s413941/Uczenie_maszynowe_Systemy_Rekomendacyjne
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
master
Uczenie_maszynowe_Systemy_R.../P6. LightFM.ipynb

1790 lines
56 KiB
Plaintext
Raw Permalink Normal View History

UMSR
2020-06-14 22:23:50 +02:00
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import helpers\n",
"import pandas as pd\n",
"import numpy as np\n",
"import scipy.sparse as sparse\n",
"from collections import defaultdict\n",
"from itertools import chain\n",
"import random\n",
"import time\n",
"import matplotlib.pyplot as plt\n",
"\n",
"train_read=pd.read_csv('./Datasets/ml-100k/train.csv', sep='\\t', header=None)\n",
"test_read=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None)\n",
"train_ui, test_ui, user_code_id, user_id_code, item_code_id, item_id_code = helpers.data_to_csr(train_read, test_read)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<943x1682 sparse matrix of type '<class 'numpy.longlong'>'\n",
"\twith 80000 stored elements in Compressed Sparse Row format>"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_ui"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Let's prepare user and item features"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Item features"
]
},
{
"cell_type": "code",
"execution_count": 3,
"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>0</th>\n",
" <th>1</th>\n",
" <th>2</th>\n",
" <th>3</th>\n",
" <th>4</th>\n",
" <th>5</th>\n",
" <th>6</th>\n",
" <th>7</th>\n",
" <th>8</th>\n",
" <th>9</th>\n",
" <th>...</th>\n",
" <th>14</th>\n",
" <th>15</th>\n",
" <th>16</th>\n",
" <th>17</th>\n",
" <th>18</th>\n",
" <th>19</th>\n",
" <th>20</th>\n",
" <th>21</th>\n",
" <th>22</th>\n",
" <th>23</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Toy Story (1995)</td>\n",
" <td>01-Jan-1995</td>\n",
" <td>NaN</td>\n",
" <td>http://us.imdb.com/M/title-exact?Toy%20Story%2...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>GoldenEye (1995)</td>\n",
" <td>01-Jan-1995</td>\n",
" <td>NaN</td>\n",
" <td>http://us.imdb.com/M/title-exact?GoldenEye%20(...</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>Four Rooms (1995)</td>\n",
" <td>01-Jan-1995</td>\n",
" <td>NaN</td>\n",
" <td>http://us.imdb.com/M/title-exact?Four%20Rooms%...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3 rows × 24 columns</p>\n",
"</div>"
],
"text/plain": [
" 0 1 2 3 \\\n",
"0 1 Toy Story (1995) 01-Jan-1995 NaN \n",
"1 2 GoldenEye (1995) 01-Jan-1995 NaN \n",
"2 3 Four Rooms (1995) 01-Jan-1995 NaN \n",
"\n",
" 4 5 6 7 8 9 ... \\\n",
"0 http://us.imdb.com/M/title-exact?Toy%20Story%2... 0 0 0 1 1 ... \n",
"1 http://us.imdb.com/M/title-exact?GoldenEye%20(... 0 1 1 0 0 ... \n",
"2 http://us.imdb.com/M/title-exact?Four%20Rooms%... 0 0 0 0 0 ... \n",
"\n",
" 14 15 16 17 18 19 20 21 22 23 \n",
"0 0 0 0 0 0 0 0 0 0 0 \n",
"1 0 0 0 0 0 0 0 1 0 0 \n",
"2 0 0 0 0 0 0 0 1 0 0 \n",
"\n",
"[3 rows x 24 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"movies = pd.read_csv('./Datasets/ml-100k/u.item', sep='|', encoding='latin-1', header=None)\n",
"movies[:3]"
]
},
{
"cell_type": "code",
"execution_count": 7,
"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>id_1</th>\n",
" <th>id_2</th>\n",
" <th>id_3</th>\n",
" <th>id_4</th>\n",
" <th>id_5</th>\n",
" <th>id_6</th>\n",
" <th>id_7</th>\n",
" <th>id_8</th>\n",
" <th>id_9</th>\n",
" <th>id_10</th>\n",
" <th>...</th>\n",
" <th>date_30-Mar-1996</th>\n",
" <th>date_30-May-1997</th>\n",
" <th>date_30-Nov-1996</th>\n",
" <th>date_30-Oct-1995</th>\n",
" <th>date_30-Oct-1996</th>\n",
" <th>date_31-Dec-1997</th>\n",
" <th>date_31-Jan-1997</th>\n",
" <th>date_31-Jul-1996</th>\n",
" <th>date_31-May-1996</th>\n",
" <th>date_4-Feb-1971</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3 rows × 1922 columns</p>\n",
