s460932/workshops_recommender_systems
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
master
workshops_recommender_systems/.ipynb_checkpoints/P5. Graph-based-checkpoint.ipynb
s460932 afa9655186 Solutions
2020-06-15 00:15:17 +02:00

608 KiB
Raw Permalink Blame History

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, 7526.70it/s]
RMSE MAE precision recall F_1 F_05 precision_super recall_super NDCG mAP MRR LAUC HR HR2 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 0.685048 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, 7444.80it/s]
 12%|█▎        | 1/8 [00:09<01:07,  9.64s/it]
0it [00:00, ?it/s]
943it [00:00, 7203.06it/s]
 25%|██▌       | 2/8 [00:19<00:58,  9.69s/it]
0it [00:00, ?it/s]
943it [00:00, 7374.19it/s]
 38%|███▊      | 3/8 [00:28<00:47,  9.44s/it]
0it [00:00, ?it/s]
943it [00:00, 7637.26it/s]
 50%|█████     | 4/8 [00:37<00:36,  9.23s/it]
0it [00:00, ?it/s]
943it [00:00, 7968.92it/s]
 62%|██████▎   | 5/8 [00:45<00:27,  9.14s/it]
0it [00:00, ?it/s]
943it [00:00, 6917.17it/s]
 75%|███████▌  | 6/8 [00:54<00:18,  9.06s/it]
0it [00:00, ?it/s]
943it [00:00, 7768.07it/s]
 88%|████████▊ | 7/8 [01:03<00:08,  8.96s/it]
0it [00:00, ?it/s]
943it [00:00, 7708.43it/s]
100%|██████████| 8/8 [01:12<00:00,  9.06s/it]
Alpha RMSE MAE precision recall F_1 F_05 precision_super recall_super NDCG mAP MRR LAUC HR HR2 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 0.629905 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 0.644751 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 0.657476 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 0.685048 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 0.685048 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 0.681866 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 0.675504 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 0.669141 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, 8050.34it/s]
 10%|█         | 1/10 [00:08<01:20,  8.92s/it]
0it [00:00, ?it/s]
943it [00:00, 7932.86it/s]
 20%|██        | 2/10 [00:17<01:10,  8.87s/it]
0it [00:00, ?it/s]
943it [00:00, 7669.08it/s]
 30%|███       | 3/10 [00:26<01:02,  8.88s/it]
0it [00:00, ?it/s]
943it [00:00, 7369.22it/s]
 40%|████      | 4/10 [00:35<00:53,  8.89s/it]
0it [00:00, ?it/s]
943it [00:00, 7830.41it/s]
 50%|█████     | 5/10 [00:44<00:44,  8.88s/it]
0it [00:00, ?it/s]
943it [00:00, 7417.00it/s]
 60%|██████    | 6/10 [00:53<00:35,  8.88s/it]
0it [00:00, ?it/s]
943it [00:00, 7286.71it/s]
 70%|███████   | 7/10 [01:02<00:26,  8.88s/it]
0it [00:00, ?it/s]
943it [00:00, 7803.32it/s]
 80%|████████  | 8/10 [01:10<00:17,  8.84s/it]
0it [00:00, ?it/s]
943it [00:00, 7918.15it/s]
 90%|█████████ | 9/10 [01:19<00:08,  8.86s/it]
0it [00:00, ?it/s]
943it [00:00, 8223.42it/s]
100%|██████████| 10/10 [01:28<00:00,  8.86s/it]
Beta RMSE MAE precision recall F_1 F_05 precision_super recall_super NDCG mAP MRR LAUC HR HR2 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 0.685048 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 0.695652 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 0.697773 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 0.707317 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 0.718982 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 0.724284 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 0.720042 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 0.693531 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 0.604454 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 0.400848 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
522 817 5 Heat (1995) Action, Crime, Thriller
85 817 4 Toy Story (1995) Animation, Children's, Comedy
28224 817 4 Conspiracy Theory (1997) Action, Mystery, Romance, Thriller
69163 817 4 Desperate Measures (1998) Crime, Drama, Thriller
62281 817 4 Broken Arrow (1996) Action, Thriller
46995 817 4 Cop Land (1997) Crime, Drama, Mystery
44432 817 4 Bound (1996) Crime, Drama, Romance, Thriller
36735 817 4 Lone Star (1996) Drama, Mystery
32392 817 4 Spawn (1997) Action, Adventure, Sci-Fi, Thriller
30211 817 4 Star Trek: First Contact (1996) Action, Adventure, Sci-Fi
25251 817 4 Twelve Monkeys (1995) Drama, Sci-Fi
7384 817 4 Saint, The (1997) Action, Romance, Thriller
1394 817 4 River Wild, The (1994) Action, Thriller
922 817 4 Rumble in the Bronx (1995) Action, Adventure, Crime
25959 817 3 Dead Man Walking (1995) Drama
user rec_nb title genres
356 817.0 1 Star Wars (1977) Action, Adventure, Romance, Sci-Fi, War
4699 817.0 2 Air Force One (1997) Action, Thriller
7275 817.0 3 Fargo (1996) Crime, Drama, Thriller
2969 817.0 4 Return of the Jedi (1983) Action, Adventure, Romance, Sci-Fi, War
1954 817.0 5 Scream (1996) Horror, Thriller
1284 817.0 6 English Patient, The (1996) Drama, Romance, War
4996 817.0 7 Titanic (1997) Action, Drama, Romance
7667 817.0 8 Rock, The (1996) Action, Adventure, Thriller
5453 817.0 9 Liar Liar (1997) Comedy
2554 817.0 10 Godfather, The (1972) Action, Crime, Drama

