Upload Sentiment Analysis of Restaurant Reviews.ipynb

Sentiment Analysis of Restaurant Reviews.ipynb

@@ -0,0 +1,776 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "Sentiment Analysis - Restaurant Reviews.ipynb",
+      "provenance": [],
+      "collapsed_sections": [],
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "kh4udnC9fZyU",
+        "colab_type": "code",
+        "outputId": "677fbeb5-d5b2-49f7-99bf-92bd1f2fa44e",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 34
+        }
+      },
+      "source": [
+        "# Connecting Google Drive with Google Colab\n",
+        "from google.colab import drive\n",
+        "drive.mount('/content/drive/')"
+      ],
+      "execution_count": 1,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Drive already mounted at /content/drive/; to attempt to forcibly remount, call drive.mount(\"/content/drive/\", force_remount=True).\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "wqtOguIVfysM",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "# Importing essential libraries\n",
+        "import numpy as np\n",
+        "import pandas as pd"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "FsZFCtjijekC",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "# Loading the dataset\n",
+        "df = pd.read_csv('/content/drive/My Drive/Colab Notebooks/Datasets/Restaurant_Reviews.tsv', delimiter='\\t', quoting=3)"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "zkdfWSlej05y",
+        "colab_type": "code",
+        "outputId": "26f108a7-5617-4abe-efae-0d64d31e8041",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 34
+        }
+      },
+      "source": [
+        "df.shape"
+      ],
+      "execution_count": 4,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(1000, 2)"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 4
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "SyYImhASubeb",
+        "colab_type": "code",
+        "outputId": "2c8efdb6-17a5-48da-8ac2-7c9d2c289b09",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 34
+        }
+      },
+      "source": [
+        "df.columns"
+      ],
+      "execution_count": 5,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "Index(['Review', 'Liked'], dtype='object')"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 5
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "b5lzlG5DMNX9",
+        "colab_type": "code",
+        "outputId": "ab125608-7f10-479c-8dab-bb298fa7bbaf",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 197
+        }
+      },
+      "source": [
+        "df.head()"
+      ],
+      "execution_count": 6,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/html": [
+              "<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>Review</th>\n",
+              "      <th>Liked</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>Wow... Loved this place.</td>\n",
+              "      <td>1</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>Crust is not good.</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>Not tasty and the texture was just nasty.</td>\n",
+              "      <td>0</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>Stopped by during the late May bank holiday of...</td>\n",
+              "      <td>1</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>The selection on the menu was great and so wer...</td>\n",
+              "      <td>1</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>"
+            ],
+            "text/plain": [
+              "                                              Review  Liked\n",
+              "0                           Wow... Loved this place.      1\n",
+              "1                                 Crust is not good.      0\n",
+              "2          Not tasty and the texture was just nasty.      0\n",
+              "3  Stopped by during the late May bank holiday of...      1\n",
+              "4  The selection on the menu was great and so wer...      1"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 6
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "38_tPfGAr0AL",
+        "colab_type": "text"
+      },
+      "source": [
+        "# **Data Preprocessing**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "gZpsSpUAkCyH",
+        "colab_type": "code",
+        "outputId": "81a672d9-a796-4789-e2e8-36d360f9e558",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 52
+        }
+      },
+      "source": [
+        "# Importing essential libraries for performing Natural Language Processing on 'Restaurant_Reviews.tsv' dataset\n",
+        "import nltk\n",
+        "import re\n",
+        "nltk.download('stopwords')\n",
+        "from nltk.corpus import stopwords\n",
+        "from nltk.stem.porter import PorterStemmer"
+      ],
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
+            "[nltk_data]   Package stopwords is already up-to-date!\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "tUnp7Dr7mFwn",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "# Cleaning the reviews\n",
+        "corpus = []\n",
+        "for i in range(0,1000):\n",
+        "\n",
+        "  # Cleaning special character from the reviews\n",
+        "  review = re.sub(pattern='[^a-zA-Z]',repl=' ', string=df['Review'][i])\n",
+        "\n",
+        "  # Converting the entire review into lower case\n",
+        "  review = review.lower()\n",
+        "\n",
+        "  # Tokenizing the review by words\n",
+        "  review_words = review.split()\n",
+        "\n",
+        "  # Removing the stop words\n",
+        "  review_words = [word for word in review_words if not word in set(stopwords.words('english'))]\n",
+        "\n",
+        "  # Stemming the words\n",
+        "  ps = PorterStemmer()\n",
+        "  review = [ps.stem(word) for word in review_words]\n",
+        "\n",
