s421818/warsztaty2
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
master
warsztaty2/P6. LightFM.ipynb
unknown 7b24851640 done
2020-06-16 19:40:37 +02:00

2050 lines
78 KiB
Plaintext
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"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.int64'>'\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": 4,
"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": 4,
"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": 5,
"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": 5,
"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": 6,
"metadata": {},
"outputs": [],
"source": [
"item_genres=movies[np.arange(5,24)]\n",
"item_genres.columns=list(genres[0])"
]
},
{
"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>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": 7,
"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": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<1682x1941 sparse matrix of type '<class 'numpy.intc'>'\n",
"\twith 6256 stored elements in Compressed Sparse Row format>"
]
},
"execution_count": 8,
"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": 9,
"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": 9,
"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": 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",
" </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": 10,
"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": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<943x1682 sparse matrix of type '<class 'numpy.int64'>'\n",
"\twith 80000 stored elements in Compressed Sparse Row format>"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_ui"
]
},
{
"cell_type": "code",
"execution_count": 12,
"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": 12,
"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": 13,
"metadata": {},
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'lightfm'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-13-0553216e5cba>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mlightfm\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mLightFM\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mlightfm\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mevaluation\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mprecision_at_k\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mloss\u001b[0m \u001b[1;32min\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;34m'logistic'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'bpr'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'warp'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'lightfm'"
]
}
],
"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": null,
"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": 14,
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'top_k_recommendations' is not defined",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-14-0200403237fb>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mtop_n\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtop_k_recommendations\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_features\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_features\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtopK\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[0mtop_n\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Recommendations generated/ml-100k/Ready_LightFM_reco.csv'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheader\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mestimations\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mestimate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_features\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_features\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtest_ui\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtest_ui\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mestimations\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Recommendations generated/ml-100k/Ready_LightFM_estimations.csv'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheader\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mNameError\u001b[0m: name 'top_k_recommendations' is not defined"
]
}
],
"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": 15,
"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": 16,
"metadata": {},
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'lightfm'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-16-f3f6cc4b505c>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mlightfm\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mLightFM\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0mmodel\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mLightFM\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mloss\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'warp'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mmodel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtrain_ui\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_features_interactions\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_features_interactions\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m30\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnum_threads\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m4\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'lightfm'"
