s452101/workshops_recommender_systems
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
f8062d7a10
workshops_recommender_systems/P2. Evaluation.ipynb

1775 lines
58 KiB
Plaintext
Raw Normal View History

Project task 1 - self made top rated
2020-09-29 20:23:22 +02:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Prepare test set"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"slideshow": {
"slide_type": "-"
}
},
"outputs": [],
"source": [
"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",
"from tqdm import tqdm\n",
"\n",
"# In evaluation we do not load train set - it is not needed\n",
"test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\\t', header=None)\n",
"test.columns=['user', 'item', 'rating', 'timestamp']\n",
"\n",
"test['user_code'] = test['user'].astype(\"category\").cat.codes\n",
"test['item_code'] = test['item'].astype(\"category\").cat.codes\n",
"\n",
"user_code_id = dict(enumerate(test['user'].astype(\"category\").cat.categories))\n",
"user_id_code = dict((v, k) for k, v in user_code_id.items())\n",
"item_code_id = dict(enumerate(test['item'].astype(\"category\").cat.categories))\n",
"item_id_code = dict((v, k) for k, v in item_code_id.items())\n",
"\n",
"test_ui = sparse.csr_matrix((test['rating'], (test['user_code'], test['item_code'])))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Estimations metrics"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"estimations_df=pd.read_csv('Recommendations generated/ml-100k/Ready_Baseline_estimations.csv', header=None)\n",
"estimations_df.columns=['user', 'item' ,'score']\n",
"\n",
"estimations_df['user_code']=[user_id_code[user] for user in estimations_df['user']]\n",
"estimations_df['item_code']=[item_id_code[item] for item in estimations_df['item']]\n",
"estimations=sparse.csr_matrix((estimations_df['score'], (estimations_df['user_code'], estimations_df['item_code'])), shape=test_ui.shape)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"def estimations_metrics(test_ui, estimations):\n",
" result=[]\n",
"\n",
" RMSE=(np.sum((estimations.data-test_ui.data)**2)/estimations.nnz)**(1/2)\n",
" result.append(['RMSE', RMSE])\n",
"\n",
" MAE=np.sum(abs(estimations.data-test_ui.data))/estimations.nnz\n",
" result.append(['MAE', MAE])\n",
" \n",
" df_result=(pd.DataFrame(list(zip(*result))[1])).T\n",
" df_result.columns=list(zip(*result))[0]\n",
" return df_result"
]
},
{
"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>RMSE</th>\n",
" <th>MAE</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.949459</td>\n",
" <td>0.752487</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" RMSE MAE\n",
"0 0.949459 0.752487"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# in case of error (in the laboratories) you might have to switch to the other version of pandas\n",
"# try !pip3 install pandas=='1.0.3' (or pip if you use python 2) and restart the kernel\n",
"\n",
"estimations_metrics(test_ui, estimations)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Ranking metrics"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([[663, 475, 62, ..., 472, 269, 503],\n",
" [ 48, 313, 475, ..., 591, 175, 466],\n",
" [351, 313, 475, ..., 591, 175, 466],\n",
" ...,\n",
" [259, 313, 475, ..., 11, 591, 175],\n",
" [ 33, 313, 475, ..., 11, 591, 175],\n",
" [ 77, 313, 475, ..., 11, 591, 175]])"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import numpy as np\n",
"reco = np.loadtxt('Recommendations generated/ml-100k/Ready_Baseline_reco.csv', delimiter=',')\n",
"# Let's ignore scores - they are not used in evaluation: \n",
"users=reco[:,:1]\n",
"items=reco[:,1::2]\n",
"# Let's use inner ids instead of real ones\n",
"users=np.vectorize(lambda x: user_id_code.setdefault(x, -1))(users)\n",
"items=np.vectorize(lambda x: item_id_code.setdefault(x, -1))(items) # maybe items we recommend are not in test set\n",
"# Let's put them into one array\n",
"reco=np.concatenate((users, items), axis=1)\n",
"reco"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"def ranking_metrics(test_ui, reco, super_reactions=[], topK=10):\n",
" \n",
" nb_items=test_ui.shape[1]\n",