"</div>"
],
"text/plain": [
" id_1 id_2 id_3 id_4 id_5 id_6 id_7 id_8 id_9 id_10 ... \\\n",
"0 1 0 0 0 0 0 0 0 0 0 ... \n",
"1 0 1 0 0 0 0 0 0 0 0 ... \n",
"2 0 0 1 0 0 0 0 0 0 0 ... \n",
"\n",
" date_30-Mar-1996 date_30-May-1997 date_30-Nov-1996 date_30-Oct-1995 \\\n",
"0 0 0 0 0 \n",
"1 0 0 0 0 \n",
"2 0 0 0 0 \n",
"\n",
" date_30-Oct-1996 date_31-Dec-1997 date_31-Jan-1997 date_31-Jul-1996 \\\n",
"0 0 0 0 0 \n",
"1 0 0 0 0 \n",
"2 0 0 0 0 \n",
"\n",
" date_31-May-1996 date_4-Feb-1971 \n",
"0 0 0 \n",
"1 0 0 \n",
"2 0 0 \n",
"\n",
"[3 rows x 1922 columns]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"movies=movies.astype(object)\n",
"id_date=pd.get_dummies(movies[[0,2]], ['id', 'date'])\n",
"id_date[:3]"
]
},
{
"cell_type": "code",
"execution_count": 8,
"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>0</th>\n",
" <th>1</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>unknown</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Action</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Adventure</td>\n",
" <td>2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0 1\n",
"0 unknown 0\n",
"1 Action 1\n",
"2 Adventure 2"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"genres = pd.read_csv('./Datasets/ml-100k/u.genre', sep='|', header=None,\n",
" encoding='latin-1')\n",
"genres[:3]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"item_genres=movies[np.arange(5,24)]\n",
"item_genres.columns=list(genres[0])"
]
},
{
"cell_type": "code",
"execution_count": 10,
"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>id_1</th>\n",
" <th>id_2</th>\n",
" <th>id_3</th>\n",
" <th>id_4</th>\n",
" <th>id_5</th>\n",
" <th>id_6</th>\n",
" <th>id_7</th>\n",
" <th>id_8</th>\n",
" <th>id_9</th>\n",
" <th>id_10</th>\n",
" <th>...</th>\n",
" <th>Fantasy</th>\n",
" <th>Film-Noir</th>\n",
" <th>Horror</th>\n",
" <th>Musical</th>\n",
" <th>Mystery</th>\n",
" <th>Romance</th>\n",
" <th>Sci-Fi</th>\n",
" <th>Thriller</th>\n",
" <th>War</th>\n",
" <th>Western</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1677</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1678</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1679</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1680</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1681</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1682 rows × 1941 columns</p>\n",
"</div>"
],
"text/plain": [
" id_1 id_2 id_3 id_4 id_5 id_6 id_7 id_8 id_9 id_10 ... \\\n",
"0 1 0 0 0 0 0 0 0 0 0 ... \n",
"1 0 1 0 0 0 0 0 0 0 0 ... \n",
"2 0 0 1 0 0 0 0 0 0 0 ... \n",
"3 0 0 0 1 0 0 0 0 0 0 ... \n",
"4 0 0 0 0 1 0 0 0 0 0 ... \n",
"... ... ... ... ... ... ... ... ... ... ... ... \n",
"1677 0 0 0 0 0 0 0 0 0 0 ... \n",
"1678 0 0 0 0 0 0 0 0 0 0 ... \n",
"1679 0 0 0 0 0 0 0 0 0 0 ... \n",
"1680 0 0 0 0 0 0 0 0 0 0 ... \n",
"1681 0 0 0 0 0 0 0 0 0 0 ... \n",
"\n",
" Fantasy Film-Noir Horror Musical Mystery Romance Sci-Fi Thriller \\\n",
"0 0 0 0 0 0 0 0 0 \n",
"1 0 0 0 0 0 0 0 1 \n",
"2 0 0 0 0 0 0 0 1 \n",
"3 0 0 0 0 0 0 0 0 \n",
"4 0 0 0 0 0 0 0 1 \n",
"... ... ... ... ... ... ... ... ... \n",
"1677 0 0 0 0 0 0 0 0 \n",
"1678 0 0 0 0 0 1 0 1 \n",
"1679 0 0 0 0 0 1 0 0 \n",
"1680 0 0 0 0 0 0 0 0 \n",
"1681 0 0 0 0 0 0 0 0 \n",
"\n",
" War Western \n",
"0 0 0 \n",
"1 0 0 \n",
"2 0 0 \n",
"3 0 0 \n",
"4 0 0 \n",
"... ... ... \n",
"1677 0 0 \n",
"1678 0 0 \n",
"1679 0 0 \n",
"1680 0 0 \n",
"1681 0 0 \n",
"\n",
"[1682 rows x 1941 columns]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"item_features_df=pd.concat([id_date, item_genres], axis=1).astype(int)\n",
"item_features_df"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<1682x1941 sparse matrix of type '<class 'numpy.longlong'>'\n",