+        "  # Joining the stemmed words\n",
+        "  review = ' '.join(review)\n",
+        "\n",
+        "  # Creating a corpus\n",
+        "  corpus.append(review)"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "6ewB2oNJ0rr9",
+        "colab_type": "code",
+        "outputId": "9f2c2e4b-adf7-4157-d573-f3383a16cee0",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 194
+        }
+      },
+      "source": [
+        "corpus[0:10]"
+      ],
+      "execution_count": 9,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "['wow love place',\n",
+              " 'crust good',\n",
+              " 'tasti textur nasti',\n",
+              " 'stop late may bank holiday rick steve recommend love',\n",
+              " 'select menu great price',\n",
+              " 'get angri want damn pho',\n",
+              " 'honeslti tast fresh',\n",
+              " 'potato like rubber could tell made ahead time kept warmer',\n",
+              " 'fri great',\n",
+              " 'great touch']"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 9
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "spNHLhGs20LV",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "# Creating the Bag of Words model\n",
+        "from sklearn.feature_extraction.text import CountVectorizer\n",
+        "cv = CountVectorizer(max_features=1500)\n",
+        "X = cv.fit_transform(corpus).toarray()\n",
+        "y = df.iloc[:, 1].values"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "jYNkfBqJ42hs",
+        "colab_type": "text"
+      },
+      "source": [
+        "# **Model Building**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "sL6FOXMx45w0",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "from sklearn.model_selection import train_test_split\n",
+        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state = 0)"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "KYTe6hjJDV8K",
+        "colab_type": "code",
+        "outputId": "56f78ef1-3f7f-40ce-cf1c-15a2b91b61c3",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 34
+        }
+      },
+      "source": [
+        "# Fitting Naive Bayes to the Training set\n",
+        "from sklearn.naive_bayes import MultinomialNB\n",
+        "classifier = MultinomialNB()\n",
+        "classifier.fit(X_train, y_train)"
+      ],
+      "execution_count": 12,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "MultinomialNB(alpha=1.0, class_prior=None, fit_prior=True)"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 12
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "CjXrDsEyDbD7",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "# Predicting the Test set results\n",
+        "y_pred = classifier.predict(X_test)"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "CcRU4PabPDY-",
+        "colab_type": "code",
+        "outputId": "4985115a-e9be-4447-9a22-026c59045ec9",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 87
+        }
+      },
+      "source": [
+        "# Accuracy, Precision and Recall\n",
+        "from sklearn.metrics import accuracy_score\n",
+        "from sklearn.metrics import precision_score\n",
+        "from sklearn.metrics import recall_score\n",
+        "score1 = accuracy_score(y_test,y_pred)\n",
+        "score2 = precision_score(y_test,y_pred)\n",
+        "score3= recall_score(y_test,y_pred)\n",
+        "print(\"---- Scores ----\")\n",
+        "print(\"Accuracy score is: {}%\".format(round(score1*100,2)))\n",
+        "print(\"Precision score is: {}\".format(round(score2,2)))\n",
+        "print(\"Recall score is: {}\".format(round(score3,2)))"
+      ],
+      "execution_count": 14,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "---- Scores ----\n",
+            "Accuracy score is: 76.5%\n",
+            "Precision score is: 0.76\n",
+            "Recall score is: 0.79\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "-77oRRHjDgwr",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "# Making the Confusion Matrix\n",
+        "from sklearn.metrics import confusion_matrix\n",
+        "cm = confusion_matrix(y_test, y_pred)"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "9lRKOJ-zjv3F",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 52
+        },
+        "outputId": "b5c14f34-e062-4cf6-b899-31a5d583d62c"
+      },
+      "source": [
+        "cm"
+      ],
+      "execution_count": 16,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "array([[72, 25],\n",
+              "       [22, 81]])"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 16
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "hYd9LdXmDkKb",
+        "colab_type": "code",
+        "outputId": "30c403fb-f204-42ff-a19c-eb2ecbdf8cd5",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 461
+        }
+      },
+      "source": [
+        "# Plotting the confusion matrix\n",
+        "import matplotlib.pyplot as plt\n",
+        "import seaborn as sns\n",
+        "%matplotlib inline\n",
+        "\n",
+        "plt.figure(figsize = (10,6))\n",
+        "sns.heatmap(cm, annot=True, cmap=\"YlGnBu\", xticklabels=['Negative', 'Positive'], yticklabels=['Negative', 'Positive'])\n",
+        "plt.xlabel('Predicted values')\n",
+        "plt.ylabel('Actual values')"
+      ],
+      "execution_count": 17,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "/usr/local/lib/python3.6/dist-packages/statsmodels/tools/_testing.py:19: FutureWarning: pandas.util.testing is deprecated. Use the functions in the public API at pandas.testing instead.\n",
+            "  import pandas.util.testing as tm\n"
+          ],
+          "name": "stderr"
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "Text(69.0, 0.5, 'Actual values')"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 17
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "image/png": "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\n",
