ML_A3_Step2_ Features selection_GaussianRandomProjection_Dataset2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2a3c6f73",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Dataset 2 : Movies\n",
    "\n",
    "import numpy as np\n",
    "import time\n",
    "import pandas as pd\n",
    "import io\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Feature selection\n",
    "from sklearn.random_projection import GaussianRandomProjection\n",
    "# will be used to convert string into float\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "labelencoder_X = LabelEncoder()\n",
    "\n",
    "#dataset\n",
    "a = io.open('Movie Dataset.csv', encoding='latin-1')\n",
    "df = pd.read_csv(a)\n",
    "df = df.take([i for i in range(1300)], axis = 0)\n",
    "df = df.apply(LabelEncoder().fit_transform)\n",
    "\n",
    "#input\n",
    "X = df.drop(columns=['Awards'])\n",
    "\n",
    "#output\n",
    "y = df['Awards']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a3bb2d6b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# preprocessing StandardScaler\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# Create the object \n",
    "scaler = StandardScaler()\n",
    "# Calculate the mean and the standard deviation\n",
    "scaler.fit(X)\n",
    "# Transform the values\n",
    "X_scaled = scaler.transform(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "2065381d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1300, 8)\n",
      "(1300, 8)\n",
      "(1300, 8)\n",
      "(1300, 8)\n",
      "(1300, 8)\n",
      "(1300, 8)\n",
      "(1300, 8)\n",
      "(1300, 8)\n",
      "time for running the algorithm = 0.03858342900275602 s\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#import necessary libraries\n",
    "from sklearn.metrics import mean_squared_error\n",
    "from math import sqrt\n",
    "\n",
    "time1 = time.perf_counter()\n",
    "\n",
    "Reconstruction_rmse = []\n",
    "\n",
    "#calculate RMSE\n",
    "for i in range(1,9):\n",
    "    grp = GaussianRandomProjection(n_components = i,random_state = 42)\n",
    "    X_grp = grp.fit_transform(X_scaled)\n",
    "    X_back = grp.inverse_transform(X_grp)\n",
    "    print(X_back.shape)\n",
    "    Reconstruction_rmse.append(sqrt(mean_squared_error(X_back,X_scaled)))\n",
    "    \n",
    "time2 = time.perf_counter()\n",
    "timeA = time2 - time1\n",
    "print('time for running the algorithm =',timeA,'s')\n",
    "    \n",
    "number_of_clusters = [i for i in range(1,9)]\n",
    "fig, ax = plt.subplots()\n",
    "ax.set_title('Reconstruction score of dataset 2')\n",
    "ax.set_xlabel('Number of components')\n",
    "ax.set_ylabel('rmse')\n",
    "ax.plot(number_of_clusters, Reconstruction_rmse, marker=\".\", label=\"Reconstruction_rmse\")\n",
    "ax.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "7641498c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1300, 8)\n"
     ]
    }
   ],
   "source": [
    "grp = GaussianRandomProjection(n_components = 8,random_state = 42)\n",
    "X_grp = grp.fit_transform(X_scaled)\n",
    "print(X_grp.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "a667c4b3",
   "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>PC1</th>\n",
       "      <th>PC2</th>\n",
       "      <th>PC3</th>\n",
       "      <th>PC4</th>\n",
       "      <th>PC5</th>\n",
       "      <th>PC6</th>\n",
       "      <th>PC7</th>\n",
       "      <th>Awards</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.320857</td>\n",
       "      <td>1.621399</td>\n",
       "      <td>-1.552120</td>\n",
       "      <td>0.638862</td>\n",
       "      <td>2.545385</td>\n",
       "      <td>2.099864</td>\n",
       "      <td>-0.023808</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.704362</td>\n",
       "      <td>1.910944</td>\n",
       "      <td>-0.935956</td>\n",
       "      <td>1.250628</td>\n",
       "      <td>2.056800</td>\n",
       "      <td>2.080472</td>\n",
       "      <td>-0.300652</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.021072</td>\n",
       "      <td>1.564530</td>\n",
       "      <td>0.065466</td>\n",
       "      <td>1.260807</td>\n",
       "      <td>1.378952</td>\n",
       "      <td>0.358339</td>\n",
       "      <td>-0.692125</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-1.037906</td>\n",
       "      <td>1.749980</td>\n",
       "      <td>1.242438</td>\n",
       "      <td>-0.331798</td>\n",
       "      <td>1.068584</td>\n",
       "      <td>0.717149</td>\n",
       "      <td>-0.799427</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.202053</td>\n",
       "      <td>1.252274</td>\n",
       "      <td>0.658773</td>\n",
       "      <td>-0.168924</td>\n",
       "      <td>0.945020</td>\n",
       "      <td>0.277124</td>\n",
       "      <td>-0.296374</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        PC1       PC2       PC3       PC4       PC5       PC6       PC7  \\\n",
       "0 -0.320857  1.621399 -1.552120  0.638862  2.545385  2.099864 -0.023808   \n",
       "1 -0.704362  1.910944 -0.935956  1.250628  2.056800  2.080472 -0.300652   \n",
       "2  0.021072  1.564530  0.065466  1.260807  1.378952  0.358339 -0.692125   \n",
       "3 -1.037906  1.749980  1.242438 -0.331798  1.068584  0.717149 -0.799427   \n",
       "4 -0.202053  1.252274  0.658773 -0.168924  0.945020  0.277124 -0.296374   \n",
       "\n",
       "   Awards  \n",
       "0       0  \n",
       "1       0  \n",
       "2       0  \n",
       "3       0  \n",
       "4       0  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# New dataframe\n",
    "\n",
    "df_new = pd.DataFrame(X_grp, columns =['PC1','PC2','PC3','PC4','PC5'\n",
    "                                         ,'PC6','PC7','PC8'] )\n",
    "df_new = df_new.drop(columns=['PC8'])\n",
    "\n",
    "df_new['Awards'] = df.Awards\n",
    "df_new.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "542dea09",
   "metadata": {},
   "outputs": [],
   "source": [
    "# save the data\n",
    "df_new.to_csv('Movie_grp.csv', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "92efeb37",
   "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}