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'
import evaluation_measures as ev

model = RP3Beta()
model.fit(train_ui, alpha = 0.8, beta = 0.6)

top_n = pd.DataFrame(model.recommend(user_code_id, item_code_id, topK = 10))
top_n.to_csv('Recommendations generated/ml-100k/Self_RP3Beta_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_RP3Beta_estimations.csv', index = False, header = False)
estimations_df = pd.read_csv('Recommendations generated/ml-100k/Self_RP3Beta_estimations.csv', header = None)

reco = np.loadtxt('Recommendations generated/ml-100k/Self_RP3Beta_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, 7573.18it/s]
RMSE MAE precision recall F_1 F_05 precision_super recall_super NDCG mAP MRR LAUC HR HR2 Reco in test Test coverage Shannon Gini
0 3.702928 3.527713 0.322694 0.216069 0.212152 0.247538 0.245279 0.284983 0.388271 0.248239 0.636318 0.605683 0.910923 0.731707 0.999788 0.178932 4.549663 0.950182 
result.sort_values(["recall"])
Beta RMSE MAE precision recall F_1 F_05 precision_super recall_super NDCG mAP MRR LAUC HR HR2 Reco in test Test coverage Shannon Gini
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 0.400848 0.800106 0.415584 5.563910 0.857396
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 0.604454 0.936373 0.341270 5.257397 0.895882
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 0.693531 0.983033 0.256854 4.898568 0.928065
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 0.685048 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 0.695652 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 0.697773 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 0.707317 1.000000 0.105339 4.147779 0.966948
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 0.720042 0.996394 0.212843 4.621938 0.945932
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 0.718982 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 0.724284 0.999046 0.168831 4.411281 0.956648 
model=RP3Beta()
model.fit(train_ui, alpha=0.8, beta=0.6)
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))
reco.to_csv('Recommendations generated/ml-100k/Self_RP3Beta_reco.csv', index=False, header=False)
estimations_df.to_csv('Recommendations generated/ml-100k/Self_RP3Beta_estimations.csv', index=False, header=False)
import imp
imp.reload(ev)

import evaluation_measures as ev
dir_path="Recommendations generated/ml-100k/"
super_reactions=[4,5]
test=pd.read_csv('./Datasets/ml-100k/test.csv', sep='\t', header=None)

