s406917/workshops_recommender_systems
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
45e88a01aa
workshops_recommender_systems/P4. Matrix Factorization.ipynb

1392 lines
72 KiB
Plaintext
Raw Normal View History

Codes added
2020-05-21 13:42:50 +02:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Self made SVD"
]
},
{
"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",
"\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",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 2,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [],
"source": [
"# Done similarly to https://github.com/albertauyeung/matrix-factorization-in-python\n",
"from tqdm import tqdm\n",
"\n",
"class SVD():\n",
" \n",
" def __init__(self, train_ui, learning_rate, regularization, nb_factors, iterations):\n",
" self.train_ui=train_ui\n",
" self.uir=list(zip(*[train_ui.nonzero()[0],train_ui.nonzero()[1], train_ui.data]))\n",
" \n",
" self.learning_rate=learning_rate\n",
" self.regularization=regularization\n",
" self.iterations=iterations\n",
" self.nb_users, self.nb_items=train_ui.shape\n",
" self.nb_ratings=train_ui.nnz\n",
" self.nb_factors=nb_factors\n",
" \n",
" self.Pu=np.random.normal(loc=0, scale=1./self.nb_factors, size=(self.nb_users, self.nb_factors))\n",
" self.Qi=np.random.normal(loc=0, scale=1./self.nb_factors, size=(self.nb_items, self.nb_factors))\n",
"\n",
" def train(self, test_ui=None):\n",
" if test_ui!=None:\n",
" self.test_uir=list(zip(*[test_ui.nonzero()[0],test_ui.nonzero()[1], test_ui.data]))\n",
" \n",
" self.learning_process=[]\n",
" pbar = tqdm(range(self.iterations))\n",
" for i in pbar:\n",
" pbar.set_description(f'Epoch {i} RMSE: {self.learning_process[-1][1] if i>0 else 0}. Training epoch {i+1}...')\n",
" np.random.shuffle(self.uir)\n",
" self.sgd(self.uir)\n",
" if test_ui==None:\n",
" self.learning_process.append([i+1, self.RMSE_total(self.uir)])\n",
" else:\n",
" self.learning_process.append([i+1, self.RMSE_total(self.uir), self.RMSE_total(self.test_uir)])\n",
" \n",
" def sgd(self, uir):\n",
" \n",
" for u, i, score in uir:\n",
" # Computer prediction and error\n",
" prediction = self.get_rating(u,i)\n",
" e = (score - prediction)\n",
" \n",
" # Update user and item latent feature matrices\n",
" Pu_update=self.learning_rate * (e * self.Qi[i] - self.regularization * self.Pu[u])\n",
" Qi_update=self.learning_rate * (e * self.Pu[u] - self.regularization * self.Qi[i])\n",
" \n",
" self.Pu[u] += Pu_update\n",
" self.Qi[i] += Qi_update\n",
" \n",
" def get_rating(self, u, i):\n",
" prediction = self.Pu[u].dot(self.Qi[i].T)\n",
" return prediction\n",
" \n",
" def RMSE_total(self, uir):\n",
" RMSE=0\n",
" for u,i, score in uir:\n",
" prediction = self.get_rating(u,i)\n",
" RMSE+=(score - prediction)**2\n",
" return np.sqrt(RMSE/len(uir))\n",
" \n",
" def estimations(self):\n",
" self.estimations=\\\n",
" np.dot(self.Pu,self.Qi.T)\n",
"\n",
" def recommend(self, user_code_id, item_code_id, topK=10):\n",
" \n",
" top_k = defaultdict(list)\n",
" for nb_user, user in enumerate(self.estimations):\n",
" \n",
" user_rated=self.train_ui.indices[self.train_ui.indptr[nb_user]:self.train_ui.indptr[nb_user+1]]\n",
" for item, score in enumerate(user):\n",
" if item not in user_rated and not np.isnan(score):\n",
" top_k[user_code_id[nb_user]].append((item_code_id[item], score))\n",
" result=[]\n",
" # Let's choose k best items in the format: (user, item1, score1, item2, score2, ...)\n",
" for uid, item_scores in top_k.items():\n",
" item_scores.sort(key=lambda x: x[1], reverse=True)\n",
" result.append([uid]+list(chain(*item_scores[:topK])))\n",
" return result\n",
" \n",
" def estimate(self, 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",
" self.estimations[user,item] if not np.isnan(self.estimations[user,item]) else 1])\n",
" return result"
]
},
{
"cell_type": "code",
Slides added
2020-05-21 16:20:12 +02:00
"execution_count": 3,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Changes in slides
2020-05-21 22:53:34 +02:00
"Epoch 39 RMSE: 0.7476169311403564. Training epoch 40...: 100%|██████████| 40/40 [01:47<00:00, 2.68s/it]\n"
Codes added
2020-05-21 13:42:50 +02:00
]
}
],
"source": [
"model=SVD(train_ui, learning_rate=0.005, regularization=0.02, nb_factors=100, iterations=40)\n",
"model.train(test_ui)"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 4,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
Changes in slides
2020-05-21 22:53:34 +02:00
"<matplotlib.legend.Legend at 0x7f963dab39b0>"
Codes added
2020-05-21 13:42:50 +02:00
]