"\twith 6256 stored elements in Compressed Sparse Row format>"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"item_features=sparse.csr_matrix(item_features_df.values)\n",
"item_features"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### User features"
]
},
{
"cell_type": "code",
"execution_count": 13,
"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>0</th>\n",
" <th>1</th>\n",
" <th>2</th>\n",
" <th>3</th>\n",
" <th>4</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>24</td>\n",
" <td>M</td>\n",
" <td>technician</td>\n",
" <td>85711</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>53</td>\n",
" <td>F</td>\n",
" <td>other</td>\n",
" <td>94043</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>23</td>\n",
" <td>M</td>\n",
" <td>writer</td>\n",
" <td>32067</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0 1 2 3 4\n",
"0 1 24 M technician 85711\n",
"1 2 53 F other 94043\n",
"2 3 23 M writer 32067"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"users = pd.read_csv('./Datasets/ml-100k/u.user', sep='|', encoding='latin-1', header=None)\n",
"users[:3]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"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>id_1</th>\n",
" <th>id_2</th>\n",
" <th>id_3</th>\n",
" <th>id_4</th>\n",
" <th>id_5</th>\n",
" <th>id_6</th>\n",
" <th>id_7</th>\n",
" <th>id_8</th>\n",
" <th>id_9</th>\n",
" <th>id_10</th>\n",
" <th>...</th>\n",
" <th>Fantasy</th>\n",
" <th>Film-Noir</th>\n",
" <th>Horror</th>\n",
" <th>Musical</th>\n",
" <th>Mystery</th>\n",
" <th>Romance</th>\n",
" <th>Sci-Fi</th>\n",
" <th>Thriller</th>\n",
" <th>War</th>\n",
" <th>Western</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>3 rows × 1941 columns</p>\n",
"</div>"
],
"text/plain": [
" id_1 id_2 id_3 id_4 id_5 id_6 id_7 id_8 id_9 id_10 ... Fantasy \\\n",
"0 1 0 0 0 0 0 0 0 0 0 ... 0 \n",
"1 0 1 0 0 0 0 0 0 0 0 ... 0 \n",
"2 0 0 1 0 0 0 0 0 0 0 ... 0 \n",
"\n",
" Film-Noir Horror Musical Mystery Romance Sci-Fi Thriller War \\\n",
"0 0 0 0 0 0 0 0 0 \n",
"1 0 0 0 0 0 0 1 0 \n",
"2 0 0 0 0 0 0 1 0 \n",
"\n",
" Western \n",
"0 0 \n",
"1 0 \n",
"2 0 \n",
"\n",
"[3 rows x 1941 columns]"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"users=users.astype(object)\n",
"user_features_df=pd.get_dummies(users, ['id', 'age', 'sex','profesion','zip_code'])\n",
"item_features_df[:3]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<943x1682 sparse matrix of type '<class 'numpy.longlong'>'\n",
"\twith 80000 stored elements in Compressed Sparse Row format>"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_ui"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<943x1822 sparse matrix of type '<class 'numpy.uint8'>'\n",
"\twith 4715 stored elements in Compressed Sparse Row format>"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"user_features=sparse.csr_matrix(user_features_df.values)\n",
"user_features"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### LightFM with user and item features"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"logistic\n",
"Train precision: 0.09\n",
"Test precision: 0.03\n",
"bpr\n",
"Train precision: 0.57\n",
"Test precision: 0.24\n",
"warp\n",
"Train precision: 0.63\n",
"Test precision: 0.34\n"
]
}
],
"source": [
"from lightfm import LightFM\n",
"from lightfm.evaluation import precision_at_k\n",
"\n",
"for loss in ['logistic', 'bpr', 'warp']:\n",
"\n",
" model = LightFM(no_components=10, loss=loss)\n",
" model.fit(train_ui, user_features=user_features, item_features=item_features, epochs=30, num_threads=4)\n",
"\n",
" print(loss)\n",
" print(\"Train precision: %.2f\" % precision_at_k(model, test_interactions=train_ui, \n",
