workshops_recommender_systems/P5. Graph-based.ipynb

Self made RP3-beta

import helpers
import pandas as pd
import numpy as np
import scipy.sparse as sparse
from collections import defaultdict
from itertools import chain
import random
import time
import matplotlib.pyplot as plt

train_read=pd.read_csv('./Datasets/ml-100k/train.csv', sep='\t', header=None)
test_read=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\t', header=None)
train_ui, test_ui, user_code_id, user_id_code, item_code_id, item_id_code = helpers.data_to_csr(train_read, test_read)

class RP3Beta():
    def fit(self, train_ui, alpha, beta):
        """We weight our edges by user's explicit ratings so if user rated movie high we'll follow that path
        with higher probability."""
        self.train_ui=train_ui
        self.train_iu=train_ui.transpose()
        
        self.alpha = alpha
        self.beta = beta
        
        # Define Pui 
        Pui=sparse.csr_matrix(self.train_ui/self.train_ui.sum(axis=1))
        
        # Define Piu
        to_divide=np.vectorize(lambda x: x if x>0 else 1)(self.train_iu.sum(axis=1)) # to avoid dividing by zero
        Piu=sparse.csr_matrix(self.train_iu/to_divide)
        item_orders=(self.train_ui>0).sum(axis=0)
        
        Pui = Pui.power(self.alpha)
        Piu = Piu.power(self.alpha)

        P3=Pui*Piu*Pui
        
        P3/=np.power(np.vectorize(lambda x: x if x>0 else 1)(item_orders), self.beta)
        
        self.estimations=np.array(P3)
    
    def recommend(self, user_code_id, item_code_id, topK=10):
        
        top_k = defaultdict(list)
        for nb_user, user in enumerate(self.estimations):
            
            user_rated=self.train_ui.indices[self.train_ui.indptr[nb_user]:self.train_ui.indptr[nb_user+1]]
            for item, score in enumerate(user):
                if item not in user_rated and not np.isnan(score):
                    top_k[user_code_id[nb_user]].append((item_code_id[item], score))
        result=[]
        # Let's choose k best items in the format: (user, item1, score1, item2, score2, ...)
        for uid, item_scores in top_k.items():
            item_scores.sort(key=lambda x: x[1], reverse=True)
            result.append([uid]+list(chain(*item_scores[:topK])))
        return result
    
    def estimate(self, user_code_id, item_code_id, test_ui):
        result=[]
        for user, item in zip(*test_ui.nonzero()):
            result.append([user_code_id[user], item_code_id[item], 
                           self.estimations[user,item] if not np.isnan(self.estimations[user,item]) else 1])
        return result

model=RP3Beta()
model.fit(train_ui, alpha=1, beta=0)

top_n=pd.DataFrame(model.recommend(user_code_id, item_code_id, topK=10))

top_n.to_csv('Recommendations generated/ml-100k/Self_P3_reco.csv', index=False, header=False)

estimations=pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))
estimations.to_csv('Recommendations generated/ml-100k/Self_P3_estimations.csv', index=False, header=False)

import evaluation_measures as ev
estimations_df=pd.read_csv('Recommendations generated/ml-100k/Self_P3_estimations.csv', header=None)
reco=np.loadtxt('Recommendations generated/ml-100k/Self_P3_reco.csv', delimiter=',')

ev.evaluate(test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\t', header=None),
            estimations_df=estimations_df, 
            reco=reco,
            super_reactions=[4,5])

943it [00:00, 7214.50it/s]

	RMSE	MAE	precision	recall	F_1	F_05	precision_super	recall_super	NDCG	mAP	MRR	LAUC	HR	Reco in test	Test coverage	Shannon	Gini
0	3.702446	3.527273	0.282185	0.192092	0.186749	0.21698	0.204185	0.240096	0.339114	0.204905	0.572157	0.593544	0.875928	1.0	0.077201	3.875892	0.974947