+            "text/plain": [
+              "<Figure size 720x432 with 2 Axes>"
+            ]
+          },
+          "metadata": {
+            "tags": [],
+            "needs_background": "light"
+          }
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "LJbZKcc9jWcV",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 230
+        },
+        "outputId": "654b7fc8-9c8e-452b-c14c-dd57c87d82ec"
+      },
+      "source": [
+        "# Hyperparameter tuning the Naive Bayes Classifier\n",
+        "best_accuracy = 0.0\n",
+        "alpha_val = 0.0\n",
+        "for i in np.arange(0.1,1.1,0.1):\n",
+        "  temp_classifier = MultinomialNB(alpha=i)\n",
+        "  temp_classifier.fit(X_train, y_train)\n",
+        "  temp_y_pred = temp_classifier.predict(X_test)\n",
+        "  score = accuracy_score(y_test, temp_y_pred)\n",
+        "  print(\"Accuracy score for alpha={} is: {}%\".format(round(i,1), round(score*100,2)))\n",
+        "  if score>best_accuracy:\n",
+        "    best_accuracy = score\n",
+        "    alpha_val = i\n",
+        "print('--------------------------------------------')\n",
+        "print('The best accuracy is {}% with alpha value as {}'.format(round(best_accuracy*100, 2), round(alpha_val,1)))"
+      ],
+      "execution_count": 18,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "Accuracy score for alpha=0.1 is: 78.0%\n",
+            "Accuracy score for alpha=0.2 is: 78.5%\n",
+            "Accuracy score for alpha=0.3 is: 78.0%\n",
+            "Accuracy score for alpha=0.4 is: 78.0%\n",
+            "Accuracy score for alpha=0.5 is: 77.5%\n",
+            "Accuracy score for alpha=0.6 is: 77.5%\n",
+            "Accuracy score for alpha=0.7 is: 77.5%\n",
+            "Accuracy score for alpha=0.8 is: 77.0%\n",
+            "Accuracy score for alpha=0.9 is: 76.5%\n",
+            "Accuracy score for alpha=1.0 is: 76.5%\n",
+            "--------------------------------------------\n",
+            "The best accuracy is 78.5% with alpha value as 0.2\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "9BNR7SfKkDsL",
+        "colab_type": "code",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 34
+        },
+        "outputId": "0ebe229f-009d-46fa-852c-90b758d548b6"
+      },
+      "source": [
+        "classifier = MultinomialNB(alpha=0.2)\n",
+        "classifier.fit(X_train, y_train)"
+      ],
+      "execution_count": 19,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "MultinomialNB(alpha=0.2, class_prior=None, fit_prior=True)"
+            ]
+          },
+          "metadata": {
+            "tags": []
+          },
+          "execution_count": 19
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "iYQVSu17MWgV",
+        "colab_type": "text"
+      },
+      "source": [
+        "# **Predictions**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "mYbh9DFvwmW1",
+        "colab_type": "code",
+        "colab": {}
+      },
+      "source": [
+        "def predict_sentiment(sample_review):\n",
+        "  sample_review = re.sub(pattern='[^a-zA-Z]',repl=' ', string = sample_review)\n",
+        "  sample_review = sample_review.lower()\n",
+        "  sample_review_words = sample_review.split()\n",
+        "  sample_review_words = [word for word in sample_review_words if not word in set(stopwords.words('english'))]\n",
+        "  ps = PorterStemmer()\n",
+        "  final_review = [ps.stem(word) for word in sample_review_words]\n",
+        "  final_review = ' '.join(final_review)\n",
+        "\n",
+        "  temp = cv.transform([final_review]).toarray()\n",
+        "  return classifier.predict(temp)"
+      ],
+      "execution_count": 0,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "Os0d_BZELC95",
+        "colab_type": "code",
+        "outputId": "3478b8c9-55a9-454f-aaae-b42ccc28d609",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 34
+        }
+      },
+      "source": [
+        "# Predicting values\n",
+        "sample_review = 'The food is really good here.'\n",
+        "\n",
+        "if predict_sentiment(sample_review):\n",
+        "  print('This is a POSITIVE review.')\n",
+        "else:\n",
+        "  print('This is a NEGATIVE review!')"
+      ],
+      "execution_count": 21,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "This is a POSITIVE review.\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "A88ILf9PNAKY",
+        "colab_type": "code",
+        "outputId": "d1fe224e-373f-4e98-9c05-da96980d4f49",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 34
+        }
+      },
+      "source": [
+        "# Predicting values\n",
+        "sample_review = 'Food was pretty bad and the service was very slow.'\n",
+        "\n",
+        "if predict_sentiment(sample_review):\n",
+        "  print('This is a POSITIVE review.')\n",
+        "else:\n",
+        "  print('This is a NEGATIVE review!')"
+      ],
+      "execution_count": 22,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "This is a NEGATIVE review!\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "UXgRRzafOX3d",
+        "colab_type": "code",
+        "outputId": "f913faa2-38b5-48c6-f6fa-456ab807a01c",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 34
+        }
+      },
+      "source": [
+        "# Predicting values\n",
+        "sample_review = 'The food was absolutely wonderful, from preparation to presentation, very pleasing.'\n",
+        "\n",
+        "if predict_sentiment(sample_review):\n",
+        "  print('This is a POSITIVE review.')\n",
+        "else:\n",
+        "  print('This is a NEGATIVE review!')"
+      ],
+      "execution_count": 23,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "text": [
+            "This is a POSITIVE review.\n"
+          ],
+          "name": "stdout"
+        }
+      ]
+    }
+  ]
+}