" user_features=user_features, item_features=item_features, k=10).mean())\n",
" print(\"Test precision: %.2f\" % precision_at_k(model, test_interactions=test_ui, train_interactions=train_ui,\n",
" user_features=user_features, item_features=item_features, k=10).mean())"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"def top_k_recommendations(model, user_features, item_features, user_code_id, item_code_id, topK=10):\n",
" result=[]\n",
" for user_code in range(test_ui.shape[0]):\n",
" user_rated=train_ui.indices[train_ui.indptr[user_code]:train_ui.indptr[user_code+1]]\n",
" scores = model.predict(user_code, np.arange(train_ui.shape[1]), user_features=user_features, item_features=item_features)\n",
" \n",
" scores[user_rated]=-np.inf # to put rated items at the end of the list\n",
" \n",
" top_items=[item_code_id[item] for item in np.argsort(-scores)[:topK]]\n",
" result.append([user_code_id[user_code]]+list(chain(*zip(top_items,-np.sort(-scores)[:topK]))))\n",
" return result\n",
"\n",
"def estimate(model, user_features, item_features, user_code_id, item_code_id, test_ui):\n",
" result=[]\n",
" for user, item in zip(*test_ui.nonzero()):\n",
" result.append([user_code_id[user], item_code_id[item], \n",
" model.predict(user, np.array([item]), user_features=user_features, item_features=item_features)[0]])\n",
" return result"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"top_n=pd.DataFrame(top_k_recommendations(model=model, user_features=user_features, item_features=item_features, user_code_id=user_code_id, item_code_id=item_code_id, topK=10))\n",
"top_n.to_csv('Recommendations generated/ml-100k/Ready_LightFM_reco.csv', index=False, header=False)\n",
"\n",
"estimations=pd.DataFrame(estimate(model=model, user_features=user_features, item_features=item_features, user_code_id=user_code_id, item_code_id=item_code_id, test_ui=test_ui))\n",
"estimations.to_csv('Recommendations generated/ml-100k/Ready_LightFM_estimations.csv', index=False, header=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Pure MF with LightFM"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"item_features_interactions=sparse.csr_matrix(item_features_df[[item_feature for item_feature in item_features_df.columns \n",
" if 'id_' in item_feature]].values)\n",
"user_features_interactions=sparse.csr_matrix(user_features_df[[user_feature for user_feature in user_features_df.columns \n",
" if 'id_' in user_feature]].values)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train precision: 0.63\n",
"Test precision: 0.33\n"
]
}
],
"source": [
"from lightfm import LightFM\n",
"\n",
"model = LightFM(loss='warp')\n",
"model.fit(train_ui, user_features=user_features_interactions, item_features=item_features_interactions, epochs=30, num_threads=4)\n",
"\n",
"from lightfm.evaluation import precision_at_k\n",
"\n",
"print(\"Train precision: %.2f\" % precision_at_k(model, test_interactions=train_ui, k=10).mean())\n",
"print(\"Test precision: %.2f\" % precision_at_k(model, test_interactions=test_ui, train_interactions=train_ui, k=10).mean())"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"top_n=pd.DataFrame(top_k_recommendations(model=model, user_features=user_features_interactions, item_features=item_features_interactions, user_code_id=user_code_id, item_code_id=item_code_id, topK=10))\n",
"top_n.to_csv('Recommendations generated/ml-100k/Ready_LightFMpureMF_reco.csv', index=False, header=False)\n",
"\n",
"estimations=pd.DataFrame(estimate(model=model, user_features=user_features_interactions, item_features=item_features_interactions, user_code_id=user_code_id, item_code_id=item_code_id, test_ui=test_ui))\n",
