def test_wrong_file_name():
"""Ensure file names are checked when creating a (custom) Dataset."""
wrong_files = [('does_not_exist', 'does_not_either')]
with pytest.raises(ValueError):
Dataset.load_from_folds(folds_files=wrong_files, reader=Reader(),
rating_scale=(1, 5))
def test_deprecated_way():
"""Test all Dataset constructors without passing rating_scale as a
parameter. Make sure we revert back to the Reader object, with a warning
message.
Also, make sure ValueError is raised if reader has no rating_scale in this
context.
Not using dataset fixtures here for more control.
"""
# test load_from_file
toy_data_path = (os.path.dirname(os.path.realpath(__file__)) +
'/custom_dataset')
with pytest.warns(UserWarning):
reader = Reader(line_format='user item rating', sep=' ', skip_lines=3,
rating_scale=(1, 5))
data = Dataset.load_from_file(file_path=toy_data_path,
reader=reader)
with pytest.raises(ValueError):
reader = Reader(line_format='user item rating', sep=' ', skip_lines=3,
rating_scale=None)
data = Dataset.load_from_file(file_path=toy_data_path,
reader=reader)
# test load_from_folds
train_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_train')
test_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_test')
with pytest.warns(UserWarning):
reader = Reader(line_format='user item rating timestamp', sep='\t',
rating_scale=(1, 5))
data = Dataset.load_from_folds([(train_file, test_file)], reader=reader)
with pytest.raises(ValueError):
reader = Reader(line_format='user item rating timestamp', sep='\t',
rating_scale=None)
data = Dataset.load_from_folds([(train_file, test_file)],
reader=reader)
# test load_from_df
ratings_dict = {'itemID': [1, 1, 1, 2, 2],
'userID': [9, 32, 2, 45, '10000'],
'rating': [3, 2, 4, 3, 1]}
df = pd.DataFrame(ratings_dict)
with pytest.warns(UserWarning):
reader = Reader(rating_scale=(1, 5))
data = Dataset.load_from_df(df[['userID', 'itemID', 'rating']],
reader=reader)
with pytest.raises(ValueError):
reader = Reader(rating_scale=None)
data = Dataset.load_from_df(df[['userID', 'itemID', 'rating']], # noqa
reader=reader)
def test_cross_validate(toy_data):
# First test with a specified CV iterator.
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
reader = Reader(line_format='user item rating', sep=' ', skip_lines=3)
data = Dataset.load_from_folds(folds_files=folds_files, reader=reader,
rating_scale=(1, 5))
algo = NormalPredictor()
pkf = ms.PredefinedKFold()
ret = ms.cross_validate(algo, data, measures=['rmse', 'mae'], cv=pkf,
verbose=1)
# Basically just test that keys (dont) exist as they should
assert len(ret['test_rmse']) == 1
assert len(ret['test_mae']) == 1
assert len(ret['fit_time']) == 1
assert len(ret['test_time']) == 1
assert 'test_fcp' not in ret
assert 'train_rmse' not in ret
assert 'train_mae' not in ret
# Test that 5 fold CV is used when cv=None
# Also check that train_* key exist when return_train_measures is True.
ret = ms.cross_validate(algo, toy_data, measures=['rmse', 'mae'], cv=None,
return_train_measures=True, verbose=True)
assert len(ret['test_rmse']) == 5
assert len(ret['test_mae']) == 5
assert len(ret['fit_time']) == 5
assert len(ret['test_time']) == 5
assert len(ret['train_rmse']) == 5
assert len(ret['train_mae']) == 5
def u1_ml100k():
"""Return a Dataset object that contains 10% of the u1 fold from movielens
100k. Trainset has 8000 ratings and testset has 2000.
"""
train_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_train')
test_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_test')
data = Dataset.load_from_folds([(train_file, test_file)],
Reader('ml-100k'), rating_scale=(1, 5))
return data
def get_rating_predictions(self, test_set, cluster_user_mapping=None):
self.test_set = test_set
test_path_tmp = "..\\resources\\tmp\\test_file.csv"
train_path_tmp = "..\\resources\\tmp\\train_file.csv"
self.train_set.to_csv(train_path_tmp, index=False, header=False)
self.test_set.to_csv(test_path_tmp, index=False, header=False)
fold_files = [(train_path_tmp, test_path_tmp)]
reader = Reader(rating_scale=(1, 10),
line_format='user item rating',
sep=',')
data = Dataset.load_from_folds(fold_files, reader=reader)
for trainset, testset in PredefinedKFold().split(data):
if cluster_user_mapping is None:
self.method.fit(trainset)
else:
df_users_in_clusters = pd.DataFrame.from_dict(
cluster_user_mapping)
df_cluser_users = df_users_in_clusters.groupby('')
#Distinct clusters:
clusters = list(set(cluster_user_mapping.values()))
#for cluster in clusters:
#cluster_train_data = trainset[trainset.userID.isin() userID]
pass
results = pd.DataFrame(columns=['userID', 'itemID', 'real', 'est'])
pbar = tqdm(total=len(self.test_set.index))
for key, val in self.test_set.iterrows():
prediction = self.method.predict(str(val.userID),
str(val.itemID),
clip=False)
results = results.append(
{
"userID": int(val.userID),
"itemID": int(val.itemID),
"real": int(val.rating),
"est": int(prediction.est)
},
ignore_index=True)
pbar.update(1)
pbar.close()
return results
def predict_rating_split_by_time(self, files_pair, algo_test):
algo = algo_test[0]
use_auto_parse = algo_test[1]
if use_auto_parse:
fold_files = [(files_pair)]
reader = Reader(rating_scale=(1, 10),
line_format='user item rating',
sep=',')
data = Dataset.load_from_folds(fold_files, reader=reader)
for trainset, testset in PredefinedKFold().split(data):
algo.fit(trainset)
predictions = algo.test(testset)
rmse = accuracy.rmse(predictions, verbose=False)
return rmse
else:
# Prepare dataset
train_set = pd.read_csv(files_pair[0], parse_dates=[3])
test_set = pd.read_csv(files_pair[1], parse_dates=[3])
item_to_id_mapping = {}
user_to_id_mapping = {}
item_index = 0