]
}
],
"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": 17,
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'top_k_recommendations' is not defined",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-17-b2fe5e332ba4>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mtop_n\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtop_k_recommendations\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_features_interactions\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_features_interactions\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtopK\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[0mtop_n\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Recommendations generated/ml-100k/Ready_LightFMpureMF_reco.csv'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheader\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mestimations\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mestimate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_features_interactions\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_features_interactions\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtest_ui\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtest_ui\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mestimations\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Recommendations generated/ml-100k/Ready_LightFMpureMF_estimations.csv'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheader\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mNameError\u001b[0m: name 'top_k_recommendations' is not defined"
]
}
],
"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": 18,
"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": 22,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\users\\adrian\\appdata\\local\\programs\\python\\python38-32\\lib\\site-packages\\lightfm\\_lightfm_fast.py:9: UserWarning: LightFM was compiled without OpenMP support. Only a single thread will be used.\n",
" warnings.warn('LightFM was compiled without OpenMP support. '\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train precision: 0.39\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": 24,
"metadata": {},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'top_k_recommendations' is not defined",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-24-1b36371fa675>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mtop_n\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtop_k_recommendations\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_features_only\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_features_only\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtopK\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m10\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[0mtop_n\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Recommendations generated/ml-100k/Ready_LightFMcontent_reco.csv'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheader\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mestimations\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mestimate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_features_only\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_features\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_features_only\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0muser_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0muser_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mitem_code_id\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitem_code_id\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtest_ui\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtest_ui\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mestimations\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto_csv\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Recommendations generated/ml-100k/Ready_LightFMcontent_estimations.csv'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheader\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mNameError\u001b[0m: name 'top_k_recommendations' is not defined"
]
}
],
"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": 21,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 10622.43it/s]\n",
"943it [00:00, 9747.58it/s]\n",
"943it [00:00, 10554.65it/s]\n",
"943it [00:00, 9450.92it/s]\n",
"943it [00:00, 10058.79it/s]\n",
"943it [00:00, 10744.58it/s]\n",
"943it [00:00, 10390.37it/s]\n",
"943it [00:00, 10578.65it/s]\n",
"943it [00:00, 11388.05it/s]\n",
"943it [00:00, 11256.24it/s]\n",
"943it [00:00, 10166.93it/s]\n",
"943it [00:00, 10388.40it/s]\n",
"943it [00:00, 10058.69it/s]\n",
"943it [00:00, 10740.81it/s]\n",
"943it [00:00, 9636.75it/s]\n",
"943it [00:00, 10511.93it/s]\n",
"943it [00:00, 10864.37it/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>Self_RP3Beta</td>\n",
" <td>3.704589</td>\n",
" <td>3.529397</td>\n",
" <td>0.286744</td>\n",
" <td>0.196524</td>\n",
" <td>0.191117</td>\n",
" <td>0.221375</td>\n",
" <td>0.213948</td>\n",
