def calculate_stats_users(pct_train):
dat_file = 'user_data_working.csv'
data = Data()
data.load(dat_file,
sep=',',
format={
'col': 0,
'row': 1,
'value': 2,
'ids': int
})
train, test = data.split_train_test(percent=pct_train)
svd = SVD()
svd.set_data(train)
svd.compute(k=100,
min_values=2,
pre_normalize=None,
mean_center=True,
post_normalize=False)
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()
print 'MAE=%s\n' % mae.compute()
def ex1(dat_file='./ml-1m/ratings.dat',
pct_train=0.5):
data = Data()
data.load(dat_file, sep='::', format={'col':0, 'row':1, 'value':2,'ids':int})
# create train/test split
train, test = data.split_train_test(percent=pct_train)
# create svd
K=100
svd = SVD()
svd.set_data(train)
svd.compute(k=K, min_values=5, pre_normalize=None, mean_center=True, post_normalize=True)
# evaluate performance
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()
print 'MAE=%s' % mae.compute()
def evaluate(data, count=5, K=100):
results = []
for i in range(count):
train, test = data.split_train_test(percent=PERCENT_TRAIN)
print len(data.get()), len(train.get()), len(test.get())
#test_in_train(test, train)
#print train.get()
svd = SVD()
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:
#print "keyerror: ===========================================================>"
continue
try:
rsu = {}
rsu["RMSE"] = rmse.compute()
rsu["MAE"] = mae.compute()
print rsu
results.append(rsu)
except:
print "one error....++++++++++++++++++++++++++++++++++++++++++++++++++++"
return results
def __init__(self):
super(TestPrediction, self).__init__()
# Prediction-based metrics: MAE, RMSE, Pearson
self.mae = MAE(self.DATA_PRED)
self.rmse = RMSE(self.DATA_PRED)
self.R = 3 # Real Rating (ground truth)
self.R_PRED = 2.1 # Predicted Rating
def test_SVD(svd, train, test, pct_train):
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()
print 'MAE=%s\n' % mae.compute()
def eval_rmse(self):
# Evaluation using prediction-based metrics
rmse = RMSE()
mae = MAE()
for rating, item_id, user_id in self.test.get():
try:
pred_rating = self.svd.predict(item_id, user_id)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
except KeyError:
continue
print 'RMSE=%s' % rmse.compute()
print 'MAE=%s' % mae.compute()
def test_SVD(svd,train,test,pct_train):
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()
print 'MAE=%s\n' % mae.compute()
def eval_reco(model, test):
""" Compute RMSE and MAE on test set
"""
#Evaluation using prediction-based metrics
rmse = RMSE()
mae = MAE()
for rating, item_id, user_id in test.get():
try:
pred_rating = model.predict(item_id, user_id)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
except KeyError:
continue
return rmse, mae
def eval_reco(model, test):
""" Compute RMSE and MAE on test set
"""
#Evaluation using prediction-based metrics
rmse = RMSE()
mae = MAE()
for rating, item_id, user_id in test.get():
try:
pred_rating = model.predict(item_id, user_id)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
except KeyError:
continue
return rmse, mae
def ex1(dat_file=DATA_DIR + 'ml-1m-ratings.dat', pct_train=0.5):
data = Data()
data.load(dat_file,
sep='::',
format={
'col': 0,
'row': 1,
'value': 2,
'ids': int
})
# 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 train/test split
train, test = data.split_train_test(percent=pct_train)
