def test_SVD_parameters(u1_ml100k, pkf):
"""Ensure that all parameters are taken into account."""
# The baseline against which to compare.
algo = SVD(n_factors=1, n_epochs=1, random_state=1)
rmse_default = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
# n_factors
algo = SVD(n_factors=2, n_epochs=1, random_state=1)
rmse_factors = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_factors
# n_epochs
algo = SVD(n_factors=1, n_epochs=2, random_state=1)
rmse_n_epochs = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_n_epochs
# biased
algo = SVD(n_factors=1, n_epochs=1, biased=False, random_state=1)
rmse_biased = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_biased
# lr_all
algo = SVD(n_factors=1, n_epochs=1, lr_all=5, random_state=1)
rmse_lr_all = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_lr_all
# reg_all
algo = SVD(n_factors=1, n_epochs=1, reg_all=5, random_state=1)
rmse_reg_all = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_reg_all
# lr_bu
algo = SVD(n_factors=1, n_epochs=1, lr_bu=5, random_state=1)
rmse_lr_bu = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_lr_bu
# lr_bi
algo = SVD(n_factors=1, n_epochs=1, lr_bi=5, random_state=1)
rmse_lr_bi = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_lr_bi
# lr_pu
algo = SVD(n_factors=1, n_epochs=1, lr_pu=5, random_state=1)
rmse_lr_pu = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_lr_pu
# lr_qi
algo = SVD(n_factors=1, n_epochs=1, lr_qi=5, random_state=1)
rmse_lr_qi = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_lr_qi
# reg_bu
algo = SVD(n_factors=1, n_epochs=1, reg_bu=5, random_state=1)
rmse_reg_bu = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_reg_bu
# reg_bi
algo = SVD(n_factors=1, n_epochs=1, reg_bi=5, random_state=1)
rmse_reg_bi = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_reg_bi
# reg_pu
algo = SVD(n_factors=1, n_epochs=1, reg_pu=5, random_state=1)
rmse_reg_pu = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_reg_pu
# reg_qi
algo = SVD(n_factors=1, n_epochs=1, reg_qi=5, random_state=1)
rmse_reg_qi = cross_validate(algo, u1_ml100k, ['rmse'], pkf)['test_rmse']
assert rmse_default != rmse_reg_qi
"""
This module describes the most basic usage of Amaze: you define a prediction
algorithm, (down)load a dataset and run a cross-validation procedure.
"""
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from amaze import SVD
from amaze import Dataset
from amaze.model_selection import cross_validate
# Load the movielens-100k dataset (download it if needed),
data = Dataset.load_builtin('ml-100k')
# We'll use the famous SVD algorithm.
algo = SVD()
# Run 5-fold cross-validation and print results
cross_validate(algo, data, measures=['RMSE', 'MAE'], cv=5, verbose=True)
"""
This module describes how to use the train_test_split() function.
"""
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from amaze import SVD
from amaze import Dataset
from amaze import accuracy
from amaze.model_selection import train_test_split
# Load the movielens-100k dataset (download it if needed),
data = Dataset.load_builtin('ml-100k')
# sample random trainset and testset
# test set is made of 25% of the ratings.
trainset, testset = train_test_split(data, test_size=.25)
# We'll use the famous SVD algorithm.
algo = SVD()
# Train the algorithm on the trainset, and predict ratings for the testset
algo.fit(trainset)
predictions = algo.test(testset)
# Then compute RMSE
accuracy.rmse(predictions)
"""
This module descibes how to test the performances of an algorithm on the
trainset.
"""
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from amaze import Dataset
from amaze import SVD
from amaze import accuracy
from amaze.model_selection import KFold
data = Dataset.load_builtin('ml-100k')
algo = SVD()
trainset = data.build_full_trainset()
algo.fit(trainset)
testset = trainset.build_testset()
predictions = algo.test(testset)
# RMSE should be low as we are biased
accuracy.rmse(predictions, verbose=True) # ~ 0.68 (which is low)
# We can also do this during a cross-validation procedure!
print('CV procedure:')
kf = KFold(n_splits=3)
for i, (trainset_cv, testset_cv) in enumerate(kf.split(data)):
print('fold number', i + 1)