" relevant_users, super_relevant_users, prec, rec, F_1, F_05, prec_super, rec_super, ndcg, mAP, MRR, LAUC, HR=\\\n",
" 0,0,0,0,0,0,0,0,0,0,0,0,0\n",
" \n",
" cg = (1.0 / np.log2(np.arange(2, topK + 2)))\n",
" cg_sum = np.cumsum(cg)\n",
" \n",
" for (nb_user, user) in tqdm(enumerate(reco[:,0])):\n",
" u_rated_items=test_ui.indices[test_ui.indptr[user]:test_ui.indptr[user+1]]\n",
" nb_u_rated_items=len(u_rated_items)\n",
" if nb_u_rated_items>0: # skip users with no items in test set (still possible that there will be no super items)\n",
" relevant_users+=1\n",
" \n",
" u_super_items=u_rated_items[np.vectorize(lambda x: x in super_reactions)\\\n",
" (test_ui.data[test_ui.indptr[user]:test_ui.indptr[user+1]])]\n",
" # more natural seems u_super_items=[item for item in u_rated_items if test_ui[user,item] in super_reactions]\n",
" # but accesing test_ui[user,item] is expensive -we should avoid doing it\n",
" if len(u_super_items)>0:\n",
" super_relevant_users+=1\n",
" \n",
" user_successes=np.zeros(topK)\n",
" nb_user_successes=0\n",
" user_super_successes=np.zeros(topK)\n",
" nb_user_super_successes=0\n",
" \n",
" # evaluation\n",
" for (item_position,item) in enumerate(reco[nb_user,1:topK+1]):\n",
" if item in u_rated_items:\n",
" user_successes[item_position]=1\n",
" nb_user_successes+=1\n",
" if item in u_super_items:\n",
" user_super_successes[item_position]=1\n",
" nb_user_super_successes+=1\n",
" \n",
" prec_u=nb_user_successes/topK \n",
" prec+=prec_u\n",
" \n",
" rec_u=nb_user_successes/nb_u_rated_items\n",
" rec+=rec_u\n",
" \n",
" F_1+=2*(prec_u*rec_u)/(prec_u+rec_u) if prec_u+rec_u>0 else 0\n",
" F_05+=(0.5**2+1)*(prec_u*rec_u)/(0.5**2*prec_u+rec_u) if prec_u+rec_u>0 else 0\n",
" \n",
" prec_super+=nb_user_super_successes/topK\n",
" rec_super+=nb_user_super_successes/max(len(u_super_items),1) # to set 0 if no super items\n",
" ndcg+=np.dot(user_successes,cg)/cg_sum[min(topK, nb_u_rated_items)-1]\n",
" \n",
" cumsum_successes=np.cumsum(user_successes)\n",
" mAP+=np.dot(cumsum_successes/np.arange(1,topK+1), user_successes)/min(topK, nb_u_rated_items)\n",
" MRR+=1/(user_successes.nonzero()[0][0]+1) if user_successes.nonzero()[0].size>0 else 0\n",
" LAUC+=(np.dot(cumsum_successes, 1-user_successes)+\\\n",
" (nb_user_successes+nb_u_rated_items)/2*((nb_items-nb_u_rated_items)-(topK-nb_user_successes)))/\\\n",
" ((nb_items-nb_u_rated_items)*nb_u_rated_items)\n",
" \n",
" HR+=nb_user_successes>0\n",
" \n",
" \n",
" result=[]\n",
" result.append(('precision', prec/relevant_users))\n",
" result.append(('recall', rec/relevant_users))\n",
" result.append(('F_1', F_1/relevant_users))\n",
" result.append(('F_05', F_05/relevant_users))\n",
" result.append(('precision_super', prec_super/super_relevant_users))\n",
" result.append(('recall_super', rec_super/super_relevant_users))\n",
" result.append(('NDCG', ndcg/relevant_users))\n",
" result.append(('mAP', mAP/relevant_users))\n",
" result.append(('MRR', MRR/relevant_users))\n",
" result.append(('LAUC', LAUC/relevant_users))\n",
" result.append(('HR', HR/relevant_users))\n",
"\n",
" df_result=(pd.DataFrame(list(zip(*result))[1])).T\n",
" df_result.columns=list(zip(*result))[0]\n",
" return df_result"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 6664.49it/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>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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.09141</td>\n",
" <td>0.037652</td>\n",
" <td>0.04603</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",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" precision recall F_1 F_05 precision_super recall_super \\\n",
"0 0.09141 0.037652 0.04603 0.061286 0.079614 0.056463 \n",
"\n",
" NDCG mAP MRR LAUC HR \n",
"0 0.095957 0.043178 0.198193 0.515501 0.437964 "
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"ranking_metrics(test_ui, reco, super_reactions=[4,5], topK=10)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Diversity metrics"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"def diversity_metrics(test_ui, reco, topK=10):\n",
" \n",
" frequencies=defaultdict(int)\n",
" \n",
" # let's assign 0 to all items in test set\n",
" for item in list(set(test_ui.indices)):\n",
