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)
class KNNPlusSVD_lib:
def __init__(self, filename, K):
self.svd = SVDNeighbourhood()
self.K = K
self.svd.load_data(filename , sep=' ', format={'col':0, 'row':1, 'value':2, 'ids': int})
def predict(self, userId, itemId):
self.svd.compute(self.K, min_values=5, pre_normalize='all' , mean_center=True, post_normalize=None)
r = self.svd.predict(11, 33, weighted=True, MIN_VALUE=1.0, MAX_VALUE=5.0)
return r
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'))
def recommend_users(probID, SVDNeighbourhood=False): if SVDNeighbourhood: svd2 = SVDNeighbourhood() svd2.load_model(os.path.join(utils.get_add_dir(), 'ratings_neigh')) else: svd2 = SVD() svd2.load_model(os.path.join(utils.get_add_dir(), 'ratings')) return svd2.recommend(probID)
def predict_rating(probID, userID, MIN_RATING, MAX_RATING, SVDNeighbourhood=False): if SVDNeighbourhood: svd2 = SVDNeighbourhood() svd2.load_model(os.path.join(utils.get_add_dir(), 'ratings_neigh')) else: svd2 = SVD() svd2.load_model(os.path.join(utils.get_add_dir(), 'ratings')) return svd2.predict(probID, userID, MIN_RATING, MAX_RATING)
def get_similar_problems(probID, SVDNeighbourhood=False): if SVDNeighbourhood: svd2 = SVDNeighbourhood() svd2.load_model(os.path.join(utils.get_add_dir(), 'ratings_neigh')) else: svd2 = SVD() svd2.load_model(os.path.join(utils.get_add_dir(), 'ratings')) return svd2.similar(probID)
def recommend_problems(userID, SVDNeighbourhood=False): if SVDNeighbourhood: svd2 = SVDNeighbourhood() svd2.load_model(os.path.join(utils.get_add_dir(), 'ratings_neigh')) else: svd2 = SVD() svd2.load_model(os.path.join(utils.get_add_dir(), 'ratings')) problems = svd2.recommend(userID, n=20, only_unknowns=False, is_row=False) ret = [] data = load_data() for problem in problems: found = False for t in data: # print t, problem if t[1] == problem[0] and t[2] == 45: found = True break if not found: # print problem ret.append(problem) return ret
# 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 = []
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
# About format parameter:
# '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()
def __init__(self, filename, K):
self.svd = SVDNeighbourhood()
self.K = K
self.svd.load_data(filename , sep=' ', format={'col':0, 'row':1, 'value':2, 'ids': int})
if __name__ == "__main__":
# 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 = []
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
__author__ = 'ponomarevandrew'
from recsys.algorithm.factorize import SVDNeighbourhood
svd = SVDNeighbourhood()
svd.load_data(filename='ml-100k/u1.base', sep=' ', format={'col':0, 'row':1, 'value':2, 'ids': int})
K=30
svd.compute(k=K, min_values=5, pre_normalize='all' , mean_center=True, post_normalize=None)
print(svd.predict(11, 33, weighted=True, MIN_VALUE=1.0, MAX_VALUE=5.0))
# About format parameter:
# '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)
#Train & Test data
sum_value = 0.0
list = []
for j in range(0,300,50):
sum_value = 0.0
for i in range(1,11):
#Create SVD
K= j
train, test = data.split_train_test(percent=PERCENT_TRAIN)
svd = SVDNeighbourhood()
svd.set_data(train)
svd.compute(k=K, min_values=20, 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, weighted=True, MIN_VALUE=0.0, MAX_VALUE=5.0)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
except KeyError:
continue
print 'RMSE=%s' % rmse.compute()
sum_value = sum_value + rmse.compute()
