Upload wine-quality.ipynb

wine-quality.ipynb

@@ -0,0 +1,634 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "d6ffc7b7",
+   "metadata": {},
+   "source": [
+    "# 1.0 Importing libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "4ca597ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\"\n",
+    "Description: Import libraries\n",
+    "\"\"\"\n",
+    "import numpy as np\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn import metrics\n",
+    "import pandas as pd\n",
+    "import os\n",
+    "import random\n",
+    "from humanfriendly import format_timespan\n",
+    "from sklearn.preprocessing import MinMaxScaler\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "import pickle\n",
+    "# from sklearn.svm import SVC\n",
+    "# from sklearn.linear_model import LogisticRegression"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "fffc59ee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\"\n",
+    "Description: Specify data path\n",
+    "\"\"\"\n",
+    "data_path = r'data\\winequality_red_label_remapped.csv'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5a2e912f",
+   "metadata": {},
+   "outputs": [
+    {
+     "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>fixed acidity</th>\n",
+       "      <th>volatile acidity</th>\n",
+       "      <th>citric acid</th>\n",
+       "      <th>residual sugar</th>\n",
+       "      <th>chlorides</th>\n",
+       "      <th>free sulfur dioxide</th>\n",
+       "      <th>total sulfur dioxide</th>\n",
+       "      <th>density</th>\n",
+       "      <th>pH</th>\n",
+       "      <th>sulphates</th>\n",
+       "      <th>alcohol</th>\n",
+       "      <th>quality</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>7.4</td>\n",
+       "      <td>0.70</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.076</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>0.9978</td>\n",
+       "      <td>3.51</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>9.4</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>7.8</td>\n",
+       "      <td>0.88</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2.6</td>\n",
+       "      <td>0.098</td>\n",
+       "      <td>25.0</td>\n",
+       "      <td>67.0</td>\n",
+       "      <td>0.9968</td>\n",
+       "      <td>3.20</td>\n",
+       "      <td>0.68</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>7.8</td>\n",
+       "      <td>0.76</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>2.3</td>\n",
+       "      <td>0.092</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>54.0</td>\n",
+       "      <td>0.9970</td>\n",
+       "      <td>3.26</td>\n",
+       "      <td>0.65</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>11.2</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.075</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>60.0</td>\n",
+       "      <td>0.9980</td>\n",
+       "      <td>3.16</td>\n",
+       "      <td>0.58</td>\n",
+       "      <td>9.8</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>7.4</td>\n",
+       "      <td>0.70</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1.9</td>\n",
+       "      <td>0.076</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>0.9978</td>\n",
+       "      <td>3.51</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>9.4</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
+       "0            7.4              0.70         0.00             1.9      0.076   \n",
+       "1            7.8              0.88         0.00             2.6      0.098   \n",
+       "2            7.8              0.76         0.04             2.3      0.092   \n",
+       "3           11.2              0.28         0.56             1.9      0.075   \n",
+       "4            7.4              0.70         0.00             1.9      0.076   \n",
+       "\n",
+       "   free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
+       "0                 11.0                  34.0   0.9978  3.51       0.56   \n",
+       "1                 25.0                  67.0   0.9968  3.20       0.68   \n",
+       "2                 15.0                  54.0   0.9970  3.26       0.65   \n",
+       "3                 17.0                  60.0   0.9980  3.16       0.58   \n",
+       "4                 11.0                  34.0   0.9978  3.51       0.56   \n",
+       "\n",
+       "   alcohol  quality  \n",
+       "0      9.4        2  \n",
+       "1      9.8        2  \n",
+       "2      9.8        2  \n",
+       "3      9.8        3  \n",
+       "4      9.4        2  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Load data\n",
+    "\"\"\"\n",
+    "df = pd.read_csv(data_path)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "2815d511",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0, 1, 2, 3, 4, 5], dtype=int64)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Get classes\n",
+    "\"\"\"\n",
+    "np.unique(df['quality'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "d11d9540",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\nDescription: Remap \\n'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Remap \n",
+    "\"\"\"\n",
+    "# df['quality'] = df['quality'].apply(lambda x: x-3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4d694106",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0, 1, 2, 3, 4, 5], dtype=int64)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Get classes\n",
+    "\"\"\"\n",
+    "np.unique(df['quality'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "43458438",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.to_csv(\"winequality_red_label_remapped.csv\",index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ade5900f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "fixed acidity           0\n",