Let's check hiperparameters

Alpha

from tqdm import tqdm
result=[]
for alpha in tqdm([round(i,1) for i in np.arange(0.2,1.6001,0.2)]):
    model=RP3Beta()
    model.fit(train_ui, alpha=alpha, beta=0)
    reco=pd.DataFrame(model.recommend(user_code_id, item_code_id, topK=10))
    estimations_df=pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))
    to_append=ev.evaluate(test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\t', header=None),
            estimations_df=estimations_df, 
            reco=np.array(reco),
            super_reactions=[4,5])
    to_append.insert(0, "Alpha", alpha)
    result.append(to_append)
    
result=pd.concat(result)
result

  0%|          | 0/8 [00:00<?, ?it/s]
0it [00:00, ?it/s]
943it [00:00, 6952.21it/s]
 12%|█▎        | 1/8 [00:09<01:06,  9.56s/it]
0it [00:00, ?it/s]
943it [00:00, 6822.51it/s]
 25%|██▌       | 2/8 [00:19<00:57,  9.53s/it]
0it [00:00, ?it/s]
943it [00:00, 6841.03it/s]
 38%|███▊      | 3/8 [00:28<00:48,  9.63s/it]
0it [00:00, ?it/s]
943it [00:00, 7086.32it/s]
 50%|█████     | 4/8 [00:38<00:38,  9.68s/it]
0it [00:00, ?it/s]
943it [00:00, 7470.38it/s]
 62%|██████▎   | 5/8 [00:48<00:29,  9.72s/it]
0it [00:00, ?it/s]
943it [00:00, 7429.22it/s]
 75%|███████▌  | 6/8 [00:58<00:19,  9.73s/it]
0it [00:00, ?it/s]
943it [00:00, 7042.01it/s]
 88%|████████▊ | 7/8 [01:07<00:09,  9.67s/it]
0it [00:00, ?it/s]
943it [00:00, 7035.02it/s]
100%|██████████| 8/8 [01:17<00:00,  9.67s/it]

	Alpha	RMSE	MAE	precision	recall	F_1	F_05	precision_super	recall_super	NDCG	mAP	MRR	LAUC	HR	Reco in test	Test coverage	Shannon	Gini
0	0.2	268.177832	211.732649	0.262672	0.166858	0.166277	0.197184	0.187661	0.203252	0.320910	0.196132	0.563378	0.580866	0.850477	1.000000	0.060606	3.669627	0.979636
0	0.4	10.546689	7.792373	0.268505	0.172669	0.171569	0.202643	0.192489	0.212653	0.326760	0.200172	0.565148	0.583801	0.854719	1.000000	0.064214	3.726996	0.978426
0	0.6	3.143988	2.948790	0.274655	0.180502	0.177820	0.208730	0.198176	0.222746	0.332872	0.203290	0.568872	0.587738	0.870626	1.000000	0.065657	3.785282	0.977090
0	0.8	3.670728	3.495735	0.281972	0.189868	0.185300	0.216071	0.203541	0.236751	0.339867	0.206688	0.573729	0.592432	0.874867	1.000000	0.070707	3.832415	0.975998
0	1.0	3.702446	3.527273	0.282185	0.192092	0.186749	0.216980	0.204185	0.240096	0.339114	0.204905	0.572157	0.593544	0.875928	1.000000	0.077201	3.875892	0.974947
0	1.2	3.704441	3.529251	0.280912	0.193633	0.187311	0.216872	0.203004	0.240588	0.338049	0.203453	0.571830	0.594313	0.883351	1.000000	0.085859	3.910718	0.974073
0	1.4	3.704580	3.529388	0.273595	0.190651	0.183874	0.212183	0.199464	0.239118	0.329550	0.195433	0.566171	0.592793	0.871686	1.000000	0.107504	3.961915	0.972674
0	1.6	3.704591	3.529399	0.263097	0.186255	0.178709	0.205170	0.191094	0.232920	0.317439	0.184917	0.552349	0.590545	0.868505	0.999576	0.156566	4.060156	0.969203

metrics=list(result.columns[[i not in ['Alpha'] for i in result.columns]])

charts_per_row=6
charts_per_column=3

fig, axes = plt.subplots(nrows=charts_per_row, ncols=charts_per_column,figsize=(18, 7*charts_per_row ))
import itertools
to_iter=[i for i in itertools.product(range(charts_per_row), range(charts_per_column))]

for i in range(len(metrics)):
    df=result[['Alpha', metrics[i]]]
    df.plot(ax=axes[to_iter[i]], title=metrics[i], x=0, y=1)

