def fit(self, data, args):
self.model = MaxAbsScaler()
with Timer() as t:
self.model.fit(data.X_train, data.y_train)
return t.interval
def test_maxabs_scaler_large_negative_value():
"""Check MaxAbsScaler on toy data with a large negative value"""
X = [[0., 1., +0.5, -1.0], [0., 1., -0.3, -0.5], [0., 1., -100.0, 0.0],
[0., 0., +0.0, -2.0]]
scaler = MaxAbsScaler()
X_trans = scaler.fit_transform(X)
X_expected = [[0., 1., 0.005, -0.5], [0., 1., -0.003, -0.25],
[0., 1., -1.0, 0.0], [0., 0., 0.0, -1.0]]
assert_array_almost_equal(X_trans, X_expected)
class MaxAbsScalerImpl():
def __init__(self, copy=True):
self._hyperparams = {'copy': copy}
self._wrapped_model = SKLModel(**self._hyperparams)
def fit(self, X, y=None):
if (y is not None):
self._wrapped_model.fit(X, y)
else:
self._wrapped_model.fit(X)
return self
def transform(self, X):
return self._wrapped_model.transform(X)
def test_maxabs_scaler_large_negative_value():
"""Check MaxAbsScaler on toy data with a large negative value"""
X = [[0., 1., +0.5, -1.0],
[0., 1., -0.3, -0.5],
[0., 1., -100.0, 0.0],
[0., 0., +0.0, -2.0]]
scaler = MaxAbsScaler()
X_trans = scaler.fit_transform(X)
X_expected = [[0., 1., 0.005, -0.5],
[0., 1., -0.003, -0.25],
[0., 1., -1.0, 0.0],
[0., 0., 0.0, -1.0]]
assert_array_almost_equal(X_trans, X_expected)
def fit(self, X, y=None):
self._sklearn_model = SKLModel(**self._hyperparams)
if (y is not None):
self._sklearn_model.fit(X, y)
else:
self._sklearn_model.fit(X)
return self
def test_maxabs_scaler_zero_variance_features():
"""Check MaxAbsScaler on toy data with zero variance features"""
X = [[0., 1., +0.5], [0., 1., -0.3], [0., 1., +1.5], [0., 0., +0.0]]
scaler = MaxAbsScaler()
X_trans = scaler.fit_transform(X)
X_expected = [[0., 1., 1.0 / 3.0], [0., 1., -0.2], [0., 1., 1.0],
[0., 0., 0.0]]
assert_array_almost_equal(X_trans, X_expected)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv)
# make sure new data gets transformed correctly
X_new = [[+0., 2., 0.5], [-1., 1., 0.0], [+0., 1., 1.5]]
X_trans_new = scaler.transform(X_new)
X_expected_new = [[+0., 2.0, 1.0 / 3.0], [-1., 1.0, 0.0], [+0., 1.0, 1.0]]
assert_array_almost_equal(X_trans_new, X_expected_new, decimal=2)
# sparse data
X_csr = sparse.csr_matrix(X)
X_trans = scaler.fit_transform(X_csr)
X_expected = [[0., 1., 1.0 / 3.0], [0., 1., -0.2], [0., 1., 1.0],
[0., 0., 0.0]]
assert_array_almost_equal(X_trans.A, X_expected)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv.A)
def test_warning_scaling_integers():
# Check warning when scaling integer data
X = np.array([[1, 2, 0], [0, 0, 0]], dtype=np.uint8)
w = "Data with input dtype uint8 was converted to float64"
clean_warning_registry()
assert_warns_message(DataConversionWarning, w, scale, X)
assert_warns_message(DataConversionWarning, w, StandardScaler().fit, X)
assert_warns_message(DataConversionWarning, w, MinMaxScaler().fit, X)
assert_warns_message(DataConversionWarning, w, MaxAbsScaler().fit, X)
class CreateMaxAbsScaler(CreateModel):
def fit(self, data, args):
self.model = MaxAbsScaler()
with Timer() as t:
self.model.fit(data.X_train, data.y_train)
return t.interval
def test(self, data):
assert self.model is not None
return self.model.transform(data.X_test)
def predict(self, data):
with Timer() as t:
self.predictions = self.test(data)
data.learning_task = LearningTask.REGRESSION
return t.interval
def make_models(X, y, y_bin):
return dict(ols=LinearRegression().fit(X, y),
lr_bin=LogisticRegression().fit(X, y_bin),
lr_ovr=LogisticRegression(multi_class='ovr').fit(X, y),
lr_mn=LogisticRegression(solver='lbfgs',
multi_class='multinomial').fit(X, y),
svc=SVC(kernel='linear').fit(X, y_bin),
svr=SVR(kernel='linear').fit(X, y),
dtc=DecisionTreeClassifier(max_depth=4).fit(X, y),
dtr=DecisionTreeRegressor(max_depth=4).fit(X, y),
rfc=RandomForestClassifier(n_estimators=3,
max_depth=3,
random_state=1).fit(X, y),
rfr=RandomForestRegressor(n_estimators=3,
max_depth=3,
random_state=1).fit(X, y),
gbc=GradientBoostingClassifier(n_estimators=3,
max_depth=3,
random_state=1).fit(X, y),
gbr=GradientBoostingRegressor(n_estimators=3,