user_index = 0
all_sets = pd.concat([train_set, test_set])
for item in all_sets['itemID']:
if item not in item_to_id_mapping.keys():
item_to_id_mapping[item] = item_index
item_index += 1
for user in all_sets['userID']:
if user not in user_to_id_mapping.keys():
user_to_id_mapping[user] = user_index
user_index += 1
train_set['itemID'] = train_set['itemID'].map(item_to_id_mapping)
test_set['itemID'] = test_set['itemID'].map(item_to_id_mapping)
train_set['userID'] = train_set['userID'].map(user_to_id_mapping)
test_set['userID'] = test_set['userID'].map(user_to_id_mapping)
algo.fit(train_set)
rec_list = algo.get_top_n_recommendations(test_set)
pass
def get_top_n_recommendations(self, test_set, top_n):
self.test_set = test_set
test_path_tmp = "..\\resources\\tmp\\test_file.csv"
train_path_tmp = "..\\resources\\tmp\\train_file.csv"
self.train_set.to_csv(train_path_tmp, index=False, header=False)
self.test_set.to_csv(test_path_tmp, index=False, header=False)
fold_files = [(train_path_tmp, test_path_tmp)]
reader = Reader(rating_scale=(1, 10),
line_format='user item rating',
sep=',')
data = Dataset.load_from_folds(fold_files, reader=reader)
for trainset, testset in PredefinedKFold().split(data):
self.method.fit(trainset)
already_ranked_items_by_users = self.train_set.groupby(
'userID')['itemID'].apply(list)
recommendations = {}
pbar = tqdm(total=len(self.test_set.userID.unique()))
for userID in self.test_set.userID.unique():
pbar.update(1)
if userID not in self.train_set.userID.unique():
recommendations[str(userID)] = []
continue
items_expected_ranking = {}
for itemID in self.train_set.itemID.unique():
if itemID in already_ranked_items_by_users[userID]:
continue
# Calc prediction for item for user
predicted = self.method.predict(str(userID),
str(itemID),
clip=False)
items_expected_ranking[itemID] = predicted[3]
sorted_predictions = sorted(items_expected_ranking.items(),
key=operator.itemgetter(1))
sorted_predictions.reverse()
sorted_predictions = [str(x[0]) for x in sorted_predictions]
user_recommendations = sorted_predictions[:top_n]
recommendations[str(userID)] = user_recommendations
pbar.close()
return recommendations
def test_cross_validate():
# First test with a specified CV iterator.
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
reader = Reader(line_format='user item rating',
sep=' ',
skip_lines=3,
rating_scale=(1, 5))
data = Dataset.load_from_folds(folds_files=folds_files, reader=reader)
algo = NormalPredictor()
pkf = ms.PredefinedKFold()
ret = ms.cross_validate(algo,
data,
measures=[['neg_rmse', neg_rmse],
['neg_mae', neg_mae]],
cv=pkf,
verbose=1)
# Basically just test that keys (dont) exist as they should
assert len(ret['test_neg_rmse']) == 1
assert len(ret['test_neg_mae']) == 1
assert len(ret['fit_time']) == 1
assert len(ret['test_time']) == 1
assert 'test_fcp' not in ret
assert 'train_neg_rmse' not in ret
assert 'train_neg_mae' not in ret
# Test that 5 fold CV is used when cv=None
# Also check that train_* key exist when return_train_measures is True.
data = Dataset.load_from_file(current_dir + '/custom_dataset', reader)
ret = ms.cross_validate(algo,
data,
measures=[['neg_rmse', neg_rmse],
['neg_mae', neg_mae]],
cv=None,
return_train_measures=True,
verbose=True)
assert len(ret['test_neg_rmse']) == 5
assert len(ret['test_neg_mae']) == 5
assert len(ret['fit_time']) == 5
assert len(ret['test_time']) == 5
assert len(ret['train_neg_rmse']) == 5
assert len(ret['train_neg_mae']) == 5
def test_trainset_testset():
"""Test the construct_trainset and construct_testset methods."""
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
data = Dataset.load_from_folds(folds_files=folds_files, reader=reader)
for trainset, testset in data.folds():
pass # just need trainset and testset to be set
# test rm:
rm = trainset.rm
assert rm[0, 0] == 4
assert rm[1, 0] == 4
assert rm[3, 1] == 5
assert rm[40, 20000] == 0 # not in the trainset
# test ur
ur = trainset.ur
assert ur[0] == [(0, 4)]
assert ur[1] == [(0, 4), (1, 2)]
assert ur[40] == [] # not in the trainset
# test ir
ir = trainset.ir
assert ir[0] == [(0, 4), (1, 4), (2, 1)]
assert ir[1] == [(1, 2), (2, 1), (3, 5)]
assert ir[20000] == [] # not in the trainset
# test n_users, n_items, r_min, r_max
assert trainset.n_users == 4
assert trainset.n_items == 2
assert trainset.r_min == 1
assert trainset.r_max == 5
# test raw2inner: ensure inner ids are given in proper order
raw2inner_id_users = trainset._raw2inner_id_users
for i in range(4):
assert raw2inner_id_users['user' + str(i)] == i
raw2inner_id_items = trainset._raw2inner_id_items
for i in range(2):
assert raw2inner_id_items['item' + str(i)] == i
def test_PredifinedKFold():
reader = Reader(line_format='user item rating',
sep=' ',
skip_lines=3,
rating_scale=(1, 5))
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
data = Dataset.load_from_folds(folds_files=folds_files, reader=reader)
# Make sure rating files are read correctly
pkf = PredefinedKFold()
trainset, testset = next(pkf.split(data))
assert trainset.n_ratings == 6
assert len(testset) == 3
def test_PredifinedKFold(toy_data_reader):
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
data = Dataset.load_from_folds(folds_files=folds_files,
reader=toy_data_reader, rating_scale=(1, 5))
# Make sure rating files are read correctly
pkf = PredefinedKFold()
trainset, testset = next(pkf.split(data))
assert trainset.n_ratings == 6
assert len(testset) == 3
# Make sure pkf returns the same folds as the deprecated data.folds()
with pytest.warns(UserWarning):
trainset_, testset_ = next(data.folds())
assert testset_ == testset
def surprise_SVDpp(train_file, test_file):
"""
Svd++ with Surprise library.
