workshops_recommender_systems/.ipynb_checkpoints/P3. k-nearest neighbours-checkpoint.ipynb
2020-06-15 00:15:17 +02:00

42 KiB

Self made simplified I-KNN

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

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 IKNN():
    
    def fit(self, train_ui):
        self.train_ui=train_ui
        
        train_iu=train_ui.transpose()
        norms=np.linalg.norm(train_iu.A, axis=1) # here we compute lenth of each item ratings vector
        norms=np.vectorize(lambda x: max(x,1))(norms[:,None]) # to avoid dividing by zero

        normalized_train_iu=sparse.csr_matrix(train_iu/norms)

        self.similarity_matrix_ii=normalized_train_iu*normalized_train_iu.transpose()
        
        self.estimations=np.array(train_ui*self.similarity_matrix_ii/((train_ui>0)*self.similarity_matrix_ii))
        
    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
# toy example
toy_train_read=pd.read_csv('./Datasets/toy-example/train.csv', sep='\t', header=None, names=['user', 'item', 'rating', 'timestamp'])
toy_test_read=pd.read_csv('./Datasets/toy-example/test.csv', sep='\t', header=None, names=['user', 'item', 'rating', 'timestamp'])

toy_train_ui, toy_test_ui, toy_user_code_id, toy_user_id_code, \
toy_item_code_id, toy_item_id_code = helpers.data_to_csr(toy_train_read, toy_test_read)


model=IKNN()
model.fit(toy_train_ui)

print('toy train ui:')
display(toy_train_ui.A)

print('similarity matrix:')
display(model.similarity_matrix_ii.A)

print('estimations matrix:')
display(model.estimations)

model.recommend(toy_user_code_id, toy_item_code_id)
toy train ui:
array([[3, 4, 0, 0, 5, 0, 0, 4],
       [0, 1, 2, 3, 0, 0, 0, 0],
       [0, 0, 0, 5, 0, 3, 4, 0]], dtype=int64)
similarity matrix:
array([[1.        , 0.9701425 , 0.        , 0.        , 1.        ,
        0.        , 0.        , 1.        ],
       [0.9701425 , 1.        , 0.24253563, 0.12478355, 0.9701425 ,
        0.        , 0.        , 0.9701425 ],
       [0.        , 0.24253563, 1.        , 0.51449576, 0.        ,
        0.        , 0.        , 0.        ],
       [0.        , 0.12478355, 0.51449576, 1.        , 0.        ,
        0.85749293, 0.85749293, 0.        ],
       [1.        , 0.9701425 , 0.        , 0.        , 1.        ,
        0.        , 0.        , 1.        ],
       [0.        , 0.        , 0.        , 0.85749293, 0.        ,
        1.        , 1.        , 0.        ],
       [0.        , 0.        , 0.        , 0.85749293, 0.        ,
        1.        , 1.        , 0.        ],
       [1.        , 0.9701425 , 0.        , 0.        , 1.        ,
        0.        , 0.        , 1.        ]])
estimations matrix:
array([[4.        , 4.        , 4.        , 4.        , 4.        ,
               nan,        nan, 4.        ],
       [1.        , 1.35990333, 2.15478388, 2.53390319, 1.        ,
        3.        , 3.        , 1.        ],
       [       nan, 5.        , 5.        , 4.05248907,        nan,
        3.95012863, 3.95012863,        nan]])
[[0, 20, 4.0, 30, 4.0],
 [10, 50, 3.0, 60, 3.0, 0, 1.0, 40, 1.0, 70, 1.0],
 [20, 10, 5.0, 20, 5.0]]
model=IKNN()
model.fit(train_ui)