# create svd
K = 100
svd = SVD()
svd.set_data(train)
svd.compute(k=K,
min_values=5,
pre_normalize=None,
mean_center=True,
post_normalize=True)
# evaluate performance
rmse = RMSE()
# mae is mean ABSOLUTE error
# ... in this case it will return 1.09 which means there is an error of almost 1 point out of 5
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()
print 'MAE=%s' % mae.compute()
def evaluate(_svd, _testData, verbose=False):
global rmse, mae, rating, item_id, user_id, pred_rating
rmse = RMSE()
mae = MAE()
for rating, item_id, user_id in _testData.get():
try:
pred_rating = _svd.predict(item_id, user_id, MIN_VALUE=0, MAX_VALUE=10)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
if verbose:
print item_id, user_id, rating, pred_rating
except Exception as e:
print 'ERROR occurred:', e.message
print 'RMSE=%s' % rmse.compute()
print 'MAE=%s' % mae.compute()
def __init__(self):
super(TestPrediction, self).__init__()
# Prediction-based metrics: MAE, RMSE, Pearson
self.mae = MAE(self.DATA_PRED)
self.rmse = RMSE(self.DATA_PRED)
self.R = 3 # Real Rating (ground truth)
self.R_PRED = 2.1 # Predicted Rating
def get_mae_rmse(step):
data = Data()
format = {'col': 1, 'row': 0, 'value': 2, 'ids': 'str'}
filename = 'second_train_test.dat.{step}'.format(step=step)
data.load(filename, sep='::', format=format)
train, test = data.split_train_test(percent=80)
try:
svd = SVD('svdn_model_{step}.zip'.format(step=step))
print('Loading model... {step}'.format(step=step))
except:
return
mae_predicted, rmse_predicted = [], []
for rating, item_id, user_id in test:
try:
predicted = svd.predict(item_id, user_id)
mae_predicted.append((rating, predicted))
rmse_predicted.append((rating, predicted))
except:
pass
mae_value, rmse_value = np.nan, np.nan
if len(mae_predicted) > 0:
mae = MAE(mae_predicted)
mae_value = mae.compute()
if len(rmse_predicted) > 0:
rmse = RMSE(rmse_predicted)
rmse_value = rmse.compute()
return mae_value, rmse_value
def __init__(self, filename, sep, **format):
# 文件信息
self.filename = filename
self.sep = sep
self.format = format
# 初始化矩阵分解
self.svd = SVD()
# 矩阵信息
self.k = 100 # 矩阵的隐因子睡昂
self.min_values = 10 # 删除评分少于10人的电影
self.post_normalize = False
# 设置是否加载模型标志
self.load_model = False
# 初始化均方误差
self.rmse = RMSE()
def test_random(data):
mae_predicted, rmse_predicted = [], []
for rating in data:
random_predicted = float(random_score(review_percentages))
mae_predicted.append((rating, random_predicted))
rmse_predicted.append((rating, random_predicted))
mae_value, rmse_value = np.nan, np.nan
if len(mae_predicted) > 0:
mae = MAE(mae_predicted)
mae_value = mae.compute()
if len(rmse_predicted) > 0:
rmse = RMSE(rmse_predicted)
rmse_value = rmse.compute()
return mae_value, rmse_value
def __init__(self, filename, sep, **format):
self.filename = filename
self.sep = sep
self.format = format
# 训练参数
self.k = 100
self.min_values = 10
self.post_normalize = True
self.svd = SVD()
# 判断是否加载
self.is_load = False
# 添加数据处理
self.data = Data()
# 添加模型评估
self.rmse = RMSE()
def calculate_stats_users(pct_train):
dat_file = 'user_data_working.csv'
data = Data()
data.load(dat_file, sep=',', format={'col':0, 'row':1, 'value':2,'ids':int})
train, test = data.split_train_test(percent=pct_train)
svd = SVD()
