{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "from surprise import SVD, NMF, KNNBasic\n", "from surprise import dataset\n", "from surprise.model_selection import cross_validate" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "train = pd.read_csv(\"C:\\\\Users\\\\venug\\\\Downloads\\\\Datasets\\\\Black_Friday\\\\train.csv\")" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
User_IDProduct_IDGenderAgeOccupationCity_CategoryStay_In_Current_City_YearsMarital_StatusProduct_Category_1Product_Category_2Product_Category_3Purchase
01000001P00069042F0-1710A203NaNNaN8370
11000001P00248942F0-1710A2016.014.015200
21000001P00087842F0-1710A2012NaNNaN1422
31000001P00085442F0-1710A201214.0NaN1057
41000002P00285442M55+16C4+08NaNNaN7969
\n", "
" ], "text/plain": [ " User_ID Product_ID Gender Age Occupation City_Category \\\n", "0 1000001 P00069042 F 0-17 10 A \n", "1 1000001 P00248942 F 0-17 10 A \n", "2 1000001 P00087842 F 0-17 10 A \n", "3 1000001 P00085442 F 0-17 10 A \n", "4 1000002 P00285442 M 55+ 16 C \n", "\n", " Stay_In_Current_City_Years Marital_Status Product_Category_1 \\\n", "0 2 0 3 \n", "1 2 0 1 \n", "2 2 0 12 \n", "3 2 0 12 \n", "4 4+ 0 8 \n", "\n", " Product_Category_2 Product_Category_3 Purchase \n", "0 NaN NaN 8370 \n", "1 6.0 14.0 15200 \n", "2 NaN NaN 1422 \n", "3 14.0 NaN 1057 \n", "4 NaN NaN 7969 " ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train.head()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [], "source": [ "test = pd.read_csv(\"C:\\\\Users\\\\venug\\\\Downloads\\\\Datasets\\\\Black_Friday\\\\test.csv\")" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
User_IDProduct_IDGenderAgeOccupationCity_CategoryStay_In_Current_City_YearsMarital_StatusProduct_Category_1Product_Category_2Product_Category_3
01000004P00128942M46-507B21111.0NaN
11000009P00113442M26-3517C0035.0NaN
21000010P00288442F36-451B4+1514.0NaN
31000010P00145342F36-451B4+149.0NaN
41000011P00053842F26-351C1045.012.0
\n", "
" ], "text/plain": [ " User_ID Product_ID Gender Age Occupation City_Category \\\n", "0 1000004 P00128942 M 46-50 7 B \n", "1 1000009 P00113442 M 26-35 17 C \n", "2 1000010 P00288442 F 36-45 1 B \n", "3 1000010 P00145342 F 36-45 1 B \n", "4 1000011 P00053842 F 26-35 1 C \n", "\n", " Stay_In_Current_City_Years Marital_Status Product_Category_1 \\\n", "0 2 1 1 \n", "1 0 0 3 \n", "2 4+ 1 5 \n", "3 4+ 1 4 \n", "4 1 0 4 \n", "\n", " Product_Category_2 Product_Category_3 \n", "0 11.0 NaN \n", "1 5.0 NaN \n", "2 14.0 NaN \n", "3 9.0 NaN \n", "4 5.0 12.0 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test.head()" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "User_ID int64\n", "Product_ID object\n", "Gender object\n", "Age object\n", "Occupation int64\n", "City_Category object\n", "Stay_In_Current_City_Years object\n", "Marital_Status int64\n", "Product_Category_1 int64\n", "Product_Category_2 float64\n", "Product_Category_3 float64\n", "Purchase int64\n", "dtype: object" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train.dtypes" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "set_1 = set(train.Product_ID)\n", "set_2 = set(test.Product_ID)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "46" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(set_2-set_1)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "User_ID 0\n", "Product_ID 0\n", "Gender 0\n", "Age 0\n", "Occupation 0\n", "City_Category 0\n", "Stay_In_Current_City_Years 0\n", "Marital_Status 0\n", "Product_Category_1 0\n", "Product_Category_2 173638\n", "Product_Category_3 383247\n", "Purchase 0\n", "dtype: int64" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train.isnull().sum()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "train['Purchase_in_th'] = train['Purchase']/1000" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
