv3rp+/foT3SMAAAAAwPONEOQxXLlyRTt37tTbb7+d7P533333safD5M2bVzNmzJAkbd++XW+++aZCQ0M1aNAg9enTRzt27NDYsWM1ZswY7dy50zhv6dKlKl26tDZu3Kg+ffpo4sSJunjxYtovTtIff/yhUaNG6dtvv5XFYlG3bt1UoEABrV+/XitWrFBERITGjh0rSbpw4YK6deumli1bavv27Zo+fbrmzp2rJUuWPFafZrPZmAqzbds2TZgwQVOnTtXOnTvVsWNHffzxx4qMjJQk9e3bV82aNdOOHTu0ZMkSHTp0SPPmzdOQIUPk5+endu3aafXq1ZKkwYMHK1++fPr777+1fPlynThxQlOnTn2i+wMAAAAAeL4RgjyGM2fOSJKKFCnyVPsJCQlRrVq1VK1aNdna2srX11f16tXTb7/9Zhzj5uamN954Q/b29qpfv77MZrNOnjz5RP16e3vL29tbJpNJoaGhOnLkiPr06SNnZ2flyZNHPXr00O+//y6LxaKlS5eqZMmSaty4sWxtbeXh4aEWLVokqfFhzGaz9uzZo3nz5qlevXqSpAoVKmjjxo0qVaqUTCaTGjZsqNu3b+vw4cOSpOvXr8vFxUU2NjbKly+f5s+fr3feeSfZ9qdNm6Zhw4bJwcFBuXPnVvXq1bVv374nuj8AAAAAYK0SEhJkNpsz9Z/UYE2Qx5C4qOidO3eMbdu2bVO7du0kSRaLRQUKFDBGI6TV6dOntXnzZnl5eRnbLBaLqlWrZvzs5uZm/N3Z2VmSdOvWrYe2GxQU9MDCqD169DCmv7i6uhrbz5w5I7PZrIoVKyY53mw2KyoqSqdPn1ZoaOgDNRYtWjTF/vfu3Wscb2NjI1dXV7333ntq27at0faUKVO0YsUKY/SHJMXFxUmSevfurYEDB2rGjBmqVq2agoKCUlzjZN++fZowYYIOHTqk+Ph4mc1mlS1b9qH3BwAAAACQvCNHjig2Njajy3hihCCPoUiRIjKZTDp+/Ljy588vSfLz81NoaKikuyM4vv7661S19bCUysnJSS1bttSQIUNSPMbGJvlBPPeGMpK0YsUK4++PWhj13je0ODo6ysXFRbt27Uqxxpo1ayo4ODjF9u5378KoyZkyZYqWL1+u4OBglS5dWhaLJcn0ombNmikwMFDr1q3T2rVr1bhxY02cOFGBgYFJ2rl27Zo6deqkli1b6rvvvlPWrFk1adIkbdq0KdW1AgAAAAD+X8mSJVP8HpoZxMTEGLMIHibzXkEmlCNHDlWtWlUzZ85Mdn9CQkKy2x0dHSUlHamROLUmOe7u7jp06FCSbRcuXEjV8J7EUCbxz72jOx6Hu7u7YmJiktQZHR2tqKgoY//hw4dlsViM/ZcuXTJGbaRFaGioAgICVKZMGdnY2Gj//v1J9kdFRSlXrlxq0qSJpk6dqs6dO2vhwoUPtHP8+HHdvHlT7du3V9asWSVJBw4cSHNdAAAAAGDtbGxsZGtrm6n/pOo6nvJ9+s8ZNGiQ9u7dq169euns2bOSpKtXr2rBggX64osvkn09bu7cuZUtWzatWrVKZrNZ//zzj3bv3m3sd3JykiSdOHFCMTExatq0qXbu3KlFixYpLi5OYWFhatasmVauXPlMrlGSSpUqJR8fH40aNUqRkZG6fv26hg4dqr59+0qSGjRooKtXr2rq1Km6deuWzpw5o3bt2umHH35Ic5+urq46ePCgYmNjdfToUU2fPl3ZsmVTRESELly4IH9/f/3zzz9KSEjQjRs3dPjwYbm7u0u6GzSdPXtW165dU8GCBWVjY6Ndu3YpJiZGs2bN0uXLl3X58uUkU5kAAAAAANaFEOQxFStWTIsWLZKTk5NatWolb29v1a1bVytWrNDAgQP1xRdfPHCOra2thg4dql9//VW+vr5avHhxkjfMeHp6ysfHR02bNtWcOXNUvHhxTZgwQdOnT5evr6969Oih9u3bq379+s/yUjVhwgRZLBYFBASodu3aMpvNGjNmjCQpV65cmjp1qtauXSs/Pz+1bt1ar776apKpOI+rc+fOMpvNqlSpkvr3768ePXrojTfe0MiRI7V//36NGjVKo0aNko+Pj+rWrassWbKoZ8+ekqQ333xTGzZs0Guvvaa8efMa64e8+uqrunbtmsaPH6+4uDi1atUqXe4NAAAAAOD5Y7LcO58BsEIxMTEKCwvTi3/Ml+021g0BAAAAgER2xUsp76QZMpvNqZ5ykhESv9d5enrKxcUlxeMYCQIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAAAAAACrQAgCAAAAAACsAiEIAAAAAACwCoQgAAAAAADAKhCCAAAAAAAAq0AIAgAAAAAArAIhCAAAAAAAsAp2GV0AkFnY5Ssg2+KlMroMAAAAAMg07NwKZ3QJ6YoQBPifbG07ycXFJaPLAAAAAIBMJeHOHclkyugy0gXTYYD/MZvNGV0CkCyz2awDBw7wjCLT4hlFZsbzicyOZxSZndls1r4DBzK6jHRDCAIAz4HY2NiMLgF4KJ5RZGY8n8jseEaR2cXHx2d0CemGEAQAAAAAAFgFQhAAAAAAAGAVCEEAAAAAAIBVIAQBAAAAAABWgRAEAAAAAABYBUIQAAAAAABgFQhBAAAAAACAVSAEAQAAAAAAVoEQBAAAAAAAWAVCEAAAAAAAYBUIQQAAAAAAgFUgBAEAAAAAAFaBEAQAAAAAAFgFQhAAAAAAAGAVCEEAAAAAAIBVIAQBAAAAAABWgRAEAAAAAABYBUIQAAAAAABgFQhBAAAAAACAVSAEAQAAAAAAVoEQBAAAAAAAWAVCEAAAAAAAYBUIQQAAAAAAgFUgBAEAAAAAAFaBEAQAAAAAAFgFQhAAAAAAAGAVCEEAAAAAAIBVIAQBAAAAAABWgRAEAAAAAABYBUIQAAAAAABgFQhBAOA54OzsnNElAA/FM4rMjOcTmR3PKDI7e3v7jC4h3ZgsFoslo4sAMlJMTIzCwsLk6ekpFxeXjC4HAAAAADKVO+Y7MskkW1vbjC4lRan9Xmf3DGsCMrVlZ/7VL+HrM7oMAAAAAMg0imUroPF+nWU2mzO6lHRBCAL8T9TtGzpw7VRGlwEAAAAAeEpYEwQAAAAAAFgFQhAAAAAAAGAVCEEAAAAAAIBVIAQBAAAAAABWgRAEAAAAAABYBUIQAAAAAABgFQhBAAAAAACAVSAEAQAAAAAAVoEQ5AksXrxY/v7+GV1Gqp09e1YeHh46duxYRpfyxI4dOyYPDw+dPXs2o0sBAAAAADwnnpsQZN++ferevbsqVaqkl19+WYGBgfr88891/fr1DKupcePGWrdu3WOflxhGtG7dOtn9Xbt2fawv+KtWrdKpU6ceu44n1b9/f3l6esrLy0teXl4qV66cGjZsqLlz5z7zWgAAAAAAeJTnIgTZuHGjWrduLW9vb61YsUK7d+/Wt99+q6NHj6ply5aKjo7O6BLT5OTJkzp37lySbdeuXdP+/fsfq52vvvoqQ0IQSapbt65CQ0MVGhqq7du3a8CAARo7dqz++OOPDKkHAAAAAICUZPoQJCEhQUOHDtXbb7+tTp06KWfOnDKZTCpevLi+/vprxcbG6ttvv5Ukbd26VT4+Ppo1a5bKly+vXbt2yWw2a/jw4fLx8VGtWrX0xx9/6LXXXlNISIgkKTIyUj179lTlypXl6+urjh076vz580b/Hh4eWrVqlVq2bKly5crp9ddf14EDByRJISEhqlq1qnHs/v379dZbb6lcuXKqU6eOli1b9tBrq169upYuXZpk26pVq1SlSpUk2x5WY6NGjXTkyBF169ZNAwYMSFUdJ06cUJMmTeTl5aW33npLFy5cMPbNmjVLgYGB8vHxUb169bRq1apHf0j/Y2dnp6pVq6pBgwZJzps7d67q1aunl19+WXXr1jXq6dOnj8aMGWMcN2nSJJUpU0Y3b96UJN26dUtly5bVwYMHdeXKFXXo0EE+Pj5q0KCB9u7dm6Tv8PBwdenSRRUrVpSfn5/69u1rhGPJPRcAAAAAAOuT6UOQ/fv368yZM2rbtu0D+xwcHNSiRQutXLnS2BYfH69Tp05p06ZNKleunH766SctX75c8+fP1++//67ly5fr4sWLxvHjxo3TzZs3tXbtWv3111+SpNGjRyfpZ/r06Ro1apQ2b96sfPnyaeLEiQ/UEhsbq86dO+u1117Tv//+q08++UT9+vV76PobdevW1ZIlS5JsW7JkierWrZtk28Nq/P333yVJU6dO1WeffZaqOhYsWKBvvvlGf/31l6KjozV9+nRJ0rZt2zRhwgRNnTpVO3fuVMeOHfXxxx8rMjIyxWtIjtlslq2trSRp3bp1GjdunEaMGKHt27erZ8+e6tOnjw4dOqSKFSsmCSS2b98ud3d37d69W5K0Z88eZc+eXR4eHho9erRu376t9evXa+bMmUaIJUkWi0XdunVTgQIFtH79eq1YsUIREREaO3asccz9zwUAAAAAwPpk+hDkzJkzcnZ2Vv78+ZPdX6xYMZ09e1YWi0XS3S+7rVq1kpOTk0wmk/766y81bNhQJUuWVPbs2fXRRx8pNjbWOP/TTz/V5MmT5eLioixZsigwMFD79u1L0kdQUJCKFSsmZ2dn+fv7Jxts/PPPP4qPj9e7774rBwcHVa1aVZMmTZKTk1OK11a1alVduXJFBw8elCRFRETo6NGjqlatWpLjUlPj49TRqlUr5cuXT7lz51blypV14sQJSVKFChW0ceNGlSpVSiaTSQ0bNtTt27d1+PDhFK/hXvHx8dq4caNWrFih+vXrS5IWLlyohg0bytfXV/b29qpfv748PT21cuVKVapUSfv371dcXJzi4uJ0+PBhBQUFaceOHZLuhiKVKlWSyWTSmjVr9N577ylHjhzKnz9/kvVUQkNDdeTIEfXp00fOzs7KkyePevTood9//z3F5wIAAAAAkHoJCQkym82Z+k9q2D3l+5QuzGazLBZLsl9ek9tesGBB4++XLl1SzZo1jZ+LFi2qrFmzGj+fOnVKY8aM0d69e3Xr1i0lJCQoZ86cSdpzc3Mz/u7s7Kzbt28/UMfp06f14osvGiMgJCkgIOCh12VnZ6cGDRro999/V+nSpbV8+XLVqVNHdnZJP5bU1JiaOhIXWr33epycnBQXFyfp7n2eMmWKVqxYkWT0R+L+5KxYsUJr1qwxrqdw4cIaOnSoAgMDjT4rVaqU5JzChQsrPDxcbm5uypcvn0JDQ2WxWOTh4SFfX199/fXXkqQdO3aoXr16ioqK0q1bt5LUXaRIEePvZ86ckdlsVsWKFZP0YzabFRUVZfx873MBAAAAAEi9I0eOJBlQ8LzK9CFI0aJFFRcXpzNnzsjd3f2B/SdOnFCRIkWSBCH3hggJCQmyt7dPco6NjY2xr3PnzqpQoYJWrlyp3Llza8GCBZo0aVKS41MzcsDGxkYJCQmPc2mS7o4yef/999WnTx8tWbJEgwYNSrI/tTU+aR2SNGXKFC1fvlzBwcEqXbq0LBaLypQp89Bz6tatm+z0oEQpBSiJ97RSpUratWuX4uPjVb58eXl5eenAgQO6ffu2du3apeHDhycJaRIljvCQJEdHR7m4uDxyrY/7wyUAAAAAQOqULFnS+C6dGcXExKRqFkPmvYL/KV26tIoUKaIff/zxgX137tzR/PnzVa9evRTPz5Mnj8LDw42fT506ZbxW9/LlywoPD1ebNm2UO3duSTIWPX1chQoVUnh4eJIv/YsXL1ZYWNhDzytbtqyyZs2qpUuX6urVqypfvnyS/Y9bY1rrkO5OKwkICFCZMmVkY2Pz2G+pSY67u7uOHz+eZNvx48dVqFAhSTLWBdm+fbt8fX3l5OSkwoUL69dff1XevHnl5uam3Llzy97ePsmCtUePHk3SR0xMjM6cOWNsi46OTjIKBAAAAACQdjY2NrK1tc3Uf1J1HU/5Pj0xk8mkYcOGaf78+Ro/frwiIyNlsVh07Ngxvffee8qWLZvat2+f4vkVK1bUkiVLdOLECd24cUMTJ06Ui4uLJCl37txycXHR7t27dfv2bS1ZskRhYWGKjo423lCSWjVq1JCLi4uCg4N1+/Zt/fvvvxo6dGiqPoigoCBNnDhRDRs2fGBfamp0dHTUqVOnFB0d/UR1uLq66uDBg4qNjdXRo0c1ffp0ZcuWTREREY91L+6/tiVLlmj37t2Kj49XSEiIjhw5ogYNGki6OxJk7969Cg0NlY+PjyTJx8dHP/30kypXrixJsre3V6VKlfTjjz/qxo0bCg8P1+zZs40+SpUqJR8fH40aNUqRkZG6fv26hg4dqr59+6a5bgAAAADAf0+mD0EkqXLlypo9e7aOHj1qvGq1S5cuxttfnJ2dUzy3Q4cO8vX1VVBQkJo2barGjRvL2dlZNjY2srOz07BhwzRt2jRVqVJF27Zt0+TJk/Xiiy/qtddee6waHRwc9P333+uvv/6Sn5+fhgwZotGjR6tUqVKPPPf111/X+fPn1ahRowf2pabGFi1a6PPPP1efPn2eqI7OnTvLbDarUqVK6t+/v3r06KE33nhDI0eO1Nq1ax/rfiRq0KCBOnfurL59+6pixYr65ZdfNHPmTGNNj/z588vFxUWurq7GWi3ly5fX0aNHjRBEkkaNGiXpbtjUsWNHvfPOO0n6mTBhgiwWiwICAlS7dm2ZzeYkr98FAAAAAMBkuXdxhf+ouLg4OTg4SLr7lpBy5cpp+vTpSb5kw3rFxMQoLCxMO+3PacKxkEefAAAAAABWokyOwgrxHyaz2ZzqKScZIfF7naenpzH7IznPxUiQJ7F48WK9+uqrOnHihOLj4/Xtt98qW7Zs8vLyyujSAAAAAADAM/Sff11Go0aNdOzYMbVt21bR0dEqUaKEpkyZkuQ1uQAAAAAA4L/vPx+C2NjY6KOPPtJHH32U0aUAAAAAAIAM9J+fDgMAAAAAACARggAAAAAAACtBCAIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAAAAAACrQAgCAAAAAACsgl1GFwBkFrkcs6lMjsIZXQYAAAAAZBrFshXI6BLSFSEI8D/1C72iph61MroMAAAAAMhU7pjvyCRTRpeRLpgOA/yP2WzO6BKAZJnNZh04cIBnFJkWzygyM55PZHY8o8jszGazDuw/kNFlpBtCEAB4DsTGxmZ0CcBD8YwiM+P5RGbHM4rMLj4+PqNLSDeEIAAAAAAAwCoQggAAAAAAAKtACAIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAAAAAACrQAgCAAAAAACsAiEIAAAAAACwCoQgAAAAAADAKhCCAAAAAAAAq0AIAgAAAAAArAIhCAAAAAAAsAqEIAAAAAAAwCoQggAAAAAAAKtACAIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAAAAAACrQAgCAAAAAACsAiEIAAAAAACwCoQgAAAAAADAKhCCAAAAAAAAq0AIAgAAAAAArAIhCAAAAAAAsAqEIAAAAAAAwCoQggAAAAAAAKtACAIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAAAAAACrQAgCAM8BZ2fnjC4BeCieUWRmPJ/I7HhGkdnZ29tndAnpxmSxWCwZXQSQkWJiYhQWFiZPT0+5uLhkdDkAAAAAkKkk3Lkji8kkW1vbjC4lRan9Xmf3DGsCMrUbP05TzMHQjC4DAAAAADINO7fCyvnxJzKbzRldSrogBAH+587F87IcO5zRZQAAAAAAnhLWBAEAAAAAAFaBEAQAAAAAAFgFQhAAAAAAAGAVCEEAAAAAAIBVIAQBAAAAAABWgRAEAAAAAABYBUIQAAAAAABgFQhBAAAAAACAVSAEAQAAAAAAVoEQxIq0adNG48ePz+gyAAAAAADIEHYZXUBm4u/vr4iICNnY/H829MILL6h27drq2bOnsmTJ8tRrWLp0qX7++WcdOnRINjY2Klq0qFq2bKkmTZo89b6fhq1bt6pt27ZycHCQJNnZ2Sl//vxq0qSJOnbsmKo2zGazfvzxR7333nuSpKtXr2r16tVq1qzZU6sbAAAAAPDfQwhyn8GDB6tly5aSJIvFoqNHj6pXr16KjY3V8OHDn2rfkyZN0vz58zV8+HDVqFFDd+7c0fr16/XJJ58oPDxcPXv2fKr9P03bt2+Xo6OjEhIStG3bNnXu3FmFChVS3bp1H3nugQMHNH36dCME2bJlixYsWEAIAgAAAAB4LEyHeQiTyaSSJUuqY8eOWr16tbE9NDRUrVq1kq+vr6pUqaKhQ4cqPj5ep0+flqenp27cuCFJunXrlsqWLatx48YZ506aNEndu3d/oK8TJ04oODhYo0ePVmBgoBwcHOTi4qL69evr888/l8ViMY6dNWuWAgMD5ePjo3r16mnVqlXGvj179qh58+by8fFRxYoVNWjQIN26dcvYbzab9cknn6h8+fKqXLmyli1bZuwLDw9Xly5dVLFiRfn5+alv376Kjo5+ouu6n42NjSpWrKjixYvrxIkTku6OFvHw8NDt27eN43r16qX+/ftr7969atGihS5fviwvLy8tX75cvXv31t69e+Xl5aUzZ84oISFBX331lQIDA/Xyyy+rSZMm2rFjh9GWv7+/vvnmGwUEBGjo0KGPrBEAAAAA8N9ECJIK8fHxSX7u1auXKlWqpK1bt2rhwoX6888/NXfuXLm7u+vFF1/U7t27JUm7d++Wm5tbki/kO3bsUOXKlR/oY82aNXJ1dVWtWrUe2Ofv768PPvhAkrRt2zZNmDBBU6dO1c6dO9WxY0d9/PHHioyMlCT17dtXzZo1044dO7RkyRIdOnRI8+bNM9paunSpateurS1btqhZs2YaNmyY7ty5I4vFom7duqlAgQJav369VqxYoYiICI0dO/aJrut+cXFx+vPPP3XmzBkFBAQ88nhvb2+NGDFCefPmVWhoqOrVq6euXbvK29tboaGhKlSokH744Qf98ccfmj59urZt26bGjRura9euiomJMdr5448/NHPmTA0bNuyRfQIAAAAAkkpISJDZbM7Uf1KD6TAPkZCQoEOHDum7777T66+/bmxfvHixHBwcZGtrq4IFC8rPz0/79u2TJFWsWFG7du1S9erVtX37djVs2FA//fST4uLiJN0dqfHpp58+0NeZM2dUpEiRR9ZUoUIFbdy4UdmzZ5ckNWzYUAMGDNDhw4dVqVIlXb9+XS4uLrKxsVG+fPk0f/78JGuclC9fXtWrV5ck1a1bV99++60iIyN14cIFHTlyRHPmzJGzs7OcnZ3Vo0cPtW/fXsOHD0/zdSXy9fWVdHckio2NjXr27KmSJUs+8npTY+HChXr33XeN+9emTRv98MMPWr9+verXry9Jql69ugoXLpwu/QEAAACAtTly5IhiY2MzuownRghyn5EjR2r06NGS7oYgzs7OatOmjd5//33jmC1btmjKlCk6efKk7ty5ozt37hhrW1SsWFG///67pLujNrp166Z///1Xe/fulY2NjXLlyqVixYo90K/JZFJCQsIj6zObzZoyZYpWrFhhjP6QZIQRvXv31sCBAzVjxgxVq1ZNQUFBKl68uHGcm5ub8XdHR0fj3DNnzshsNqtixYoP9BcVFZXm60p075ogJ06c0JAhQ3T27Nl0WWfl9OnTGjVqlPG5SXc/u/Pnzxs/u7q6PnE/AAAAAGCtSpYsmeQX7JlNTEyMDh8+/MjjCEHuc+/CqP/884/ef/99BQUFyc7u7q06duyYPvjgA/Xr10/NmzeXk5OT+vTpozt37kiSKlWqpBEjRuj27ds6cOCAXn75Zfn4+GjHjh0ymUwpThkpUqSI/vzzT1ksFplMphTrmzJlipYvX67g4GCVLl1aFotFZcqUMfY3a9ZMgYGBWrdundauXavGjRtr4sSJCgwMlKQU23Z0dJSLi4t27dqV7P60Xtf9bGxsVLx4cX344Ydq27atBgwYkOxxqR3KJElOTk4aOXKk6tSpk+Ixtra2qW4PAAAAAJCUjY1Npv5eldraMm+MkwlUq1ZNAQEBGjJkiLEwaVhYmBwcHNS2bVs5OTnJYrEoLCzMOKdAgQLKkyePQkJCVKxYMTk5Oal8+fLauXOndu7cmWJYEBgYqMuXL2vp0qUP7Pvnn3/UvHlz3blzR6GhoQoICFCZMmVkY2Oj/fv3Jzk2KipKuXLlUpMmTTR16lR17txZCxcufOS1uru7KyYmRmfOnDG2RUdHKyoq6omu62EsFotu3bpljEi5d2jVvXU8SqFChXTo0KEk286ePfvY9QAAAAAA/tsIQR5h4MCBOnjwoLG4qKurq27duqWwsDBdu3ZN48aNk4ODgy5evGgEJZUqVdIPP/ygChUqSJLKlSunPXv2KDQ0NMWwoFChQurWrZuGDBmiBQsW6NatW4qNjdXSpUvVq1cvYzSKq6urDh48qNjYWB09elTTp09XtmzZFBERoQsXLsjf31///POPEhISdOPGDR0+fFju7u6PvM5SpUrJx8dHo0aNUmRkpK5fv66hQ4eqb9++xjFpua7knD9/XlOmTFGNGjWUK1cuubm5ydbWVitXrtSdO3f066+/JpnK4uTkpBs3bigiIsIITS5duqSrV68qLi5OLVq00OzZs7V7926ZzWYtW7ZMDRs21Llz51JdEwAAAADgv48Q5BHy5s2r3r17a9y4cYqIiJCPj4/efvtttW7dWg0aNJCrq6sGDhyow4cPq1evXpLurgty4sQJIyzIkSOH8uTJo5w5cypfvnwp9tW9e3d9+umnmj9/vipXrqyaNWtq7ty5GjdunN5++21JUufOnWU2m1WpUiX1799fPXr00BtvvKGRI0dq//79GjVqlEaNGiUfHx/VrVtXWbJkUc+ePVN1rRMmTJDFYlFAQIBq164ts9msMWPGGPvTel3S3YVRvby85OXlpebNm6to0aKaMGGCcY8//vhjTZo0SZUqVVJYWJixoKl0N3xxc3MzpvkEBgbKYrGoVq1a2rdvn5o2bapWrVqpe/fuqlChgqZPn66vv/5aBQsWTNV1AwAAAACsg8mSOHwBsFIxMTEKCwvTi3/Ml+22TRldDgAAAABkGnbFSynvpBkym82Zek2QxO91np6ecnFxSfE4RoIAAAAAAACrQAgCAAAAAACsAiEIAAAAAACwCoQgAAAAAADAKhCCAAAAAAAAq0AIAgAAAAAArEK6hyC8cRcAAAAAAGRGaQpB6tSpk+z269evq0qVKk9UEAAAAAAAwNNg9zgHb968WZs2bVJ4eLi++OKLB/afPXtWcXFx6VYcAAAAAABAenmsECRHjhyKiYmR2WzWrl27Htjv5OSkkSNHpltxwLNkl6+AbIuXyugyAAAAACDTsHMrnNElpKvHCkHKlCmjMmXKyGQyafDgwU+rJiBDZGvbSS4uLhldBgAAAABkKgl37kgmU0aXkS7StCZI3759NWnSJG3fvt3Y9vvvv+uLL75gOgyeW2azOaNLAJJlNpt14MABnlFkWjyjyMx4PpHZ8YwiszObzdp34EBGl5Fu0hSCjBw5Uhs2bFD27NmNbSVKlNC///6rUaNGpVtxAIC7YmNjM7oE4KF4RpGZ8Xwis+MZRWYXHx+f0SWkmzSFIGvWrNGMGTNUqtT/r59QpkwZffPNN1qzZk26FQcAAAAAAJBe0hSCmM1mmZKZDxQfH6/bt28/cVEAAAAAAADp7bEWRk302muv6f3331e7du3k6uoqi8WiEydOaPr06WrQoEF61wgAAAAAAPDE0hSCDBo0SBMmTNCAAQN0/fp1SVL27Nn15ptv6qOPPkrXAgEAAAAAANJDmkIQJycnDRo0SIMGDVJUVJRsbGyUI0eO9K4NAAAAAAAg3aQpBNm2bdtD9/v5+aWpGAAAAAAAgKclTSFImzZtkm/Mzk5OTk7avn37ExUFAAAAAACQ3tIUguzduzfJz2azWadOndL333+v119/PV0KAwAAAAAASE9pekWug4NDkj/Ozs4qXbq0Bg8erBEjRqR3jQAAAAAAAE8sTSFISmJiYnTx4sX0bBIAAAAAACBdpGk6THKvwY2NjdWePXtYFBUAAAAAAGRKaQpBHBwcHtiWNWtWdejQQU2bNn3iogAAAAAAANJbmkKQzz77LL3rAAAAAAAAeKpSHYIMGDAg1Y0SkgAAAAAAgMwm1SHI7du3jb8nJCTor7/+kpubm4oWLaqEhAQdO3ZMERERqlev3lMpFAAAAAAA4EmkOgT54osvjL8PHz5cgwcPVpMmTZIcM3v2bB09ejT9qgMAAAAAAEgnaXpF7pIlSxQUFPTA9mbNmmnJkiVPXBQAAAAAAEB6S1MIki1bNm3YsOGB7Zs3b1a2bNmeuCgAAAAAAID0lqa3w3Tp0kXvv/++ypQpIzc3N5nNZp0/f15hYWEaNGhQetcIAAAAAADwxNIUgjRv3ly+vr5au3atIiIiFBcXp9KlS2vo0KHy9vZO7xoBAAAAAACeWJpCEEkqVqyYChUqpIsXL8pkMil//vyytbVNz9oAAAAAAADSTZpCkGvXrmnYsGFas2aN7ty5I0lydHRUw4YNNWTIEDk6OqZrkQAAAAAAAE8qTSHIp59+qkuXLunrr79W4cKFJUnHjh1TcHCwxo8fz7ogAAAAAAAg00lTCPL3339r5cqVyp07t7GtSJEiKlu2rFq0aEEIAgAAAAAAMp00vSLX1tZWzs7OD2zPnj27YmJinrgoAAAAAACA9JamEKR8+fIaPny4IiMjjW2RkZEaMWKEvLy80q04AAAAAACA9JKm6TBDhw5V165dVbVqVWXPnl2SdP36dRUvXlxTp05N1wIBAAAAAADSQ5pCkPz58yskJEQHDx7U2bNnFRcXp0KFCjEKBAAAAAAAZFppCkG6dOmi4OBglS5dWqVLl07vmgAAAAAAANJdmtYEOXfunPbt25fetQAAAAAAADw1aRoJUqNGDfXs2VPe3t4qWLCg7OySNtO7d+90KQ4AAAAAACC9pCkE2bNnj1xdXXXlyhVduXIlyT6TyZQuhQEA/l9yryUHMhOeUWRmPJ/I7HhGkdnZ29tndAnpxmSxWCyPc8LZs2e1YcMG2dnZqWbNmsqfP//Tqg14JmJiYhQWFiZPT0+5uLhkdDkAAAAAkKncMd+RSSbZ2tpmdCkpSu33uscaCbJt2zZ16tRJ+fLlk9ls1tixYzVr1izeCoP/hGVn/tUv4eszugwAAAAAyDSKZSug8X6dZTabM7qUdPFYIciXX36pnj176r333pMkzZgxQxMmTNCsWbOeRm3AMxV1+4YOXDuV0WUAAAAAAJ6Sx3o7zKFDh9SqVSvj55YtWyosLCzdiwIAAAAAAEhvjxWCxMXFydHR0fjZxcVFt27dSveiAAAAAAAA0ttjhSAAAAAAAADPq8daE8RsNmv+/Pm694UyyW1766230q9CAAAAAACAdPBYIUi+fPkUHBz80G0mk4kQBAAAAAAAZDqPFYKsW7fuadUBAAAAAADwVLEmCAAAAAAAsAqEIAAAAAAAwCpYVQgyefJkNW/ePF3aun37tjw8PLR169Z0aS89DB48WH379pWUvtf6KCEhIapateoz6etR5syZI39//4wuAwAAAACQCT3WmiDpLT4+Xt98843++OMPRUREyGQyqWzZsvrggw/k6+ubkaU9MX9/f0VERMjG5m7O5ODgIA8PD3344Yd65ZVXnkqfI0eOfCrtJmrRooVCQ0O1fv16vfDCC0+1LwAAAAAA0luGjgQZM2aM1q1bp6+++ko7duzQ33//rSpVqqhdu3Y6c+ZMRpaWLgYPHqzQ0FCFhobqn3/+UWBgoDp16vRcXtvRo0d15MgRVa1aVb/++mtGlwMAAAAAwGPL0BBk48aNatCggTw8PGRra6usWbOqa9euGjlypBwcHCRJbdq00dSpU9W9e3eVK1dODRs21PHjxzVy5Ej5+vqqZs2a2rBhg9HmkSNH1LZtW/n6+qpixYoaOnSobt++nWz/s2fPVo0aNXThwgVJ0rJlyxQUFKRy5copICBA8+bNM46NiYlR79695evrq8DAwMd+U46zs7PatWunfPnyGfVGRkaqZ8+eqly5snx9fdWxY0edP39eknT27Fl5eHho5cqVatCggby9vdW6dWtdunRJkrR161b5+Pho1qxZKl++vHbt2qX+/furV69eqbrWWbNmKTAwUD4+PqpXr55WrVr10PoXLlyoV199VQ0bNlRISEiKxyXWvX79etWrV08vv/yyBgwYoNOnT6tFixYqV66c2rRpo2vXrhnnzJ071zi2bt26WrZsmbGvTZs2Cg4OVp8+fVS+fHlVr15dv/32m7F/z549atSokcqVK6f33ntPV65cMfbFxsaqX79+qly5snx8fNSiRQvt27fvodcJAAAAAPjvytAQpGjRovr1118VFhaWZHujRo2UP39+4+f58+erU6dO+ueff2Rra6t27dqpTJky2rRpk2rUqKFx48ZJkuLi4tSuXTu9/PLL+ueff7RgwQJt27ZNX3755QN9b968WV9++aWmTZumF198UaGhoRo0aJD69OmjHTt2aOzYsRozZox27twpSQoODtbBgwf1xx9/aOHChVqxYkWartlsNsvW1laSNG7cON28eVNr167VX3/9JUkaPXp0kuN//vlnzZw5U3///bdMJpOGDRtm7IuPj9epU6e0adMmlStXLsU+77/Wbdu2acKECZo6dap27typjh076uOPP1ZkZGSy58fFxem3335To0aNFBgYqIiICG3fvv2h17l48WLNnz9f06dPV0hIiPr3769x48Zp9erVOnHihBYtWiTp7muXx40bpxEjRmj79u3q2bOn+vTpo0OHDhltzZ49W40aNdLWrVvVvHlzDR8+XPHx8TKbzerZs6eqVaumrVu36sMPP9T8+fON83744QddvnxZq1ev1tatW1W9enUNGTLkoXUDAAAAAP67MjQEGTJkiLJnz67GjRvL399fffr00dKlSxUXF5fkuPLly8vb21tZs2bVK6+8Ijs7O7355ptycHBQzZo1dfLkSUnShg0bFBsbqx49esjJyUnu7u56++23tXz58iTtnTx5Ur1799b48eNVunRpSXcX96xVq5aqVasmW1tb+fr6ql69esaog9WrV6tly5bKnz+/cubMqY4dOz7Wtd68eVMzZsxQZGSkatasKUn69NNPNXnyZLm4uChLliwKDAx8YKRCq1atlD9/fuXIkUPvvvuuNmzYoISEBEl3Q5BWrVrJyclJJpMp2X6Tu9YKFSpo48aNKlWqlEwmkxo2bKjbt2/r8OHDybaxbt062draqmrVqnJxcdFrr71mhBgpadKkibJlyyY/Pz9ly5ZNVatWVaFChfTCCy/I29vb+MwWLlyohg0bytfXV/b29qpfv748PT21cuVKoy0fHx9Vr15d9vb2qlevnqKjo3Xx4kXt27dPFy9eVNeuXeXo6KiXX35ZtWvXNs67fv267O3t5eTkJAcHB3Xr1u2ho1gAAAAAAMlLSEiQ2WzO1H9SI0MXRi1YsKDmzp2ro0ePatOmTdq2bZsGDx6sL7/8Uj///LMxGuTFF180znF0dEwySsTBwcEITc6ePatChQoZU2kkqXDhwjp37pwRHERHR6tLly6qWrWqatSoYRx3+vRpbd68WV5eXsY2i8WiatWqSZIuXLggNzc3Y1+RIkUeeX0jR440RnY4OTnJ09NTs2bNUoECBSRJp06d0pgxY7R3717dunVLCQkJypkzZ5I2ihYtavzd1dVVcXFxunr1apJ7mJKUrtVsNmvKlClasWJFktEf94dPiRYsWKAGDRoYI1iCgoL0/vvva/DgwcqSJUuy5yReo/TgZ+bo6JjkM6tUqVKScwsXLqzw8HDj53vvu5OTkyTp1q1bunDhgrJnz65s2bIZ++/9XFq1aqX27durZs2aql69ugIDAxUQEJBsvQAAAACAlB05ckSxsbEZXcYTy9AQJFGJEiVUokQJtW3bVpcuXVKzZs30ww8/GK97TXzDSqL7f06U0pf4e0dJHDt2TI0bN9ayZcv03nvv6aWXXpJ098t1y5YtU5wukTj9IpHFYnnkdQ0ePFgtW7ZMdl9CQoI6d+6sChUqaOXKlcqdO7cWLFigSZMmPXDcw/q0s0v5I0zpWqdMmaLly5crODhYpUuXlsViUZkyZZJt49y5c9q0aZP+/fffJFNNYmJitGzZMjVr1izZ8+4fmfIkn9nDzr0/7bv3frm5uWnZsmXaunWr1q1bp08++US///67vvrqq2TbAwAAAAAkr2TJkil+N8sMYmJiUpzdcK8MC0EuXLig4OBgffzxx8qaNaux/YUXXlDp0qXTlDAVKlRIZ86cUVxcnDEa5Pjx43JzczM+rLJly2rs2LHKnTu3+vXrp5CQEDk4OMjd3V2hoaEP1PjCCy/I1tZW+fLlMxYtle6+LeVJXL58WeHh4Zo0aZJy584tSTpw4MADx50+fdoIKMLDw+Xk5KRcuXKlqo+UrjU0NFQBAQFGu3v37k2xjZCQEBUvXlxTpkxJsn3mzJlatGhRiiFIarm7u+v48eNJth0/flyBgYGPPDdfvnyKjo7WjRs3jNEgx44dM/bfvHlT9vb2qlKliqpUqaL33ntP/v7+ioqKSvU9BAAAAADc/eV04uyAzCi1tWVYjJM7d25t2rRJffr00fHjx5WQkKDY2FgtXbpUmzdvlr+//2O3WaNGDdnZ2WnKlCmKi4vT8ePH9eOPP6px48bGMYk3plevXrJYLJo4caIkqWnTptq5c6cWLVqkuLg4hYWFqVmzZsbaFNWrV9f8+fN16dIlRUZGavr06U98/S4uLtq9e7du376tJUuWKCwsTNHR0bp586Zx3Jw5c3T58mVdvXpVP/zwg2rWrJni+h/3S+laXV1ddfDgQcXGxuro0aOaPn26smXLpoiIiCTnJyQkKCQkRE2aNFHhwoWT/GndurV27dqVJHRIi6CgIC1ZskS7d+9WfHy8QkJCdOTIETVo0OCR57788svKkSOHpk+frri4OG3fvl1//vmnsb9nz54aO3asoqOjlZCQoF27dilnzpzKkSPHE9UMAAAAAHg+ZVgI4uDgoJ9++kl58uRR+/bt5ePjoypVquiXX37RhAkTVL169cduM0uWLJo2bZq2bdumypUrq2PHjgoKClKXLl2S7X/s2LH66aeftG3bNhUvXlwTJkzQ9OnT5evrqx49eqh9+/aqX7++JKlPnz4qWrSo6tatq6ZNm+qNN9546FSUR7Gzs9OwYcM0bdo0ValSRdu2bdPkyZP14osv6rXXXjOOa9Sokd555x3jfgwdOvSx+7r/Wjt37iyz2axKlSqpf//+6tGjh9544w2NHDlSa9euNc7btGmTLl68qKCgoAfaLFmypLy9vR+5QOqjNGjQQJ07d1bfvn1VsWJF/fLLL5o5c2aq1lxxcnLSlClTtHbtWvn5+enrr79Wu3btjP0jRozQqVOnVKNGDfn5+ennn3/WlClTMvUQLgAAAADA02OypGZxCzxzZ8+eVUBAgJYtW6bixYtndDn/aTExMQoLC9NO+3OacIy3xwAAAABAojI5CivEf5jMZnOmng6T+L3O09NTLi4uKR7Hr8QBAAAAAIBVIAQBAAAAAABWIVO8IhcPcnNz06FDhzK6DAAAAAAA/jMYCQIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAAAAAACrQAgCAAAAAACsAiEIAAAAAACwCoQgAAAAAADAKthldAFAZpHLMZvK5Cic0WUAAAAAQKZRLFuBjC4hXRGCAP9Tv9AraupRK6PLAAAAAIBM5Y75jkwyZXQZ6YLpMMD/mM3mjC4BSJbZbNaBAwd4RpFp8YwiM+P5RGbHM4rMzmw268D+AxldRrohBAGA50BsbGxGlwA8FM8oMjOeT2R2PKPI7OLj4zO6hHRDCAIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAAAAAACrQAgCAAAAAACsAiEIAAAAAACwCoQgAAAAAADAKhCCAAAAAAAAq0AIAgAAAAAArAIhCAAAAAAAsAqEIAAAAAAAwCoQggAAAAAAAKtACAIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAAAAAACrQAgCAAAAAACsAiEIAAAAAACwCoQgAAAAAADAKhCCAAAAAAAAq0AIAgAAAAAArAIhCAAAAAAAsAqEIAAAAAAAwCoQggAAAAAAAKtACAIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAAAAAACrQAgCAAAAAACsAiEIAAAAAACwCoQgAPAccHZ2zugSgIfiGUVmxvOJzI5nFJmdvb19RpeQbkwWi8WS0UUAGSkmJkZhYWHy9PSUi4tLRpcDAAAAAJnKHfMdmWSSra1tRpeSotR+r7N7hjUBmdqyM//ql/D1GV0GAAAAAGQaxbIV0Hi/zjKbzRldSrogBAH+J+r2DR24diqjywAAAAAAPCWsCQIAAAAAAKwCIQgAAAAAALAKhCAAAAAAAMAqEIIAAAAAAACrQAgCAAAAAACsAiEIAAAAAACwCoQgAAAAAADAKhCCAAAAAAAAq0AIAgAAAAAArAIhSAosFot69uypcuXKaenSpTp8+LDq1KmjcuXK6ezZs/Lw8NCxY8cyusxnpk2bNho/fny6tBUSEqKqVaum6tjJkyerefPm6dIvAAAAAMC62WV0AemhXbt22rZtmyTJbDYrISFB9vb2xv4VK1bI1dX1sdoMCwvTypUr9fvvv8vDw0MjR45U9uzZ9ccff+jChQtPVG9ERIQmTZqkjRs3KioqSs7OzqpWrZo+/vhjFSxY8InaTslff/2l7777TocPH1ZMTIwKFCigZs2aqWPHjjKZTI/V1tWrV7V69Wo1a9Ys2f39+/fXb7/9Jju7Bx+vZcuWpal+AAAAAACe1H8iBJk5c6bx98mTJ+vvv//W/Pnzn6jN6OhoSVKRIkUkSTdv3pSbm1uyX+wfh8ViUYcOHeTh4aEFCxYoX758ioiI0KhRo9ShQwctXbpUNjbpO0Bn9+7d6tGjh0aNGqXAwEA5ODho165d+uCDD2SxWNS5c+fHam/Lli1asGBBiiGIJNWtW1cTJ05Mdl9iYAUAAAAAwLNkNdNhPDw8NGvWLFWrVk3Tpk1LdkpG8+bNNXnyZG3cuFHt2rWTJPn6+srDw0OLFy/WihUr5OXl9UDbV69e1ccff6xq1arJx8dHXbt2VURERLJ1XL58WYcPH1bbtm2VP39+mUwmvfjii/r000/VrVs3xcfHS5LCw8PVpUsXVaxYUX5+furbt68RzEjS77//rvr168vHx0f+/v765ZdfUrz2f//9V25ubnr99dfl7OwsW1tb+fr66quvvpKfn59x3KxZsxQYGCgfHx/Vq1dPq1ateqCt5cuXq3fv3tq7d6+8vLx05syZh9z11Pnnn3/05ptvysfHR9WrV9dXX32V4rGzZ89WjRo1jNE4y5YtU1BQkMqVK6eAgADNmzfPOHbPnj1q3ry5fHx8VLFiRQ0aNEi3bt164noBAAAAAM8nqwlBJGnNmjVavHixOnbs+NDjqlatqhkzZkiStm/frkOHDikoKEh169ZVaGjoA8f3799ft27d0h9//KG///5bLi4uGjBgQLJt58qVSzlz5tR3332nixcvGttz586thg0bytHRURaLRd26dVOBAgW0fv16rVixQhERERo7dqwk6cyZM+rXr58GDx6snTt3atSoURoxYoQOHjyYbJ9FixbViRMntGDBAsXFxRnbK1SooPLly0u6OzpjwoQJmjp1qnbu3KmOHTvq448/VmRkZJK26tWrp65du8rb21uhoaEqVKjQQ+/lo8TExKhHjx5q2bKldu7cqenTp+v777/XunXrHjh28+bN+vLLLzVt2jS9+OKLCg0N1aBBg9SnTx/t2LFDY8eO1ZgxY7Rz505JUt++fdWsWTPt2LFDS5Ys0aFDh5KEJAAAAACA1ElISJDZbM7Uf1LjPzEdJrXq1aunvHnzpmubV65c0Z9//qlly5YpR44ckqSPP/5YtWrV0qVLl/TCCy8kOd7Ozk6TJk3SwIEDVbNmTZUsWVKvvPKKAgICVLlyZUlSaGiojhw5ojlz5sjZ2VnOzs7q0aOH2rdvr+HDh8vNzU1btmwx+qtcubLy5Mmj/fv3q3Tp0g/UGBgYqHbt2unTTz/V6NGjVa5cOVWuXFkNGjQw1kqpUKGCNm7cqOzZs0uSGjZsqAEDBujw4cOqVKlSut6ze7m4uGjDhg3KkiWLTCaTPDw85OHhoX379snf39847uTJk+rdu7fGjx9vXGNISIhq1aqlatWqSbo7aqdevXr67bffVL58eV2/fl0uLi6ysbFRvnz5NH/+/HSfagQAAAAA1uDIkSOKjY3N6DKemFWFIE9j0dHE6SCNGzdOst3W1lbnz59/IASR7oYWa9as0a5du7RlyxZt3bpVs2fPVvXq1RUcHKwzZ87IbDarYsWKSc4zm82KiopS7ty5NWfOHC1cuFAXL16UxWJRXFxcklEe9zKZTOrTp486deqkjRs3atu2bZo7d66+/PJLjRo1So0bN5bZbNaUKVO0YsWKJKM/UmrzUVasWKE1a9Yk2WZnZ6ddu3Y9cOzy5cs1a9YshYeHKyEhQfHx8fL19TX2R0dHq0uXLqpatapq1KhhbD99+rQ2b96cZIqSxWIxQpHevXtr4MCBmjFjhqpVq6agoCAVL148TdcDAAAAANasZMmSmfqXyjExMTp8+PAjj7OqEMTW1vah+1M7fOZeTk5OkqQNGzYoV65cj1WLr6+vfH191b17d+3YsUOtWrXS33//LUdHR7m4uCQbGEjSggULNG3aNE2dOlV+fn6ytbVVzZo1H9lnjhw5VL9+fdWvX18Wi0WffPKJxo4dq8aNG2vKlClavny5goODVbp0aVksFpUpUybV13O/hy2Meq/Nmzdr2LBhGj9+vGrXri17e3u1atUqyTHHjh1T48aNtWzZMr333nt66aWXJN299y1bttSQIUOSbbtZs2YKDAzUunXrtHbtWjVu3FgTJ05UYGBgmq8LAAAAAKyRjY3NI79TZ6TU1pZ5Y5ynzNHRMclQHrPZrPDw8Mdux9XVVTY2Njp06JCxLT4+PsWFUbdv365JkyY9sL18+fLKmjWrYmJi5O7urpiYmCSLjkZHRysqKkrS3ekyvr6+qlSpkmxtbXXp0qUk64vcb/r06Vq/fn2SbSaTSdWqVdOtW7dksVgUGhqqgIAAlSlTRjY2Ntq/f/9j3IW027t3r4oWLar69evL3t5et2/f1rFjx5IcU7ZsWY0dO1atW7dWv379jNEp7u7uSe67JF24cMEIs6KiopQrVy41adJEU6dOVefOnbVw4cJncl0AAAAAgMzHakOQwoUL6+bNm/rnn38UFxenb7/9VhaL5bHbyZYtm+rXr6/x48frwoULunXrlr744gu1a9cu2fZy5Mih77//XpMmTdLly5clSZGRkZo4caJMJpNeeeUVlSpVSj4+Pho1apQiIyN1/fp1DR06VH379pV0N3g5fvy4rl27pvDwcI0cOVIFCxZMMXiJiYnRoEGD9Ndff+nWrVtKSEjQoUOHNG3aNPn7+8tkMsnV1VUHDx5UbGysjh49qunTpytbtmzJtuno6KhLly7p6tWraZ4uk8jV1VUXLlzQ+fPndfnyZQ0bNsx4bXCixESvV69eslgsxgiTpk2baufOnVq0aJHi4uIUFhamZs2aaeXKlbpw4YL8/f31zz//KCEhQTdu3NDhw4fl7u7+RPUCAAAAAJ5fVhuClC1bVu+++6569eqlGjVqyM7OTj4+Pmlqa8iQISpcuLAaNGig6tWr6+jRo5o6dapMJtMDx5YsWVI//PCDDh48qKCgIHl5ealevXo6duyYZs+erTx58kiSJkyYIIvFooCAANWuXVtms1ljxoyRJLVs2VKFCxdWzZo11alTJ7Vu3VqtW7fW999/r9mzZz/QZ48ePdSpUydNnDhRVatW1csvv6zu3buratWqGjVqlCSpc+fOMpvNqlSpkvr3768ePXrojTfe0MiRI7V27dok7QUGBspisahWrVrat29fmu5Zojp16qhGjRqqX7++3nrrLdWqVUtdu3bVmjVrNG7cuCTHOjg4aOzYsfrpp5+0bds2FS9eXBMmTND06dPl6+trLB5bv359vfjiixo1apRGjRolHx8f1a1bV1myZFHPnj2fqF4AAAAAwPPLZEnL8AfgPyQmJkZhYWHaaX9OE46FZHQ5AAAAAJBplMlRWCH+w2Q2mzP1miCJ3+s8PT3l4uKS4nFWOxIEAAAAAABYF0IQAAAAAABgFQhBAAAAAACAVSAEAQAAAAAAVoEQBAAAAAAAWAVCEAAAAAAAYBUIQQAAAAAA+A+xrD0jy7f7MrqMTMkuowsAAAAAAOC/zmJOkNadlfZclq7FSSZJblml2u4yFc3+5O3/fU6qUkAmW5NMAYWkgEJPXnQaLFy4UP7+/sqdO3eG9P8ojAQBAAAAAOBpW3pSOhAltfaQPq0oDfKTSuSUZhyQJfLWEzVtiY6Xlp2UEizpUWmamc1mjRkzRlFRURlax8MwEgT4n1yO2VQmR+GMLgMAAADAf9CR46HKVaWE8nqU+f+NbxTTVdeTypIrn2ydHRQRsls39obrzs3bci6SRwVa+MqpQA5J0v6uc1SoUzVdWXtQsWei5JA3q1zfrST7HM46/Nnvslgk06f/qkArP8Vfuano/edVrN9runk4Qqe/2SDXdyvrwvydMt+8rdz+Hsr+sqvCf/pX8ZejlcXzRRXqUFUmWxtZEiy69Mc+Xf33pO5ci9VZt2PakeN1lStXTpLk7++vrl27avXq1dq2bZvy5MmjYcOGqVq1anrllVcUHR2toKAgdenSRd27d8+AO/1whCDA/9Qv9IqaetTK6DIAAAAA/Ad1XRChU3tPadQ7b8nT0/P/d/jf/T8jR47UvutZ9eVvK5QjRw599dVXWvfTOi1avlwmk0kemqPcW29o2tc/qUCBAurevbts/onVd999pa0F3lTbtm21Z+duOTo6avLkyfr77N+a7z9MW7Ns1btx61XrZhF9tG6yVq5cqf79+8v7dn7NXrhc165dU6NGjdQloarq1K6j77//XnMPbNHPsxepYMGCmjdvnrp06aJ169YpW7ZskqQZM2bo888/V+nSpTVs2DCNHj1ay5Yt02+//aaAgAD99ttvKl68+LO/yanAdBjgf8xmc0aXACTLbDbrwIEDPKPItHhGkZnxfCKz4xm1HkOGDFH27NnVuHFj+fv7q0+fPlq6dKni4uKUkJCgkJAQdevWTfnz55eTk5M+/PBDnTt3Tnv37jXaCAoKUrFixeTs7Cx/f38dO3YsVX0nJCSoVatWxnkWi0V16tRR7ty5VbRoURUrVkynTp2SdHdNj3fffVdFihSRg4ODcd5ff/1ltPfqq6/K29tbDg4OqlOnjk6ePKmEhIT0vWFPCSNBAOA5EBsbm9ElAA/FM4rMjOcTmR3PqHUoWLCg5s6dq6NHj2rTpk3atm2bBg8erC+//FI///yzbt68qW7duslkMhnnJCQk6Pz583r55ZclSW5ubsY+Z2dn3b59O9X9FyhQQJLk6OgoScqfP7+xz9HR0Wjr9OnTGjVqlEaPHm3sN5vNOn/+vPHzvXU4OTnJbDYrPj4+1bVkJEIQAAAAAACekRIlSqhEiRJq27atLl26pGbNmmnGjBmSpLlz56ps2bIpnntvQPK4bGxsHvpzIicnJ40cOVJ16tSRdDcA2b17t7EmyMPOfR48v5UDAAAAAPAcuHDhgoYNG6bo6Ogk21944QWVLl1a8fHxypkzpw4dOpRk/9mzZ59lmZKkQoUKPVDHpUuXnnkdTwshCAAAAAAAT1Hu3Lm1adMm9enTR8ePH1dCQoJiY2O1dOlSbd68Wf7+/mrRooW++eYbHTt2TPHx8Zo1a5aaNm2aqulSTk5OkqQTJ04oJibmiWpt0aKFZs+erd27d8tsNmv58uXq27evzp07l+o6Tp48+UDgk1kwHQYAAAAAgKfIwcFBP/30kyZPnqz27dsrMjJSNjY28vT01IQJE1S9enW98sorun79ulq1aqX4+Hh5enrqu+++k7Oz8yPb9/T0lI+Pj5o2bapevXo9Ua1NmzbV+fPn1b17d0VHR6to0aLq1auXChYs+Mhz8+bNqzp16uiDDz5QixYtNHjw4Ceq5WkwWSwWS0YXAWSkmJgYhYWFqVSpUsYrn4DM5N55mLa2thldDvAAnlFkZjyfyOx4RpHZPS/PaOL3Ok9PT7m4uKR4HNNhAAAAAACAVSAEAQAAAAAAVoEQBAAAAAAAWAVCEAAAAAAAYBUIQQAAAAAAgFUgBAEAAAAAAFaBEAQAAAAAAFgFQhAAAAAAAGAVCEEAAAAAAIBVIAQBAAAAAAAP2LZtm8qVK6f4+Phk93l5eSkuLi4DKks7u4wuAAAAAACAzMxsSZCt6dmMIUhLX/7+/oqIiJCNzd3zHBwc5OHhoQ8//FCvvPJKmmvx8/PT7t27tXv3bknSqlWr5OHhocKFC8vPz0+hoaFpbjujEIIAAAAAAPAQtiYbfbztWx2/cf6p9lMsWwGN9+ucpnMHDx6sli1bSpJiY2M1Z84cderUSUuWLFGhQoXSpb6vvvpKffv2VeHChdOlvYxACAIAAAAAwCMcv3FeB66dyugyUsXZ2Vnt2rXT3LlztWHDBjVt2lTjxo3TmjVrFBUVpbJly2rw4MHy9PSUJE2bNk1z5sxRZGSkXnzxRXXr1k1BQUHaunWr2rZtq1mzZumNN97QkSNH1K1bN73++utq3Lix2rZtq71796p169aqWbOmunfvbtQwcuRInThxQjNmzFB4eLhGjBihXbt2KSEhQa+++qo++eQTZc2a9ZnfG9YEAQAAAADgP8hsNsvW1lYTJ07Utm3b9PPPP2vr1q0qU6aMOnfurLi4OO3cuVM//vijZs+erd27d2vIkCEaNmyYrly5kqStX3/9VZI0depUffbZZ0n21a1bV2vWrEmybe3atWrQoIEsFou6deumAgUKaP369VqxYoUiIiI0duzYp3vxKSAEAQAAAADgP+TmzZuaMWOGIiMjVbNmTS1cuFCdO3eWm5ubnJyc9OGHH+rSpUvauXOnbty4IRsbGzk5OclkMqlatWrasWOH8uTJk+r+6tatq4MHDyo8PFyStG/fPl26dEmBgYEKDQ3VkSNH1KdPHzk7OytPnjzq0aOHfv/9d1kslqd1C1LEdBgAAAAAAJ5zI0eO1OjRoyVJTk5O8vT01KxZs+Ti4qIbN26oWLFixrFZsmRRnjx5FB4ertdff11lypSRv7+/KleurBo1aigoKEguLi6p7tvV1VVeXl5as2aN3nnnHa1evVrVq1dX9uzZdebMGZnNZlWsWDHJOWazWVFRUcqdO3f63IBUIgQBAAAAAOA5d+/CqPe6dOlSiueYTCY5ODgoODhYBw8e1Nq1azV79mzNnDlTISEhj9V/vXr1koQgXbt2lSQ5OjrKxcVFu3bterwLekqYDgMAAAAAwH9Unjx5lCVLFh0/ftzYdu3aNV25ckXu7u6Kj49XdHS0Spcurffff1+LFy+WyWTSpk2bHqufOnXqaOfOndqzZ4/Cw8Pl7+8vSXJ3d1dMTIzOnDljHBsdHa2oqKj0ucDHRAgCAAAAAMB/lI2NjRo2bKhp06bpwoULiomJ0fjx41WoUCH5+Pho5syZ6tixoy5cuCBJOnbsmK5duyZ3d/cH2nJ0dNSpU6cUHR39wD5XV1e99NJL+vzzz1WzZk1lyZJFklSqVCn5+Pho1KhRioyM1PXr1zV06FD17dv36V54CpgOAwAAAADAIxTLVuC57aN///4aMWKEmjVrpri4OPn4+Oj777+Xra2t3nvvPZ07d06NGzfWrVu3VKBAAX388cfy9PTU1q1bk7TTokULff7559q0aZPefffdB/qpW7euxo4dq6+++irJ9gkTJmj48OEKCAiQg4ODKleurDFjxjyVa30UkyUjlmMFMpGYmBiFhYWpVKlSypYtW0aXAzzAbDZr9+7dKleunGxtbTO6HOABPKPIzHg+kdnxjD4fzJYE2ZqezUSKZ9lXajwvz2ji9zpPT8+HLuqaee4sAAAAAACZ0LMMJTJTAPJfxN0FAAAAAABWgRAEAAAAAABYBUIQAAAAAABgFQhBAOA54OzsnNElAA/FM4rMjOcTmR3PKDI7e3v7jC4h3fB2GFi91K4iDAAAAADWKMEcL4ts/hNvh7F7hjUBmVrcgenS2V8zugwAAAAAyDRscpaSU61vZTabM7qUdEEIAvxPws0LSriyN6PLAAAAAAA8JawJAgAAAAAArAIjQQAAAAAAeAhTFleZnPI8k74st67IcjP8mfT1rGzdulVt27bV3r175ejomKG1EIIAAAAAAJACUxZXuTTZLJN9lmfSnyX+pmIWVX6sIKRhcC6ZE6SQDlFydvj/7dtP22vYsqxa2iXqiWq6evWqVq5cqbfeeuuJ2skMCEEAAAAAAEiBySmPTPZZdGt9ZyVcPfxU+0pchNTklOexR4PEmU36brOLetaMSfe6tmzZooULFxKCAAAAAABgDRKuHs7UL1LoXC1GX63PoiCvWyqcO+GB/eev2ejzNVm055y9EhKkGiXi1DfwprI6WvR7qKO+3pBFq96PNI5/56ccqlI0XiWKxmrA3N5KSEiQl5eXli1bpilTpsjW1lanT59WVFSUli5dqtOnT+vTTz/Vvn37JElVq1bVsGHDlD179md2D1KDhVEBAAAAAHjOFctj1psv39K4tVkf2GexSL1/za782RP0R5dIhXSI0sUbNpr056On+NT2dlbXrl3l5eWl0NBQFSpUSJK0du1atWvXTkuWLJEkDR48WPny5dPff/+t5cuX68SJE5o6dWr6XmQ6IAQBAAAAAOA/oFPVGB2+aKd1hx2SbD9wwU7HLtnqg5o35Wwv5c5iUeeqMVp2wFEWS9r6cnV11auvviqTySRJmjZtmoYNGyYHBwflzp1b1atXN0aFZCZMhwEAAAAA4D8gq6NFH9S6qS/WZVGVonHG9rNXbWS2mOQ/OekbbswJ0tVYU5r6cnV1TfLzvn37NGHCBB06dEjx8fEym80qW7Zsmtp+mghBAAAAAAD4j2jw0m0t2u2k77e4yK9wvCTJ0U5ysU/Q370iH3H2/0t4xAgRW1tb4+/Xrl1Tp06d1LJlS3333XfKmjWrJk2apE2bNqXpGp4mpsPgqVu8eLH8/f0zugwAAAAAsAr9AqM1e7uzwq/e/crvltOsmHgb42dJunnbZIwCcbSz6Fb8/59vTpDOXbNVah0/flw3b95U+/btlTXr3TVJDhw4kA5Xkv4IQR5T27ZtNXjw4GT3/fbbbypfvrxiYtL/lURpNXnyZJUuXVpeXl7y8vKSt7e36tSpo+DgYJnN5jS3u3nzZoWGhqbq2MaNG2vdunVp6ickJEQeHh5G/T4+PgoKCtKiRYvS1B4AAAAA/Nd55DerYdlbmvq3iySpxAtmvewar/FrsygqxqQbt0watSqLPvkjmyTJPZdZN+NstPmEveLN0vdbnHXvQBBHR0ddunRJV69eVVxc3AP9FSxYUDY2Ntq1a5diYmI0a9YsXb58WZcvX9adO3eexSWnGtNhHlPTpk316aefavDgwXJyckqyb/HixWrQoIFcXFwyqLrkeXt7a/78+ZKkhIQE7du3T927d5eNjY06deqUpjZnzZqlWrVqycvLKz1LTVbevHm1ceNGSdKdO3e0evVq9erVSyVLlpS3t/dT7x8AAAAAbHKWeq766FY9RqsPOsre9m6cMarhDY1ZnVWvf5tbDnYWveIer2H1bkiSPF80623fWA34PZtsbaQ2r8Tq5YL/PzQkMDBQs2fPVq1atTRz5swH+sqfP7969+6tgQMHSpJatWql8ePHq23btmrVqpU++uijdLuuJ2WyWNK6Fqx1un37tqpVq6YhQ4aoUaNGxvbz58/L399f8+bNk7e3t37++WfNnj1b586dk5ubm3r16qXAwEBJUmRkpHr16qVdu3apaNGi6t27tzp16qS1a9fKzc1NoaGh+uyzz3T48GE5ODiodu3aGjx4sOzt7bV161Z169ZNEydO1OjRo3XhwgVVqFBBX3zxhXLkyPFAvZMnT9bff/9thCCJvvnmG61du1YLFy5USEiIZs6cqWrVqmnu3LlauXKlXnjhBX3zzTdavHixIiIiVLx4cfXt21eVK1dWly5d9Oeff8rOzk6+vr764YcfFB4erhEjRmjXrl1KSEjQq6++qk8++URZs2ZVSEiIJkyYoI0bN+rs2bMKCAjQzJkzNW7cOJ08eVKlS5fW+PHj5ebm9kD99557r0qVKmngwIHGZ/D7778rODhY58+fV65cudShQwe1atXKuAf79u2Ts7OzNmzYoJ07dyZpKyYmRmFhYSoavUgOR79Nw1MBAAAA4L/KlMVVLk02y2T/6NfJpgdL/E3FLKosy83wZ9Lfo9jk8ZZL4z9lNpuTrAOS2SR+r/P09HzowARGgjwmR0dHvf766/r111+ThCC//fabSpQoIW9vb61atUpff/21pk+frtKlS2vdunX68MMPtWrVKhUsWFCDBg1SfHy8NmzYoKioqAdSsV69eqlRo0b66aefFBERoRYtWqhEiRJq06aNJCk2NlZ//PGH5s2bp9jYWDVt2lTz589Xx44dU30d9z/AFy9elKOjo7Zt2yZ7e3v99NNPWrBggb799lsVLVpUP//8s7p166Y1a9YoODhY/v7+6tixo1q2bCmLxaJu3bqpfPnymjhxomJiYtS7d2+NHTtWI0aMSLb/H3/8Ud9++60cHR3Vtm1bTZ8+XcOGDXtk3bdu3dKSJUtkY2OjKlWqSJLOnDmjfv36acaMGapcubK2bNmidu3aqXz58ipdurQkaffu3frggw80YcKEVN8jAAAAALDcDFfMosoyOeV59MHp0d+tK5kmALlXQkJCRpfwUKld7oEQJA2aNWumN998U+fPn1eBAgUkSb/++qsx8mDhwoVq2rSp8Tqg1157TRUqVNDSpUvVoUMH/f3335o0aZJy5sypnDlz6q233tInn3xitL948WI5ODjI1tZWBQsWlJ+fX5L3K5vNZnXo0EE5cuRQjhw5VKFCBR0/fjxVtZvNZu3bt0/z5s1T+/btje03btxQx44dZW9vb1xDq1at5OHhIUlq166dpk+frvXr16tJkyZJ2gwNDdWRI0c0Z84cOTs7y9nZWT169FD79u01fPjwZOto2bKl8ufPL0mqVq3aQ9cXuXz5sjHt5s6dO3JyctKQIUOUN29eSZKbm5u2bNlijISpXLmy8uTJo/379xshiK2trVq2bGm8wxoAAAAAUstyMzxTBhPP0pEjRxQbG5vRZTwxQpA08PT0lKenpxYvXqyuXbtq165dOnfunDEy5PTp09q4caN++OEH4xyLxaISJUro6tWrio+PT/JO5fvX1diyZYumTJmikydP6s6dO7pz547q1q2b5Jh7p444Ozvr1q1bKda7d+9eow8bGxu5urrqvffeU9u2bY1jsmfPbqziK0lnz55V8eLFk7Tj7u6u8PAH/+GfOXNGZrNZFStWTLLdbDYrKioq2Zrur//27dsp1n//miAHDx5Unz59dOnSJXXu3Fkmk0lz5szRwoULdfHiRVksFsXFxSVZsOfFF18kAAEAAACANCpZsqRsbDLvu1ViYmJ0+PDhRx5HCJJGTZs21Q8//KCuXbvq119/VWBgoHLlyiVJcnJy0kcffaR27do9cN6VK1ckSXZ2/3/r732Qjh07pg8++ED9+vVT8+bN5eTkpD59+jywou7jPHz3LoyaknvrkZTsir+Skg0SHB0d5eLiol27dqW6prQGEnZ2dipbtqw6deqkcePGqXPnzlqwYIGmTZumqVOnys/PT7a2tqpZs+YD5wEAAAAA0sbGxiZTrwmS2toyb4yTyb3++uu6cOGCdu7cqZUrV6pZs2bGPnd3dx06dCjJ8efOnZPFYlHOnDlla2urc+fOGfvunQoSFhYmBwcHtW3bVk5OTrJYLAoLC3v6F3Qfd3f3JFNs7ty5o1OnTqlQoULJHhsTE6MzZ84Y26Kjo1McBZJeEke/hIaGytfXV5UqVZKtra0uXbqkixcvPtW+AQAAAADPH0KQNMqWLZvq1Kmjzz77TFmyZFHlypWNfW+99ZaWLVum9evX686dO9qyZYsaNmyoPXv2yNbWVr6+vvr+++9148YNnThxQgsWLDDOdXV11a1btxQWFqZr165p3LhxcnBwMKZ5PCtBQUH65ZdfdOzYMcXFxSk4OFhms1n+/v6S7o7+OH36tG7cuKFSpUrJx8dHo0aNUmRkpK5fv66hQ4eqb9++T6W248ePa+bMmcb0I1dXVx0/flzXrl1TeHi4Ro4cqYIFCyoiIuKp9A8AAAAAeD4RgjyBZs2aae/evWrSpEmS6R1Vq1ZVv379NHz4cJUvX17Dhw/XsGHDVK5cOUnSqFGjdP36dVWtWlUDBgxQ586dJd0dXuTj46O3335brVu3VoMGDeTq6qqBAwfq8OHD6tWr1zO7tnbt2qlu3brq2LGjqlSpoq1bt+rHH39U9uzZJUnNmzfXL7/8otatW0uSJkyYIIvFooCAANWuXVtms1ljxoxJl1oSF0b18vKSt7e3OnTooFdffdV4B3XLli1VuHBh1axZU506dVLr1q3VunVrff/995o9e3a61AAAAAAAeP6ZLM9yeAEMcXFxcnBwkHR3IdT33ntPe/bsMbbh2Ul8n3TR6EVyOPptRpcDAAAAAJmGTR5vuTT+U2azOVOvCZL4vc7T01MuLi4pHsdIkAwwcOBAdezYUdevX9eNGzf0/fffq0qVKgQgAAAAAAA8RbwyIwP06dNHQ4cOVWBgoEwmkypUqKBPP/00o8sCAAAAACTDlMVVJqc8z6Qvy60rstwMfyZ9PS1eXl4KDg5W1apVM7qUBxCCZIBcuXLpq6++yugyAAAAAACPYMriKpc3t8jkkPIUi/RkiYtRTEilxwpCGgbnkjlBCukQJed7JhhsP22vYcuyammXp/vmzv379+vatWuqUqWKpKRvQM1sCEEAAAAAAEiBySmPTA4uujp+uO6cPfVU+7JzK6ycH38ik1Oexx4NEmc26bvNLupZM+YpVZeyRYsWycXFxQhBMjNCEAAAAAAAHuHO2VO6c+xwRpeRos7VYvTV+iwK8rqlwrkTHth//pqNPl+TRXvO2SshQapRIk59A28qq+Pdd6Us3uuoKRuyKM4sNXn5lq7G2shskUa0kSwWi7744gstXbpU169fV5EiRTRw4ED5+flpxIgR+uWXX2RjY6OVK1dq9erV8vDw0HfffaetW7dq7969+umnn4w6Vq9erQEDBmjTpk1KSEjQ559/rnXr1unq1avy8vLS0KFDVaJEiad2n1gYFQAAAACA51yxPGa9+fItjVub9YF9FovU+9fsyp89QX90iVRIhyhdvGGjSX9mkSSFXbDVyBVZ1b92tFa9Hykne4v+PPL/82p+++03LV68WPPmzdP27dsVEBCgnj17ymw2a8iQIfLz81O7du20evXqJP3WrVtXO3bs0NWrV41tq1evVmBgoBwcHDR+/HgdOHBA8+bN05YtW+Tl5aXu3bvrab7ElhAEAAAAAID/gE5VY3T4op3WHU765tEDF+x07JKtPqh5U872Uu4sFnWuGqNlBxxlsUibTjioZD6zAjz+r717j6qqTtg4/uWuXETRGXRIwSJNA+Ew6FGkqWBZoIOStRwrNd/JMRUxL3ipwaEmR3TUxl5n0GSVThMtnXydsChTREYR0/CSWMCytAYQ0VBkULkdzvuHeYoB03Ryq+f5/OX57X32fvZxr6XnOfu3dwNuzvD0oAu0d/m2iIiLiyMrK4uuXbvi5OTEsGHDOH36NMePH//ePMHBwXTr1o3t27cD0NTURG5uLrGxsTQ3N7Nx40amTJmCr68v7dq1Y/r06Rw/fpxDhw799z+cb2g6jIiIiIiIiMhtwNPNyrMPnOPlHA8iejbYxsuqHbFYHYha0fIJN5ZmqL7gwNe1jnTrYLGNOznCPb5NttcXLlwgNTWVvLw8zp49axtvaGjgSmJiYsjOzuaRRx5h7969ODg4MHjwYKqqqjh37hxTpkzBwcHBtn5zczMVFRWEhIRc02dwJSpBRERERERERG4Tw+6t5/8OtmPNR+70928EwM0Z3F2a2TnjdJvvabaCs1PLse/0Erz44ouUlJSQkZGBv78/paWlDBky5KryxMbGMmbMGOrq6tiyZQsPPfQQzs7OtGvXDoB169YRFBT0ww/0GqkEEfmGo0dXHDv3MzqGiIiIiIjcRBy87zZknz/o3hVOlTh2uBPHzm4APPdYI/+z8mv8/LzB6d/0COjK+cZTVDj0xc/nYg1wrr6Zxibo6OFI5y41FBXX49i5JwCWZivFp07S/y5XHDv24tChQzz66KMEBAQAFx+Je7WCgoLo0qUL+fn5ZGdns2TJEgC8vLzo2LEjJSUlLUqQsrIy7rjjjh9y9D+IShCRb7j2nYB7+DSjY4iIiIiIiJ1r/+DqH7S+4/9G4RaZirvZDIAJeOTUi6Rt3Yqre1f6TcrBlDuaZXs7snDhQpydnVn04ovU1NSQnp7OfX4fs3rsWPZ2TCEiIoLXV6+mwTED5x730+6BRfi98T8cPnyYhoYGPvvsM7KysgA4efIkd911F25ubpSVlXH27Fm8vb1b5YuJieG1117DarUyYMAA2/jo0aNZuXIloaGh9OjRg4yMDFatWsX27dtp3779tX+A30MliMg3LBbLlVcSMYDFYqGkpITevXvj5OR05TeI3GA6R+VmpvNTbnY6R28dznf431L7mD59Oh988AGurhdvkrps2TJ+//vfEx0djaurK4MGDWLRokUA9O/fn+nTp5OUlISLiwtPPfUUZrMZBwcHLBYLI0bEs3r1agYMGEBISAh//OMfAZgyZQpvvvkmI0eOJDk5mYceeoj8/PxWWWJiYkhPT2fMmDEtzvMpU6ZQU1PDE088QWNjI3369CE9Pf1HK0AAHKw/5rNnRG4B58+fp6ioiF69euHl5WV0HJFWLBYLBw8eJDQ0VP85kpuSzlG5men8lJudztFbg7XZgoPjjfn7uZH7+q6GhgZbYQIwZswYwsPDSUxMvCXO0Uvf6/r06YO7u/tl19MjckVERERERES+x40sJYwoQEpLSzGZTOTk5NDc3ExeXh4HDhzgF7/4xQ3P8mPTdBgRERERERERO9a9e3cWLVrEkiVLmDlzJr6+vqSkpBAWFnbb3TZAJYiIiIiIiIiInYuLiyMuLs7oGD86TYcREREREREREbugEkRERERERERE7IJKEBERERERERGxCypBRERERERERMQuqAQREREREREREbugEkRERERERERE7IJKEBERERERERGxCypBRERERERERMQuqAQREREREREREbugEkRERERERERE7IJKEBERERERERGxC85GBxAxWnNzMwB1dXU4OTkZnEakNYvFAsD58+d1jspNSeeo3Mx0fsrNTueo3OxulXP0woULwLff7y7HwWq1Wm9EIJGbVVVVFV9++aXRMUREREREROQ6BQQE0Llz58suVwkidq+pqYmzZ8/i5uaGo6NmiImIiIiIiNxqmpubqa+vx9vbG2fny096UQkiIiIiIiIiInZBP3uLiIiIiIiIiF1QCSIiIiIiIiIidkEliNi18vJyJk6ciNls5sEHH2TJkiVXvJuwyI1UXl5OQkICZrOZiIgI5s2bR01NjdGxRFpZuHAhvXv3NjqGSCsrV64kMjKS0NBQxo8fT1lZmdGRRGw+++wzxo0bR3h4OIMHDyYpKYnTp08bHUvs2M6dO4mIiGDGjBmtlr3//vvExcVhMpkYOXIkeXl5BiS8fipBxK4lJibi6+tLdnY2a9asITs7m7/+9a9GxxKxmTRpEh06dCAnJ4eNGzdy5MgRFi9ebHQskRaKiorIzMw0OoZIKxkZGWzatIk33niDvLw8AgMDWbt2rdGxRICLN+efOHEioaGh5Ofn895773H69GleeOEFo6OJnUpPT2fBggX4+/u3WlZUVMTcuXNJSkrio48+Yvz48UydOpUTJ04YkPT6qAQRu1VYWEhxcTFJSUl4eXkREBDA+PHjWb9+vdHRRACoqakhKCiIWbNm4eHhQdeuXXnkkUcoKCgwOpqITXNzMykpKYwfP97oKCKtvP7668yYMYM777wTT09PkpOTSU5ONjqWCACnTp3i1KlTjBgxAldXVzp16sSQIUMoKioyOprYKTc3NzZs2NBmCfL2229z//33c//99+Pm5sbw4cPp1asXmzZtMiDp9VEJInbr008/xc/PD29vb9vYvffey7Fjx6itrTUwmchFHTp0IDU1lS5dutjGKioq+OlPf2pgKpGW1q1bh5ubG3FxcUZHEWmhsrKSsrIyzp49y9ChQzGbzUybNk1TDeSm4evrS58+fVi/fj3nzp2jqqqKLVu28MADDxgdTezUuHHj8PLyanPZp59+St++fVuM9e3bl8LCwhsR7b9KJYjYrerqajp06NBi7FIhcubMGSMiiXyvwsJC3nzzTSZPnmx0FBEAvv76a1asWEFKSorRUURauXSJ9ubNm1mzZg2ZmZmcOHFCV4LITcPR0ZEVK1awbds2wsLCiIiIoKmpiVmzZhkdTaSV6urqFj8ew8XvTrfi9yaVIGLXrFar0RFErsq+fft4+umnmTVrFhEREUbHEQEgNTWVkSNHEhgYaHQUkVYu/Rs/YcIEfH196dq1K4mJieTk5FBfX29wOhFoaGhg0qRJxMTEUFBQwI4dO/Dy8iIpKcnoaCJtul2+O6kEEbvl4+NDdXV1i7Hq6mocHBzw8fExJpRIG3Jycpg4cSLPP/8848aNMzqOCAC7d+/mwIEDJCQkGB1FpE2XphJ+96pPPz8/rFYrVVVVRsUSsdm9ezdlZWXMnDkTLy8vfH19mTZtGlu3bm31f1QRo3Xq1KnN70634vcmlSBit4KCgqioqGgxN7iwsJDAwEA8PDwMTCbyrf379zN37lxeeeUV4uPjjY4jYrNp0yaqqqp48MEHMZvNjBw5EgCz2UxWVpbB6USga9eueHp6trjJZHl5OS4uLrq3ktwULBYLzc3NLX5db2hoMDCRyOUFBQVx+PDhFmOFhYWEhIQYlOjaqQQRu9W3b1+Cg4NZtmwZtbW1fPHFF6xZs4bHH3/c6GgiwMVH5yUnJ5OUlERkZKTRcURamDdvHh9++CGZmZlkZmayevVqADIzM4mKijI4nQg4Ozvz2GOPsWrVKr766iuqqqr4y1/+QlxcHM7OzkbHE8FkMuHu7s6KFSu4cOECZ86cYeXKlfTv35+OHTsaHU+khVGjRpGfn09ubi719fVs2LCBL7/8kuHDhxsd7QdzsN4uE3tErsGJEyeYP38+e/fuxdPTk9GjRzN16lQcHByMjiZCQUEBTz75JK6urq2Wbd68GT8/PwNSibStrKyM6OhoSkpKjI4iYtPQ0EBqaipZWVk0Njby8MMPM3/+fF3xKTeNw4cPs3jxYoqLi3F1dWXAgAHMmzcPX19fo6OJHQoODgYu/hAH2ArjS0+A2bJlC8uWLaO8vJzAwEB++9vf0r9/f2PCXgeVICIiIiIiIiJiFzQdRkRERERERETsgkoQEREREREREbELKkFERERERERExC6oBBERERERERERu6ASRERERERERETsgkoQEREREREREbELKkFERERERERExC6oBBERERERERERu6ASREREROQGGTt2LEuXLjVs/5WVlYwcOZKQkBAqKipu+P7feecdoqKibvh+RURELnE2OoCIiIiIEaKiomhqamLz5s24u7vbxvfs2cNzzz1HTk6Ogel+HB988AFVVVXs2bOHdu3atVoeFRVFZWUljo7f/k72k5/8hCFDhjBt2jQ8PDyua//x8fHEx8df1zZERESuh64EEREREbvV0NBAWlqa0TFumNraWnx9fdssQC5JTk6msLCQwsJCDh06xKuvvsquXbtYvHjxDUwqIiLy41AJIiIiInYrMTGRjIwMjh071ubysrIyevfuzRdffGEbW7p0KWPHjgUuXjUSFhbGtm3biIqKwmQysXz5cgoLCxk+fDgmk4mpU6fS2Nhoe39dXR2zZs3CZDIxZMgQNm/ebFtWXV1NUlISkZGRmEwmJk+eTGVlZYssb731FgMGDOC9995rM/O6deuIjY0lJCSEmJgY3n//fQCWL19OWloahw4dIjg4mPLy8it+Pg4ODtx999385je/YevWrbbx8vJyJk2ahNlspn///syZM4fa2lr+/e9/ExQUxN69e1tsZ/jw4axevZqNGzcyePBg23hxcTFPPfUU4eHhDBw4kAULFtDY2Mju3bsxm8229f71r3/Zjv2S2bNnk5qaytdff01CQgJms5mwsDDGjx9PaWnpFY9NRETsk0oQERERsVuBgYGMGjWKBQsWXPM2Lly4wO7du8nKyiIlJYVVq1aRlpbG2rVr2bhxI//85z9bTK3JzMxk6NCh7NmzhzFjxpCUlGQrOubNm0ddXR1ZWVns3LkTd3d3nnvuuRb727t3Lzk5OQwbNqxVlpycHJYsWcJLL71EQUEB06ZNY/bs2ZSUlDB9+nQmT55Mv379KCwsxM/P76qP8bsljtVqZcqUKXTr1o3c3Fw2b95MZWUlixcvxsvLi8GDB5OdnW1bv7S0lJKSEmJjY1t9bhMmTCAiIoL8/Hzefvtt9uzZw2uvvYbJZOL8+fMcPXoUgI8//piePXuyb98+2/v37dtHREQEr7zyCt7e3uzYsYO8vDx69Oihq1ZEROSyVIKIiIiIXUtMTKSkpKTFlQ4/RHNzM0888QTt27cnKioKq9XKww8/jI+PDz179uTOO+/kq6++sq3fr18/oqOjcXV1ZcyYMXh4eJCfn09VVRXbt29nxowZeHt74+npSVJSErt27eLUqVO298fHx+Pp6YmDg0OrLBs2bOCXv/wl4eHhuLi4MHToUPr06cOHH354zcdWVFREeno6cXFxABQWFnLkyBFmz55N+/bt6dy5M4mJiWzatAmr1UpsbCzbtm2zbWPr1q3069eP7t27t9h2bm4uVquVZ555BldXV7p3787TTz9NZmYm7dq1IzQ0lAMHDgBQUFDAr371K9vriooKTp48SXh4ODU1Nbi4uODq6oq7uzsvvPACf/7zn6/peEVE5PanG6OKiIiIXbtUNqSmpnLfffdd0za6desGgJubGwC+vr62ZW5ubtTX19teBwYG2v7s5OSEn58flZWVtikc/3njUCcnJyoqKvDx8QHgZz/72WVzlJWVMXDgwBZj/v7+VzX15ZIFCxawcOFC4GIJ0r59e8aOHUtCQgJw8coOi8XSYroKgMVi4cyZM0RHR5OcnExxcTH33HMPW7dubfOqldLSUqqqqggODraNWa1WXF1dATCbzRw4cIBHH32Ujz/+mISEBDIyMjhx4gQFBQX069cPDw8PJkyYwOTJk9m5cyeRkZHExsYyaNCgqz5eERGxLypBRERExO7Fx8ezfv16Xn311VYlwn+yWCytxr77NJW2Xl9pmZubm+1mpTt27KBTp06t1ikrKwMuliKX09DQ0OZ4W1eNXE5ycjKPP/44AHl5eSQkJDBixAicnZ1tWd3d3W1XZbQlMjKS7OxsOnfuzKFDh1i+fHmrddzc3Lj77rt5991329zGwIEDSUlJobKyksbGRu644w5CQ0MpKCigoKDAVnQEBweTk5PDzp07yc3NZerUqYwaNYq5c+de9TGLiIj90HQYEREREeB3v/sda9eubXFTzUtXdtTV1dnGrvemm9+9CavFYqG8vBxfX1/8/PxwdHSkpKTEtryxsdF2v5Cr0aNHD9t9NC45evRoq6koVysyMpLo6Gjmz5+P1Wq17eP8+fMtPofa2lrOnDljex0TE8P27dvJzs4mNDS0xZUx381aWlrKuXPnbGNnzpyhtrYWuDht6Pjx42RnZ/Pzn/8cAJPJxP79+9m/f7+tBKmursbFxYXo6GheeuklVq5cybp1667peEVE5PanEkREREQE6NOnD/Hx8S2uWvDx8cHLy4stW7ZgsVjIy8vj4MGD17Wf/fv3s2vXLhobG1m3bh11dXVERkbi5eXF0KFDWbp0KSdOnKCuro6XX36ZX//617YC4kpGjBjBu+++y8GDB2lsbGTjxo0cOXKkzekoV+v555+nuLiY9evXA9CrVy9MJhN/+MMfOH36NDU1NaSkpDBnzhzbe6Kjo/n888/ZtGkTQ4cObXO7kZGR+Pj4sHjxYmprazl16hTPPvssS5cuBcDV1RWTycTf/vY3WwkSFhZGfn4+FRUVhISEADB69GjS09Opr6+nsbGRTz75BH9//2s+XhERub2pBBERERH5xvTp02lqarK9dnJyIiUlhX/84x+Eh4fzzjvv8OSTT17XPkaNGsXf//53BgwYwBtvvMGf/vQnOnToAMD8+fPx9/dn2LBh3HfffXz++eekpaVd9XSWYcOG8cwzzzBnzhzMZjNvvfUWr7/+OgEBAdect0uXLsycOZMlS5bYrkpZtmwZVquV6OhohgwZgsViYdGiRbb3eHl5MWjQID755BNiYmLa3K6LiwtpaWkcPXqUwYMHEx8fT0BAQItpLGazmWPHjtlKkF69enHy5EnCwsJwcXEBLj76d/v27QwcOJCIiAh2795tK1JERET+k4P1an9aEBERERERERG5helKEBERERERERGxCypBRERERERERMQuqAQREREREREREbugEkRERERERERE7IJKEBERERERERGxCypBRERERERERMQuqAQREREREREREbugEkRERERERERE7IJKEBERERERERGxCypBRERERERERMQuqAQREREREREREbugEkRERERERERE7ML/A36dfbccdOUGAAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "📊 Saved: sentiment_per_product.png\n"
          ]
        }
      ],
      "source": [
        "# Use synthetic products (they have readable names)\n",
        "df_named = df_synthetic.copy()\n",
        "sent_pivot = df_named.groupby(['product_name','sentiment_label']).size().unstack(fill_value=0)\n",
        "for col in ['Positive','Neutral','Negative']:\n",
        "    if col not in sent_pivot.columns: sent_pivot[col] = 0\n",
        "sent_pivot = sent_pivot[['Positive','Neutral','Negative']]\n",
        "\n",
        "fig, ax = plt.subplots(figsize=(11, 5))\n",
        "sent_pivot.plot(kind='barh', stacked=True, ax=ax,\n",
        "    color=['#27ae60','#f39c12','#e74c3c'], edgecolor='white')\n",
        "ax.set_title('Sentiment Breakdown per Synthetic Product', fontsize=13, fontweight='bold')\n",
        "ax.set_xlabel('Number of Reviews')\n",
        "ax.set_ylabel('Product')\n",
        "ax.legend(title='Sentiment', loc='lower right')\n",
        "ax.invert_yaxis()\n",
        "plt.tight_layout()\n",
        "plt.savefig(PY_FIG / 'sentiment_per_product.png', dpi=150, bbox_inches='tight')\n",
        "plt.show()\n",
        "print('📊 Saved: sentiment_per_product.png')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "pfz8AErmGR33"
      },
      "source": [
        "### *f. Helpful votes analysis*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "1scY_sFoGR33",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 529
        },
        "outputId": "bf5b1d57-192f-46fc-f61f-4fa2dde796b1"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/tmp/ipykernel_1475/3474279436.py:27: UserWarning: Glyph 11088 (\\N{WHITE MEDIUM STAR}) missing from font(s) Liberation Sans.\n",
            "  plt.tight_layout()\n",
            "/tmp/ipykernel_1475/3474279436.py:28: UserWarning: Glyph 11088 (\\N{WHITE MEDIUM STAR}) missing from font(s) Liberation Sans.\n",
            "  plt.savefig(PY_FIG / 'helpfulness_analysis.png', dpi=150, bbox_inches='tight')\n",
            "/usr/local/lib/python3.12/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 11088 (\\N{WHITE MEDIUM STAR}) missing from font(s) Liberation Sans.\n",
            "  fig.canvas.print_figure(bytes_io, **kw)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1300x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "fig, axes = plt.subplots(1, 2, figsize=(13, 5))\n",
        "fig.suptitle('Helpfulness & Engagement Analysis', fontsize=14, fontweight='bold')\n",
        "\n",
        "# Avg helpful votes by sentiment\n",
        "avg_h = df.groupby('sentiment_label')['helpful_votes'].mean().reindex(['Positive','Neutral','Negative'])\n",
        "avg_h.plot(kind='bar', ax=axes[0], color=['#27ae60','#f39c12','#e74c3c'], edgecolor='white', width=0.6)\n",
        "axes[0].set_title('Avg Helpful Votes by Sentiment', fontweight='bold')\n",
        "axes[0].set_xticklabels(['Positive','Neutral','Negative'], rotation=0)\n",
        "axes[0].set_ylabel('Avg Helpful Votes')\n",
        "for p in axes[0].patches:\n",
        "    axes[0].annotate(f'{p.get_height():.1f}',\n",
        "                     (p.get_x()+p.get_width()/2, p.get_height()),\n",
        "                     ha='center', va='bottom', fontsize=10)\n",
        "\n",
        "# Avg helpful votes by star rating\n",