svd.set_data(train)
svd.compute(k=100, min_values=2, pre_normalize=None, mean_center=True,
post_normalize=False)
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()
print 'MAE=%s\n' % mae.compute()
def evaluate(clf, _testData, verbose = False):
rmse = RMSE()
mae = MAE()
numErrors = 0
for rating, item_id, user_id in _testData.get():
try:
pred_rating = clf.predict(item_id, user_id)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
if verbose:
print item_id, user_id, rating, pred_rating
except KeyError as e:
if verbose:
print 'ERROR occurred:', e.message
numErrors += 1
print '\n%i/%i data points raised errors.' % (numErrors, len(_testData))
print 'RMSE=%s' % rmse.compute()
print 'MAE=%s' % mae.compute()
def ex1(dat_file='ml-1m/ratings.dat',
pct_train=0.5):
data = Data()
data.load(dat_file, sep='::', format={'col':0, 'row':1, 'value':2,
'ids':int})
# 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 train/test split
train, test = data.split_train_test(percent=pct_train)
# create svd
K = 100
svd = SVD()
svd.set_data(train)
svd.compute(
k=K, min_values=5, pre_normalize=None, mean_center=True, post_normalize=True)
# evaluate performance
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()
print 'MAE=%s' % mae.compute()
def root_mean_square_error(train_values, predicted_values):
if len(train_values) != len(predicted_values):
sys.stderr.write("mean_absolute_error: Invalid list lengths")
exit(1)
rmse = RMSE()
rmse.load_ground_truth(train_values)
rmse.load_test(predicted_values)
return rmse.compute()
def test_PRED_RMSE_load_test(self):
rmse = RMSE()
self.TEST_DATA = [2.3, 0.9, 4.9, 0.9, 1.5]
rmse.load_test(self.TEST_DATA)
assert_equal(len(rmse.get_test()), len(self.TEST_DATA))
def test_PRED_RMSE_compute_one_empty_datasets(self):
rmse = RMSE()
assert_equal(rmse.compute(self.R, self.R_PRED), 0.9)
class TestPrediction(Test):
def __init__(self):
super(TestPrediction, self).__init__()
# Prediction-based metrics: MAE, RMSE, Pearson
self.mae = MAE(self.DATA_PRED)
self.rmse = RMSE(self.DATA_PRED)
self.R = 3 # Real Rating (ground truth)
self.R_PRED = 2.1 # Predicted Rating
# test_PRED MAE
def test_PRED_MAE_compute_one(self):
assert_equal(self.mae.compute(self.R, self.R_PRED), 0.9)
def test_PRED_MAE_compute_one_empty_datasets(self):
mae = MAE()
assert_equal(mae.compute(self.R, self.R_PRED), 0.9)
def test_PRED_MAE_compute_all(self):
assert_equal(self.mae.compute(), 0.7)
def test_PRED_MAE_nan(self):
mae = MAE()
mae.add(2.0, nan)
assert_equal(mae.get_test(), [])
assert_equal(mae.get_ground_truth(), [])
def test_PRED_MAE_load(self):
mae = MAE()
mae.load(self.GT_DATA, self.TEST_DATA)
assert_equal(mae.compute(), 0.7)
def test_PRED_MAE_load_test(self):
mae = MAE()
mae.load_test(self.TEST_DATA)
assert_equal(len(mae.get_test()), len(self.TEST_DATA))
assert_equal(len(mae.get_ground_truth()), 0)
assert_raises(ValueError, mae.compute) #Raise: GT is empty!
def test_PRED_MAE_load_test_and_ground_truth(self):
mae = MAE()
mae.load_test(self.TEST_DATA)
mae.load_ground_truth(self.GT_DATA)
assert_equal(mae.compute(), 0.7)
def test_PRED_MAE_add_entry(self):
self.mae.add(1, 4) #1: GT rating, 4: Predicted rating
assert_equal(len(self.mae.get_test()), len(self.DATA_PRED)+1)
assert_equal(self.mae.compute(), 1.083333)
def test_PRED_MAE_different_list_sizes(self):