" frequencies[item]=0\n",
" \n",
" # counting frequencies\n",
" for item in reco[:,1:].flat:\n",
" frequencies[item]+=1\n",
" \n",
" nb_reco_outside_test=frequencies[-1]\n",
" del frequencies[-1]\n",
" \n",
" frequencies=np.array(list(frequencies.values()))\n",
" \n",
" nb_rec_items=len(frequencies[frequencies>0])\n",
" nb_reco_inside_test=np.sum(frequencies)\n",
" \n",
" frequencies=frequencies/np.sum(frequencies)\n",
" frequencies=np.sort(frequencies)\n",
" \n",
" with np.errstate(divide='ignore'): # let's put zeros put items with 0 frequency and ignore division warning\n",
" log_frequencies=np.nan_to_num(np.log(frequencies), posinf=0, neginf=0)\n",
" \n",
" result=[]\n",
" result.append(('Reco in test', nb_reco_inside_test/(nb_reco_inside_test+nb_reco_outside_test)))\n",
" result.append(('Test coverage', nb_rec_items/test_ui.shape[1]))\n",
" result.append(('Shannon', -np.dot(frequencies, log_frequencies)))\n",
" result.append(('Gini', np.dot(frequencies, np.arange(1-len(frequencies), len(frequencies), 2))/(len(frequencies)-1)))\n",
" \n",
" df_result=(pd.DataFrame(list(zip(*result))[1])).T\n",
" df_result.columns=list(zip(*result))[0]\n",
" return df_result"
]
},
{
"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>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>1.0</td>\n",
" <td>0.033911</td>\n",
" <td>2.836513</td>\n",
" <td>0.991139</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Reco in test Test coverage Shannon Gini\n",
"0 1.0 0.033911 2.836513 0.991139"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# in case of errors try !pip3 install numpy==1.18.4 (or pip if you use python 2) and restart the kernel\n",
"\n",
"import evaluation_measures as ev\n",
"import imp\n",
"imp.reload(ev)\n",
"\n",
"x=diversity_metrics(test_ui, reco, topK=10)\n",
"x"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# To be used in other notebooks"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 7817.92it/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>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>0.949459</td>\n",
" <td>0.752487</td>\n",
" <td>0.09141</td>\n",
" <td>0.037652</td>\n",
" <td>0.04603</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>1.0</td>\n",
" <td>0.033911</td>\n",
" <td>2.836513</td>\n",
" <td>0.991139</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" RMSE MAE precision recall F_1 F_05 \\\n",
"0 0.949459 0.752487 0.09141 0.037652 0.04603 0.061286 \n",
"\n",
" precision_super recall_super NDCG mAP MRR LAUC \\\n",
"0 0.079614 0.056463 0.095957 0.043178 0.198193 0.515501 \n",
"\n",
" HR Reco in test Test coverage Shannon Gini \n",
"0 0.437964 1.0 0.033911 2.836513 0.991139 "
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import evaluation_measures as ev\n",
"import imp\n",
"imp.reload(ev)\n",
"\n",
"estimations_df=pd.read_csv('Recommendations generated/ml-100k/Ready_Baseline_estimations.csv', header=None)\n",
"reco=np.loadtxt('Recommendations generated/ml-100k/Ready_Baseline_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])\n",
"#also you can just type ev.evaluate_all(estimations_df, reco) - I put above values as default"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"943it [00:00, 7598.17it/s]\n",
"943it [00:00, 7277.83it/s]\n",
"943it [00:00, 8064.39it/s]\n",
"943it [00:00, 7990.96it/s]\n",
"943it [00:00, 7472.14it/s]\n",
"943it [00:00, 7330.59it/s]\n",
"943it [00:00, 7154.76it/s]\n",
"943it [00:00, 8088.85it/s]\n",
"943it [00:00, 8019.93it/s]\n",
"943it [00:00, 7194.86it/s]\n"
]
}
],
"source": [
"import evaluation_measures as ev\n",
"import imp\n",
"imp.reload(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",
"#also you can just type ev.evaluate_all() - I put above values as default"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Model</th>\n",
" <th>RMSE</th>\n",
" <th>MAE</th>\n",
" <th>precision</th>\n",
" <th>recall</th>\n",
" <th>F_1</th>\n",
" <th>F_05</th>\n",
" <th>precision_super</th>\n",
" <th>recall_super</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFMpureMF</td>\n",
" <td>7.953192</td>\n",
" <td>7.462008</td>\n",
" <td>0.334464</td>\n",
" <td>0.219997</td>\n",
" <td>0.217225</td>\n",