User_IDProduct_IDGenderAgeOccupationCity_CategoryStay_In_Current_City_YearsMarital_StatusProduct_Category_1Product_Category_2Product_Category_3PurchasePurchase_in_th
01000001P00069042F0-1710A203NaNNaN83708.370
11000001P00248942F0-1710A2016.014.01520015.200
21000001P00087842F0-1710A2012NaNNaN14221.422
31000001P00085442F0-1710A201214.0NaN10571.057
41000002P00285442M55+16C4+08NaNNaN79697.969
\n", "
" ], "text/plain": [ " User_ID Product_ID Gender Age Occupation City_Category \\\n", "0 1000001 P00069042 F 0-17 10 A \n", "1 1000001 P00248942 F 0-17 10 A \n", "2 1000001 P00087842 F 0-17 10 A \n", "3 1000001 P00085442 F 0-17 10 A \n", "4 1000002 P00285442 M 55+ 16 C \n", "\n", " Stay_In_Current_City_Years Marital_Status Product_Category_1 \\\n", "0 2 0 3 \n", "1 2 0 1 \n", "2 2 0 12 \n", "3 2 0 12 \n", "4 4+ 0 8 \n", "\n", " Product_Category_2 Product_Category_3 Purchase Purchase_in_th \n", "0 NaN NaN 8370 8.370 \n", "1 6.0 14.0 15200 15.200 \n", "2 NaN NaN 1422 1.422 \n", "3 14.0 NaN 1057 1.057 \n", "4 NaN NaN 7969 7.969 " ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train.head()" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [], "source": [ "train.replace(np.nan, 99, inplace = True)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "from surprise.reader import Reader" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [], "source": [ "r = Reader(rating_scale=(0,24))" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [], "source": [ "D = dataset.Dataset.load_from_df(train[['User_ID','Product_ID','Purchase_in_th']],reader=r)" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'fit_time': (30.117451906204224,\n", " 29.93055558204651,\n", " 31.14846634864807,\n", " 30.985767126083374,\n", " 34.45454430580139,\n", " 32.89558291435242,\n", " 33.4782989025116),\n", " 'test_mae': array([1.97594841, 1.96132075, 1.95979817, 1.96281766, 1.96432126,\n", " 1.9618209 , 1.96302703]),\n", " 'test_rmse': array([2.71396117, 2.69141944, 2.68430397, 2.68798983, 2.68931951,\n", " 2.68679188, 2.69259348]),\n", " 'test_time': (0.540067195892334,\n", " 0.8783109188079834,\n", " 0.8875720500946045,\n", " 0.5775535106658936,\n", " 0.852200984954834,\n", " 1.1433093547821045,\n", " 0.5590999126434326)}" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cross_validate(SVD(),D,cv=7)" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(,\n", " dtype=object)" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.array(D)" ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [], "source": [ "s = SVD(n_factors=1000)" ] }, { "cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [], "source": [ "d1 = D.build_full_trainset()" ] }, { "cell_type": "code", "execution_count": 44, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "s.fit(d1)" ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [], "source": [ "pred_test = []\n", "for u,i in zip(test.User_ID, test.Product_ID):\n", " pred = s.predict(uid=u,iid=i)[3]\n", " pred = pred*1000\n", " pred_test.append((u,i,pred))" ] }, { "cell_type": "code", "execution_count": 46, "metadata": {}, "outputs": [], "source": [ "pred4 = pd.DataFrame(pred_test,columns=['User_ID','Product_ID','Purchase'])\n", "pred4.to_csv(\"C:\\\\Users\\\\venug\\\\Downloads\\\\Datasets\\\\Black_Friday\\\\pred4.csv\")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.6.4" } }, "nbformat": 4, "nbformat_minor": 2 }