+       "volatile acidity        0\n",
+       "citric acid             0\n",
+       "residual sugar          0\n",
+       "chlorides               0\n",
+       "free sulfur dioxide     0\n",
+       "total sulfur dioxide    0\n",
+       "density                 0\n",
+       "pH                      0\n",
+       "sulphates               0\n",
+       "alcohol                 0\n",
+       "quality                 0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Check null value\n",
+    "\"\"\"\n",
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "1b34f13e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(1599, 11)"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Prepare data\n",
+    "\"\"\"\n",
+    "x=df.drop(['quality'], axis=1)\n",
+    "x.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "238dc707",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(1599,)"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Get target label\n",
+    "\"\"\"\n",
+    "y = df['quality']\n",
+    "y.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "5617aeb1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\"\n",
+    "Description: Split data\n",
+    "\"\"\"\n",
+    "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=40,stratify=y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "f5d3b86f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "shape of x_train:  (1279, 11)\n",
+      "shape of y_train: (1279,)\n",
+      "shape of x_test: (320, 11)\n",
+      "shape of y_test: (320,)\n"
+     ]
+    }
+   ],
+   "source": [
+    "'''\n",
+    "Description : Check size of dataset\n",
+    "'''\n",
+    "print(\"shape of x_train: \",x_train.shape)\n",
+    "print(\"shape of y_train: {}\".format(y_train.shape))\n",
+    "print(f'shape of x_test: {x_test.shape}')\n",
+    "print(f'shape of y_test: {y_test.shape}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "67168e49",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=1000)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(n_estimators=1000)</pre></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "RandomForestClassifier(n_estimators=1000)"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Create model architecture\n",
+    "\"\"\"\n",
+    "model = RandomForestClassifier(n_estimators=1000)\n",
+    "model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "fcad50e5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=1000)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(n_estimators=1000)</pre></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "RandomForestClassifier(n_estimators=1000)"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Train model\n",
+    "\"\"\"\n",
+    "model.fit(x_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "a20a2ec3",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "RandomForestClassifier(n_estimators=1000) : \n",
+      "Training Accuracy :  1.0\n",
+      "Validation Accuracy :  0.66875\n"
+     ]
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Get training and test accuracy\n",
+    "\"\"\"\n",
+    "print(f'{model} : ')\n",
+    "print('Training Accuracy : ', metrics.accuracy_score(y_train, model.predict(x_train)))\n",
+    "print('Validation Accuracy : ', metrics.accuracy_score(y_test, model.predict(x_test)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "5c20bc9e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pickle.dump(model, open(\"random_forest_model.pkl\", 'wb'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "f55a0ec8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "fixed acidity            15.90000\n",
+       "volatile acidity          1.58000\n",
+       "citric acid               1.00000\n",
+       "residual sugar           15.50000\n",
+       "chlorides                 0.61100\n",
+       "free sulfur dioxide      72.00000\n",
+       "total sulfur dioxide    289.00000\n",
+       "density                   1.00369\n",
+       "pH                        4.01000\n",
+       "sulphates                 2.00000\n",
+       "alcohol                  14.90000\n",
+       "quality                   5.00000\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: min, max\n",
+    "\"\"\"\n",
+    "df.max()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "234d7a65",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "fixed acidity           4.60000\n",
+       "volatile acidity        0.12000\n",
+       "citric acid             0.00000\n",
+       "residual sugar          0.90000\n",
+       "chlorides               0.01200\n",
+       "free sulfur dioxide     1.00000\n",
+       "total sulfur dioxide    6.00000\n",
+       "density                 0.99007\n",
+       "pH                      2.74000\n",
+       "sulphates               0.33000\n",
+       "alcohol                 8.40000\n",
+       "quality                 0.00000\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: min, max\n",
+    "\"\"\"\n",
+    "df.min()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "3fcb0d81",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',\n",
+       "       'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',\n",
+       "       'pH', 'sulphates', 'alcohol', 'quality'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "Description: Check columns\n",
+    "\"\"\"\n",
+    "df.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "29e30ec2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}