        "avg_r = df.groupby('rating')['helpful_votes'].mean()\n",
        "avg_r.plot(kind='bar', ax=axes[1],\n",
        "    color=['#e74c3c','#e67e22','#f1c40f','#2ecc71','#27ae60'], edgecolor='white', width=0.6)\n",
        "axes[1].set_title('Avg Helpful Votes by Star Rating', fontweight='bold')\n",
        "axes[1].set_xticklabels(['1⭐','2⭐','3⭐','4⭐','5⭐'], rotation=0)\n",
        "axes[1].set_ylabel('Avg Helpful Votes')\n",
        "for p in axes[1].patches:\n",
        "    axes[1].annotate(f'{p.get_height():.1f}',\n",
        "                     (p.get_x()+p.get_width()/2, p.get_height()),\n",
        "                     ha='center', va='bottom', fontsize=10)\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.savefig(PY_FIG / 'helpfulness_analysis.png', dpi=150, bbox_inches='tight')\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Eo1pvyfGGR33"
      },
      "source": [
        "### *g. Category sentiment heatmap (synthetic products)*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "i4Os9kpbGR33",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 563
        },
        "outputId": "e12522ce-db33-4d45-b06a-2df30cca3e0a"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 900x540 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "📊 Saved: category_sentiment_heatmap.png\n"
          ]
        }
      ],
      "source": [
        "if 'category' in df_synthetic.columns:\n",
        "    cat_sent = df_synthetic.groupby(['category','sentiment_label']).size().unstack(fill_value=0)\n",
        "    for col in ['Positive','Neutral','Negative']:\n",
        "        if col not in cat_sent.columns: cat_sent[col] = 0\n",
        "    cat_sent = cat_sent[['Positive','Neutral','Negative']]\n",
        "    cat_pct  = cat_sent.div(cat_sent.sum(axis=1), axis=0) * 100\n",
        "\n",
        "    fig, ax = plt.subplots(figsize=(9, max(4, len(cat_sent)*0.9)))\n",
        "    sns.heatmap(cat_pct, annot=True, fmt='.1f', cmap='RdYlGn',\n",
        "                linewidths=0.5, ax=ax, cbar_kws={'label':'% of Reviews'})\n",
        "    ax.set_title('Sentiment Share (%) by Food Category', fontsize=13, fontweight='bold')\n",
        "    plt.tight_layout()\n",
        "    plt.savefig(PY_FIG / 'category_sentiment_heatmap.png', dpi=150, bbox_inches='tight')\n",
        "    plt.show()\n",
        "    print('📊 Saved: category_sentiment_heatmap.png')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "BnSmsdpzGR34"
      },
      "source": [
        "## **5.** 🔢 Quantitative Analysis"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4thOj0vbGR34"
      },
      "source": [
        "### *a. Key Performance Indicators (KPIs)*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "UnuO-wkgGR34",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1890fb97-94f1-460f-e087-51a7aced76c7"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "=============================================\n",
            "        KEY PERFORMANCE INDICATORS\n",
            "=============================================\n",
            "  total_reviews            : 560\n",
            "  real_reviews             : 500\n",
            "  synthetic_reviews        : 60\n",
            "  unique_products          : 245\n",
            "  avg_rating               : 3.04\n",
            "  avg_sentiment_score      : 0.161\n",
            "  pct_positive             : 60.5\n",
            "  pct_negative             : 11.4\n",
            "  pct_neutral              : 28.0\n",
            "  avg_helpful_votes        : 5.0\n",
            "=============================================\n",
            "\n",
            "💾 Saved: kpis.json\n"
          ]
        }
      ],
      "source": [
        "kpis = {\n",
        "    'total_reviews'      : int(len(df)),\n",
        "    'real_reviews'       : int(len(df_real)),\n",
        "    'synthetic_reviews'  : int(len(df_synthetic)),\n",
        "    'unique_products'    : int(df['product_id'].nunique()),\n",
        "    'avg_rating'         : round(float(df['rating'].mean()), 2),\n",
        "    'avg_sentiment_score': round(float(df['sentiment_score'].mean()), 3),\n",
        "    'pct_positive'       : round(float((df['sentiment_label']=='Positive').mean()*100), 1),\n",
        "    'pct_negative'       : round(float((df['sentiment_label']=='Negative').mean()*100), 1),\n",
        "    'pct_neutral'        : round(float((df['sentiment_label']=='Neutral').mean()*100), 1),\n",
        "    'avg_helpful_votes'  : round(float(df['helpful_votes'].mean()), 1),\n",
        "}\n",
        "\n",
        "print('=' * 45)\n",
        "print('        KEY PERFORMANCE INDICATORS')\n",
        "print('=' * 45)\n",
        "for k, v in kpis.items():\n",
        "    print(f'  {k:<25}: {v}')\n",
        "print('=' * 45)\n",
        "\n",
        "with open(PY_TAB / 'kpis.json', 'w') as f:\n",
        "    json.dump(kpis, f, indent=2)\n",
        "print('\\n💾 Saved: kpis.json')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "AiarBy2qGR34"
      },
      "source": [
        "### *b. Synthetic product-level performance table*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "8MA70um3GR34",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 479
        },
        "outputId": "8647b7a2-9e9b-4d4e-be5a-11641431dd46"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "📋 Synthetic Product Performance Table:\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "                         avg_rating  n_reviews  avg_sentiment  total_helpful  \\\n",
              "product_name                                                                   \n",
              "Organic Matcha Powder           5.0         10           0.36            249   \n",
              "Smoked Paprika Almonds          5.0         10           0.36            371   \n",
              "Truffle Sea Salt Flakes         4.0         10           0.43            312   \n",
              "Vegan Protein Bar               3.0         10           0.19            262   \n",
              "Gluten-Free Pasta               2.0         10          -0.12            333   \n",
              "Raw Cashew Butter               1.0         10          -0.23            358   \n",
              "\n",
              "                         Positive  Neutral  Negative  positive_ratio  \\\n",
              "product_name                                                           \n",
              "Organic Matcha Powder          10        0         0             1.0   \n",
              "Smoked Paprika Almonds         10        0         0             1.0   \n",
              "Truffle Sea Salt Flakes        10        0         0             1.0   \n",
              "Vegan Protein Bar               0       10         0             0.0   \n",
              "Gluten-Free Pasta               0        0        10             0.0   \n",
              "Raw Cashew Butter               0        0        10             0.0   \n",
              "\n",
              "                         negative_ratio  \n",
              "product_name                             \n",
              "Organic Matcha Powder               0.0  \n",
              "Smoked Paprika Almonds              0.0  \n",
              "Truffle Sea Salt Flakes             0.0  \n",
              "Vegan Protein Bar                   0.0  \n",
              "Gluten-Free Pasta                   1.0  \n",
              "Raw Cashew Butter                   1.0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-fe3a2c94-7c7a-444d-a4fa-a696f820f04f\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>avg_rating</th>\n",
              "      <th>n_reviews</th>\n",
              "      <th>avg_sentiment</th>\n",
              "      <th>total_helpful</th>\n",
              "      <th>Positive</th>\n",
              "      <th>Neutral</th>\n",
              "      <th>Negative</th>\n",
              "      <th>positive_ratio</th>\n",
              "      <th>negative_ratio</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>product_name</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>Organic Matcha Powder</th>\n",
              "      <td>5.0</td>\n",
              "      <td>10</td>\n",
              "      <td>0.36</td>\n",
              "      <td>249</td>\n",
              "      <td>10</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Smoked Paprika Almonds</th>\n",
              "      <td>5.0</td>\n",
              "      <td>10</td>\n",
              "      <td>0.36</td>\n",
              "      <td>371</td>\n",
              "      <td>10</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Truffle Sea Salt Flakes</th>\n",
              "      <td>4.0</td>\n",
              "      <td>10</td>\n",
              "      <td>0.43</td>\n",
              "      <td>312</td>\n",
              "      <td>10</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Vegan Protein Bar</th>\n",
              "      <td>3.0</td>\n",
              "      <td>10</td>\n",
              "      <td>0.19</td>\n",
              "      <td>262</td>\n",
              "      <td>0</td>\n",
              "      <td>10</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Gluten-Free Pasta</th>\n",
              "      <td>2.0</td>\n",
              "      <td>10</td>\n",
              "      <td>-0.12</td>\n",
              "      <td>333</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>10</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Raw Cashew Butter</th>\n",
              "      <td>1.0</td>\n",
              "      <td>10</td>\n",
              "      <td>-0.23</td>\n",
              "      <td>358</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>10</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-fe3a2c94-7c7a-444d-a4fa-a696f820f04f')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-fe3a2c94-7c7a-444d-a4fa-a696f820f04f button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-fe3a2c94-7c7a-444d-a4fa-a696f820f04f');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "  <div id=\"id_0a2256c8-8b30-424f-a2b3-ee530a14776f\">\n",
              "    <style>\n",
              "      .colab-df-generate {\n",
              "        background-color: #E8F0FE;\n",
              "        border: none;\n",
              "        border-radius: 50%;\n",
              "        cursor: pointer;\n",
              "        display: none;\n",
              "        fill: #1967D2;\n",
              "        height: 32px;\n",
              "        padding: 0 0 0 0;\n",
              "        width: 32px;\n",
              "      }\n",