Compute the predictions on a test_set after training on a train_set using the method Svd++ from Surprise.
Args:
train_file (string): path to created test file
test_file (string): path to created train file
Hyperparameters:
n_factors : The number of factors.
n_epochs : The number of iteration of the SGD procedure
lr_'x': The learning rate for 'x'
reg_'x' : The regularization term for 'x'
'x':
bi : The item biases
bu : The user biases
qi : The item factors
yj : The (implicit) item factors
pu : The user factors
Returns:
numpy array: predictions
"""
print("SVDpp")
fold = [(train_file, test_file)]
reader = Reader(line_format='user item rating', sep=',')
data = Dataset.load_from_folds(fold, reader=reader)
pkf = PredefinedKFold()
# Algorithm
algo = SVDpp(n_epochs=40, n_factors=100, lr_all=0.01, reg_all=0.01)
for trainset, testset in pkf.split(data):
# Train
algo.fit(trainset)
# Predict
predictions = algo.test(testset)
pred = np.zeros(len(predictions))
for i in range(len(predictions)):
val = predictions[i].est
pred[i] = val
return pred
def test_performances():
"""Test the returned dict. Also do dumping."""
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
reader = Reader(line_format='user item rating', sep=' ', skip_lines=3)
data = Dataset.load_from_folds(folds_files=folds_files, reader=reader,
rating_scale=(1, 5))
algo = NormalPredictor()
tmp_dir = tempfile.mkdtemp() # create tmp dir
with pytest.warns(UserWarning):
performances = evaluate(algo, data, measures=['RmSe', 'Mae'],
with_dump=True, dump_dir=tmp_dir, verbose=2)
shutil.rmtree(tmp_dir) # remove tmp dir
assert performances['RMSE'] is performances['rmse']
assert performances['MaE'] is performances['mae']
def test_PredifinedKFold(toy_data_reader):
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
data = Dataset.load_from_folds(folds_files=folds_files,
reader=toy_data_reader,
rating_scale=(1, 5))
# Make sure rating files are read correctly
pkf = PredefinedKFold()
trainset, testset = next(pkf.split(data))
assert trainset.n_ratings == 6
assert len(testset) == 3
# Make sure pkf returns the same folds as the deprecated data.folds()
with pytest.warns(UserWarning):
trainset_, testset_ = next(data.folds())
assert testset_ == testset
def test_gridsearchcv_best_estimator():
"""Ensure that the best estimator is the one giving the best score (by
re-running it)"""
train_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_train')
test_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_test')
data = Dataset.load_from_folds([(train_file, test_file)],
Reader('ml-100k'))
param_grid = {'n_epochs': [5], 'lr_all': [0.002, 0.005],
'reg_all': [0.4, 0.6], 'n_factors': [1], 'init_std_dev': [0]}
gs = GridSearchCV(SVD, param_grid, measures=['mae'],
cv=PredefinedKFold(), joblib_verbose=100)
gs.fit(data)
best_estimator = gs.best_estimator['mae']
# recompute MAE of best_estimator
mae = cross_validate(best_estimator, data, measures=['MAE'],
cv=PredefinedKFold())['test_mae']
assert mae == gs.best_score['mae']
def load_data(file_dict, dataformat): # 加载数据
if dataformat == "builtin":
data = Dataset.load_builtin(name=file_dict["name"], prompt=True)
elif dataformat == "file":
reader = Reader(line_format=file_dict["line_format"], sep=file_dict.get("sep", None),
rating_scale=file_dict.get("rating_scale", (1, 5)),
skip_lines=file_dict.get("skip_lines", 0))
data = Dataset.load_from_file(file_path=file_dict["file_path"], reader=reader)
elif dataformat == "dataframe":
reader = Reader(rating_scale=file_dict.get("rating_scale", (1, 5)))
data = Dataset.load_from_df(df=file_dict["df"][file_dict["header"]], reader=reader)
elif dataformat == "folds": # 已经进行k折交叉验证
files_dir = os.path.expanduser(file_dict["file_dir"])
reader = Reader(name=file_dict["name"])
train_file = files_dir + file_dict["train_name"]
test_file = files_dir + file_dict["test_name"]
folds_files = [(train_file % i, test_file % i) for i in file_dict["file_num"]]
print(folds_files)
data = Dataset.load_from_folds(folds_files=folds_files, reader=reader)
else:
ValueError("dataframe 超出了可处理的文件的类型范围")
return data
def test_knns():
"""Ensure the k and min_k parameters are effective for knn algorithms."""