" <td>0.254981</td>\n",
" <td>0.233798</td>\n",
" <td>0.266952</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFM</td>\n",
" <td>162.707436</td>\n",
" <td>160.855483</td>\n",
" <td>0.340827</td>\n",
" <td>0.217682</td>\n",
" <td>0.217990</td>\n",
" <td>0.258010</td>\n",
" <td>0.243884</td>\n",
" <td>0.260663</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_P3</td>\n",
" <td>3.702446</td>\n",
" <td>3.527273</td>\n",
" <td>0.282185</td>\n",
" <td>0.192092</td>\n",
" <td>0.186749</td>\n",
" <td>0.216980</td>\n",
" <td>0.204185</td>\n",
" <td>0.240096</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_ImplicitALS</td>\n",
" <td>3.266101</td>\n",
" <td>3.065824</td>\n",
" <td>0.255037</td>\n",
" <td>0.188653</td>\n",
" <td>0.176852</td>\n",
" <td>0.201189</td>\n",
" <td>0.166631</td>\n",
" <td>0.214925</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_TopPop</td>\n",
" <td>2.508258</td>\n",
" <td>2.217909</td>\n",
" <td>0.188865</td>\n",
" <td>0.116919</td>\n",
" <td>0.118732</td>\n",
" <td>0.141584</td>\n",
" <td>0.130472</td>\n",
" <td>0.137473</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFMcontent</td>\n",
" <td>182.471340</td>\n",
" <td>180.405210</td>\n",
" <td>0.160339</td>\n",
" <td>0.101224</td>\n",
" <td>0.102198</td>\n",
" <td>0.121074</td>\n",
" <td>0.102682</td>\n",
" <td>0.112455</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Baseline</td>\n",
" <td>0.949459</td>\n",
" <td>0.752487</td>\n",
" <td>0.091410</td>\n",
" <td>0.037652</td>\n",
" <td>0.046030</td>\n",
" <td>0.061286</td>\n",
" <td>0.079614</td>\n",
" <td>0.056463</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_GlobalAvg</td>\n",
" <td>1.125760</td>\n",
" <td>0.943534</td>\n",
" <td>0.061188</td>\n",
" <td>0.025968</td>\n",
" <td>0.031383</td>\n",
" <td>0.041343</td>\n",
" <td>0.040558</td>\n",
" <td>0.032107</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Random</td>\n",
" <td>1.514355</td>\n",
" <td>1.216383</td>\n",
" <td>0.049735</td>\n",
" <td>0.022300</td>\n",
" <td>0.025782</td>\n",
" <td>0.033598</td>\n",
" <td>0.028219</td>\n",
" <td>0.021751</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_BaselineUI</td>\n",
" <td>0.967585</td>\n",
" <td>0.762740</td>\n",
" <td>0.000954</td>\n",
" <td>0.000170</td>\n",
" <td>0.000278</td>\n",
" <td>0.000463</td>\n",
" <td>0.000644</td>\n",
" <td>0.000189</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model RMSE MAE precision recall \\\n",
"0 Ready_LightFMpureMF 7.953192 7.462008 0.334464 0.219997 \n",
"0 Ready_LightFM 162.707436 160.855483 0.340827 0.217682 \n",
"0 Self_P3 3.702446 3.527273 0.282185 0.192092 \n",
"0 Ready_ImplicitALS 3.266101 3.065824 0.255037 0.188653 \n",
"0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 \n",
"0 Ready_LightFMcontent 182.471340 180.405210 0.160339 0.101224 \n",
"0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 \n",
"0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 \n",
"0 Ready_Random 1.514355 1.216383 0.049735 0.022300 \n",
"0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 \n",
"\n",
" F_1 F_05 precision_super recall_super \n",
"0 0.217225 0.254981 0.233798 0.266952 \n",
"0 0.217990 0.258010 0.243884 0.260663 \n",
"0 0.186749 0.216980 0.204185 0.240096 \n",
"0 0.176852 0.201189 0.166631 0.214925 \n",
"0 0.118732 0.141584 0.130472 0.137473 \n",
"0 0.102198 0.121074 0.102682 0.112455 \n",
"0 0.046030 0.061286 0.079614 0.056463 \n",
"0 0.031383 0.041343 0.040558 0.032107 \n",
"0 0.025782 0.033598 0.028219 0.021751 \n",
"0 0.000278 0.000463 0.000644 0.000189 "
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[:,:9]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Model</th>\n",
" <th>NDCG</th>\n",
" <th>mAP</th>\n",
" <th>MRR</th>\n",
" <th>LAUC</th>\n",
" <th>HR</th>\n",
" <th>Reco in test</th>\n",
" <th>Test coverage</th>\n",
" <th>Shannon</th>\n",
" <th>Gini</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFMpureMF</td>\n",
" <td>0.398778</td>\n",
" <td>0.263058</td>\n",
" <td>0.629129</td>\n",
" <td>0.607709</td>\n",
" <td>0.913043</td>\n",
" <td>1.000000</td>\n",
" <td>0.275613</td>\n",
" <td>5.085818</td>\n",