mae = MAE()
GT = [3, 1, 5, 2]
# GT list has one element less than self.TEST_DATA
mae.load(GT, self.TEST_DATA)
assert_raises(ValueError, mae.compute)
# test_PRED RMSE
def test_PRED_RMSE_compute_one(self):
#Even though rmse has data, we only compute these two param values
assert_equal(self.rmse.compute(self.R, self.R_PRED), 0.9)
def test_PRED_RMSE_compute_one_empty_datasets(self):
rmse = RMSE()
assert_equal(rmse.compute(self.R, self.R_PRED), 0.9)
def test_PRED_RMSE_compute_all(self):
assert_equal(self.rmse.compute(), 0.891067)
def test_PRED_RMSE_load_test(self):
rmse = RMSE()
self.TEST_DATA = [2.3, 0.9, 4.9, 0.9, 1.5]
rmse.load_test(self.TEST_DATA)
assert_equal(len(rmse.get_test()), len(self.TEST_DATA))
def test_PRED_RMSE_add_entry(self):
self.rmse.add(1,4)
assert_equal(len(self.rmse.get_test()), len(self.DATA_PRED)+1)
assert_equal(self.rmse.compute(), 1.470261)
def test_PRED_RMSE_different_list_sizes(self):
rmse = RMSE()
GT = [3, 1, 5, 2]
# GT list has one element less than self.TEST_DATA
rmse.load(GT, self.TEST_DATA)
assert_raises(ValueError, rmse.compute)
def test_PRED_RMSE_numpy_array(self):
rmse = RMSE()
rmse.load(array(self.GT_DATA), array(self.TEST_DATA))
assert(rmse.compute(), 0.891067)
def test_PRED_RMSE_different_list_sizes(self):
rmse = RMSE()
GT = [3, 1, 5, 2]
# GT list has one element less than self.TEST_DATA
rmse.load(GT, self.TEST_DATA)
assert_raises(ValueError, rmse.compute)
dist[i] = sorted(dist[i], key=itemgetter(1), reverse=True)
#print str(i)+": "+str(item_id)
#print dist[i]
i += 1
#print dist
print "mean leng = "+str(statistics.mean(leng))
print "max leng = "+str(max(leng))
print "min leng = "+str(min(leng))
for k in range(3, 46):
print str(k)+"NN: "+str(p)+" fold..."
if k not in rmse.keys():
rmse[k] = []
result = RMSE()
i = 0
for rating, item_id, user_id in test:
if len(dist[i]) < 5:
if item_id in train_item.keys():
pred_rating = statistics.mean(train_item[item_id].values())
elif user_id in train_user.keys():
pred_rating = statistics.mean(train_user[user_id].values())
else:
pred_rating = average
else:
ratings = []
for j in range(0, k):
if j == len(dist[i]):
break
ratings.append(train_item[dist[i][j][0]][user_id])
#3.10
[items_full[str(x[0])].get_data() for x in films]
#3.11
get_name_item_reviewed(10,user_full,items_full)
#3.12
items_full[str(2628)].get_data()
users_for_star_wars = svd.recommend(2628,only_unknowns=True)
users_for_star_wars
#3.13
movies_reviewed_by_sw_rec =[get_name_item_reviewed(x[0],user_full,items_full) for x in users_for_star_wars]
movies_flatten = [movie for movie_list in movies_reviewed_by_sw_rec for movie in movie_list]
movie_aggregate = movies_by_category(movies_flatten, 3)
movies_sort = sorted(movie_aggregate,key=lambda x: x[1], reverse=True)
movies_sort
#3.14
from recsys.evaluation.prediction import RMSE
err = RMSE()
for rating, item_id, user_id in data.get():
try:
prediction = svd.predict(item_id, user_id)
err.add(rating, prediction)
except KeyError, k:
continue
print 'RMSE is ' + str(err.compute())
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:
try:
pred_rating_svd = svd.predict(item_id, user_id)
rmse_svd.add(rating, pred_rating_svd)
mae_svd.add(rating, pred_rating_svd)
pred_rating_svd_neig = svd_neig.predict(item_id,
user_id) #Koren & co.