" <td>0.251263</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>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_SVD</td>\n",
" <td>0.949165</td>\n",
" <td>0.746667</td>\n",
" <td>0.093955</td>\n",
" <td>0.044969</td>\n",
" <td>0.051197</td>\n",
" <td>0.065474</td>\n",
" <td>0.083906</td>\n",
" <td>0.073996</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_SVD</td>\n",
" <td>0.916330</td>\n",
" <td>0.720153</td>\n",
" <td>0.103393</td>\n",
" <td>0.044455</td>\n",
" <td>0.053177</td>\n",
" <td>0.070073</td>\n",
" <td>0.093884</td>\n",
" <td>0.079366</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>Ready_SVDBiased</td>\n",
" <td>0.938146</td>\n",
" <td>0.739917</td>\n",
" <td>0.086532</td>\n",
" <td>0.037067</td>\n",
" <td>0.044832</td>\n",
" <td>0.058877</td>\n",
" <td>0.078004</td>\n",
" <td>0.057865</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>1.510030</td>\n",
" <td>1.211848</td>\n",
" <td>0.050053</td>\n",
" <td>0.022367</td>\n",
" <td>0.025984</td>\n",
" <td>0.033727</td>\n",
" <td>0.030687</td>\n",
" <td>0.023255</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNN</td>\n",
" <td>1.030386</td>\n",
" <td>0.813067</td>\n",
" <td>0.026087</td>\n",
" <td>0.006908</td>\n",
" <td>0.010593</td>\n",
" <td>0.016046</td>\n",
" <td>0.021137</td>\n",
" <td>0.009522</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNNWithZScore</td>\n",
" <td>0.957701</td>\n",
" <td>0.752387</td>\n",
" <td>0.003712</td>\n",
" <td>0.001994</td>\n",
" <td>0.002380</td>\n",
" <td>0.002919</td>\n",
" <td>0.003433</td>\n",
" <td>0.002401</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNNBaseline</td>\n",
" <td>0.935327</td>\n",
" <td>0.737424</td>\n",
" <td>0.002545</td>\n",
" <td>0.000755</td>\n",
" <td>0.001105</td>\n",
" <td>0.001602</td>\n",
" <td>0.002253</td>\n",
" <td>0.000930</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNNWithMeans</td>\n",
" <td>0.935327</td>\n",
" <td>0.737424</td>\n",
" <td>0.002545</td>\n",
" <td>0.000755</td>\n",
" <td>0.001105</td>\n",
" <td>0.001602</td>\n",
" <td>0.002253</td>\n",
" <td>0.000930</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_U-KNN</td>\n",
" <td>1.023495</td>\n",
" <td>0.807913</td>\n",
" <td>0.000742</td>\n",
" <td>0.000205</td>\n",
" <td>0.000305</td>\n",
" <td>0.000449</td>\n",
" <td>0.000536</td>\n",
" <td>0.000198</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_TopRated</td>\n",
" <td>2.508258</td>\n",
" <td>2.217909</td>\n",
" <td>0.000954</td>\n",
" <td>0.000188</td>\n",
" <td>0.000298</td>\n",
" <td>0.000481</td>\n",
" <td>0.000644</td>\n",
" <td>0.000223</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",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_IKNN</td>\n",
" <td>1.018363</td>\n",
" <td>0.808793</td>\n",
" <td>0.000318</td>\n",
" <td>0.000108</td>\n",
" <td>0.000140</td>\n",
" <td>0.000189</td>\n",
" <td>0.000000</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model RMSE MAE precision recall F_1 \\\n",
"0 Self_RP3Beta 3.704589 3.529397 0.286744 0.196524 0.191117 \n",
"0 Self_P3 3.702446 3.527273 0.282185 0.192092 0.186749 \n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n",
"0 Ready_SVD 0.949165 0.746667 0.093955 0.044969 0.051197 \n",
"0 Self_SVD 0.916330 0.720153 0.103393 0.044455 0.053177 \n",
"0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n",
"0 Ready_SVDBiased 0.938146 0.739917 0.086532 0.037067 0.044832 \n",
"0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
"0 Ready_Random 1.510030 1.211848 0.050053 0.022367 0.025984 \n",
"0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 \n",
"0 Ready_I-KNNWithZScore 0.957701 0.752387 0.003712 0.001994 0.002380 \n",
"0 Ready_I-KNNBaseline 0.935327 0.737424 0.002545 0.000755 0.001105 \n",
"0 Ready_I-KNNWithMeans 0.935327 0.737424 0.002545 0.000755 0.001105 \n",
"0 Ready_U-KNN 1.023495 0.807913 0.000742 0.000205 0.000305 \n",
"0 Self_TopRated 2.508258 2.217909 0.000954 0.000188 0.000298 \n",
"0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 \n",
"0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 \n",
"\n",
" F_05 precision_super recall_super \n",
"0 0.221375 0.213948 0.251263 \n",
"0 0.216980 0.204185 0.240096 \n",
"0 0.141584 0.130472 0.137473 \n",
"0 0.065474 0.083906 0.073996 \n",
"0 0.070073 0.093884 0.079366 \n",
"0 0.061286 0.079614 0.056463 \n",
"0 0.058877 0.078004 0.057865 \n",
"0 0.041343 0.040558 0.032107 \n",
"0 0.033727 0.030687 0.023255 \n",
"0 0.016046 0.021137 0.009522 \n",
"0 0.002919 0.003433 0.002401 \n",
"0 0.001602 0.002253 0.000930 \n",
"0 0.001602 0.002253 0.000930 \n",
"0 0.000449 0.000536 0.000198 \n",
"0 0.000481 0.000644 0.000223 \n",
"0 0.000463 0.000644 0.000189 \n",
"0 0.000189 0.000000 0.000000 "
]
},
"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>Self_RP3Beta</td>\n",
" <td>0.344598</td>\n",
" <td>0.207836</td>\n",
" <td>0.587953</td>\n",
" <td>0.595770</td>\n",
" <td>0.885472</td>\n",
" <td>0.998197</td>\n",
" <td>0.193362</td>\n",
" <td>4.291821</td>\n",
" <td>0.960775</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>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_SVD</td>\n",
" <td>0.104672</td>\n",
" <td>0.048211</td>\n",
" <td>0.220757</td>\n",
" <td>0.519187</td>\n",