"estimations.to_csv('Recommendations generated/ml-100k/Ready_LightFMpureMF_estimations.csv', index=False, header=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### LightFM with user/item attributes only (without treating id as a feature)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"item_features_only=sparse.csr_matrix(item_features_df[[item_feature for item_feature in item_features_df.columns \n",
" if 'id_' not in item_feature]].values)\n",
"user_features_only=sparse.csr_matrix(user_features_df[[user_feature for user_feature in user_features_df.columns \n",
" if 'id_' not in user_feature]].values)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train precision: 0.40\n",
"Test precision: 0.16\n"
]
}
],
"source": [
"from lightfm import LightFM\n",
"\n",
"model = LightFM(loss='warp')\n",
"model.fit(train_ui, user_features=user_features_only, item_features=item_features_only, epochs=30, num_threads=4)\n",
"\n",
"from lightfm.evaluation import precision_at_k\n",
"\n",
"print(\"Train precision: %.2f\" % precision_at_k(model, test_interactions=train_ui, \n",
" user_features=user_features_only, item_features=item_features_only, k=10).mean())\n",
"print(\"Test precision: %.2f\" % precision_at_k(model, test_interactions=test_ui, train_interactions=train_ui,\n",
" user_features=user_features_only, item_features=item_features_only, k=10).mean())"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"top_n=pd.DataFrame(top_k_recommendations(model=model, user_features=user_features_only, item_features=item_features_only, user_code_id=user_code_id, item_code_id=item_code_id, topK=10))\n",
"top_n.to_csv('Recommendations generated/ml-100k/Ready_LightFMcontent_reco.csv', index=False, header=False)\n",
"\n",
"estimations=pd.DataFrame(estimate(model=model, user_features=user_features_only, item_features=item_features_only, user_code_id=user_code_id, item_code_id=item_code_id, test_ui=test_ui))\n",
"estimations.to_csv('Recommendations generated/ml-100k/Ready_LightFMcontent_estimations.csv', index=False, header=False)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 8294.93it/s]\n",
"943it [00:00, 7480.38it/s]\n",
"943it [00:00, 8182.78it/s]\n",
"943it [00:00, 7942.50it/s]\n",
"943it [00:00, 7571.16it/s]\n",
"943it [00:00, 7715.40it/s]\n",
"943it [00:00, 8094.16it/s]\n",
"943it [00:00, 9015.90it/s]\n",
"943it [00:00, 7848.42it/s]\n",
"943it [00:00, 7401.02it/s]\n"
]
},
{
"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>Model</th>\n",
" <th>RMSE</th>\n",
" <th>MAE</th>\n",
" <th>precision</th>\n",
" <th>recall</th>\n",
" <th>F_1</th>\n",
" <th>F_05</th>\n",
" <th>precision_super</th>\n",
" <th>recall_super</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFMpureMF</td>\n",
" <td>7.953192</td>\n",
" <td>7.462008</td>\n",
" <td>0.334464</td>\n",
" <td>0.219997</td>\n",
" <td>0.217225</td>\n",
" <td>0.254981</td>\n",
" <td>0.233798</td>\n",
" <td>0.266952</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFM</td>\n",
" <td>162.707436</td>\n",
" <td>160.855483</td>\n",
" <td>0.340827</td>\n",
" <td>0.217682</td>\n",
" <td>0.217990</td>\n",
" <td>0.258010</td>\n",
" <td>0.243884</td>\n",
" <td>0.260663</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_P3</td>\n",
" <td>3.702446</td>\n",
" <td>3.527273</td>\n",
" <td>0.282185</td>\n",
" <td>0.192092</td>\n",
" <td>0.186749</td>\n",
" <td>0.216980</td>\n",
" <td>0.204185</td>\n",
" <td>0.240096</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_ImplicitALS</td>\n",
" <td>3.266101</td>\n",
" <td>3.065824</td>\n",
" <td>0.255037</td>\n",
" <td>0.188653</td>\n",
" <td>0.176852</td>\n",
" <td>0.201189</td>\n",
" <td>0.166631</td>\n",
" <td>0.214925</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_TopPop</td>\n",
" <td>2.508258</td>\n",
" <td>2.217909</td>\n",