def test_PRED_RMSE_compute_one_empty_datasets(self):
rmse = RMSE()
assert_equal(rmse.compute(self.R, self.R_PRED), 0.9)
#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()
print '-------'
print 'the k value is %s' %j
print 'Final RMSE=%s' % sum_value
print '-------'
def evaluate_matrices_rmse(self, original_matrix, imputed_matrix):
return self.evaluate_matrices(original_matrix,
imputed_matrix,
evaluator=RMSE())
from recsys.evaluation.prediction import RMSE, MAE
from recsys.datamodel.data import Data
from baseline import Baseline #Import the test class we've just created
#Dataset
PERCENT_TRAIN = int(sys.argv[2])
data = Data()
data.load(sys.argv[1], sep='::', format={'col':0, 'row':1, 'value':2, 'ids': int})
#Train & Test data
train, test = data.split_train_test(percent=PERCENT_TRAIN)
baseline = Baseline()
baseline.set_data(train)
baseline.compute() # In this case, it does nothing
# Evaluate
rmse = RMSE()
mae = MAE()
for rating, item_id, user_id in test.get():
try:
pred_rating = baseline.predict(item_id, user_id, user_is_row=False)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
except KeyError:
continue
print 'RMSE=%s' % rmse.compute() # in my case (~80% train, ~20% test set) returns RMSE = 1.036374
print 'MAE=%s' % mae.compute() # in my case (~80% train, ~20% test set) returns MAE = 0.829024
#Dataset
PERCENT_TRAIN = int(sys.argv[2])
data = Data()
data.load(sys.argv[1], sep='::', format={'col':0, 'row':1, 'value':2, 'ids':int})
#Train & Test data
train, test = data.split_train_test(percent=PERCENT_TRAIN)
svdlibc = SVDLIBC('./ml-1m/ratings.dat')
svdlibc.to_sparse_matrix(sep='::', format={'col':0, 'row':1, 'value':2, 'ids': int})
svdlibc.compute(k=100)
svd = svdlibc.export()
svd.save_model('/tmp/svd-model', options={'k': 100})
#svd.similar(ITEMID1) # results might be different than example 4. as there's no min_values=10 set here
#Evaluation using prediction-based metrics
print 'Evaluating...'
rmse = RMSE()
mae = MAE()
for rating, item_id, user_id in test.get():
try:
pred_rating = svd.predict(item_id, user_id, 0.0, 5.0)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
except KeyError:
continue
print 'RMSE=%s' % rmse.compute()
print 'MAE=%s' % mae.compute()
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:
try:
pred_rating_svd = svd.predict(item_id, user_id)
rmse_svd.add(rating, pred_rating_svd)
mae_svd.add(rating, pred_rating_svd)
pred_rating_svd_neig = svd_neig.predict(item_id, user_id) # Koren & co.
if pred_rating_svd_neig is not nan:
def test_PRED_RMSE_different_list_sizes(self):
rmse = RMSE()
GT = [3, 1, 5, 2]
# GT list has one element less than self.TEST_DATA
rmse.load(GT, self.TEST_DATA)
assert_raises(ValueError, rmse.compute)
def test_PRED_RMSE_numpy_array(self):
rmse = RMSE()
rmse.load(array(self.GT_DATA), array(self.TEST_DATA))
assert (rmse.compute(), 0.891067)
print ''
print 'GENERATING PREDICTION'
MIN_RATING = 0.0
MAX_RATING = 5.0
ITEMID = 1
USERID = 1
print svd.predict(ITEMID, USERID, MIN_RATING,
MAX_RATING) # predicted rating value
print svd.get_matrix().value(ITEMID, USERID) # real rating value
print ''
print 'GENERATING RECOMMENDATION'
print svd.recommend(USERID, n=5, only_unknowns=True, is_row=False)
#Evaluation using prediction-based metrics
rmse = RMSE()
mae = MAE()
spearman = SpearmanRho()
kendall = KendallTau()
#decision = PrecisionRecallF1()
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)
spearman.add(rating, pred_rating)
kendall.add(rating, pred_rating)
except KeyError:
continue
print ''
class TestPrediction(Test):
def __init__(self):
super(TestPrediction, self).__init__()
# Prediction-based metrics: MAE, RMSE, Pearson
self.mae = MAE(self.DATA_PRED)
self.rmse = RMSE(self.DATA_PRED)
self.R = 3 # Real Rating (ground truth)
self.R_PRED = 2.1 # Predicted Rating
# test_PRED MAE
def test_PRED_MAE_compute_one(self):
assert_equal(self.mae.compute(self.R, self.R_PRED), 0.9)
def test_PRED_MAE_compute_one_empty_datasets(self):
mae = MAE()
assert_equal(mae.compute(self.R, self.R_PRED), 0.9)
def test_PRED_MAE_compute_all(self):
assert_equal(self.mae.compute(), 0.7)
def test_PRED_MAE_nan(self):
mae = MAE()
mae.add(2.0, nan)
assert_equal(mae.get_test(), [])
assert_equal(mae.get_ground_truth(), [])
def test_PRED_MAE_load(self):
mae = MAE()
mae.load(self.GT_DATA, self.TEST_DATA)
assert_equal(mae.compute(), 0.7)
def test_PRED_MAE_load_test(self):
mae = MAE()
mae.load_test(self.TEST_DATA)
assert_equal(len(mae.get_test()), len(self.TEST_DATA))
assert_equal(len(mae.get_ground_truth()), 0)
assert_raises(ValueError, mae.compute) #Raise: GT is empty!