},
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 4,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
Changes in slides
2020-05-21 22:53:34 +02:00
"image/png": "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
Codes added
2020-05-21 13:42:50 +02:00
"text/plain": [
Changes in slides
2020-05-21 22:53:34 +02:00
"<Figure size 432x288 with 1 Axes>"
Codes added
2020-05-21 13:42:50 +02:00
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"df=pd.DataFrame(model.learning_process).iloc[:,:2]\n",
"df.columns=['epoch', 'train_RMSE']\n",
"plt.plot('epoch', 'train_RMSE', data=df, color='blue')\n",
"plt.legend()"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 5,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
Changes in slides
2020-05-21 22:53:34 +02:00
"<matplotlib.legend.Legend at 0x7f963ce5ddd8>"
Codes added
2020-05-21 13:42:50 +02:00
]
},
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 5,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
Changes in slides
2020-05-21 22:53:34 +02:00
"image/png": "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
Codes added
2020-05-21 13:42:50 +02:00
"text/plain": [
Changes in slides
2020-05-21 22:53:34 +02:00
"<Figure size 432x288 with 1 Axes>"
Codes added
2020-05-21 13:42:50 +02:00
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"df=pd.DataFrame(model.learning_process[10:], columns=['epoch', 'train_RMSE', 'test_RMSE'])\n",
"plt.plot('epoch', 'train_RMSE', data=df, color='blue')\n",
"plt.plot('epoch', 'test_RMSE', data=df, color='yellow', linestyle='dashed')\n",
"plt.legend()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Saving and evaluating recommendations"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 6,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [],
"source": [
"model.estimations()\n",
"\n",
"top_n=pd.DataFrame(model.recommend(user_code_id, item_code_id, topK=10))\n",
"\n",
"top_n.to_csv('Recommendations generated/ml-100k/Self_SVD_reco.csv', index=False, header=False)\n",
"\n",
"estimations=pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))\n",
"estimations.to_csv('Recommendations generated/ml-100k/Self_SVD_estimations.csv', index=False, header=False)"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 7,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Changes in slides
2020-05-21 22:53:34 +02:00
"943it [00:00, 5237.55it/s]\n"
Codes added
2020-05-21 13:42:50 +02:00
]
},
{
"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>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",
" <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",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>0.913861</td>\n",
" <td>0.717063</td>\n",
" <td>0.10403</td>\n",
" <td>0.044109</td>\n",
" <td>0.053339</td>\n",
" <td>0.07051</td>\n",
" <td>0.094313</td>\n",
" <td>0.075814</td>\n",
" <td>0.107692</td>\n",
" <td>0.051047</td>\n",
" <td>0.201273</td>\n",
" <td>0.518782</td>\n",
" <td>0.481442</td>\n",
" <td>0.87211</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>0.146465</td>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>3.881417</td>\n",
" <td>0.972029</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
Changes in slides
2020-05-21 22:53:34 +02:00
" RMSE MAE precision recall F_1 F_05 \\\n",
"0 0.913861 0.717063 0.10403 0.044109 0.053339 0.07051 \n",
Codes added
2020-05-21 13:42:50 +02:00
"\n",
Slides added
2020-05-21 16:20:12 +02:00
" precision_super recall_super NDCG mAP MRR LAUC \\\n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.094313 0.075814 0.107692 0.051047 0.201273 0.518782 \n",
Codes added
2020-05-21 13:42:50 +02:00
"\n",
Slides added
2020-05-21 16:20:12 +02:00
" HR Reco in test Test coverage Shannon Gini \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.481442 0.87211 0.146465 3.881417 0.972029 "
Codes added
2020-05-21 13:42:50 +02:00
]
},
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 7,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import evaluation_measures as ev\n",
"\n",
"estimations_df=pd.read_csv('Recommendations generated/ml-100k/Self_SVD_estimations.csv', header=None)\n",
"reco=np.loadtxt('Recommendations generated/ml-100k/Self_SVD_reco.csv', delimiter=',')\n",
"\n",
"ev.evaluate(test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None),\n",
" estimations_df=estimations_df, \n",
" reco=reco,\n",
" super_reactions=[4,5])"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 8,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Changes in slides
2020-05-21 22:53:34 +02:00
"943it [00:00, 6996.89it/s]\n",