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

top_n.to_csv('Recommendations generated/ml-100k/Self_IKNN_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_IKNN_estimations.csv', index=False, header=False)
import evaluation_measures as ev
estimations_df=pd.read_csv('Recommendations generated/ml-100k/Self_IKNN_estimations.csv', header=None)
reco=np.loadtxt('Recommendations generated/ml-100k/Self_IKNN_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, 7867.08it/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 1.018363 0.808793 0.000318 0.000108 0.00014 0.000189 0.0 0.0 0.000214 0.000037 0.000368 0.496391 0.003181 0.0 0.392153 0.11544 4.174741 0.965327
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, 8630.78it/s]
943it [00:00, 9234.18it/s]
943it [00:00, 9860.04it/s]
943it [00:00, 9890.74it/s]
943it [00:00, 9782.25it/s]
943it [00:00, 8807.11it/s]
943it [00:00, 8925.24it/s]
943it [00:00, 8808.87it/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_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 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 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 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

Ready-made KNNs - Surprise implementation

I-KNN - basic

import helpers
import surprise as sp
import imp
imp.reload(helpers)

sim_options = {'name': 'cosine',
              'user_based': False}  # compute similarities between items
algo = sp.KNNBasic(sim_options=sim_options)

helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_I-KNN_reco.csv',
          estimations_path='Recommendations generated/ml-100k/Ready_I-KNN_estimations.csv')
Computing the cosine similarity matrix...
Done computing similarity matrix.
Generating predictions...
Generating top N recommendations...
Generating predictions...

U-KNN - basic

import helpers
import surprise as sp
import imp
imp.reload(helpers)

sim_options = {'name': 'cosine',
              'user_based': True}  # compute similarities between users
algo = sp.KNNBasic(sim_options=sim_options)

helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_U-KNN_reco.csv',
          estimations_path='Recommendations generated/ml-100k/Ready_U-KNN_estimations.csv')
Computing the cosine similarity matrix...
Done computing similarity matrix.
Generating predictions...
Generating top N recommendations...
Generating predictions...

I-KNN - on top baseline

import helpers
import surprise as sp
import imp
imp.reload(helpers)

sim_options = {'name': 'cosine',
              'user_based': False}  # compute similarities between items
algo = sp.KNNBaseline()

helpers.ready_made(algo, reco_path='Recommendations generated/ml-100k/Ready_I-KNNBaseline_reco.csv',
          estimations_path='Recommendations generated/ml-100k/Ready_I-KNNBaseline_estimations.csv')
Estimating biases using als...
Computing the msd similarity matrix...
Done computing similarity matrix.
Generating predictions...
Generating top N recommendations...
Generating predictions...

project task 4: use a version of your choice of Surprise KNNalgorithm

# read the docs and try to find best parameter configuration (let say in terms of RMSE)
# https://surprise.readthedocs.io/en/stable/knn_inspired.html##surprise.prediction_algorithms.knns.KNNBaseline
# the solution here can be similar to examples above
# please save the output in 'Recommendations generated/ml-100k/Self_KNNSurprisetask_reco.csv' and
# 'Recommendations generated/ml-100k/Self_KNNSurprisetask_estimations.csv'
import helpers
import surprise as sp
import imp

imp.reload(helpers)

sim_options = {'name': 'cosine',
              'user_based': False}

algo = sp.KNNBaseline(sim_options = sim_options)

helpers.ready_made(algo, reco_path = 'Recommendations generated/ml-100k/Self_KNNSurprisetask_reco.csv',
          estimations_path = 'Recommendations generated/ml-100k/Self_KNNSurprisetask_estimations.csv')
Estimating biases using als...
Computing the cosine similarity matrix...
Done computing similarity matrix.
Generating predictions...
Generating top N recommendations...
Generating predictions...
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, 9238.34it/s]
943it [00:00, 9588.43it/s]
943it [00:00, 9569.67it/s]
943it [00:00, 9293.69it/s]
943it [00:00, 9863.41it/s]
943it [00:00, 8672.47it/s]
943it [00:00, 9321.91it/s]
943it [00:00, 9440.66it/s]
943it [00:00, 9619.66it/s]
943it [00:00, 9841.64it/s]
943it [00:00, 9634.00it/s]
943it [00:00, 8838.72it/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_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 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 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