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)
# recommender = Recommender() # recommender.load_web_data('dataset', # [{'Запах женщины': 9, 'The Usual Suspects': 8, 'The Departed': 8, # 'Тутси': 7, 'Выпускник': 10, 'Залечь на дно в Брюгге': 4, 'Евротур': 7, # 'Goodfellas': 6, 'Донни Браско': 8, 'Амели': 3, 'Идиократия': 7}], # 100, 0, 10, 10) # recommender.load_local_data('dataset', K=100, min_values=0) # m = recommender.matrix.get_rating_matrix() # # m1 = recommender.get_predictions_for_all_users() from recsys.algorithm.factorize import SVDNeighbourhood svd = SVDNeighbourhood() svd.load_data('test_dataset', sep=' ', format={ 'col': 1, 'row': 0, 'value': 2, 'ids': int }) svd.compute(100, 0) print svd.predict(108, 698) # svd.load_data(filename=sys.argv[1], sep='::', format={'col':0, 'row':1, 'value':2, 'ids': int}) # K=100 # svd.compute(k=K, min_values=5, pre_normalize=None, mean_center=True, post_normalize=True)
import sys from numpy import nan, mean #To show some messages: import recsys.algorithm recsys.algorithm.VERBOSE = True from recsys.algorithm.factorize import SVD, SVDNeighbourhood from recsys.datamodel.data import Data from recsys.evaluation.prediction import RMSE, MAE # Create SVD K = 100 svd = SVD() svd_neig = SVDNeighbourhood() #Dataset PERCENT_TRAIN = int(sys.argv[2]) 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 = []