# the test and train files are from the ml-100k dataset (10% of u1.base and
# 10 % of u1.test)
train_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_train')
test_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_test')
data = Dataset.load_from_folds([(train_file, test_file)],
Reader('ml-100k'))
# Actually, as KNNWithMeans and KNNBaseline have back up solutions for when
# there are not enough neighbors, we can't really test them...
klasses = (KNNBasic, ) # KNNWithMeans, KNNBaseline)
k, min_k = 20, 5
for klass in klasses:
algo = klass(k=k, min_k=min_k)
for trainset, testset in data.folds():
algo.fit(trainset)
predictions = algo.test(testset)
for pred in predictions:
if not pred.details['was_impossible']:
assert min_k <= pred.details['actual_k'] <= k
def func7():
import os
from surprise import SVD
from surprise import Dataset
from surprise import Reader
from surprise import accuracy
from surprise.model_selection import PredefinedKFold
files_dir = os.path.expanduser('~/.surprise_data/ml-100k/ml-100k/')
reader = Reader('ml-100k')
train_file = files_dir + 'u%d.base'
test_file = files_dir + 'u%d.test'
folds_files = [(train_file % i, test_file % i) for i in (1, 2, 3, 4, 5)]
data = Dataset.load_from_folds(folds_files, reader=reader)
pkf = PredefinedKFold()
algo = SVD()
for trainset, testset in pkf.split(data):
algo.fit(trainset)
predictions = algo.test(testset)
accuracy.rmse(predictions, verbose=True)
def basic_rec(model_name, train_path, test_path, target_id):
# build data
# TODO check float and min_r
reader = Reader(line_format='user item rating',
sep='\t',
rating_scale=(1, 5))
data = Dataset.load_from_folds([(train_path, test_path)], reader=reader)
trainset, testset = None, None
pkf = PredefinedKFold()
for trainset_, testset_ in pkf.split(data):
trainset, testset = trainset_, testset_
# train model
rec_algo = get_model(model_name)
rec_algo.fit(trainset)
# eval
preds = rec_algo.test(testset)
rmse = accuracy.rmse(preds, verbose=True)
# predor target
fn_pred = lambda uid: rec_algo.predict(str(uid), str(target_id), r_ui=0
).est
target_predictions = list(map(fn_pred, range(trainset.n_users)))
# topn
testset = trainset.build_anti_testset()
predictions = rec_algo.test(testset)
top_n = get_top_n(predictions, n=50)
hit_ratios = {}
for uid, user_ratings in top_n.items():
topN = [int(iid) for (iid, _) in user_ratings]
hits = [
1 if target_id in topN[:i] else 0 for i in [1, 3, 5, 10, 20, 50]
]
hit_ratios[int(uid)] = hits
return target_predictions, hit_ratios
for x in ratingRDD.collect():
ratingMap[(x[0], x[1])] = x[2]
# print("total data: " + str(len(ratingMap)))
# add avg business stars
# avgBusList = list()
# userRatingRDD = userRatingRDD.filter(lambda t: int(preUserMap[t[0]]) % 30 == 0)
# busRatingRDD = busRatingRDD.filter(lambda t: int(preBusinessMap[t[0]]) % 40 == 0)
# print("add user avg count: " + str(userRatingRDD.count()))
# print("add bus avg count: " + str(busRatingRDD.count()))
reader = Reader(line_format='user item rating', sep=",", skip_lines=1)
folds_files = [(trainingFilePath, validationFilePath)]
data = Dataset.load_from_folds(folds_files, reader=reader)
pkf = PredefinedKFold()
algo = SVD()
predictionList = list()
for trainset, testset in pkf.split(data):
# train and test algorithm.
algo.fit(trainset)
predictions = algo.test(testset)
for uid, iid, true_r, est, _ in predictions:
predictionList.append((uid, iid, est))
# Compute and print Root Mean Squared Error
accuracy.rmse(predictions, verbose=True)
from __future__ import (absolute_import, division, print_function,
unicode_literals)
import os
import pytest
from surprise import NMF
from surprise import Dataset
from surprise import Reader
from surprise import evaluate
# the test and train files are from the ml-100k dataset (10% of u1.base and
# 10 % of u1.test)
train_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_train')
test_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_test')
data = Dataset.load_from_folds([(train_file, test_file)], Reader('ml-100k'))
def test_NMF_parameters():
"""Ensure that all parameters are taken into account."""
# The baseline against which to compare.
algo = NMF(n_factors=1, n_epochs=1)
rmse_default = evaluate(algo, data, measures=['rmse'])['rmse']
# n_factors
algo = NMF(n_factors=2, n_epochs=1)
rmse_factors = evaluate(algo, data, measures=['rmse'])['rmse']
assert rmse_default != rmse_factors
# n_epochs
def test_trainset_testset():
"""Test the construct_trainset and construct_testset methods."""
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
data = Dataset.load_from_folds(folds_files=folds_files, reader=reader)
for trainset, testset in data.folds():
pass # just need trainset and testset to be set
# test ur
ur = trainset.ur
assert ur[0] == [(0, 4)]
assert ur[1] == [(0, 4), (1, 2)]
assert ur[40] == [] # not in the trainset
# test ir
ir = trainset.ir
assert ir[0] == [(0, 4), (1, 4), (2, 1)]
assert ir[1] == [(1, 2), (2, 1), (3, 5)]
assert ir[20000] == [] # not in the trainset
# test n_users, n_items, n_ratings, rating_scale
assert trainset.n_users == 4
assert trainset.n_items == 2
assert trainset.n_ratings == 6
assert trainset.rating_scale == (1, 5)
# test raw2inner
for i in range(4):
assert trainset.to_inner_uid('user' + str(i)) == i
with pytest.raises(ValueError):
trainset.to_inner_uid('unkown_user')
for i in range(2):
assert trainset.to_inner_iid('item' + str(i)) == i
with pytest.raises(ValueError):
trainset.to_inner_iid('unkown_item')
# test inner2raw
assert trainset._inner2raw_id_users is None
assert trainset._inner2raw_id_items is None
for i in range(4):
assert trainset.to_raw_uid(i) == 'user' + str(i)
for i in range(2):
assert trainset.to_raw_iid(i) == 'item' + str(i)
assert trainset._inner2raw_id_users is not None
assert trainset._inner2raw_id_items is not None
# Test the build_testset() method
algo = BaselineOnly()
algo.train(trainset)
testset = trainset.build_testset()
algo.test(testset) # ensure an algorithm can manage the data
assert ('user0', 'item0', 4) in testset
assert ('user3', 'item1', 5) in testset
assert ('user3', 'item1', 0) not in testset
# Test the build_anti_testset() method
algo = BaselineOnly()
algo.train(trainset)
testset = trainset.build_anti_testset()
algo.test(testset) # ensure an algorithm can manage the data
assert ('user0', 'item0', trainset.global_mean) not in testset
assert ('user3', 'item1', trainset.global_mean) not in testset
assert ('user0', 'item1', trainset.global_mean) in testset
assert ('user3', 'item0', trainset.global_mean) in testset
def test_wrong_file_name():
"""Ensure file names are checked when creating a (custom) Dataset."""