max_depth=3,
random_state=1).fit(X, y),
abc=AdaBoostClassifier(algorithm='SAMME',
n_estimators=3,
random_state=1).fit(X, y),
abc2=AdaBoostClassifier(algorithm='SAMME.R',
n_estimators=3,
random_state=1).fit(X, y),
abc3=AdaBoostClassifier(algorithm='SAMME',
n_estimators=3,
random_state=1).fit(X, y_bin),
abc4=AdaBoostClassifier(algorithm='SAMME.R',
n_estimators=3,
random_state=1).fit(X, y_bin),
km=KMeans(1).fit(X),
km2=KMeans(5).fit(X),
pc1=PCA(1).fit(X),
pc2=PCA(2).fit(X),
pc3=PCA(2, whiten=True).fit(X),
mlr1=MLPRegressor([2], 'relu').fit(X, y),
mlr2=MLPRegressor([2, 1], 'tanh').fit(X, y),
mlr3=MLPRegressor([2, 2, 2], 'identity').fit(X, y),
mlc=MLPClassifier([2, 2], 'tanh').fit(X, y),
mlc_bin=MLPClassifier([2, 2], 'identity').fit(X, y_bin),
bin=Binarizer(0.5),
mms=MinMaxScaler().fit(X),
mas=MaxAbsScaler().fit(X),
ss1=StandardScaler().fit(X),
ss2=StandardScaler(with_mean=False).fit(X),
ss3=StandardScaler(with_std=False).fit(X),
n1=Normalizer('l1'),
n2=Normalizer('l2'),
n3=Normalizer('max'))
def test_maxabs_scaler_zero_variance_features():
"""Check MaxAbsScaler on toy data with zero variance features"""
X = [[0., 1., +0.5],
[0., 1., -0.3],
[0., 1., +1.5],
[0., 0., +0.0]]
scaler = MaxAbsScaler()
X_trans = scaler.fit_transform(X)
X_expected = [[0., 1., 1.0 / 3.0],
[0., 1., -0.2],
[0., 1., 1.0],
[0., 0., 0.0]]
assert_array_almost_equal(X_trans, X_expected)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv)
# make sure new data gets transformed correctly
X_new = [[+0., 2., 0.5],
[-1., 1., 0.0],
[+0., 1., 1.5]]
X_trans_new = scaler.transform(X_new)
X_expected_new = [[+0., 2.0, 1.0 / 3.0],
[-1., 1.0, 0.0],
[+0., 1.0, 1.0]]
assert_array_almost_equal(X_trans_new, X_expected_new, decimal=2)
# sparse data
X_csr = sparse.csr_matrix(X)
X_trans = scaler.fit_transform(X_csr)
X_expected = [[0., 1., 1.0 / 3.0],
[0., 1., -0.2],
[0., 1., 1.0],
[0., 0., 0.0]]
assert_array_almost_equal(X_trans.A, X_expected)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv.A)
('w2v_title_content', Word2VecTitleContent()),
('sw', StopWordsCount()),
('sw_title', StopWordsTitle()),
('pmi', PMI()),
# ('lda', LDAVectorContent()),
('CountingWords', CountingWords()),
# ('readability', ReadabilityFeatures()),
('typos', TyposCount()),
('english', EnglishInTitle()),
('pos', POSFeatures())
# ('fastext_sup', FastTextSupervised()),
# ('fast_text', FastTextAverageContentVector()),
# ('dicts', Dicts()),
# ('wmd', WMDDistance()),
])),
('scaler', MaxAbsScaler()),
('clf', LinearSVC(random_state=42))
])
# grid_search = GridSearchCV(pipe, tuned_parameters, cv=5,
# scoring='accuracy', verbose=1, n_jobs=-1)
# grid_search.fit(train, train['click_bait_score'])
# print(grid_search.best_params_)
print("training...")
pipe.fit_transform(train, train['click_bait_score'])
print("testing...")
score = pipe.score(test, test['click_bait_score'])
print(score)
'LassoLars':LassoLars(), 'LassoLarsCV':LassoLarsCV(), 'LassoLarsIC':LassoLarsIC(), 'LatentDirichletAllocation':LatentDirichletAllocation(), 'LedoitWolf':LedoitWolf(), 'LinearDiscriminantAnalysis':LinearDiscriminantAnalysis(), 'LinearRegression':LinearRegression(), 'LinearSVC':LinearSVC(), 'LinearSVR':LinearSVR(), 'LocallyLinearEmbedding':LocallyLinearEmbedding(), 'LogisticRegression':LogisticRegression(), 'LogisticRegressionCV':LogisticRegressionCV(), 'MDS':MDS(), 'MLPClassifier':MLPClassifier(), 'MLPRegressor':MLPRegressor(), 'MaxAbsScaler':MaxAbsScaler(), 'MeanShift':MeanShift(), 'MinCovDet':MinCovDet(), 'MinMaxScaler':MinMaxScaler(), 'MiniBatchDictionaryLearning':MiniBatchDictionaryLearning(), 'MiniBatchKMeans':MiniBatchKMeans(), 'MiniBatchSparsePCA':MiniBatchSparsePCA(), 'MultiTaskElasticNet':MultiTaskElasticNet(), 'MultiTaskElasticNetCV':MultiTaskElasticNetCV(), 'MultiTaskLasso':MultiTaskLasso(), 'MultiTaskLassoCV':MultiTaskLassoCV(), 'MultinomialNB':MultinomialNB(), 'NMF':NMF(), 'NearestCentroid':NearestCentroid(), 'NearestNeighbors':NearestNeighbors(), 'Normalizer':Normalizer(),
def __init__(self, copy=True):
self._hyperparams = {'copy': copy}
self._wrapped_model = SKLModel(**self._hyperparams)