              "\n",
              "      .colab-df-generate:hover {\n",
              "        background-color: #E2EBFA;\n",
              "        box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "        fill: #174EA6;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate:hover {\n",
              "        background-color: #434B5C;\n",
              "        box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "        filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "        fill: #FFFFFF;\n",
              "      }\n",
              "    </style>\n",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('df_prod')\"\n",
              "            title=\"Generate code using this dataframe.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_0a2256c8-8b30-424f-a2b3-ee530a14776f button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('df_prod');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df_prod",
              "summary": "{\n  \"name\": \"df_prod\",\n  \"rows\": 6,\n  \"fields\": [\n    {\n      \"column\": \"product_name\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 6,\n        \"samples\": [\n          \"Organic Matcha Powder\",\n          \"Smoked Paprika Almonds\",\n          \"Raw Cashew Butter\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"avg_rating\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.632993161855452,\n        \"min\": 1.0,\n        \"max\": 5.0,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          4.0,\n          1.0,\n          3.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"n_reviews\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 10,\n        \"max\": 10,\n        \"num_unique_values\": 1,\n        \"samples\": [\n          10\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"avg_sentiment\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.2771822505139894,\n        \"min\": -0.23,\n        \"max\": 0.43,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          0.43\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"total_helpful\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 49,\n        \"min\": 249,\n        \"max\": 371,\n        \"num_unique_values\": 6,\n        \"samples\": [\n          249\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Positive\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5,\n        \"min\": 0,\n        \"max\": 10,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Neutral\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 4,\n        \"min\": 0,\n        \"max\": 10,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          10\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Negative\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 5,\n        \"min\": 0,\n        \"max\": 10,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          10\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"positive_ratio\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5477225575051661,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"negative_ratio\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5163977794943223,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "💾 Saved: product_performance.csv\n"
          ]
        }
      ],
      "source": [
        "df_prod = df_synthetic.groupby('product_name').agg(\n",
        "    avg_rating      = ('rating','mean'),\n",
        "    n_reviews       = ('rating','count'),\n",
        "    avg_sentiment   = ('sentiment_score','mean'),\n",
        "    total_helpful   = ('helpful_votes','sum')\n",
        ").round(2)\n",
        "\n",
        "# Add sentiment ratios\n",
        "sc = df_synthetic.groupby(['product_name','sentiment_label']).size().unstack(fill_value=0)\n",
        "for col in ['Positive','Neutral','Negative']:\n",
        "    if col not in sc.columns: sc[col] = 0\n",
        "sc['total']          = sc[['Positive','Neutral','Negative']].sum(axis=1)\n",
        "sc['positive_ratio'] = (sc['Positive']/sc['total']).round(2)\n",
        "sc['negative_ratio'] = (sc['Negative']/sc['total']).round(2)\n",
        "\n",
        "df_prod = df_prod.join(sc[['Positive','Neutral','Negative','positive_ratio','negative_ratio']])\n",
        "df_prod = df_prod.sort_values('avg_rating', ascending=False)\n",
        "\n",
        "print('📋 Synthetic Product Performance Table:')\n",
        "display(df_prod)\n",
        "df_prod.to_csv(PY_TAB / 'product_performance.csv')\n",
        "print('\\n💾 Saved: product_performance.csv')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9AqRn3lEGR34"
      },
      "source": [
        "### *c. Top vs Bottom synthetic products (meaningful comparison)*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "tmw3D6vGGR34",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 726
        },
        "outputId": "13020884-8840-4c78-d6d9-e0d883acd617"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/tmp/ipykernel_1475/3389713133.py:23: UserWarning: Glyph 9989 (\\N{WHITE HEAVY CHECK MARK}) missing from font(s) Liberation Sans.\n",
            "  plt.tight_layout()\n",
            "/tmp/ipykernel_1475/3389713133.py:23: UserWarning: Glyph 9888 (\\N{WARNING SIGN}) missing from font(s) Liberation Sans.\n",
            "  plt.tight_layout()\n",
            "/tmp/ipykernel_1475/3389713133.py:23: UserWarning: Glyph 65039 (\\N{VARIATION SELECTOR-16}) missing from font(s) Liberation Sans.\n",
            "  plt.tight_layout()\n",
            "/tmp/ipykernel_1475/3389713133.py:24: UserWarning: Glyph 9989 (\\N{WHITE HEAVY CHECK MARK}) missing from font(s) Liberation Sans.\n",
            "  plt.savefig(PY_FIG / 'top_bottom_products.png', dpi=150, bbox_inches='tight')\n",
            "/tmp/ipykernel_1475/3389713133.py:24: UserWarning: Glyph 9888 (\\N{WARNING SIGN}) missing from font(s) Liberation Sans.\n",
            "  plt.savefig(PY_FIG / 'top_bottom_products.png', dpi=150, bbox_inches='tight')\n",
            "/tmp/ipykernel_1475/3389713133.py:24: UserWarning: Glyph 65039 (\\N{VARIATION SELECTOR-16}) missing from font(s) Liberation Sans.\n",
            "  plt.savefig(PY_FIG / 'top_bottom_products.png', dpi=150, bbox_inches='tight')\n",
            "/usr/local/lib/python3.12/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 9989 (\\N{WHITE HEAVY CHECK MARK}) missing from font(s) Liberation Sans.\n",
            "  fig.canvas.print_figure(bytes_io, **kw)\n",
            "/usr/local/lib/python3.12/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 9888 (\\N{WARNING SIGN}) missing from font(s) Liberation Sans.\n",
            "  fig.canvas.print_figure(bytes_io, **kw)\n",
            "/usr/local/lib/python3.12/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 65039 (\\N{VARIATION SELECTOR-16}) missing from font(s) Liberation Sans.\n",
            "  fig.canvas.print_figure(bytes_io, **kw)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "📊 Saved: top_bottom_products.png\n"
          ]
        }
      ],
      "source": [
        "top_prod    = df_prod.nlargest(3, 'avg_rating')\n",
        "bottom_prod = df_prod.nsmallest(3, 'avg_rating')\n",
        "\n",
        "fig, axes = plt.subplots(1, 2, figsize=(14, 5))\n",
        "fig.suptitle('Top 3 vs Bottom 3 Products by Average Rating\\n(Synthetic Products)', fontsize=13, fontweight='bold')\n",
        "\n",
        "top_prod['avg_rating'].plot(kind='barh', ax=axes[0], color='#27ae60', edgecolor='white')\n",
        "axes[0].set_title('Top 3 Products ✅', fontweight='bold', color='#27ae60')\n",
        "axes[0].set_xlabel('Average Rating'); axes[0].set_xlim(0, 5.5)\n",
        "axes[0].invert_yaxis()\n",
        "for p in axes[0].patches:\n",
        "    axes[0].annotate(f'{p.get_width():.2f}',\n",
        "                     (p.get_width()+0.05, p.get_y()+p.get_height()/2), va='center', fontsize=11)\n",
        "\n",
        "bottom_prod['avg_rating'].plot(kind='barh', ax=axes[1], color='#e74c3c', edgecolor='white')\n",
        "axes[1].set_title('Bottom 3 Products ⚠️', fontweight='bold', color='#e74c3c')\n",
        "axes[1].set_xlabel('Average Rating'); axes[1].set_xlim(0, 5.5)\n",
        "axes[1].invert_yaxis()\n",
        "for p in axes[1].patches:\n",
        "    axes[1].annotate(f'{p.get_width():.2f}',\n",
        "                     (p.get_width()+0.05, p.get_y()+p.get_height()/2), va='center', fontsize=11)\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.savefig(PY_FIG / 'top_bottom_products.png', dpi=150, bbox_inches='tight')\n",
        "plt.show()\n",
        "print('📊 Saved: top_bottom_products.png')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5rAxQOxbGR35"
      },
      "source": [
        "### *d. Correlation analysis*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "5-GXkmGCGR35",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 559
        },
        "outputId": "8da4e579-6dab-49f3-a028-688fb11bab7d"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 700x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "💡 Rating ↔ Sentiment Score correlation: 0.567\n",
            "   → Strong: TextBlob aligns well with star ratings\n"
          ]
        }
      ],
      "source": [
        "corr_cols = ['rating','sentiment_score','helpful_votes']\n",
        "if 'helpfulness_ratio' in df.columns: corr_cols.append('helpfulness_ratio')\n",
        "\n",
        "corr_matrix = df[corr_cols].dropna().corr().round(3)\n",
        "\n",
        "fig, ax = plt.subplots(figsize=(7, 5))\n",
        "sns.heatmap(corr_matrix, annot=True, fmt='.3f', cmap='coolwarm',\n",
        "            center=0, linewidths=0.5, ax=ax)\n",
        "ax.set_title('Correlation Matrix — Key Numeric Variables', fontsize=12, fontweight='bold')\n",
        "plt.tight_layout()\n",
        "plt.savefig(PY_FIG / 'correlation_matrix.png', dpi=150, bbox_inches='tight')\n",
        "plt.show()\n",
        "\n",
        "r = corr_matrix.loc['rating','sentiment_score']\n",
        "print(f'\\n💡 Rating ↔ Sentiment Score correlation: {r:.3f}')\n",
        "if abs(r) > 0.5: print('   → Strong: TextBlob aligns well with star ratings')\n",
        "elif abs(r) > 0.3: print('   → Moderate: broadly tracks ratings')\n",
        "else: print('   → Weak: reviews contain nuanced language TextBlob partially misses')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "BqdtlKOeGR35"
      },
      "source": [
        "## **6.** 💬 Qualitative Analysis"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "QRy0r6GnGR35"
      },
      "source": [