def test_PRED_MAE_load_test_and_ground_truth(self):
mae = MAE()
mae.load_test(self.TEST_DATA)
mae.load_ground_truth(self.GT_DATA)
assert_equal(mae.compute(), 0.7)
def test_PRED_MAE_add_entry(self):
self.mae.add(1, 4) #1: GT rating, 4: Predicted rating
assert_equal(len(self.mae.get_test()), len(self.DATA_PRED) + 1)
assert_equal(self.mae.compute(), 1.083333)
def test_PRED_MAE_different_list_sizes(self):
mae = MAE()
GT = [3, 1, 5, 2]
# GT list has one element less than self.TEST_DATA
mae.load(GT, self.TEST_DATA)
assert_raises(ValueError, mae.compute)
# test_PRED RMSE
def test_PRED_RMSE_compute_one(self):
#Even though rmse has data, we only compute these two param values
assert_equal(self.rmse.compute(self.R, self.R_PRED), 0.9)
def test_PRED_RMSE_compute_one_empty_datasets(self):
rmse = RMSE()
assert_equal(rmse.compute(self.R, self.R_PRED), 0.9)
def test_PRED_RMSE_compute_all(self):
assert_equal(self.rmse.compute(), 0.891067)
def test_PRED_RMSE_load_test(self):
rmse = RMSE()
self.TEST_DATA = [2.3, 0.9, 4.9, 0.9, 1.5]
rmse.load_test(self.TEST_DATA)
assert_equal(len(rmse.get_test()), len(self.TEST_DATA))
def test_PRED_RMSE_add_entry(self):
self.rmse.add(1, 4)
assert_equal(len(self.rmse.get_test()), len(self.DATA_PRED) + 1)
assert_equal(self.rmse.compute(), 1.470261)
def test_PRED_RMSE_different_list_sizes(self):
rmse = RMSE()
GT = [3, 1, 5, 2]
# GT list has one element less than self.TEST_DATA
rmse.load(GT, self.TEST_DATA)
assert_raises(ValueError, rmse.compute)
def test_PRED_RMSE_numpy_array(self):
rmse = RMSE()
rmse.load(array(self.GT_DATA), array(self.TEST_DATA))
assert (rmse.compute(), 0.891067)
def test_PRED_RMSE_numpy_array(self):
rmse = RMSE()
rmse.load(array(self.GT_DATA), array(self.TEST_DATA))
assert(rmse.compute(), 0.891067)
class RecommendSystem(object):
def __init__(self, filename, sep, **format):
# 文件信息
self.filename = filename
self.sep = sep
self.format = format
# 初始化矩阵分解
self.svd = SVD()
# 矩阵信息
self.k = 100 # 矩阵的隐因子睡昂
self.min_values = 10 # 删除评分少于10人的电影
self.post_normalize = False
# 设置是否加载模型标志
self.load_model = False
# 初始化均方误差
self.rmse = RMSE()
def get_data(self):
# 如果模型不存在，则需要加载数据
if not os.path.exists(filename):
if not os.path.exists(self.filename):
sys.exit()
# SVD加载数据
# self.svd.load_data(filename=self.filename, sep=self.sep, format=self.format)
data = Data()
data.load(self.filename, sep=self.sep, format=self.format)
# 分割数据集
train, test = data.split_train_test(percent=80)
return train, test
else:
# 直接加载模型
self.svd.load_model(filename)
# 将是否加载模型设为True
self.load_model = True
return None, None
def train(self, train):
"""
训练数据
:param train: 训练集
:return:
"""
if not self.load_model:
# svd去获取训练数据集
self.svd.set_data(train)
# 注意传入的文件名字，不是带后缀名
self.svd.compute(k=self.k,
min_values=self.min_values,
post_normalize=self.post_normalize,
savefile=filename[:-4])
return None
def recommend_to_user(self, userid):
"""
推荐结果
:param usrid: 用于ID
:return: None
"""