" <td>0.913665</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFM</td>\n",
" <td>0.403850</td>\n",
" <td>0.268266</td>\n",
" <td>0.637590</td>\n",
" <td>0.606568</td>\n",
" <td>0.898197</td>\n",
" <td>1.000000</td>\n",
" <td>0.351371</td>\n",
" <td>5.366291</td>\n",
" <td>0.885046</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_P3</td>\n",
" <td>0.339114</td>\n",
" <td>0.204905</td>\n",
" <td>0.572157</td>\n",
" <td>0.593544</td>\n",
" <td>0.875928</td>\n",
" <td>1.000000</td>\n",
" <td>0.077201</td>\n",
" <td>3.875892</td>\n",
" <td>0.974947</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_ImplicitALS</td>\n",
" <td>0.305908</td>\n",
" <td>0.172546</td>\n",
" <td>0.523871</td>\n",
" <td>0.591709</td>\n",
" <td>0.889714</td>\n",
" <td>1.000000</td>\n",
" <td>0.502886</td>\n",
" <td>5.722957</td>\n",
" <td>0.827507</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_TopPop</td>\n",
" <td>0.214651</td>\n",
" <td>0.111707</td>\n",
" <td>0.400939</td>\n",
" <td>0.555546</td>\n",
" <td>0.765642</td>\n",
" <td>1.000000</td>\n",
" <td>0.038961</td>\n",
" <td>3.159079</td>\n",
" <td>0.987317</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_LightFMcontent</td>\n",
" <td>0.180079</td>\n",
" <td>0.087429</td>\n",
" <td>0.337825</td>\n",
" <td>0.547572</td>\n",
" <td>0.704136</td>\n",
" <td>0.974973</td>\n",
" <td>0.264791</td>\n",
" <td>4.909893</td>\n",
" <td>0.926201</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Baseline</td>\n",
" <td>0.095957</td>\n",
" <td>0.043178</td>\n",
" <td>0.198193</td>\n",
" <td>0.515501</td>\n",
" <td>0.437964</td>\n",
" <td>1.000000</td>\n",
" <td>0.033911</td>\n",
" <td>2.836513</td>\n",
" <td>0.991139</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_GlobalAvg</td>\n",
" <td>0.067695</td>\n",
" <td>0.027470</td>\n",
" <td>0.171187</td>\n",
" <td>0.509546</td>\n",
" <td>0.384942</td>\n",
" <td>1.000000</td>\n",
" <td>0.025974</td>\n",
" <td>2.711772</td>\n",
" <td>0.992003</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Ready_Random</td>\n",
" <td>0.054383</td>\n",
" <td>0.021119</td>\n",
" <td>0.133978</td>\n",
" <td>0.507680</td>\n",
" <td>0.339343</td>\n",
" <td>0.986957</td>\n",
" <td>0.177489</td>\n",
" <td>5.088670</td>\n",
" <td>0.907676</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Self_BaselineUI</td>\n",
" <td>0.000752</td>\n",
" <td>0.000168</td>\n",
" <td>0.001677</td>\n",
" <td>0.496424</td>\n",
" <td>0.009544</td>\n",
" <td>0.600530</td>\n",
" <td>0.005051</td>\n",
" <td>1.803126</td>\n",
" <td>0.996380</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model NDCG mAP MRR LAUC HR \\\n",
"0 Ready_LightFMpureMF 0.398778 0.263058 0.629129 0.607709 0.913043 \n",
"0 Ready_LightFM 0.403850 0.268266 0.637590 0.606568 0.898197 \n",
"0 Self_P3 0.339114 0.204905 0.572157 0.593544 0.875928 \n",
"0 Ready_ImplicitALS 0.305908 0.172546 0.523871 0.591709 0.889714 \n",
"0 Self_TopPop 0.214651 0.111707 0.400939 0.555546 0.765642 \n",
"0 Ready_LightFMcontent 0.180079 0.087429 0.337825 0.547572 0.704136 \n",
"0 Ready_Baseline 0.095957 0.043178 0.198193 0.515501 0.437964 \n",
"0 Self_GlobalAvg 0.067695 0.027470 0.171187 0.509546 0.384942 \n",
"0 Ready_Random 0.054383 0.021119 0.133978 0.507680 0.339343 \n",
"0 Self_BaselineUI 0.000752 0.000168 0.001677 0.496424 0.009544 \n",
"\n",
" Reco in test Test coverage Shannon Gini \n",
"0 1.000000 0.275613 5.085818 0.913665 \n",
"0 1.000000 0.351371 5.366291 0.885046 \n",
"0 1.000000 0.077201 3.875892 0.974947 \n",
"0 1.000000 0.502886 5.722957 0.827507 \n",
"0 1.000000 0.038961 3.159079 0.987317 \n",
"0 0.974973 0.264791 4.909893 0.926201 \n",
"0 1.000000 0.033911 2.836513 0.991139 \n",
"0 1.000000 0.025974 2.711772 0.992003 \n",
"0 0.986957 0.177489 5.088670 0.907676 \n",
"0 0.600530 0.005051 1.803126 0.996380 "
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[:,np.append(0,np.arange(9, df.shape[1]))]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Check metrics on toy dataset"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"3it [00:00, 2511.56it/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",
" <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_BaselineUI</td>\n",