wrong_files = [('does_not_exist', 'does_not_either')]
with pytest.raises(ValueError):
Dataset.load_from_folds(folds_files=wrong_files, reader=reader)
from surprise import Dataset
from surprise import Reader
from surprise import accuracy
from surprise.model_selection import PredefinedKFold
# path to dataset folder
files_dir = os.path.expanduser('~/.surprise_data/ml-100k/ml-100k/')
# This time, we'll use the built-in reader.
reader = Reader('ml-100k')
# folds_files is a list of tuples containing file paths:
# [(u1.base, u1.test), (u2.base, u2.test), ... (u5.base, u5.test)]
train_file = files_dir + 'u%d.base'
test_file = files_dir + 'u%d.test'
folds_files = [(train_file % i, test_file % i) for i in (1, 2, 3, 4, 5)]
data = Dataset.load_from_folds(folds_files, reader=reader, rating_scale=(1, 5))
pkf = PredefinedKFold()
algo = SVD()
for trainset, testset in pkf.split(data):
# train and test algorithm.
algo.fit(trainset)
predictions = algo.test(testset)
# Compute and print Root Mean Squared Error
accuracy.rmse(predictions, verbose=True)
def k_recommend(model, k, testset):
reader = Reader(line_format='user item rating', sep=',', skip_lines=1)
fold_files = [('~/Desktop/Tufts/Fall2018/COMP135/Project3/trainset.csv',
'~/Desktop/Tufts/Fall2018/COMP135/Project3/testset.csv')]
pdkfold = sp.model_selection.split.PredefinedKFold()
clf = model.best_estimator['mae']
data = Dataset.load_from_folds(fold_files, reader=reader)
for train, test in pdkfold.split(data):
clf.fit(train)
test1 = train.build_anti_testset()
preds = clf.test(test1)
top_n = defaultdict(list)
for uid, iid, true_r, est, _ in preds:
top_n[uid].append((iid, est))
for uid, user_ratings in top_n.items():
user_ratings.sort(key=lambda x: x[1], reverse=True)
top_n[uid] = user_ratings[:k]
"""
for uid, user_ratings in top_n.items():
print(uid, [iid for (iid, _) in user_ratings])
for uid, user_ratings in top_n.items():
print uid, user_ratings
"""
for uid in top_n:
i = 0
for iid in top_n[uid]:
found = False
for iid2 in testset[uid]:
if iid[0] == str(iid2[0]):
a = iid[0]
top_n[uid].remove(top_n[uid][i])
top_n[uid].insert(i,(a, iid2[1]))
found = True
i += 1
break
if found == False:
a = iid[0]
top_n[uid].remove(top_n[uid][i])
top_n[uid].insert(i,(a, 2))
i += 1
total_sum = 0.0
user_sum = 0.0
us_rec = []
for uid in top_n:
i = 0.0
for iid in top_n[uid]:
i += 1.0
user_sum += iid[1]
total_sum += float(user_sum / i)
us_rec.append(user_sum / i)
user_sum = 0.0
#print us_rec
print "Average rating: ", (total_sum/float(len(top_n)))
def test_refit():
data_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_test')
data = Dataset.load_from_file(data_file, Reader('ml-100k'))
param_grid = {
'n_epochs': [5],
'lr_all': [0.002, 0.005],
'reg_all': [0.4, 0.6],
'n_factors': [2]
}
# assert gs.fit() and gs.test will use best estimator for mae (first
# appearing in measures)
gs = GridSearchCV(SVD,
param_grid,
measures=['mae', 'rmse'],
cv=2,
refit=True)
gs.fit(data)
gs_preds = gs.test(data.construct_testset(data.raw_ratings))
mae_preds = gs.best_estimator['mae'].test(
data.construct_testset(data.raw_ratings))
assert gs_preds == mae_preds
# assert gs.fit() and gs.test will use best estimator for rmse
gs = GridSearchCV(SVD,
param_grid,
measures=['mae', 'rmse'],
cv=2,
refit='rmse')
gs.fit(data)
gs_preds = gs.test(data.construct_testset(data.raw_ratings))
rmse_preds = gs.best_estimator['rmse'].test(
data.construct_testset(data.raw_ratings))
assert gs_preds == rmse_preds
# test that predict() can be called
gs.predict(2, 4)
# assert test() and predict() cannot be used when refit is false
gs = GridSearchCV(SVD,
param_grid,
measures=['mae', 'rmse'],
cv=2,
refit=False)
gs.fit(data)
with pytest.raises(ValueError):
gs_preds = gs.test(data.construct_testset(data.raw_ratings))
with pytest.raises(ValueError):
gs.predict('1', '2')
# test that error is raised if used with load_from_folds
train_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_train')
test_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_test')
data = Dataset.load_from_folds([(train_file, test_file)],
Reader('ml-100k'))
gs = GridSearchCV(SVD,
param_grid,
measures=['mae', 'rmse'],
cv=2,
refit=True)
with pytest.raises(ValueError):
gs.fit(data)
"""
Created on Fri Nov 6 09:40:38 2020
@author: sasha
"""
from surprise import Dataset, Reader
from surprise.model_selection import PredefinedKFold
from surprise import accuracy
from lsh_jaccard import lsh_jaccard
train_file_path = "train.csv"
test_file_path = "test.csv"
reader = Reader(line_format='user item rating timestamp', sep=',')
#data = Dataset.load_from_file(train_file_path, reader=reader)
data = Dataset.load_from_folds([(train_file_path, test_file_path)], reader=reader)
pkf = PredefinedKFold()
algo = lsh_jaccard(threshold = 0.1)
for trainset, testset in pkf.split(data):
# train and test algorithm.
algo.fit(trainset)
predictions = algo.test(testset)
# Compute and print Root Mean Squared Error
accuracy.rmse(predictions, verbose=True)
def test_trainset_testset():
"""Test the construct_trainset and construct_testset methods."""