recommend_list = self.svd.recommend(userid, is_row=False)
# 打印电影的名称，和预测的评分
# 构建电影名字的列表
movies_list = []
for line in open("./data/ml-1m/movies.dat", "r"):
movies_list.append(' '.join(line.split("::")[1:2]))
# 依次取出推荐ID
for itemid, rating in recommend_list:
print "给你推荐的电影叫%s, 预测你对它的评分是%f" % (movies_list[itemid], rating)
return None
def rs_predict(self, userid, itemid):
"""
得出评分
:param userid: 用户ID
:param itemid: 物品ID
:return: 评分
"""
score = self.svd.predict(itemid, userid)
return score
def evaluation(self, test):
"""
均方误差评估模型
:param test: 测试数据
:return: None
"""
if not self.load_model:
# 获取测试数据中的id,rat, <rat, row(itemid), col(userid)>
for rating, itemid, userid in test.get():
try:
# rating真是值
score = self.rs_predict(userid, itemid)
# 添加所有的测试数据
self.rmse.add(rating, score)
except KeyError:
continue
error = self.rmse.compute()
print "均方误差为：%s" % error
return None
get_name_item_reviewed(10, user_full, items_full)
#3.12
items_full[str(2628)].get_data()
users_for_star_wars = svd.recommend(2628, only_unknowns=True)
users_for_star_wars
#3.13
movies_reviewed_by_sw_rec = [
get_name_item_reviewed(x[0], user_full, items_full)
for x in users_for_star_wars
]
movies_flatten = [
movie for movie_list in movies_reviewed_by_sw_rec for movie in movie_list
]
movie_aggregate = movies_by_category(movies_flatten, 3)
movies_sort = sorted(movie_aggregate, key=lambda x: x[1], reverse=True)
movies_sort
#3.14
from recsys.evaluation.prediction import RMSE
err = RMSE()
for rating, item_id, user_id in data.get():
try:
prediction = svd.predict(item_id, user_id)
err.add(rating, prediction)
except KeyError, k:
continue
print 'RMSE is ' + str(err.compute())
#Load SVD from /tmp
svd2 = SVD(filename='/tmp/movielens') # Loading already computed SVD model
#Predict User rating for given user and movie:
USERID = 2
ITEMID= 1 # Toy Story
rating1=svd2.predict(ITEMID, USERID, 0.0, 5.0)
print 'Predicted rating=%f'% rating1
flag=0
#Retrieve actual rating for given user and movie
for rating, item_id, user_id in data.get():
if user_id == USERID and item_id == ITEMID:
rat = rating
#print 'Actual rating=%f' % rating
flag=1
break
if flag == 1:
print 'Actual rating=%f'% rat
else :
sys.exit("No actual rating available")
#Evaluating prediction
rmse = RMSE()
mae = MAE()
rmse.add(rating1, rat)
mae.add(rating1, rat)
print 'RMSE=%s' % rmse.compute()
print 'MAE=%s' % mae.compute()
def test_PRED_RMSE_load_test(self):
rmse = RMSE()
self.TEST_DATA = [2.3, 0.9, 4.9, 0.9, 1.5]
rmse.load_test(self.TEST_DATA)
assert_equal(len(rmse.get_test()), len(self.TEST_DATA))
class RecommendSystem(object):
def __init__(self, filename, sep, **format):
self.filename = filename
self.sep = sep
self.format = format
# 训练参数
self.k = 100
self.min_values = 10
self.post_normalize = True
self.svd = SVD()
# 判断是否加载
self.is_load = False
# 添加数据处理
self.data = Data()
# 添加模型评估
self.rmse = RMSE()
def get_data(self):
"""
获取数据
:return: None
"""