" <td>1.612452</td>\n",
" <td>1.4</td>\n",
" <td>0.444444</td>\n",
" <td>0.888889</td>\n",
" <td>0.555556</td>\n",
" <td>0.478632</td>\n",
" <td>0.333333</td>\n",
" <td>0.75</td>\n",
" <td>0.676907</td>\n",
" <td>0.574074</td>\n",
" <td>0.611111</td>\n",
" <td>0.638889</td>\n",
" <td>1.0</td>\n",
" <td>0.888889</td>\n",
" <td>0.8</td>\n",
" <td>1.386294</td>\n",
" <td>0.25</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Model RMSE MAE precision recall F_1 F_05 \\\n",
"0 Self_BaselineUI 1.612452 1.4 0.444444 0.888889 0.555556 0.478632 \n",
"\n",
" precision_super recall_super NDCG mAP MRR LAUC HR \\\n",
"0 0.333333 0.75 0.676907 0.574074 0.611111 0.638889 1.0 \n",
"\n",
" Reco in test Test coverage Shannon Gini \n",
"0 0.888889 0.8 1.386294 0.25 "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Training data:\n"
]
},
{
"data": {
"text/plain": [
"matrix([[3, 4, 0, 0, 5, 0, 0, 4],\n",
" [0, 1, 2, 3, 0, 0, 0, 0],\n",
" [0, 0, 0, 5, 0, 3, 4, 0]], dtype=int64)"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Test data:\n"
]
},
{
"data": {
"text/plain": [
"matrix([[0, 0, 0, 0, 0, 0, 3, 0],\n",
" [0, 0, 0, 0, 5, 0, 0, 0],\n",
" [5, 0, 4, 0, 0, 0, 0, 2]], dtype=int64)"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Recommendations:\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>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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>30</td>\n",
" <td>5.0</td>\n",
" <td>20</td>\n",
" <td>4.0</td>\n",
" <td>60</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>10</td>\n",
" <td>40</td>\n",
" <td>3.0</td>\n",
" <td>60</td>\n",
" <td>2.0</td>\n",
" <td>70</td>\n",
" <td>2.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>20</td>\n",
" <td>40</td>\n",
" <td>5.0</td>\n",
" <td>20</td>\n",
" <td>4.0</td>\n",
" <td>70</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0 1 2 3 4 5 6\n",
"0 0 30 5.0 20 4.0 60 4.0\n",
"1 10 40 3.0 60 2.0 70 2.0\n",
"2 20 40 5.0 20 4.0 70 4.0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Estimations:\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>user</th>\n",
" <th>item</th>\n",
" <th>est_score</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>60</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>10</td>\n",
" <td>40</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>20</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>20</td>\n",
" <td>20</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20</td>\n",
" <td>70</td>\n",
" <td>4.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" user item est_score\n",
"0 0 60 4.0\n",
"1 10 40 3.0\n",
"2 20 0 3.0\n",
"3 20 20 4.0\n",
"4 20 70 4.0"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import evaluation_measures as ev\n",
"import imp\n",
"import helpers\n",
"imp.reload(ev)\n",
"\n",
"dir_path=\"Recommendations generated/toy-example/\"\n",
"super_reactions=[4,5]\n",
"test=pd.read_csv('./Datasets/toy-example/test.csv', sep='\\t', header=None)\n",
"\n",
"display(ev.evaluate_all(test, dir_path, super_reactions, topK=3))\n",
"#also you can just type ev.evaluate_all() - I put above values as default\n",
"\n",
"toy_train_read=pd.read_csv('./Datasets/toy-example/train.csv', sep='\\t', header=None, names=['user', 'item', 'rating', 'timestamp'])\n",
"toy_test_read=pd.read_csv('./Datasets/toy-example/test.csv', sep='\\t', header=None, names=['user', 'item', 'rating', 'timestamp'])\n",
"reco=pd.read_csv('Recommendations generated/toy-example/Self_BaselineUI_reco.csv', header=None)\n",
"estimations=pd.read_csv('Recommendations generated/toy-example/Self_BaselineUI_estimations.csv', names=['user', 'item', 'est_score'])\n",
"toy_train_ui, toy_test_ui, toy_user_code_id, toy_user_id_code, \\\n",
"toy_item_code_id, toy_item_id_code = helpers.data_to_csr(toy_train_read, toy_test_read)\n",
"\n",
"print('Training data:')\n",
"display(toy_train_ui.todense())\n",
"\n",
"print('Test data:')\n",
"display(toy_test_ui.todense())\n",
"\n",
"print('Recommendations:')\n",
"display(reco)\n",
"\n",
"print('Estimations:')\n",