"943it [00:00, 5574.45it/s]\n",
"943it [00:00, 5909.51it/s]\n",
"943it [00:00, 6568.51it/s]\n",
"943it [00:00, 5488.25it/s]\n",
"943it [00:00, 5363.29it/s]\n",
"943it [00:00, 6280.36it/s]\n",
"943it [00:00, 5709.71it/s]\n",
"943it [00:00, 6279.20it/s]\n",
"943it [00:00, 5819.38it/s]\n"
Codes added
2020-05-21 13:42:50 +02:00
]
},
{
"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",
" <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_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",
" <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>Self_SVD</td>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>0.913861</td>\n",
" <td>0.717063</td>\n",
" <td>0.104030</td>\n",
" <td>0.044109</td>\n",
" <td>0.053339</td>\n",
" <td>0.070510</td>\n",
" <td>0.094313</td>\n",
" <td>0.075814</td>\n",
" <td>0.107692</td>\n",
" <td>0.051047</td>\n",
" <td>0.201273</td>\n",
" <td>0.518782</td>\n",
" <td>0.481442</td>\n",
" <td>0.872110</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>0.146465</td>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>3.881417</td>\n",
" <td>0.972029</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </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",
" <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>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",
" <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",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1.517787</td>\n",
" <td>1.217953</td>\n",
" <td>0.047826</td>\n",
" <td>0.017861</td>\n",
" <td>0.022711</td>\n",
" <td>0.031080</td>\n",
" <td>0.028219</td>\n",
" <td>0.016982</td>\n",
" <td>0.051154</td>\n",
" <td>0.019551</td>\n",
" <td>0.125693</td>\n",
" <td>0.505448</td>\n",
" <td>0.318134</td>\n",
" <td>0.986426</td>\n",
" <td>0.186869</td>\n",
" <td>5.091730</td>\n",
" <td>0.908288</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </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",
" <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-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",
" <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>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",
" <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_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",
" <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>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",
" <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 RMSE MAE precision recall F_1 \\\n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 Self_SVD 0.913861 0.717063 0.104030 0.044109 0.053339 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n",
"0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 Ready_Random 1.517787 1.217953 0.047826 0.017861 0.022711 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 \n",
"0 Ready_I-KNNBaseline 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_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 NDCG mAP MRR \\\n",
"0 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.070510 0.094313 0.075814 0.107692 0.051047 0.201273 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n",
"0 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.031080 0.028219 0.016982 0.051154 0.019551 0.125693 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.016046 0.021137 0.009522 0.024214 0.008958 0.048068 \n",
"0 0.001602 0.002253 0.000930 0.003444 0.001362 0.011760 \n",
"0 0.000449 0.000536 0.000198 0.000845 0.000274 0.002744 \n",
"0 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 \n",
"0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n",
"\n",
" LAUC HR Reco in test Test coverage Shannon Gini \n",
"0 0.555546 0.765642 1.000000 0.038961 3.159079 0.987317 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.518782 0.481442 0.872110 0.146465 3.881417 0.972029 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.515501 0.437964 1.000000 0.033911 2.836513 0.991139 \n",
"0 0.509546 0.384942 1.000000 0.025974 2.711772 0.992003 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.505448 0.318134 0.986426 0.186869 5.091730 0.908288 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.499885 0.154825 0.402333 0.434343 5.133650 0.877999 \n",
"0 0.496724 0.021209 0.482821 0.059885 2.232578 0.994487 \n",
"0 0.496441 0.007423 0.602121 0.010823 2.089186 0.995706 \n",
"0 0.496424 0.009544 0.600530 0.005051 1.803126 0.996380 \n",
"0 0.496391 0.003181 0.392153 0.115440 4.174741 0.965327 "
]
},
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 8,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import imp\n",