        "### *a. VADER sentiment — better model for product reviews*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "lsmiRGeeGR35",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "01b210d9-6f9e-414f-f2d4-742b35826d57"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "✅ VADER sentiment computed\n",
            "\n",
            "VADER distribution:\n",
            "vader_label\n",
            "Positive    421\n",
            "Negative    122\n",
            "Neutral      17\n",
            "\n",
            "TextBlob vs VADER agreement: 65.9%\n"
          ]
        }
      ],
      "source": [
        "analyzer = SentimentIntensityAnalyzer()\n",
        "\n",
        "def vader_sentiment(text):\n",
        "    c = analyzer.polarity_scores(str(text))['compound']\n",
        "    label = 'Positive' if c >= 0.05 else ('Negative' if c <= -0.05 else 'Neutral')\n",
        "    return label, round(c, 3)\n",
        "\n",
        "vres = df['review_text'].apply(vader_sentiment)\n",
        "df['vader_label'] = vres.apply(lambda x: x[0])\n",
        "df['vader_score'] = vres.apply(lambda x: x[1])\n",
        "\n",
        "print('✅ VADER sentiment computed')\n",
        "print(f'\\nVADER distribution:')\n",
        "print(df['vader_label'].value_counts().to_string())\n",
        "agreement = (df['sentiment_label'] == df['vader_label']).mean()\n",
        "print(f'\\nTextBlob vs VADER agreement: {agreement*100:.1f}%')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2rXkztZEGR35"
      },
      "source": [
        "### *b. Compare TextBlob vs VADER*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "XhOqjCA3GR35",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 405
        },
        "outputId": "e0863276-3872-4288-9ee2-0d553f48540c"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1300x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "fig, axes = plt.subplots(1, 2, figsize=(13, 5))\n",
        "fig.suptitle('TextBlob vs VADER Sentiment Comparison', fontsize=14, fontweight='bold')\n",
        "clrs = ['#27ae60','#f39c12','#e74c3c']\n",
        "\n",
        "for ax, col, title in zip(axes, ['sentiment_label','vader_label'], ['TextBlob','VADER']):\n",
        "    counts = df[col].value_counts().reindex(['Positive','Neutral','Negative']).fillna(0)\n",
        "    counts.plot(kind='bar', ax=ax, color=clrs, edgecolor='white', width=0.6)\n",
        "    ax.set_title(f'{title} Sentiment', fontweight='bold')\n",
        "    ax.set_xticklabels(['Positive','Neutral','Negative'], rotation=0)\n",
        "    ax.set_ylabel('Count')\n",
        "    for p in ax.patches:\n",
        "        ax.annotate(str(int(p.get_height())),\n",
        "                    (p.get_x()+p.get_width()/2, p.get_height()),\n",
        "                    ha='center', va='bottom', fontsize=10)\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.savefig(PY_FIG / 'textblob_vs_vader.png', dpi=150, bbox_inches='tight')\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eldJATgwGR35"
      },
      "source": [
        "### *c. Qualitative review samples per sentiment*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "iVkZi4e2GR35",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "0f749987-585f-4e57-dc07-465295a8f0c7"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "======================================================================\n",
            "QUALITATIVE REVIEW SAMPLES — 3 per sentiment (real reviews only)\n",
            "======================================================================\n",
            "\n",
            "--- POSITIVE REVIEWS ---\n",
            "  Rating  : 5⭐  |  VADER: +0.10  |  Helpful: 0 votes\n",
            "  Title   : Yummy nuts\n",
            "  Review  : \"Awesome tasting nuts!  Love them?  Will be ordering them again.  The entire neighborhood wants to eat them all but I am stingy.\"\n",
            "\n",
            "  Rating  : 3⭐  |  VADER: +0.93  |  Helpful: 0 votes\n",
            "  Title   : I wouldn't call it bold\n",
            "  Review  : \"I got this coffee as part of a \"bold\" sampler pack.  While I found it flavorful I wouldn't call it bold.  My first WP k-cup was French Roast which I found extremely bitter.  This coffee doesn't have t\"\n",
            "\n",
            "  Rating  : 2⭐  |  VADER: +0.93  |  Helpful: 0 votes\n",
            "  Title   : Meh\n",
            "  Review  : \"It's not real crispy, sticks to your teeth and lots of hulls.  I know homemade popcorn has a few more kernel hulls than your store-bought microwave, but it's a little too much for me. I was really hop\"\n",
            "\n",
            "\n",
            "--- NEUTRAL REVIEWS ---\n",
            "  Rating  : 1⭐  |  VADER: +0.00  |  Helpful: 4 votes\n",
            "  Title   : The other reviewer is totally right!!!\n",
            "  Review  : \"You can get these SOOOOOOOOOOOOO much cheaper at wholesale clubs.  I get the 24/20oz(yes 20oz!) for $11 or $12!! Its actually even cheaper then buying the bottles from the regular store!\"\n",
            "\n",
            "  Rating  : 1⭐  |  VADER: +0.00  |  Helpful: 1 votes\n",
            "  Title   : Great drink, horrible price!\n",
            "  Review  : \"I can get it at Walmart for $1.78 each or the gas station for $3.50 for 2. Why, just why?\"\n",
            "\n",
            "  Rating  : 2⭐  |  VADER: +0.04  |  Helpful: 0 votes\n",
            "  Title   : Nothing Special\n",
            "  Review  : \"I expected better from a premium Maine chowder. This is no better than, say, Snow's, which you can get for less than half the price. Not bad, but not worth the money.\"\n",
            "\n",
            "\n",
            "--- NEGATIVE REVIEWS ---\n",
            "  Rating  : 1⭐  |  VADER: -0.19  |  Helpful: 0 votes\n",
            "  Title   : not quality at all\n",
            "  Review  : \"this product taste stale and is full of artificial ingredients. NO REAL PEPPERMINT IS IN THIS PRODUCT and to be honest it doesnt even taste like real cocoa is either.\"\n",
            "\n",
            "  Rating  : 1⭐  |  VADER: -0.42  |  Helpful: 0 votes\n",
            "  Title   : Stale, Rancid Oil Taste, And if You Like Even the Tiniest Bit of Salt Flavor on \n",
            "  Review  : \"...you can absolutely forget about these. Confirmed by other reviewers, these chips are now total garbage. Like chewing on styrofoam packaging \"peanuts\". Positively awful, no hyperbole or exaggeration\"\n",
            "\n",
            "  Rating  : 1⭐  |  VADER: -0.73  |  Helpful: 2 votes\n",
            "  Title   : Beware - contains fragrance\n",
            "  Review  : \"This product gave me a horrible rash.  It contains both soybean oil and fragrance which are allergens.  They need to list allergens.\"\n",
            "\n"
          ]
        }
      ],
      "source": [
        "print('=' * 70)\n",
        "print('QUALITATIVE REVIEW SAMPLES — 3 per sentiment (real reviews only)')\n",
        "print('=' * 70)\n",
        "\n",
        "for sentiment in ['Positive', 'Neutral', 'Negative']:\n",
        "    # Filter the main 'df' for real reviews (is_synthetic == False) and the specific VADER sentiment\n",
        "    subset = df[(df['is_synthetic'] == False) & (df['vader_label'] == sentiment)].dropna(subset=['review_text'])\n",
        "    samples = subset.sample(min(3, len(subset)), random_state=42)\n",
        "    print(f'\\n--- {sentiment.upper()} REVIEWS ---')\n",
        "    for _, row in samples.iterrows():\n",
        "        print(f'  Rating  : {row[\"rating\"]}⭐  |  VADER: {row[\"vader_score\"]:+.2f}  |  Helpful: {int(row[\"helpful_votes\"])} votes')\n",
        "        print(f'  Title   : {str(row[\"review_title\"])[:80]}')\n",
        "        print(f'  Review  : \"{str(row[\"review_text\"])[:200]}\"')\n",
        "        print()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zt3WDQpLGR35"
      },
      "source": [
        "### *d. Most helpful negative reviews — key pain points*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "XcZevPyFGR35",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "e117d79e-ae72-4860-ce18-ec284a20e62e"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "🔍 TOP 5 MOST HELPFUL NEGATIVE REVIEWS (real Kaggle data)\n",
            "   These reveal the most impactful customer pain points\n",
            "======================================================================\n",
            "  Rating      : 2⭐  |  Helpful votes: 100\n",
            "  VADER score : -0.659\n",
            "  Title       : Beware hidden ingredients\n",
            "  Review      : \"I hate to type this, because there are so many people that really enjoy this product, but take a look at the ingredients in this so-called \"all-natural\" product. I have the cheddar cheese flavor right in front of me, so that is the only flavor I can \"\n",
            "\n",
            "  Rating      : 1⭐  |  Helpful votes: 22\n",
            "  VADER score : -0.930\n",
            "  Title       : Shipping is INSANE!!!\n",
            "  Review      : \"I love the popcorn, but the shipping costs are INSANE!! A total rip off. Wabash Valley Farms or Amazon or whoever is charging the shipping is out of their mind. 5 Stars for the popcorn. Minus 4 stars for the terrible cost associated with shipping. Ar\"\n",
            "\n",
            "  Rating      : 1⭐  |  Helpful votes: 9\n",
            "  VADER score : -0.823\n",
            "  Title       : Candy look liked it was open & it is OLD. Do not Buy!\n",
            "  Review      : \"I bought this bag and found it 50% cheaper at smart and final. It was also old and and white. This was terrible! I bought it to put in the candy canisters I give to co-workers. So I didn't find out it was OLD till a co-worker informed me. I was so em\"\n",
            "\n",
            "  Rating      : 2⭐  |  Helpful votes: 9\n",
            "  VADER score : -0.101\n",
            "  Title       : Why does this have sucralose?\n",
            "  Review      : \"My whole family(7 people) tasted all 3 flavors and they are sickly sweet.  Very disappointed that product has sucralose.  I wouldn't buy it again\"\n",
            "\n",
            "  Rating      : 2⭐  |  Helpful votes: 9\n",
            "  VADER score : -0.144\n",
            "  Title       : Not good enough\n",
            "  Review      : \"I cringed a little after reading the ingredient list. Way too much grains and not enough quality protein for our dogs. Notice all of them are at the beginning, which means they make up quite a bit of the diet. Soy protein is included but some dogs do\"\n",
            "\n",
            "💾 Saved: top_negative_reviews.csv\n"