" <td>0.188865</td>\n",
" <td>0.116919</td>\n",
" <td>0.118732</td>\n",
" <td>0.141584</td>\n",
" <td>0.130472</td>\n",
" <td>0.137473</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFMcontent</td>\n",
" <td>182.471340</td>\n",
" <td>180.405210</td>\n",
" <td>0.160339</td>\n",
" <td>0.101224</td>\n",
" <td>0.102198</td>\n",
" <td>0.121074</td>\n",
" <td>0.102682</td>\n",
" <td>0.112455</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Baseline</td>\n",
" <td>0.949459</td>\n",
" <td>0.752487</td>\n",
" <td>0.091410</td>\n",
" <td>0.037652</td>\n",
" <td>0.046030</td>\n",
" <td>0.061286</td>\n",
" <td>0.079614</td>\n",
" <td>0.056463</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_GlobalAvg</td>\n",
" <td>1.125760</td>\n",
" <td>0.943534</td>\n",
" <td>0.061188</td>\n",
" <td>0.025968</td>\n",
" <td>0.031383</td>\n",
" <td>0.041343</td>\n",
" <td>0.040558</td>\n",
" <td>0.032107</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Random</td>\n",
" <td>1.514355</td>\n",
" <td>1.216383</td>\n",
" <td>0.049735</td>\n",
" <td>0.022300</td>\n",
" <td>0.025782</td>\n",
" <td>0.033598</td>\n",
" <td>0.028219</td>\n",
" <td>0.021751</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_BaselineUI</td>\n",
" <td>0.967585</td>\n",
" <td>0.762740</td>\n",
" <td>0.000954</td>\n",
" <td>0.000170</td>\n",
" <td>0.000278</td>\n",
" <td>0.000463</td>\n",
" <td>0.000644</td>\n",
" <td>0.000189</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model RMSE MAE precision recall \\\n",
"0 Ready_LightFMpureMF 7.953192 7.462008 0.334464 0.219997 \n",
"0 Ready_LightFM 162.707436 160.855483 0.340827 0.217682 \n",
"0 Self_P3 3.702446 3.527273 0.282185 0.192092 \n",
"0 Ready_ImplicitALS 3.266101 3.065824 0.255037 0.188653 \n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 \n",
"0 Ready_LightFMcontent 182.471340 180.405210 0.160339 0.101224 \n",
"0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 \n",
"0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 \n",
"0 Ready_Random 1.514355 1.216383 0.049735 0.022300 \n",
"0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 \n",
"\n",
" F_1 F_05 precision_super recall_super \n",
"0 0.217225 0.254981 0.233798 0.266952 \n",
"0 0.217990 0.258010 0.243884 0.260663 \n",
"0 0.186749 0.216980 0.204185 0.240096 \n",
"0 0.176852 0.201189 0.166631 0.214925 \n",
"0 0.118732 0.141584 0.130472 0.137473 \n",
"0 0.102198 0.121074 0.102682 0.112455 \n",
"0 0.046030 0.061286 0.079614 0.056463 \n",
"0 0.031383 0.041343 0.040558 0.032107 \n",
"0 0.025782 0.033598 0.028219 0.021751 \n",
"0 0.000278 0.000463 0.000644 0.000189 "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"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>Model</th>\n",
" <th>NDCG</th>\n",
" <th>mAP</th>\n",
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
" <th>Gini</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFMpureMF</td>\n",
" <td>0.398778</td>\n",
" <td>0.263058</td>\n",
" <td>0.629129</td>\n",
" <td>0.607709</td>\n",
" <td>0.913043</td>\n",
" <td>1.000000</td>\n",
" <td>0.275613</td>\n",
" <td>5.085818</td>\n",
" <td>0.913665</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFM</td>\n",
" <td>0.403850</td>\n",
" <td>0.268266</td>\n",
" <td>0.637590</td>\n",
" <td>0.606568</td>\n",
" <td>0.898197</td>\n",
" <td>1.000000</td>\n",
" <td>0.351371</td>\n",
" <td>5.366291</td>\n",
" <td>0.885046</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_P3</td>\n",
" <td>0.339114</td>\n",
" <td>0.204905</td>\n",
" <td>0.572157</td>\n",
" <td>0.593544</td>\n",
" <td>0.875928</td>\n",
" <td>1.000000</td>\n",
" <td>0.077201</td>\n",
" <td>3.875892</td>\n",
" <td>0.974947</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_ImplicitALS</td>\n",