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
data = Dataset.load_from_folds(folds_files=folds_files, reader=reader)
with pytest.warns(UserWarning):
trainset, testset = next(data.folds())
# test ur
ur = trainset.ur
assert ur[0] == [(0, 4, None)]
assert ur[1] == [(0, 4, None), (1, 2, None)]
assert ur[40] == [] # not in the trainset
# test ir
ir = trainset.ir
assert ir[0] == [(0, 4, None), (1, 4, None), (2, 1, None)]
assert ir[1] == [(1, 2, None), (2, 1, None), (3, 5, None)]
assert ir[20000] == [] # not in the trainset
# test n_users, n_items, n_ratings, rating_scale
assert trainset.n_users == 4
assert trainset.n_items == 2
assert trainset.n_ratings == 6
assert trainset.rating_scale == (1, 5)
# test user features
u_features = trainset.u_features
assert u_features[0] == [] # no u_features_df added
assert u_features[1] == [] # no u_features_df added
assert u_features[3] == [] # no u_features_df added
assert u_features[40] == [] # not in trainset and no u_features_df
assert trainset.user_features_labels == []
assert trainset.n_user_features == 0
# test item features
i_features = trainset.i_features
assert i_features[0] == [] # no i_features_df added
assert i_features[1] == [] # no i_features_df added
assert i_features[20000] == [] # not in trainset and no i_features_df
assert trainset.item_features_labels == []
assert trainset.n_item_features == 0
# test raw2inner
for i in range(4):
assert trainset.to_inner_uid('user' + str(i)) == i
with pytest.raises(ValueError):
trainset.to_inner_uid('unknown_user')
for i in range(2):
assert trainset.to_inner_iid('item' + str(i)) == i
with pytest.raises(ValueError):
trainset.to_inner_iid('unknown_item')
# test inner2raw
assert trainset._inner2raw_id_users is None
assert trainset._inner2raw_id_items is None
for i in range(4):
assert trainset.to_raw_uid(i) == 'user' + str(i)
for i in range(2):
assert trainset.to_raw_iid(i) == 'item' + str(i)
assert trainset._inner2raw_id_users is not None
assert trainset._inner2raw_id_items is not None
# Test the build_testset() method
algo = BaselineOnly()
algo.fit(trainset)
testset = trainset.build_testset()
algo.test(testset) # ensure an algorithm can manage the data
assert ('user0', 'item0', [], [], 4) in testset
assert ('user3', 'item1', [], [], 5) in testset
assert ('user3', 'item1', [], [], 0) not in testset
# Test the build_anti_testset() method
algo = BaselineOnly()
algo.fit(trainset)
testset = trainset.build_anti_testset()
algo.test(testset) # ensure an algorithm can manage the data
assert ('user0', 'item0', [], [], trainset.global_mean) not in testset
assert ('user3', 'item1', [], [], trainset.global_mean) not in testset
assert ('user0', 'item1', [], [], trainset.global_mean) in testset
assert ('user3', 'item0', [], [], trainset.global_mean) in testset
def run_knn_baseline(sparse_data):
#filename = "test.json"
prefix = "knn_baseline_"
trainFile = prefix + "train.txt"
testFile = prefix + "test.txt"
raw_data, userPurchasedSet, userTrueTestSet = preprocess(
sparse_data, trainFile, testFile)
folds_files = [(trainFile, testFile)]
reader = Reader(line_format='user item rating', sep='\t')
data = Dataset.load_from_folds(folds_files, reader=reader)
pkf = PredefinedKFold()