"imp.reload(ev)\n",
"\n",
"import evaluation_measures as ev\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",
"ev.evaluate_all(test, dir_path, super_reactions)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Embeddings"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 9,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[1, 2],\n",
" [3, 4]])"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"array([[0.4472136 , 0.89442719],\n",
" [0.6 , 0.8 ]])"
]
},
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 9,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"x=np.array([[1,2],[3,4]])\n",
"display(x)\n",
"x/np.linalg.norm(x, axis=1)[:,None]"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 10,
Codes added
2020-05-21 13:42:50 +02:00
"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>code</th>\n",
" <th>score</th>\n",
" <th>item_id</th>\n",
" <th>id</th>\n",
" <th>title</th>\n",
" <th>genres</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1051</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" <td>1.000000</td>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1052</td>\n",
" <td>1052</td>\n",
" <td>Dracula: Dead and Loving It (1995)</td>\n",
" <td>Comedy, Horror</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1177</td>\n",
" <td>0.951303</td>\n",
" <td>1178</td>\n",
" <td>1178</td>\n",
" <td>Major Payne (1994)</td>\n",
" <td>Comedy</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1290</td>\n",
" <td>0.950489</td>\n",
" <td>1291</td>\n",
" <td>1291</td>\n",
" <td>Celtic Pride (1996)</td>\n",
" <td>Comedy</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1375</td>\n",
" <td>0.949864</td>\n",
" <td>1376</td>\n",
" <td>1376</td>\n",
" <td>Meet Wally Sparks (1997)</td>\n",
" <td>Comedy</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1489</td>\n",
" <td>0.947375</td>\n",
" <td>1490</td>\n",
" <td>1490</td>\n",
" <td>Fausto (1993)</td>\n",
" <td>Comedy</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1495</td>\n",
" <td>0.947368</td>\n",
" <td>1496</td>\n",
" <td>1496</td>\n",
" <td>Carpool (1996)</td>\n",
" <td>Comedy, Crime</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1497</td>\n",
" <td>0.947347</td>\n",
" <td>1498</td>\n",
" <td>1498</td>\n",
" <td>Farmer &amp; Chase (1995)</td>\n",
" <td>Comedy</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1490</td>\n",
" <td>0.946829</td>\n",
" <td>1491</td>\n",
" <td>1491</td>\n",
" <td>Tough and Deadly (1995)</td>\n",
" <td>Action, Drama, Thriller</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1320</td>\n",
" <td>0.946152</td>\n",
" <td>1321</td>\n",
" <td>1321</td>\n",
" <td>Open Season (1996)</td>\n",
" <td>Comedy</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1487</td>\n",
" <td>0.945425</td>\n",
" <td>1488</td>\n",
" <td>1488</td>\n",
" <td>Germinal (1993)</td>\n",
" <td>Drama</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
Changes in slides
2020-05-21 22:53:34 +02:00
" code score item_id id title \\\n",
"0 1051 1.000000 1052 1052 Dracula: Dead and Loving It (1995) \n",
"1 1177 0.951303 1178 1178 Major Payne (1994) \n",
"2 1290 0.950489 1291 1291 Celtic Pride (1996) \n",
"3 1375 0.949864 1376 1376 Meet Wally Sparks (1997) \n",
"4 1489 0.947375 1490 1490 Fausto (1993) \n",
"5 1495 0.947368 1496 1496 Carpool (1996) \n",
"6 1497 0.947347 1498 1498 Farmer & Chase (1995) \n",
"7 1490 0.946829 1491 1491 Tough and Deadly (1995) \n",
"8 1320 0.946152 1321 1321 Open Season (1996) \n",
"9 1487 0.945425 1488 1488 Germinal (1993) \n",
Codes added
2020-05-21 13:42:50 +02:00
"\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" genres \n",
"0 Comedy, Horror \n",
"1 Comedy \n",
"2 Comedy \n",
"3 Comedy \n",
"4 Comedy \n",
"5 Comedy, Crime \n",
"6 Comedy \n",
"7 Action, Drama, Thriller \n",
"8 Comedy \n",
"9 Drama "
Codes added
2020-05-21 13:42:50 +02:00
]
},
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 10,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"item=random.choice(list(set(train_ui.indices)))\n",
"\n",
"embeddings_norm=model.Qi/np.linalg.norm(model.Qi, axis=1)[:,None] # we do not mean-center here\n",
"# omitting normalization also makes sense, but items with a greater magnitude will be recommended more often\n",
"\n",
"similarity_scores=np.dot(embeddings_norm,embeddings_norm[item].T)\n",
"top_similar_items=pd.DataFrame(enumerate(similarity_scores), columns=['code', 'score'])\\\n",
".sort_values(by=['score'], ascending=[False])[:10]\n",
"\n",