" <td>0.305908</td>\n",
" <td>0.172546</td>\n",
" <td>0.523871</td>\n",
" <td>0.591709</td>\n",
" <td>0.889714</td>\n",
" <td>1.000000</td>\n",
" <td>0.502886</td>\n",
" <td>5.722957</td>\n",
" <td>0.827507</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_TopPop</td>\n",
" <td>0.214651</td>\n",
" <td>0.111707</td>\n",
" <td>0.400939</td>\n",
" <td>0.555546</td>\n",
" <td>0.765642</td>\n",
" <td>1.000000</td>\n",
" <td>0.038961</td>\n",
" <td>3.159079</td>\n",
" <td>0.987317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFMcontent</td>\n",
" <td>0.180079</td>\n",
" <td>0.087429</td>\n",
" <td>0.337825</td>\n",
" <td>0.547572</td>\n",
" <td>0.704136</td>\n",
" <td>0.974973</td>\n",
" <td>0.264791</td>\n",
" <td>4.909893</td>\n",
" <td>0.926201</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Baseline</td>\n",
" <td>0.095957</td>\n",
" <td>0.043178</td>\n",
" <td>0.198193</td>\n",
" <td>0.515501</td>\n",
" <td>0.437964</td>\n",
" <td>1.000000</td>\n",
" <td>0.033911</td>\n",
" <td>2.836513</td>\n",
" <td>0.991139</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_GlobalAvg</td>\n",
" <td>0.067695</td>\n",
" <td>0.027470</td>\n",
" <td>0.171187</td>\n",
" <td>0.509546</td>\n",
" <td>0.384942</td>\n",
" <td>1.000000</td>\n",
" <td>0.025974</td>\n",
" <td>2.711772</td>\n",
" <td>0.992003</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Random</td>\n",
" <td>0.054383</td>\n",
" <td>0.021119</td>\n",
" <td>0.133978</td>\n",
" <td>0.507680</td>\n",
" <td>0.339343</td>\n",
" <td>0.986957</td>\n",
" <td>0.177489</td>\n",
" <td>5.088670</td>\n",
" <td>0.907676</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_BaselineUI</td>\n",
" <td>0.000752</td>\n",
" <td>0.000168</td>\n",
" <td>0.001677</td>\n",
" <td>0.496424</td>\n",
" <td>0.009544</td>\n",
" <td>0.600530</td>\n",
" <td>0.005051</td>\n",
" <td>1.803126</td>\n",
" <td>0.996380</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model NDCG mAP MRR LAUC HR \\\n",
"0 Ready_LightFMpureMF 0.398778 0.263058 0.629129 0.607709 0.913043 \n",
"0 Ready_LightFM 0.403850 0.268266 0.637590 0.606568 0.898197 \n",
"0 Self_P3 0.339114 0.204905 0.572157 0.593544 0.875928 \n",
"0 Ready_ImplicitALS 0.305908 0.172546 0.523871 0.591709 0.889714 \n",
"0 Self_TopPop 0.214651 0.111707 0.400939 0.555546 0.765642 \n",
"0 Ready_LightFMcontent 0.180079 0.087429 0.337825 0.547572 0.704136 \n",
"0 Ready_Baseline 0.095957 0.043178 0.198193 0.515501 0.437964 \n",
"0 Self_GlobalAvg 0.067695 0.027470 0.171187 0.509546 0.384942 \n",
"0 Ready_Random 0.054383 0.021119 0.133978 0.507680 0.339343 \n",
"0 Self_BaselineUI 0.000752 0.000168 0.001677 0.496424 0.009544 \n",
"\n",
" Reco in test Test coverage Shannon Gini \n",
"0 1.000000 0.275613 5.085818 0.913665 \n",
"0 1.000000 0.351371 5.366291 0.885046 \n",
"0 1.000000 0.077201 3.875892 0.974947 \n",
"0 1.000000 0.502886 5.722957 0.827507 \n",
"0 1.000000 0.038961 3.159079 0.987317 \n",
"0 0.974973 0.264791 4.909893 0.926201 \n",
"0 1.000000 0.033911 2.836513 0.991139 \n",
"0 1.000000 0.025974 2.711772 0.992003 \n",
"0 0.986957 0.177489 5.088670 0.907676 \n",
"0 0.600530 0.005051 1.803126 0.996380 "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import evaluation_measures as ev\n",
"\n",
"dir_path=\"Recommendations generated/ml-100k/\"\n",
"super_reactions=[4,5]\n",
"test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None)\n",
"\n",
"df=ev.evaluate_all(test, dir_path, super_reactions)\n",
"display(df.iloc[:,:9])\n",
"display(df.iloc[:,np.append(0,np.arange(9, df.shape[1]))])"
]
},
{
"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": "3.6.9"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Reference in New Issue Copy Permalink