"display(estimations)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Sample recommendations"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Here is what user rated high:\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>user</th>\n",
" <th>rating</th>\n",
" <th>title</th>\n",
" <th>genres</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>25695</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>Citizen Kane (1941)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20098</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>Return of the Jedi (1983)</td>\n",
" <td>Action, Adventure, Romance, Sci-Fi, War</td>\n",
" </tr>\n",
" <tr>\n",
" <th>44215</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>Patton (1970)</td>\n",
" <td>Drama, War</td>\n",
" </tr>\n",
" <tr>\n",
" <th>43087</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>2001: A Space Odyssey (1968)</td>\n",
" <td>Drama, Mystery, Sci-Fi, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>42117</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>Dr. Strangelove or: How I Learned to Stop Worr...</td>\n",
" <td>Sci-Fi, War</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26819</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>Cool Hand Luke (1967)</td>\n",
" <td>Comedy, Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2996</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>Star Wars (1977)</td>\n",
" <td>Action, Adventure, Romance, Sci-Fi, War</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23610</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>Casablanca (1942)</td>\n",
" <td>Drama, Romance, War</td>\n",
" </tr>\n",
" <tr>\n",
" <th>79771</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>Santa with Muscles (1996)</td>\n",
" <td>Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16089</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>Godfather, The (1972)</td>\n",
" <td>Action, Crime, Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6128</th>\n",
" <td>781</td>\n",
" <td>5</td>\n",
" <td>Raiders of the Lost Ark (1981)</td>\n",
" <td>Action, Adventure</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18463</th>\n",
" <td>781</td>\n",
" <td>4</td>\n",
" <td>Amadeus (1984)</td>\n",
" <td>Drama, Mystery</td>\n",
" </tr>\n",
" <tr>\n",
" <th>31832</th>\n",
" <td>781</td>\n",
" <td>4</td>\n",
" <td>Shawshank Redemption, The (1994)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>63511</th>\n",
" <td>781</td>\n",
" <td>4</td>\n",
" <td>Sling Blade (1996)</td>\n",
" <td>Drama, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>48916</th>\n",
" <td>781</td>\n",
" <td>4</td>\n",
" <td>Lost Highway (1997)</td>\n",
" <td>Mystery</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" user rating title \\\n",
"25695 781 5 Citizen Kane (1941) \n",
"20098 781 5 Return of the Jedi (1983) \n",
"44215 781 5 Patton (1970) \n",
"43087 781 5 2001: A Space Odyssey (1968) \n",
"42117 781 5 Dr. Strangelove or: How I Learned to Stop Worr... \n",
"26819 781 5 Cool Hand Luke (1967) \n",
"2996 781 5 Star Wars (1977) \n",
"23610 781 5 Casablanca (1942) \n",
"79771 781 5 Santa with Muscles (1996) \n",
"16089 781 5 Godfather, The (1972) \n",
"6128 781 5 Raiders of the Lost Ark (1981) \n",
"18463 781 4 Amadeus (1984) \n",
"31832 781 4 Shawshank Redemption, The (1994) \n",
"63511 781 4 Sling Blade (1996) \n",
"48916 781 4 Lost Highway (1997) \n",
"\n",
" genres \n",
"25695 Drama \n",
"20098 Action, Adventure, Romance, Sci-Fi, War \n",
"44215 Drama, War \n",
"43087 Drama, Mystery, Sci-Fi, Thriller \n",
"42117 Sci-Fi, War \n",
"26819 Comedy, Drama \n",
"2996 Action, Adventure, Romance, Sci-Fi, War \n",
"23610 Drama, Romance, War \n",
"79771 Comedy \n",
"16089 Action, Crime, Drama \n",
"6128 Action, Adventure \n",
"18463 Drama, Mystery \n",
"31832 Drama \n",
"63511 Drama, Thriller \n",
"48916 Mystery "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Here is what we recommend:\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>user</th>\n",
" <th>rec_nb</th>\n",
" <th>title</th>\n",
" <th>genres</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>779</th>\n",
" <td>781.0</td>\n",
" <td>1</td>\n",
" <td>Great Day in Harlem, A (1994)</td>\n",
" <td>Documentary</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1721</th>\n",