          ]
        }
      ],
      "source": [
        "df_neg = df[(df['is_synthetic'] == False) & (df['vader_label']=='Negative')].sort_values('helpful_votes', ascending=False)\n",
        "\n",
        "print('🔍 TOP 5 MOST HELPFUL NEGATIVE REVIEWS (real Kaggle data)')\n",
        "print('   These reveal the most impactful customer pain points')\n",
        "print('=' * 70)\n",
        "for _, row in df_neg.head(5).iterrows():\n",
        "    print(f'  Rating      : {row[\"rating\"]}⭐  |  Helpful votes: {int(row[\"helpful_votes\"])}')\n",
        "    print(f'  VADER score : {row[\"vader_score\"]:+.3f}')\n",
        "    print(f'  Title       : {str(row[\"review_title\"])[:80]}')\n",
        "    print(f'  Review      : \"{str(row[\"review_text\"])[:250]}\"')\n",
        "    print()\n",
        "\n",
        "df_neg.head(10)[['product_id','rating','helpful_votes','vader_score','review_title','review_text']].to_csv(\n",
        "    PY_TAB / 'top_negative_reviews.csv', index=False\n",
        ")\n",
        "print('💾 Saved: top_negative_reviews.csv')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "moYDbVpJGR35"
      },
      "source": [
        "## **7.** 🎯 Business Decision Engine"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uiFbiB9iGR35"
      },
      "source": [
        "### *a. Build the decision dataframe*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Z1uXjQuvGR35",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "3193ee11-7a3a-482f-9dc5-27685d5d984e"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "           product_name  avg_rating  positive_ratio  negative_ratio\n",
            "      Gluten-Free Pasta         2.0             0.4             0.6\n",
            "  Organic Matcha Powder         5.0             1.0             0.0\n",
            "      Raw Cashew Butter         1.0             0.2             0.7\n",
            " Smoked Paprika Almonds         5.0             1.0             0.0\n",
            "Truffle Sea Salt Flakes         4.0             1.0             0.0\n",
            "      Vegan Protein Bar         3.0             0.9             0.1\n"
          ]
        }
      ],
      "source": [
        "df_dec = df[df['is_synthetic'] == True].groupby('product_name').agg(\n",
        "    avg_rating    = ('rating','mean'),\n",
        "    avg_sentiment = ('vader_score','mean'),\n",
        "    n_reviews     = ('rating','count'),\n",
        "    helpful_votes = ('helpful_votes','sum')\n",
        ").round(3).reset_index()\n",
        "\n",
        "sc2 = df[df['is_synthetic'] == True].groupby(['product_name','vader_label']).size().unstack(fill_value=0).reset_index()\n",
        "for col in ['Positive','Neutral','Negative']:\n",
        "    if col not in sc2.columns: sc2[col] = 0\n",
        "sc2['total']          = sc2[['Positive','Neutral','Negative']].sum(axis=1)\n",
        "sc2['positive_ratio'] = (sc2['Positive']/sc2['total']).round(2)\n",
        "sc2['negative_ratio'] = (sc2['Negative']/sc2['total']).round(2)\n",
        "df_dec = df_dec.merge(sc2, on='product_name', how='left')\n",
        "print(df_dec[['product_name','avg_rating','positive_ratio','negative_ratio']].to_string(index=False))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "raBlGutrGR36"
      },
      "source": [
        "### *b. Apply pricing and churn decision rules*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Uh6QhMwdGR36",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "53b673fd-395d-4622-cbd9-158e99a8325c"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "📋 Business Decision Summary:\n",
            "           product_name  avg_rating  positive_ratio  negative_ratio                 pricing_action churn_risk\n",
            "      Gluten-Free Pasta         2.0             0.4             0.6 Reduce Price / Improve Product  High Risk\n",
            "  Organic Matcha Powder         5.0             1.0             0.0                 Increase Price   Low Risk\n",
            "      Raw Cashew Butter         1.0             0.2             0.7 Reduce Price / Improve Product  High Risk\n",
            " Smoked Paprika Almonds         5.0             1.0             0.0                 Increase Price   Low Risk\n",
            "Truffle Sea Salt Flakes         4.0             1.0             0.0                 Increase Price   Low Risk\n",
            "      Vegan Protein Bar         3.0             0.9             0.1                     Keep Price   Low Risk\n"
          ]
        }
      ],
      "source": [
        "def pricing_decision(row):\n",
        "    if row['positive_ratio'] >= 0.7 and row['avg_rating'] >= 4.0:\n",
        "        return 'Increase Price'\n",
        "    elif row['negative_ratio'] >= 0.4 or row['avg_rating'] < 2.5:\n",
        "        return 'Reduce Price / Improve Product'\n",
        "    else:\n",
        "        return 'Keep Price'\n",
        "\n",
        "def churn_risk(row):\n",
        "    if row['negative_ratio'] >= 0.5: return 'High Risk'\n",
        "    elif row['negative_ratio'] >= 0.3: return 'Medium Risk'\n",
        "    else: return 'Low Risk'\n",
        "\n",
        "df_dec['pricing_action'] = df_dec.apply(pricing_decision, axis=1)\n",
        "df_dec['churn_risk']     = df_dec.apply(churn_risk, axis=1)\n",
        "\n",
        "print('📋 Business Decision Summary:')\n",
        "print(df_dec[['product_name','avg_rating','positive_ratio','negative_ratio',\n",
        "              'pricing_action','churn_risk']].to_string(index=False))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "r1h4_7A-GR36"
      },
      "source": [
        "### *c. Visualize business decisions*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Qw5n_HDZGR36",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 422
        },
        "outputId": "f7f0838a-133a-4922-8152-6631231da21e"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1300x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "📊 Saved: business_decisions.png\n"
          ]
        }
      ],
      "source": [
        "fig, axes = plt.subplots(1, 2, figsize=(13, 5))\n",
        "fig.suptitle('Business Decision Engine Output', fontsize=14, fontweight='bold')\n",
        "\n",
        "action_counts = df_dec['pricing_action'].value_counts()\n",
        "action_colors = {'Increase Price':'#27ae60','Keep Price':'#f39c12','Reduce Price / Improve Product':'#e74c3c'}\n",
        "action_counts.plot(kind='bar', ax=axes[0],\n",
        "    color=[action_colors.get(a,'#95a5a6') for a in action_counts.index],\n",
        "    edgecolor='white', width=0.6)\n",
        "axes[0].set_title('Recommended Pricing Actions', fontweight='bold')\n",
        "axes[0].set_xticklabels(action_counts.index, rotation=15, ha='right')\n",
        "axes[0].set_ylabel('Number of Products')\n",
        "\n",
        "churn_counts = df_dec['churn_risk'].value_counts().reindex(['Low Risk','Medium Risk','High Risk']).fillna(0)\n",
        "churn_counts.plot(kind='bar', ax=axes[1],\n",
        "    color=['#27ae60','#f39c12','#e74c3c'], edgecolor='white', width=0.6)\n",
        "axes[1].set_title('Churn Risk by Product', fontweight='bold')\n",
        "axes[1].set_xticklabels(['Low Risk','Medium Risk','High Risk'], rotation=0)\n",
        "axes[1].set_ylabel('Number of Products')\n",
        "\n",
        "plt.tight_layout()\n",
        "plt.savefig(PY_FIG / 'business_decisions.png', dpi=150, bbox_inches='tight')\n",
        "plt.show()\n",
        "print('📊 Saved: business_decisions.png')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Gn2LzkbFGR36"
      },
      "source": [
        "## **8.** 💾 Save Python Outputs for the Hugging Face Dashboard"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HPjhAxSwGR36"
      },
      "source": [
        "Exports HF-ready artifacts:\n",
        "- `artifacts/py/figures/` — Python-generated visuals\n",
        "- `artifacts/py/tables/` — tables and metrics"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ZGaF3HHsGR36",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "b460cb24-1bf1-4008-a715-d7472418bf78"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "✅ All artifacts exported to artifacts/\n",
            "   py/figures/ : ['business_decisions.png', 'category_sentiment_heatmap.png', 'correlation_matrix.png', 'helpfulness_analysis.png', 'rating_sentiment_overview.png', 'sentiment_per_product.png', 'sentiment_score_analysis.png', 'textblob_vs_vader.png', 'top_bottom_products.png']\n",
            "   py/tables/  : ['business_decisions.csv', 'df_dashboard.csv', 'df_final_with_vader.csv', 'kpis.json', 'product_performance.csv', 'top_negative_reviews.csv']\n"
          ]
        }
      ],
      "source": [
        "# Dashboard summary table\n",
        "df_dashboard = df.groupby('sentiment_label').agg(\n",
        "    n_reviews     = ('rating','count'),\n",
        "    avg_rating    = ('rating','mean'),\n",
        "    avg_sentiment = ('sentiment_score','mean'),\n",
        "    avg_helpful   = ('helpful_votes','mean')\n",
        ").round(3).reset_index()\n",
        "df_dashboard.to_csv(PY_TAB / 'df_dashboard.csv', index=False)\n",
        "\n",
        "# Full decision table\n",
        "df_dec.to_csv(PY_TAB / 'business_decisions.csv', index=False)\n",
        "\n",
        "# Full enriched df with VADER\n",
        "df.to_csv(PY_TAB / 'df_final_with_vader.csv', index=False)\n",
        "\n",
        "print('✅ All artifacts exported to artifacts/')\n",
        "print('   py/figures/ :', [p.name for p in sorted(PY_FIG.iterdir())])\n",
        "print('   py/tables/  :', [p.name for p in sorted(PY_TAB.iterdir())])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "aqPWvveDGR36"
      },
      "source": [
        "---\n",
        "## ✅ Notebook 2 Complete!\n",
        "\n",
        "| Section | Output |\n",
        "|---|---|\n",
        "| Data loaded | `food_reviews_enriched.csv` |\n",
        "| Quality check | Shape, types, missing values, samples |\n",
        "| Visualizations | 6 charts saved to `artifacts/py/figures/` |\n",
        "| Quantitative | KPIs, correlations, product rankings |\n",
        "| Qualitative | VADER sentiment, review samples, pain points |\n",
        "| Business decisions | Pricing actions + churn risk per product |\n",
        "| **Artifacts** | All saved to `artifacts/` for Hugging Face |\n",
        "\n",
        "### ➡️ Next: Build the Hugging Face app using the `artifacts/` folder"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.10.0"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}