Beta

from tqdm import tqdm
result=[]
for beta in tqdm([round(i,1) for i in np.arange(0,1,0.1)]):
    model=RP3Beta()
    model.fit(train_ui, alpha=1, beta=beta)
    reco=pd.DataFrame(model.recommend(user_code_id, item_code_id, topK=10))
    estimations_df=pd.DataFrame(model.estimate(user_code_id, item_code_id, test_ui))
    to_append=ev.evaluate(test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\t', header=None),
            estimations_df=estimations_df, 
            reco=np.array(reco),
            super_reactions=[4,5])
    to_append.insert(0, "Beta", beta)
    result.append(to_append)
    
result=pd.concat(result)
result

  0%|          | 0/10 [00:00<?, ?it/s]
0it [00:00, ?it/s]
943it [00:00, 7111.67it/s]
 10%|█         | 1/10 [00:10<01:36, 10.70s/it]
0it [00:00, ?it/s]
943it [00:00, 7130.50it/s]
 20%|██        | 2/10 [00:21<01:26, 10.87s/it]
0it [00:00, ?it/s]
943it [00:00, 6952.85it/s]
 30%|███       | 3/10 [00:32<01:16, 10.90s/it]
0it [00:00, ?it/s]
943it [00:00, 7108.39it/s]
 40%|████      | 4/10 [00:43<01:05, 10.87s/it]
0it [00:00, ?it/s]
943it [00:00, 6175.82it/s]
 50%|█████     | 5/10 [00:54<00:54, 10.89s/it]
0it [00:00, ?it/s]
943it [00:00, 6668.87it/s]
 60%|██████    | 6/10 [01:05<00:43, 10.87s/it]
0it [00:00, ?it/s]
943it [00:00, 7369.27it/s]
 70%|███████   | 7/10 [01:16<00:33, 11.01s/it]
0it [00:00, ?it/s]
943it [00:00, 7014.52it/s]
 80%|████████  | 8/10 [01:27<00:21, 10.95s/it]
0it [00:00, ?it/s]
943it [00:00, 6965.11it/s]
 90%|█████████ | 9/10 [01:38<00:10, 10.91s/it]
0it [00:00, ?it/s]
943it [00:00, 7744.74it/s]
100%|██████████| 10/10 [01:49<00:00, 10.94s/it]

	Beta	RMSE	MAE	precision	recall	F_1	F_05	precision_super	recall_super	NDCG	mAP	MRR	LAUC	HR	Reco in test	Test coverage	Shannon	Gini
0	0.0	3.702446	3.527273	0.282185	0.192092	0.186749	0.216980	0.204185	0.240096	0.339114	0.204905	0.572157	0.593544	0.875928	1.000000	0.077201	3.875892	0.974947
0	0.1	3.703312	3.528128	0.290138	0.197597	0.192259	0.223336	0.210944	0.246153	0.347768	0.212034	0.581038	0.596328	0.884411	1.000000	0.085137	3.957416	0.972784
0	0.2	3.703825	3.528636	0.297137	0.201202	0.196067	0.228169	0.218026	0.252767	0.355655	0.219909	0.588904	0.598160	0.886532	1.000000	0.094517	4.053212	0.969980
0	0.3	3.704130	3.528939	0.303499	0.204749	0.199901	0.232829	0.225107	0.260797	0.363757	0.226825	0.599969	0.599964	0.888653	1.000000	0.105339	4.147779	0.966948
0	0.4	3.704313	3.529120	0.308908	0.208811	0.203854	0.237241	0.229614	0.266918	0.370758	0.232673	0.609385	0.602014	0.895016	0.999894	0.132035	4.259682	0.962989
0	0.5	3.704422	3.529229	0.314316	0.211411	0.206768	0.240986	0.237124	0.273416	0.378307	0.239297	0.622792	0.603327	0.903499	0.999046	0.168831	4.411281	0.956648
0	0.6	3.704488	3.529295	0.314634	0.206209	0.204818	0.240159	0.242489	0.273850	0.376438	0.238428	0.622042	0.600721	0.897137	0.996394	0.212843	4.621938	0.945932
0	0.7	3.704528	3.529335	0.304136	0.187298	0.191990	0.228749	0.238305	0.256201	0.358807	0.226808	0.593897	0.591207	0.868505	0.983033	0.256854	4.898568	0.928065
0	0.8	3.704552	3.529360	0.266384	0.147571	0.158660	0.194838	0.214485	0.209336	0.299850	0.184356	0.492852	0.571152	0.803818	0.936373	0.341270	5.257397	0.895882
0	0.9	3.704567	3.529375	0.162354	0.076967	0.089233	0.114583	0.134657	0.113253	0.160868	0.085486	0.243590	0.535405	0.580064	0.800106	0.415584	5.563910	0.857396