" <td>781.0</td>\n",
" <td>2</td>\n",
" <td>Tough and Deadly (1995)</td>\n",
" <td>Action, Drama, Thriller</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2663</th>\n",
" <td>781.0</td>\n",
" <td>3</td>\n",
" <td>Aiqing wansui (1994)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3605</th>\n",
" <td>781.0</td>\n",
" <td>4</td>\n",
" <td>Delta of Venus (1994)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4547</th>\n",
" <td>781.0</td>\n",
" <td>5</td>\n",
" <td>Someone Else's America (1995)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5489</th>\n",
" <td>781.0</td>\n",
" <td>6</td>\n",
" <td>Saint of Fort Washington, The (1993)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6431</th>\n",
" <td>781.0</td>\n",
" <td>7</td>\n",
" <td>Celestial Clockwork (1994)</td>\n",
" <td>Comedy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7372</th>\n",
" <td>781.0</td>\n",
" <td>8</td>\n",
" <td>Some Mother's Son (1996)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9268</th>\n",
" <td>781.0</td>\n",
" <td>9</td>\n",
" <td>Maya Lin: A Strong Clear Vision (1994)</td>\n",
" <td>Documentary</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8314</th>\n",
" <td>781.0</td>\n",
" <td>10</td>\n",
" <td>Prefontaine (1997)</td>\n",
" <td>Drama</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" user rec_nb title \\\n",
"779 781.0 1 Great Day in Harlem, A (1994) \n",
"1721 781.0 2 Tough and Deadly (1995) \n",
"2663 781.0 3 Aiqing wansui (1994) \n",
"3605 781.0 4 Delta of Venus (1994) \n",
"4547 781.0 5 Someone Else's America (1995) \n",
"5489 781.0 6 Saint of Fort Washington, The (1993) \n",
"6431 781.0 7 Celestial Clockwork (1994) \n",
"7372 781.0 8 Some Mother's Son (1996) \n",
"9268 781.0 9 Maya Lin: A Strong Clear Vision (1994) \n",
"8314 781.0 10 Prefontaine (1997) \n",
"\n",
" genres \n",
"779 Documentary \n",
"1721 Action, Drama, Thriller \n",
"2663 Drama \n",
"3605 Drama \n",
"4547 Drama \n",
"5489 Drama \n",
"6431 Comedy \n",
"7372 Drama \n",
"9268 Documentary \n",
"8314 Drama "
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train=pd.read_csv('./Datasets/ml-100k/train.csv', sep='\\t', header=None, names=['user', 'item', 'rating', 'timestamp'])\n",
"items=pd.read_csv('./Datasets/ml-100k/movies.csv')\n",
"\n",
"user=random.choice(list(set(train['user'])))\n",
"\n",
"train_content=pd.merge(train, items, left_on='item', right_on='id')\n",
"\n",
"print('Here is what user rated high:')\n",
"display(train_content[train_content['user']==user][['user', 'rating', 'title', 'genres']]\\\n",
" .sort_values(by='rating', ascending=False)[:15])\n",
"\n",
"reco = np.loadtxt('Recommendations generated/ml-100k/Self_BaselineUI_reco.csv', delimiter=',')\n",
"items=pd.read_csv('./Datasets/ml-100k/movies.csv')\n",
"\n",
"# Let's ignore scores - they are not used in evaluation: \n",
"reco_users=reco[:,:1]\n",
"reco_items=reco[:,1::2]\n",
"# Let's put them into one array\n",
"reco=np.concatenate((reco_users, reco_items), axis=1)\n",
"\n",
"# Let's rebuild it user-item dataframe\n",
"recommended=[]\n",
"for row in reco:\n",
" for rec_nb, entry in enumerate(row[1:]):\n",
" recommended.append((row[0], rec_nb+1, entry))\n",
"recommended=pd.DataFrame(recommended, columns=['user','rec_nb', 'item'])\n",
"\n",
"recommended_content=pd.merge(recommended, items, left_on='item', right_on='id')\n",
"\n",
"print('Here is what we recommend:')\n",
"recommended_content[recommended_content['user']==user][['user', 'rec_nb', 'title', 'genres']].sort_values(by='rec_nb')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# project task 3: implement some other evaluation measure"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# it may be your idea, modification of what we have already implemented \n",
"# (for example Hit2 rate which would count as a success users whoreceived at least 2 relevant recommendations) \n",
"# or something well-known\n",
"# expected output: modification of evaluation_measures.py such that evaluate_all will also display your measure"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"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