bsl_options = {
'method': 'sgd',
'n_epochs': 20,
'learning_rate': 0.005,
}
### sim name: cosine msd pearson pearson_baseline
### user_based : True ---- similarity will be computed based on users
### : False ---- similarity will be computed based on items.
sim_options = {'name': 'pearson_baseline', 'user_based': False}
predictions = {}
top_n = {}
testsSet = None
total_precisions = 0.0
total_recalls = 0.0
total_hit = 0.0
total_nDCG = 0.0
total_ffeature = 0.0
result_file = prefix + "result.txt"
result_f = open(result_file, "w")
for trainset, testset in pkf.split(data):
testsSet = testset
#algo = SVD(n_factors = 5)
algo = KNNBaseline(bsl_options=bsl_options, sim_options=sim_options)
algo.fit(trainset)
pre = algo.test(testset)
accuracy.rmse(pre)
accuracy.mae(pre)
#calculate_rmse(predictions)
### test
rowNum = raw_data.get_row_size()
colNum = raw_data.get_col_size()
cur_time = time.time()
time_cost = 0
for i in range(rowNum):
user = raw_data.get_userID(i)
predictions[user] = set()
pq = []
heapq.heapify(pq)
for j in range(colNum):
item = raw_data.get_itemID(j)
if user not in userPurchasedSet or item in userPurchasedSet[
user]:
continue
value = raw_data.get_val(user, item, 'rating')
predict = algo.predict(user, item, r_ui=0, verbose=False)[3]
if len(pq) >= 10:
heapq.heappop(pq)
heapq.heappush(pq, (predict, item))
top_n[user] = set()
for items in pq:
top_n[user].add(items[1])
if user in userTrueTestSet:
curPrecisions = calculate_precision(top_n[user],
userTrueTestSet[user])
curRecalls = calculate_recall(top_n[user],
userTrueTestSet[user])
ffeature = calculate_f_feature(curPrecisions, curRecalls)
curHit = isHit(top_n[user], userTrueTestSet[user])
cur_nDCG = calculate_NDCG(top_n[user], userTrueTestSet[user])
total_precisions += curPrecisions
total_recalls += curRecalls
total_hit += curHit
total_nDCG += cur_nDCG
total_ffeature += ffeature
result_f.write(user + "\t" + str(curPrecisions) + "\t" +
str(curRecalls) + "\t" + str(ffeature) + "\t" +
str(curHit) + '\t' + str(cur_nDCG) + "\n")
if i != 0 and i % 1000 == 0:
duration = (time.time() - cur_time) / 60
time_cost += duration
remaining_time = ((rowNum - i) / 1000) * duration
cur_time = time.time()
#print 'precisions', total_precisions, ' recalls', total_recalls, ' nDCG', total_nDCG
print 'i:', i, "/", rowNum, 'remaining time:', remaining_time, 'min'
print 'precicions', total_precisions, ' recalls', total_recalls, ' hit', total_hit, 'nDCG:', total_nDCG
rowNum = raw_data.get_row_size()
print 'avg_precisions:', total_precisions / rowNum, 'avg_recalls:', total_recalls / rowNum, 'avg_ffeature', str(
total_ffeature / rowNum
), 'avg_hit:', total_hit / rowNum, 'avg_nDCG:', total_nDCG / rowNum
result_f.write("avg:\t" + str(total_precisions / rowNum) + "\t" +
str(total_recalls / rowNum) + "\t" +
str(total_ffeature / rowNum) + "\t" +
str(total_hit / rowNum) + '\t' + str(total_nDCG / rowNum) +
"\n")
result_f.close()
def test_randomizedsearchcv_refit():
"""Test refit method of RandomizedSearchCV class."""
data_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_test')
data = Dataset.load_from_file(data_file, Reader('ml-100k'))
param_distributions = {
'n_epochs': [5],
'lr_all': uniform(0.002, 0.003),
'reg_all': uniform(0.4, 0.2),
'n_factors': [2]
}
# assert rs.fit() and rs.test will use best estimator for mae (first
# appearing in measures)
rs = RandomizedSearchCV(SVD,
param_distributions,
measures=['mae', 'rmse'],
cv=2,
refit=True)
rs.fit(data)
rs_preds = rs.test(data.construct_testset(data.raw_ratings))
mae_preds = rs.best_estimator['mae'].test(
data.construct_testset(data.raw_ratings))
assert rs_preds == mae_preds
# assert rs.fit() and rs.test will use best estimator for rmse
rs = RandomizedSearchCV(SVD,
param_distributions,
measures=['mae', 'rmse'],
cv=2,
refit='rmse')
rs.fit(data)
rs_preds = rs.test(data.construct_testset(data.raw_ratings))
rmse_preds = rs.best_estimator['rmse'].test(
data.construct_testset(data.raw_ratings))
assert rs_preds == rmse_preds
# test that predict() can be called
rs.predict(2, 4)
# assert test() and predict() cannot be used when refit is false
rs = RandomizedSearchCV(SVD,
param_distributions,
measures=['mae', 'rmse'],
cv=2,
refit=False)
rs.fit(data)
with pytest.raises(ValueError):
rs.test(data.construct_testset(data.raw_ratings))
with pytest.raises(ValueError):
rs.predict('1', '2')
# test that error is raised if used with load_from_folds
train_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_train')
test_file = os.path.join(os.path.dirname(__file__), './u1_ml100k_test')
data = Dataset.load_from_folds([(train_file, test_file)],
Reader('ml-100k'))
rs = RandomizedSearchCV(SVD,
param_distributions,
measures=['mae', 'rmse'],
cv=2,
refit=True)
with pytest.raises(ValueError):
rs.fit(data)
import numpy as np
import pandas as pd
from surprise import SVD, Dataset, Reader
from surprise.model_selection import PredefinedKFold
from matrix_vis import visualization
u_cols = ['movie_id', 'movie_title', 'unknown', 'action', 'adventure', 'animation', 'childrens', 'comedy', 'crime', 'documentary', 'drama', 'fantasy', 'film-noir', 'horror', 'musical', 'mystery', 'romance', 'sci-fi', 'thriller', 'war', 'western']
# users = pd.read_csv('data/movies.txt', sep='\t', names = u_cols, encoding = 'latin-1')
r_cols = ['user_id', 'movie_id', 'rating']
reader = Reader(line_format='user item rating', sep='\t')
data = Dataset.load_from_folds([('data/train.txt', 'data/test.txt')], reader=reader)
pkf = PredefinedKFold()
for trainset, testset in pkf.split(data):
algo = SVD()
algo.fit(trainset)
u = algo.pu
v = algo.qi
v = np.transpose(v)
a, _, _ = np.linalg.svd(v)
a = a[:2]
vplot = np.dot(a, v)
predictions = algo.test(testset)
print('method 2 error: %f' % accuracy.rmse(predictions)
movie_ratings = np.genfromtxt("data/summary.txt", names=True)
movie_titles = []
movie_data = []
with open("data/movies.txt", mode="r", encoding="ISO-8859-1") as f:
for line in f:
def test_trainset_testset_ui_features():
"""Test the construct_trainset and construct_testset methods with user and
item features."""