" <td>0.483563</td>\n",
" <td>0.997985</td>\n",
" <td>0.204906</td>\n",
" <td>4.408913</td>\n",
" <td>0.954288</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_SVD</td>\n",
" <td>0.107792</td>\n",
" <td>0.051281</td>\n",
" <td>0.200210</td>\n",
" <td>0.518957</td>\n",
" <td>0.475080</td>\n",
" <td>0.853022</td>\n",
" <td>0.147186</td>\n",
" <td>3.911356</td>\n",
" <td>0.971196</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>Ready_SVDBiased</td>\n",
" <td>0.094583</td>\n",
" <td>0.043013</td>\n",
" <td>0.202391</td>\n",
" <td>0.515202</td>\n",
" <td>0.433722</td>\n",
" <td>0.996076</td>\n",
" <td>0.166667</td>\n",
" <td>4.168354</td>\n",
" <td>0.964092</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>0.055392</td>\n",
" <td>0.021602</td>\n",
" <td>0.137690</td>\n",
" <td>0.507713</td>\n",
" <td>0.338282</td>\n",
" <td>0.987911</td>\n",
" <td>0.187590</td>\n",
" <td>5.111878</td>\n",
" <td>0.906685</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNN</td>\n",
" <td>0.024214</td>\n",
" <td>0.008958</td>\n",
" <td>0.048068</td>\n",
" <td>0.499885</td>\n",
" <td>0.154825</td>\n",
" <td>0.402333</td>\n",
" <td>0.434343</td>\n",
" <td>5.133650</td>\n",
" <td>0.877999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNNWithZScore</td>\n",
" <td>0.005137</td>\n",
" <td>0.002158</td>\n",
" <td>0.016458</td>\n",
" <td>0.497349</td>\n",
" <td>0.027572</td>\n",
" <td>0.389926</td>\n",
" <td>0.067821</td>\n",
" <td>2.475747</td>\n",
" <td>0.992793</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNNBaseline</td>\n",
" <td>0.003444</td>\n",
" <td>0.001362</td>\n",
" <td>0.011760</td>\n",
" <td>0.496724</td>\n",
" <td>0.021209</td>\n",
" <td>0.482821</td>\n",
" <td>0.059885</td>\n",
" <td>2.232578</td>\n",
" <td>0.994487</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_I-KNNWithMeans</td>\n",
" <td>0.003444</td>\n",
" <td>0.001362</td>\n",
" <td>0.011760</td>\n",
" <td>0.496724</td>\n",
" <td>0.021209</td>\n",
" <td>0.482821</td>\n",
" <td>0.059885</td>\n",
" <td>2.232578</td>\n",
" <td>0.994487</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_U-KNN</td>\n",
" <td>0.000845</td>\n",
" <td>0.000274</td>\n",
" <td>0.002744</td>\n",
" <td>0.496441</td>\n",
" <td>0.007423</td>\n",
" <td>0.602121</td>\n",
" <td>0.010823</td>\n",
" <td>2.089186</td>\n",
" <td>0.995706</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_TopRated</td>\n",
" <td>0.001043</td>\n",
" <td>0.000335</td>\n",
" <td>0.003348</td>\n",
" <td>0.496433</td>\n",
" <td>0.009544</td>\n",
" <td>0.699046</td>\n",
" <td>0.005051</td>\n",
" <td>1.945910</td>\n",
" <td>0.995669</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",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_IKNN</td>\n",
" <td>0.000214</td>\n",
" <td>0.000037</td>\n",
" <td>0.000368</td>\n",
" <td>0.496391</td>\n",
" <td>0.003181</td>\n",
" <td>0.392153</td>\n",
" <td>0.115440</td>\n",
" <td>4.174741</td>\n",
" <td>0.965327</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model NDCG mAP MRR LAUC HR \\\n",
"0 Self_RP3Beta 0.344598 0.207836 0.587953 0.595770 0.885472 \n",
"0 Self_P3 0.339114 0.204905 0.572157 0.593544 0.875928 \n",
"0 Self_TopPop 0.214651 0.111707 0.400939 0.555546 0.765642 \n",
"0 Ready_SVD 0.104672 0.048211 0.220757 0.519187 0.483563 \n",
"0 Self_SVD 0.107792 0.051281 0.200210 0.518957 0.475080 \n",
"0 Ready_Baseline 0.095957 0.043178 0.198193 0.515501 0.437964 \n",
"0 Ready_SVDBiased 0.094583 0.043013 0.202391 0.515202 0.433722 \n",
"0 Self_GlobalAvg 0.067695 0.027470 0.171187 0.509546 0.384942 \n",
"0 Ready_Random 0.055392 0.021602 0.137690 0.507713 0.338282 \n",
"0 Ready_I-KNN 0.024214 0.008958 0.048068 0.499885 0.154825 \n",
"0 Ready_I-KNNWithZScore 0.005137 0.002158 0.016458 0.497349 0.027572 \n",
"0 Ready_I-KNNBaseline 0.003444 0.001362 0.011760 0.496724 0.021209 \n",
"0 Ready_I-KNNWithMeans 0.003444 0.001362 0.011760 0.496724 0.021209 \n",
"0 Ready_U-KNN 0.000845 0.000274 0.002744 0.496441 0.007423 \n",
"0 Self_TopRated 0.001043 0.000335 0.003348 0.496433 0.009544 \n",
"0 Self_BaselineUI 0.000752 0.000168 0.001677 0.496424 0.009544 \n",
"0 Self_IKNN 0.000214 0.000037 0.000368 0.496391 0.003181 \n",
"\n",
" Reco in test Test coverage Shannon Gini \n",
"0 0.998197 0.193362 4.291821 0.960775 \n",
"0 1.000000 0.077201 3.875892 0.974947 \n",
"0 1.000000 0.038961 3.159079 0.987317 \n",
"0 0.997985 0.204906 4.408913 0.954288 \n",
"0 0.853022 0.147186 3.911356 0.971196 \n",
"0 1.000000 0.033911 2.836513 0.991139 \n",
"0 0.996076 0.166667 4.168354 0.964092 \n",
"0 1.000000 0.025974 2.711772 0.992003 \n",
"0 0.987911 0.187590 5.111878 0.906685 \n",
"0 0.402333 0.434343 5.133650 0.877999 \n",
"0 0.389926 0.067821 2.475747 0.992793 \n",
"0 0.482821 0.059885 2.232578 0.994487 \n",
"0 0.482821 0.059885 2.232578 0.994487 \n",
"0 0.602121 0.010823 2.089186 0.995706 \n",
"0 0.699046 0.005051 1.945910 0.995669 \n",
"0 0.600530 0.005051 1.803126 0.996380 \n",
"0 0.392153 0.115440 4.174741 0.965327 "
]
},
"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": []
},
{
"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": "3.8.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Reference in New Issue View Git Blame Copy Permalink