# 如果模型不存在
if not os.path.exists(tmpfile):
# 如果数据文件不存在
if not os.path.exists(self.filename):
sys.exit()
# self.svd.load_data(filename=self.filename, sep=self.sep, format=self.format)
# 使用Data()来获取数据
self.data.load(self.filename, sep=self.sep, format=self.format)
train, test = self.data.split_train_test(percent=80)
return train, test
else:
self.svd.load_model(tmpfile)
self.is_load = True
return None, None
def train(self, train):
"""
训练模型
:param train: 训练数据
:return: None
"""
if not self.is_load:
self.svd.set_data(train)
self.svd.compute(k=self.k,
min_values=self.min_values,
post_normalize=self.post_normalize,
savefile=tmpfile[:-4])
return None
def rs_predict(self, itemid, userid):
"""
评分预测
:param itemid: 电影id
:param userid: 用户id
:return: None
"""
score = self.svd.predict(itemid, userid)
print "推荐的分数为：%f" % score
return score
def recommend_to_user(self, userid):
"""
推荐给用户
:param userid: 用户id
:return: None
"""
recommend_list = self.svd.recommend(userid, is_row=False)
# 读取文件里的电影名称
movie_list = []
for line in open(moviefile, "r"):
movie_list.append(' '.join(line.split("::")[1:2]))
# 推荐具体电影名字和分数
for itemid, rate in recommend_list:
print "给您推荐了%s,我们预测分数为%s" % (movie_list[itemid], rate)
return None
def evaluation(self, test):
"""
模型的评估
:param test: 测试集
:return: None
"""
# 如果模型不是直接加载
if not self.is_load:
# 循环取出测试集里面的元组数据<评分，电影，用户>
for value, itemid, userid in test.get():
try:
predict = self.rs_predict(itemid, userid)
self.rmse.add(value, predict)
except KeyError:
continue
# 计算返回误差（均方误差）
error = self.rmse.compute()
print "模型误差为%s:" % error
return None
s3 = 0
for item in items:
item_history = train_item[item].values()
mean = statistics.mean(item_history)
s1 += (train_item[item][user1]-mean)*(train_item[item][user2]-mean)
s2 += math.pow((train_item[item][user1]-mean), 2)
s3 += math.pow((train_item[item][user2]-mean), 2)
if math.sqrt(s2*s3) == 0:
return -sys.float_info.max
else:
return s1/(math.sqrt(s2*s3))
# Evaluate
k = 8
rmse = RMSE()
i = 0
for rating, item_id, user_id in test:
print "==========================================="
try:
print i
i += 1
dist = {}
if item_id in train_item.keys():
for user in train_item[item_id].keys():
sim = similarity(user_id, user)
if sim >= 0:
if len(dist) < k:
data.load(sys.argv[1],
sep='::',
format={
'col': 0,
'row': 1,
'value': 2,
'ids': int
})
#Train & Test data
train, test = data.split_train_test(percent=PERCENT_TRAIN)
baseline = Baseline()
baseline.set_data(train)
baseline.compute() # In this case, it does nothing
# Evaluate
rmse = RMSE()
mae = MAE()
for rating, item_id, user_id in test.get():
try:
pred_rating = baseline.predict(item_id, user_id, user_is_row=False)
rmse.add(rating, pred_rating)
mae.add(rating, pred_rating)
except KeyError:
continue
print 'RMSE=%s' % rmse.compute(
) # in my case (~80% train, ~20% test set) returns RMSE = 1.036374
print 'MAE=%s' % mae.compute(
) # in my case (~80% train, ~20% test set) returns MAE = 0.829024
