def compute_SVDNeighbourhood(): svd = SVDNeighbourhood() svd.set_data(load_data()) K=100 svd.compute(k=K, min_values=10, pre_normalize=None, mean_center=True, post_normalize=True, savefile=None) svd.save_model(os.path.join(utils.get_add_dir(), 'ratings_neigh'))
data = Data() data.load(sys.argv[1], sep="::", format={"col": 0, "row": 1, "value": 2, "ids": int}) rmse_svd_all = [] mae_svd_all = [] rmse_svd_neig_all = [] mae_svd_neig_all = [] RUNS = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] for run in RUNS: print "RUN(%d)" % run # Train & Test data train, test = data.split_train_test(percent=PERCENT_TRAIN) svd.set_data(train) svd_neig.set_data(train) # Compute SVD svd.compute(k=K, min_values=None, pre_normalize=None, mean_center=True, post_normalize=True) svd_neig.compute(k=K, min_values=None, pre_normalize=None, mean_center=True, post_normalize=True) # Evaluate rmse_svd = RMSE() mae_svd = MAE() rmse_svd_neig = RMSE() mae_svd_neig = MAE() i = 1 total = len(test.get()) print "Total Test ratings: %s" % total for rating, item_id, user_id in test:
# 'row': 1 -> Rows in matrix come from column 1 in ratings.dat file # 'col': 0 -> Cols in matrix come from column 0 in ratings.dat file # 'value': 2 -> Values (Mij) in matrix come from column 2 in ratings.dat file # 'ids': int -> Ids (row and col ids) are integers (not strings) #Create SVD list = [] for j in range(50,80,2): sum_value = 0.0 for i in range(1,11): #Train & Test data train, test = data.split_train_test(percent=PERCENT_TRAIN) K=j svd = SVDNeighbourhood() svd.set_data(train) svd.compute(k=K, min_values=5, pre_normalize=None, mean_center=True, post_normalize=True) #Evaluation using prediction-based metrics rmse = RMSE() mae = MAE() for rating, item_id, user_id in test.get(): try: pred_rating = svd.predict(item_id, user_id) rmse.add(rating, pred_rating) mae.add(rating, pred_rating) except KeyError: continue print 'RMSE=%s' % rmse.compute() sum_value = sum_value + rmse.compute()
'ids': int }) rmse_svd_all = [] mae_svd_all = [] rmse_svd_neig_all = [] mae_svd_neig_all = [] RUNS = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] for run in RUNS: print 'RUN(%d)' % run #Train & Test data train, test = data.split_train_test(percent=PERCENT_TRAIN) svd.set_data(train) svd_neig.set_data(train) #Compute SVD svd.compute(k=K, min_values=None, pre_normalize=None, mean_center=True, post_normalize=True) svd_neig.compute(k=K, min_values=None, pre_normalize=None, mean_center=True, post_normalize=True) # Evaluate rmse_svd = RMSE()
class Collaborative_filtering(object): def __init__(self, ratings_file, movies): #No need to pass as ,will be provided in views.py #self.users = users self.movies = movies self.K = 100 self.PERCENT_TRAIN = 85 #Need to provide a default file location for ratings.csv instead of loading everytime.run below 2lines only once #or just provide this file instead. #self.users.to_csv("/home/sourabhkondapaka/Desktop/ratingsss.csv",index= False) self.ratings_file = ratings_file #Give your path to ratings.csv created from above 2 lines. self.data = None self.svd = None self.recommend_movies_list = None self.recommend_movies_ids = None self.similar_movies_list = None self.similar_movies_ids = None self.movie_id = None self.train = None self.test = None def compute_svd(self): ''' ratings = pd.read_csv("/home/sourabhkondapaka/Desktop/ratingsss.csv",index_col= False) ratings = ratings.ix[1:] ratings.to_csv("/home/sourabhkondapaka/Desktop/ratingsss.csv",index = False) self.data = Data() self.data.load(self.ratings_file, sep=',', format={'col':0, 'row':1 ,'value':2, 'ids':float}) self.train , self.test = self.data.split_train_test(percent=self.PERCENT_TRAIN) self.svd = SVD() self.svd.set_data(self.train) self.svd.compute(k=self.K, min_values=1, pre_normalize=None, mean_center=True, post_normalize=True)''' self.data = Data() self.data.load(self.ratings_file, sep=',', format={ 'col': 0, 'row': 1, 'value': 2, 'ids': float }) self.train, self.test = self.data.split_train_test(percent=85) self.svd = SVDNeighbourhood() self.svd.set_data(self.train) self.svd.compute(k=100, min_values=1, pre_normalize=None, mean_center=False, post_normalize=True) def similarity_measure( self, movie1, movie2): #gives a similarity measure value between -1 to 1 return round(self.svd.similarity(movie1, movie2), 4) def recommend_movies(self, user_id): l = self.svd.recommend(user_id, n=10, only_unknowns=True, is_row=False) self.recommend_movies_list = [] self.recommend_movies_ids = [] for p in l: #movie names bb = str(movies.ix[movies['movie_id'] == p[0]]['title']).split() q = bb.index('Name:') bb = ' '.join(bb[1:q]) self.recommend_movies_list.append(bb) #movie ids gg = movies.ix[movies['movie_id'] == p[0]] gg = gg.reset_index() del gg['index'] gg = gg.ix[:, 0:2].as_matrix(columns=None).tolist() self.recommend_movies_ids.append(gg[0][0]) return self.recommend_movies_list, self.recommend_movies_ids def get_similar_movies(self, movie1): #Returns a PYTHON list for similar movies. movie1 = int(movie1) l = self.svd.similar(movie1) self.similar_movies_list = [] self.similar_movies_ids = [] l = l[1:] for p in l: #getting movie names bb = str(movies.ix[movies['movie_id'] == p[0]]['title']).split() q = bb.index('Name:') bb = ' '.join(bb[1:q]) self.similar_movies_list.append(bb) #getting movie id's self.similar_movies_ids.append(p[0]) return self.similar_movies_list, self.similar_movies_ids