{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\Users\\Ashok Chava\\Anaconda3\\lib\\site-packages\\sklearn\\utils\\fixes.py:313: FutureWarning: numpy not_equal will not check object identity in the future. The comparison did not return the same result as suggested by the identity (`is`)) and will change.\n", " _nan_object_mask = _nan_object_array != _nan_object_array\n" ] } ], "source": [ "#random forrest\n", "from IPython.core.interactiveshell import InteractiveShell\n", "InteractiveShell.ast_node_interactivity = \"all\"\n", "import pandas as pd\n", "import numpy as np\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.metrics import explained_variance_score\n", "from sklearn.metrics import mean_squared_error\n", "from sklearn.metrics import mean_squared_log_error\n", "from sklearn.preprocessing import PolynomialFeatures\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.ensemble import RandomForestRegressor\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "train=pd.read_csv('train.csv')\n", "meal_info=pd.read_csv('meal_info.csv')\n", "full_filment=pd.read_csv('fulfilment_center_info.csv')\n", "test=pd.read_csv('test_QoiMO9B.csv')\n", "train=train.merge(meal_info,on='meal_id',how='left')\n", "train=train.merge(full_filment,on='center_id',how='left')\n", "#train.head()\n", "#train.shape\n", "test=test.merge(meal_info,on='meal_id',how='left')\n", "test=test.merge(full_filment,on='center_id',how='left')\n", "#test.head()\n", "#test.shape" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": true }, "outputs": [], "source": [ "train['category']=train['category'].astype('category')\n", "train['cuisine']=train['cuisine'].astype('category')\n", "train['center_type']=train['center_type'].astype('category')" ] }, { "cell_type": "code", "execution_count": 30, "metadata": { "collapsed": true }, "outputs": [], "source": [ "test['category']=test['category'].astype('category')\n", "test['cuisine']=test['cuisine'].astype('category')\n", "test['center_type']=test['center_type'].astype('category')" ] }, { "cell_type": "code", "execution_count": 31, "metadata": { "collapsed": true }, "outputs": [], "source": [ "test_dummies = pd.get_dummies(data=test, columns=['center_id', 'meal_id','category','cuisine','city_code','region_code','center_type'],drop_first=True)" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | checkout_price | \n", "base_price | \n", "emailer_for_promotion | \n", "homepage_featured | \n", "op_area | \n", "center_id_11 | \n", "center_id_13 | \n", "center_id_14 | \n", "center_id_17 | \n", "center_id_20 | \n", "... | \n", "city_code_713 | \n", "region_code_34 | \n", "region_code_35 | \n", "region_code_56 | \n", "region_code_71 | \n", "region_code_77 | \n", "region_code_85 | \n", "region_code_93 | \n", "center_type_TYPE_B | \n", "center_type_TYPE_C | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "158.11 | \n", "159.11 | \n", "0 | \n", "0 | \n", "2.0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
1 | \n", "160.11 | \n", "159.11 | \n", "0 | \n", "0 | \n", "2.0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
2 | \n", "157.14 | \n", "159.14 | \n", "0 | \n", "0 | \n", "2.0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
3 | \n", "162.02 | \n", "162.02 | \n", "0 | \n", "0 | \n", "2.0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
4 | \n", "163.93 | \n", "163.93 | \n", "0 | \n", "0 | \n", "2.0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
5 rows × 206 columns
\n", "\n", " | id | \n", "week | \n", "checkout_price | \n", "base_price | \n", "emailer_for_promotion | \n", "homepage_featured | \n", "num_orders | \n", "op_area | \n", "center_id_11 | \n", "center_id_13 | \n", "... | \n", "city_code_713 | \n", "region_code_34 | \n", "region_code_35 | \n", "region_code_56 | \n", "region_code_71 | \n", "region_code_77 | \n", "region_code_85 | \n", "region_code_93 | \n", "center_type_TYPE_B | \n", "center_type_TYPE_C | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "1379560 | \n", "1 | \n", "136.83 | \n", "152.29 | \n", "0 | \n", "0 | \n", "177 | \n", "2.0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
1 | \n", "1466964 | \n", "1 | \n", "136.83 | \n", "135.83 | \n", "0 | \n", "0 | \n", "270 | \n", "2.0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
2 | \n", "1346989 | \n", "1 | \n", "134.86 | \n", "135.86 | \n", "0 | \n", "0 | \n", "189 | \n", "2.0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
3 | \n", "1338232 | \n", "1 | \n", "339.50 | \n", "437.53 | \n", "0 | \n", "0 | \n", "54 | \n", "2.0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
4 | \n", "1448490 | \n", "1 | \n", "243.50 | \n", "242.50 | \n", "0 | \n", "0 | \n", "40 | \n", "2.0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
5 rows × 209 columns
\n", "\n", " | checkout_price | \n", "base_price | \n", "emailer_for_promotion | \n", "homepage_featured | \n", "op_area | \n", "center_id_11 | \n", "center_id_13 | \n", "center_id_14 | \n", "center_id_17 | \n", "center_id_20 | \n", "... | \n", "city_code_713 | \n", "region_code_34 | \n", "region_code_35 | \n", "region_code_56 | \n", "region_code_71 | \n", "region_code_77 | \n", "region_code_85 | \n", "region_code_93 | \n", "center_type_TYPE_B | \n", "center_type_TYPE_C | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "136.83 | \n", "152.29 | \n", "0 | \n", "0 | \n", "2.0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
1 | \n", "136.83 | \n", "135.83 | \n", "0 | \n", "0 | \n", "2.0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
2 | \n", "134.86 | \n", "135.86 | \n", "0 | \n", "0 | \n", "2.0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
3 | \n", "339.50 | \n", "437.53 | \n", "0 | \n", "0 | \n", "2.0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
4 | \n", "243.50 | \n", "242.50 | \n", "0 | \n", "0 | \n", "2.0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "... | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "0 | \n", "1 | \n", "
5 rows × 206 columns
\n", "