### import matplotlib.pyplot as plt

metrics=list(result.columns[[i not in ['Beta'] for i in result.columns]])

charts_per_row=6
charts_per_column=3

fig, axes = plt.subplots(nrows=charts_per_row, ncols=charts_per_column,figsize=(18, 7*charts_per_row ))
import itertools
to_iter=[i for i in itertools.product(range(charts_per_row), range(charts_per_column))]

for i in range(len(metrics)):
    df=result[['Beta', metrics[i]]]
    df.plot(ax=axes[to_iter[i]], title=metrics[i], x=0, y=1)

Check sample recommendations

train=pd.read_csv('./Datasets/ml-100k/train.csv', sep='\t', header=None, names=['user', 'item', 'rating', 'timestamp'])
items=pd.read_csv('./Datasets/ml-100k/movies.csv')

user=random.choice(list(set(train['user'])))

train_content=pd.merge(train, items, left_on='item', right_on='id')
display(train_content[train_content['user']==user][['user', 'rating', 'title', 'genres']]\
        .sort_values(by='rating', ascending=False)[:15])

reco = np.loadtxt('Recommendations generated/ml-100k/Self_P3_reco.csv', delimiter=',')
items=pd.read_csv('./Datasets/ml-100k/movies.csv')

# Let's ignore scores - they are not used in evaluation: 
reco_users=reco[:,:1]
reco_items=reco[:,1::2]
# Let's put them into one array
reco=np.concatenate((reco_users, reco_items), axis=1)

# Let's rebuild it user-item dataframe
recommended=[]
for row in reco:
    for rec_nb, entry in enumerate(row[1:]):
        recommended.append((row[0], rec_nb+1, entry))
recommended=pd.DataFrame(recommended, columns=['user','rec_nb', 'item'])

recommended_content=pd.merge(recommended, items, left_on='item', right_on='id')
recommended_content[recommended_content['user']==user][['user', 'rec_nb', 'title', 'genres']].sort_values(by='rec_nb')

	user	rating	title	genres
47381	504	5	Crow, The (1994)	Action, Romance, Thriller
38682	504	5	First Wives Club, The (1996)	Comedy
49310	504	5	Schindler's List (1993)	Drama, War
47893	504	5	Nell (1994)	Drama
22082	504	5	Men in Black (1997)	Action, Adventure, Comedy, Sci-Fi
15938	504	5	Godfather, The (1972)	Action, Crime, Drama
51421	504	5	Interview with the Vampire (1994)	Drama, Horror
47837	504	5	Omen, The (1976)	Horror
14267	504	5	Fargo (1996)	Crime, Drama, Thriller
51759	504	5	Man Without a Face, The (1993)	Drama
45355	504	5	Lion King, The (1994)	Animation, Children's, Musical
77192	504	5	Ghosts of Mississippi (1996)	Drama
19123	504	5	Scream (1996)	Horror, Thriller
56591	504	5	My Favorite Year (1982)	Comedy
41312	504	5	Gone with the Wind (1939)	Drama, Romance, War

	user	rec_nb	title	genres
3231	504.0	1	Toy Story (1995)	Animation, Children's, Comedy
6474	504.0	2	Pulp Fiction (1994)	Crime, Drama
5823	504.0	3	Contact (1997)	Drama, Sci-Fi
6689	504.0	4	Empire Strikes Back, The (1980)	Action, Adventure, Drama, Romance, Sci-Fi, War
7779	504.0	5	Princess Bride, The (1987)	Action, Adventure, Comedy, Romance
4212	504.0	6	Twelve Monkeys (1995)	Drama, Sci-Fi
1420	504.0	7	Fugitive, The (1993)	Action, Thriller
6847	504.0	8	Braveheart (1995)	Action, Drama, War
7615	504.0	9	Rock, The (1996)	Action, Adventure, Thriller
7914	504.0	10	Amadeus (1984)	Drama, Mystery

project task 6: generate recommendations of RP3Beta for hiperparameters found to optimize recall

# use better values than (1,0) for alpha and beta
# if you want you can also modify the model to consider different weights (we took as weights user ratings, maybe take ones or squares of ratings instead)
# save the outptut in 'Recommendations generated/ml-100k/Self_RP3Beta_estimations.csv'
# and 'Recommendations generated/ml-100k/Self_RP3Beta_reco.csv'

project task 7 (optional): implement graph-based model of your choice

# for example change length of paths in RP3beta
# save the outptut in 'Recommendations generated/ml-100k/Self_GraphTask_estimations.csv'
# and 'Recommendations generated/ml-100k/Self_GraphTask_reco.csv'