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
data = Dataset.load_from_folds(folds_files=folds_files, reader=reader)
u_features_df = pd.DataFrame(
{
'urid': ['user0', 'user2', 'user3', 'user1'],
'isMale': [False, True, False, True]
},
columns=['urid', 'isMale'])
data = data.load_features_df(u_features_df, user_features=True)
i_features_df = pd.DataFrame(
{
'irid': ['item0', 'item1'],
'isNew': [False, True],
'webRating': [4, 3],
'isComedy': [True, False]
},
columns=['irid', 'isNew', 'webRating', 'isComedy'])
data = data.load_features_df(i_features_df, user_features=False)
with pytest.warns(UserWarning):
trainset, testset = next(data.folds())
# test ur
ur = trainset.ur
assert ur[0] == [(0, 4, None)]
assert ur[1] == [(0, 4, None), (1, 2, None)]
assert ur[40] == [] # not in the trainset
# test ir
ir = trainset.ir
assert ir[0] == [(0, 4, None), (1, 4, None), (2, 1, None)]
assert ir[1] == [(1, 2, None), (2, 1, None), (3, 5, None)]
assert ir[20000] == [] # not in the trainset
# test n_users, n_items, n_ratings, rating_scale
assert trainset.n_users == 4
assert trainset.n_items == 2
assert trainset.n_ratings == 6
assert trainset.rating_scale == (1, 5)
# test user features
u_features = trainset.u_features
assert u_features[0] == [False]
assert u_features[40] == [] # not in trainset and u_features_df
assert trainset.user_features_labels == ['isMale']
assert trainset.n_user_features == 1
# test item features
i_features = trainset.i_features
assert i_features[0] == [False, 4, True]
assert i_features[20000] == [] # not in trainset and i_features_df
assert trainset.item_features_labels == ['isNew', 'webRating', 'isComedy']
assert trainset.n_item_features == 3
# test raw2inner
for i in range(4):
assert trainset.to_inner_uid('user' + str(i)) == i
with pytest.raises(ValueError):
trainset.to_inner_uid('unknown_user')
for i in range(2):
assert trainset.to_inner_iid('item' + str(i)) == i
with pytest.raises(ValueError):
trainset.to_inner_iid('unknown_item')
# test inner2raw
assert trainset._inner2raw_id_users is None
assert trainset._inner2raw_id_items is None
for i in range(4):
assert trainset.to_raw_uid(i) == 'user' + str(i)
for i in range(2):
assert trainset.to_raw_iid(i) == 'item' + str(i)
assert trainset._inner2raw_id_users is not None
assert trainset._inner2raw_id_items is not None
# Test the build_testset() method
algo = BaselineOnly()
algo.fit(trainset)
testset = trainset.build_testset()
algo.test(testset) # ensure an algorithm can manage the data
assert ('user0', 'item0', [False], [False, 4, True], 4) in testset
assert ('user2', 'item1', [True], [True, 3, False], 1) in testset
assert ('user3', 'item1', [False], [True, 3, False], 5) in testset
assert ('user3', 'item1', [False], [True, 3, False], 0) not in testset
# Test the build_anti_testset() method
algo = BaselineOnly()
algo.fit(trainset)
testset = trainset.build_anti_testset()
algo.test(testset) # ensure an algorithm can manage the data
assert (('user0', 'item0', [False], [False, 4, True], trainset.global_mean)
not in testset)
assert (('user3', 'item1', [False], [True, 3, False], trainset.global_mean)
not in testset)
assert (('user0', 'item1', [False], [True, 3, False], trainset.global_mean)
in testset)
assert (('user3', 'item0', [False], [False, 4, True], trainset.global_mean)
in testset)
def test_trainset_testset(toy_data_reader):
"""Test the construct_trainset and construct_testset methods."""
current_dir = os.path.dirname(os.path.realpath(__file__))
folds_files = [(current_dir + '/custom_train',
current_dir + '/custom_test')]
data = Dataset.load_from_folds(folds_files=folds_files,
reader=toy_data_reader, rating_scale=(1, 5))
with pytest.warns(UserWarning):
trainset, testset = next(data.folds())
# test ur
ur = trainset.ur
assert ur[0] == [(0, 4)]
assert ur[1] == [(0, 4), (1, 2)]
assert ur[40] == [] # not in the trainset
# test ir
ir = trainset.ir
assert ir[0] == [(0, 4), (1, 4), (2, 1)]
assert ir[1] == [(1, 2), (2, 1), (3, 5)]
assert ir[20000] == [] # not in the trainset
# test n_users, n_items, n_ratings, rating_scale
assert trainset.n_users == 4
assert trainset.n_items == 2
assert trainset.n_ratings == 6
assert trainset.rating_scale == (1, 5)
# test raw2inner
for i in range(4):
assert trainset.to_inner_uid('user' + str(i)) == i
with pytest.raises(ValueError):
trainset.to_inner_uid('unkown_user')
for i in range(2):
assert trainset.to_inner_iid('item' + str(i)) == i
with pytest.raises(ValueError):
trainset.to_inner_iid('unkown_item')
# test inner2raw
assert trainset._inner2raw_id_users is None
assert trainset._inner2raw_id_items is None
for i in range(4):
assert trainset.to_raw_uid(i) == 'user' + str(i)
for i in range(2):
assert trainset.to_raw_iid(i) == 'item' + str(i)
assert trainset._inner2raw_id_users is not None
assert trainset._inner2raw_id_items is not None
# Test the build_testset() method
algo = BaselineOnly()
algo.fit(trainset)
testset = trainset.build_testset()
algo.test(testset) # ensure an algorithm can manage the data
assert ('user0', 'item0', 4) in testset
assert ('user3', 'item1', 5) in testset
assert ('user3', 'item1', 0) not in testset
# Test the build_anti_testset() method
algo = BaselineOnly()
algo.fit(trainset)
testset = trainset.build_anti_testset()
algo.test(testset) # ensure an algorithm can manage the data
assert ('user0', 'item0', trainset.global_mean) not in testset
assert ('user3', 'item1', trainset.global_mean) not in testset
assert ('user0', 'item1', trainset.global_mean) in testset
assert ('user3', 'item0', trainset.global_mean) in testset