"top_similar_items['item_id']=top_similar_items['code'].apply(lambda x: item_code_id[x])\n",
"\n",
"items=pd.read_csv('./Datasets/ml-100k/movies.csv')\n",
"\n",
"result=pd.merge(top_similar_items, items, left_on='item_id', right_on='id')\n",
"\n",
"result"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# project task 5: implement SVD on top baseline (as it is in Surprise library)"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 11,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [],
"source": [
"# making changes to our implementation by considering additional parameters in the gradient descent procedure \n",
"# seems to be the fastest option\n",
"# please save the output in 'Recommendations generated/ml-100k/Self_SVDBaseline_reco.csv' and\n",
"# 'Recommendations generated/ml-100k/Self_SVDBaseline_estimations.csv'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Ready-made SVD - Surprise implementation"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### SVD"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 12,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Generating predictions...\n",
"Generating top N recommendations...\n",
"Generating predictions...\n"
]
}
],
"source": [
"import helpers\n",
"import surprise as sp\n",
"import imp\n",
"imp.reload(helpers)\n",
"\n",
"algo = sp.SVD(biased=False) # to use unbiased version\n",
"\n",
"helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_SVD_reco.csv',\n",
" estimations_path='Recommendations generated/ml-100k/Ready_SVD_estimations.csv')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### SVD biased - on top baseline"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 13,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Generating predictions...\n",
"Generating top N recommendations...\n",
"Generating predictions...\n"
]
}
],
"source": [
"import helpers\n",
"import surprise as sp\n",
"import imp\n",
"imp.reload(helpers)\n",
"\n",
"algo = sp.SVD() # default is biased=True\n",
"\n",
"helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_SVDBiased_reco.csv',\n",
" estimations_path='Recommendations generated/ml-100k/Ready_SVDBiased_estimations.csv')"
]
},
{
"cell_type": "code",
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 14,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Changes in slides
2020-05-21 22:53:34 +02:00
"943it [00:00, 5528.02it/s]\n",
"943it [00:00, 6531.06it/s]\n",
"943it [00:00, 5593.54it/s]\n",
"943it [00:00, 5845.59it/s]\n",
"943it [00:00, 5997.91it/s]\n",
"943it [00:00, 6080.78it/s]\n",
"943it [00:00, 6121.00it/s]\n",
"943it [00:00, 5934.94it/s]\n",
"943it [00:00, 5026.29it/s]\n",
"943it [00:00, 5850.46it/s]\n",
"943it [00:00, 5530.89it/s]\n",
"943it [00:00, 6004.16it/s]\n"
Codes added
2020-05-21 13:42:50 +02:00
]
},
{
"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",
" <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_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",
" <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",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>0.949892</td>\n",
" <td>0.749292</td>\n",
" <td>0.104666</td>\n",
" <td>0.048611</td>\n",
" <td>0.055656</td>\n",
" <td>0.071900</td>\n",
" <td>0.092811</td>\n",
" <td>0.078241</td>\n",
" <td>0.117730</td>\n",
" <td>0.057464</td>\n",
" <td>0.244097</td>\n",
" <td>0.521054</td>\n",
" <td>0.501591</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>0.998091</td>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>0.217172</td>\n",
" <td>4.458001</td>\n",
" <td>0.951551</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_SVD</td>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>0.913861</td>\n",
" <td>0.717063</td>\n",
" <td>0.104030</td>\n",
" <td>0.044109</td>\n",
" <td>0.053339</td>\n",
" <td>0.070510</td>\n",
" <td>0.094313</td>\n",
" <td>0.075814</td>\n",
" <td>0.107692</td>\n",
" <td>0.051047</td>\n",
" <td>0.201273</td>\n",
" <td>0.518782</td>\n",
" <td>0.481442</td>\n",
" <td>0.872110</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>0.146465</td>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>3.881417</td>\n",
" <td>0.972029</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </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",
" <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",
Slides added
2020-05-21 16:20:12 +02:00
" <td>Ready_SVDBiased</td>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>0.942994</td>\n",
" <td>0.743492</td>\n",
" <td>0.083351</td>\n",
" <td>0.034097</td>\n",
" <td>0.041677</td>\n",