ev.evaluate_all(test, dir_path, super_reactions)
943it [00:00, 8158.14it/s]
943it [00:00, 9333.50it/s]
943it [00:00, 9476.19it/s]
943it [00:00, 9525.85it/s]
943it [00:00, 8598.75it/s]
943it [00:00, 8068.36it/s]
943it [00:00, 8083.56it/s]
943it [00:00, 8668.60it/s]
943it [00:00, 9727.66it/s]
943it [00:00, 9319.03it/s]
943it [00:00, 9498.31it/s]
943it [00:00, 8207.35it/s]
943it [00:00, 9366.05it/s]
943it [00:00, 9705.08it/s]
943it [00:00, 9080.16it/s]
943it [00:00, 9075.35it/s]
943it [00:00, 9200.95it/s]
943it [00:00, 9218.29it/s]
Model RMSE MAE precision recall F_1 F_05 precision_super recall_super NDCG mAP MRR LAUC HR HR2 Reco in test Test coverage Shannon Gini
0 Self_RP3Beta 3.702928 3.527713 0.322694 0.216069 0.212152 0.247538 0.245279 0.284983 0.388271 0.248239 0.636318 0.605683 0.910923 0.731707 0.999788 0.178932 4.549663 0.950182
0 Self_P3 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 0.685048 1.000000 0.077201 3.875892 0.974947
0 Self_TopPop 2.508258 2.217909 0.188865 0.116919 0.118732 0.141584 0.130472 0.137473 0.214651 0.111707 0.400939 0.555546 0.765642 0.492047 1.000000 0.038961 3.159079 0.987317
0 Self_SVDBaseline 3.644790 3.479397 0.137010 0.082007 0.083942 0.100776 0.106974 0.105605 0.160418 0.080222 0.322261 0.537895 0.626723 0.360551 0.999894 0.276335 5.123235 0.910511
0 Ready_SVD 0.950945 0.749680 0.098834 0.049106 0.054037 0.068741 0.087768 0.073987 0.113242 0.054201 0.243492 0.521280 0.493107 0.248144 0.998515 0.214286 4.413166 0.953488
0 Self_SVD 0.915079 0.718240 0.104772 0.045496 0.054393 0.071374 0.094421 0.076826 0.109517 0.052005 0.206646 0.519484 0.487805 0.264051 0.874549 0.142136 3.890472 0.972126
0 Ready_Baseline 0.949459 0.752487 0.091410 0.037652 0.046030 0.061286 0.079614 0.056463 0.095957 0.043178 0.198193 0.515501 0.437964 0.239661 1.000000 0.033911 2.836513 0.991139
0 Ready_SVDBiased 0.938535 0.738678 0.085366 0.036921 0.044151 0.057832 0.074893 0.056396 0.095960 0.044204 0.212483 0.515132 0.446448 0.217391 0.997561 0.168110 4.191946 0.963341
0 Self_KNNSurprisetask 0.946255 0.745209 0.083457 0.032848 0.041227 0.055493 0.074785 0.048890 0.089577 0.040902 0.189057 0.513076 0.417815 0.217391 0.888547 0.130592 3.611806 0.978659
0 Self_GlobalAvg 1.125760 0.943534 0.061188 0.025968 0.031383 0.041343 0.040558 0.032107 0.067695 0.027470 0.171187 0.509546 0.384942 0.142100 1.000000 0.025974 2.711772 0.992003
0 Ready_Random 1.522798 1.222501 0.049841 0.020656 0.025232 0.033446 0.030579 0.022927 0.051680 0.019110 0.123085 0.506849 0.331919 0.119830 0.985048 0.183983 5.097973 0.907483
0 Ready_I-KNN 1.030386 0.813067 0.026087 0.006908 0.010593 0.016046 0.021137 0.009522 0.024214 0.008958 0.048068 0.499885 0.154825 0.072110 0.402333 0.434343 5.133650 0.877999
0 Ready_I-KNNBaseline 0.935327 0.737424 0.002545 0.000755 0.001105 0.001602 0.002253 0.000930 0.003444 0.001362 0.011760 0.496724 0.021209 0.004242 0.482821 0.059885 2.232578 0.994487
0 Ready_U-KNN 1.023495 0.807913 0.000742 0.000205 0.000305 0.000449 0.000536 0.000198 0.000845 0.000274 0.002744 0.496441 0.007423 0.000000 0.602121 0.010823 2.089186 0.995706
0 Self_TopRated 2.508258 2.217909 0.000954 0.000188 0.000298 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 0.496433 0.009544 0.000000 0.699046 0.005051 1.945910 0.995669
0 Self_BaselineIU 0.958136 0.754051 0.000954 0.000188 0.000298 0.000481 0.000644 0.000223 0.001043 0.000335 0.003348 0.496433 0.009544 0.000000 0.699046 0.005051 1.945910 0.995669
0 Self_BaselineUI 0.967585 0.762740 0.000954 0.000170 0.000278 0.000463 0.000644 0.000189 0.000752 0.000168 0.001677 0.496424 0.009544 0.000000 0.600530 0.005051 1.803126 0.996380
0 Self_IKNN 1.018363 0.808793 0.000318 0.000108 0.000140 0.000189 0.000000 0.000000 0.000214 0.000037 0.000368 0.496391 0.003181 0.000000 0.392153 0.115440 4.174741 0.965327

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'