" <td>0.055673</td>\n",
" <td>0.073283</td>\n",
" <td>0.052910</td>\n",
" <td>0.091866</td>\n",
" <td>0.042598</td>\n",
" <td>0.198210</td>\n",
" <td>0.513705</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" <td>0.423118</td>\n",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>0.997561</td>\n",
" <td>0.168831</td>\n",
" <td>4.195234</td>\n",
" <td>0.963319</td>\n",
Slides added
2020-05-21 16:20:12 +02:00
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
Codes added
2020-05-21 13:42:50 +02:00
" <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",
" <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",
Changes in slides
2020-05-21 22:53:34 +02:00
" <td>1.517787</td>\n",
" <td>1.217953</td>\n",
" <td>0.047826</td>\n",
" <td>0.017861</td>\n",
" <td>0.022711</td>\n",
" <td>0.031080</td>\n",
" <td>0.028219</td>\n",
" <td>0.016982</td>\n",
" <td>0.051154</td>\n",
" <td>0.019551</td>\n",
" <td>0.125693</td>\n",
" <td>0.505448</td>\n",
" <td>0.318134</td>\n",
" <td>0.986426</td>\n",
" <td>0.186869</td>\n",
" <td>5.091730</td>\n",
" <td>0.908288</td>\n",
Codes added
2020-05-21 13:42:50 +02:00
" </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",
" <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-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",
" <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>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",
" <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_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",
" <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>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",
" <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 RMSE MAE precision recall F_1 \\\n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 Ready_SVD 0.949892 0.749292 0.104666 0.048611 0.055656 \n",
"0 Self_SVD 0.913861 0.717063 0.104030 0.044109 0.053339 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 Ready_SVDBiased 0.942994 0.743492 0.083351 0.034097 0.041677 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 Ready_Random 1.517787 1.217953 0.047826 0.017861 0.022711 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 \n",
"0 Ready_I-KNNBaseline 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_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 NDCG mAP MRR \\\n",
"0 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.071900 0.092811 0.078241 0.117730 0.057464 0.244097 \n",
"0 0.070510 0.094313 0.075814 0.107692 0.051047 0.201273 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.055673 0.073283 0.052910 0.091866 0.042598 0.198210 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.031080 0.028219 0.016982 0.051154 0.019551 0.125693 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.016046 0.021137 0.009522 0.024214 0.008958 0.048068 \n",
"0 0.001602 0.002253 0.000930 0.003444 0.001362 0.011760 \n",
"0 0.000449 0.000536 0.000198 0.000845 0.000274 0.002744 \n",
"0 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 \n",
"0 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 \n",
"\n",
" LAUC HR Reco in test Test coverage Shannon Gini \n",
"0 0.555546 0.765642 1.000000 0.038961 3.159079 0.987317 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.521054 0.501591 0.998091 0.217172 4.458001 0.951551 \n",
"0 0.518782 0.481442 0.872110 0.146465 3.881417 0.972029 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.515501 0.437964 1.000000 0.033911 2.836513 0.991139 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.513705 0.423118 0.997561 0.168831 4.195234 0.963319 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.509546 0.384942 1.000000 0.025974 2.711772 0.992003 \n",
Changes in slides
2020-05-21 22:53:34 +02:00
"0 0.505448 0.318134 0.986426 0.186869 5.091730 0.908288 \n",
Codes added
2020-05-21 13:42:50 +02:00
"0 0.499885 0.154825 0.402333 0.434343 5.133650 0.877999 \n",
"0 0.496724 0.021209 0.482821 0.059885 2.232578 0.994487 \n",
"0 0.496441 0.007423 0.602121 0.010823 2.089186 0.995706 \n",
"0 0.496424 0.009544 0.600530 0.005051 1.803126 0.996380 \n",
"0 0.496391 0.003181 0.392153 0.115440 4.174741 0.965327 "
]
},
Changes in slides
2020-05-21 22:53:34 +02:00
"execution_count": 14,
Codes added
2020-05-21 13:42:50 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import imp\n",
"imp.reload(ev)\n",
"\n",
"import evaluation_measures as ev\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",
"ev.evaluate_all(test, dir_path, super_reactions)"
]
}
],
"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