def test_scaler_1d():
"""Test scaling of dataset along single axis"""
rng = np.random.RandomState(0)
X = rng.randn(5)
X_orig_copy = X.copy()
scaler = StandardScaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
# check inverse transform
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_array_almost_equal(X_scaled_back, X_orig_copy)
# Test with 1D list
X = [0., 1., 2, 0.4, 1.]
scaler = StandardScaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
X_scaled = scale(X)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
def test_scaler_without_centering():
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
X_csr = sparse.csr_matrix(X)
X_csc = sparse.csc_matrix(X)
assert_raises(ValueError, StandardScaler().fit, X_csr)
null_transform = StandardScaler(with_mean=False, with_std=False, copy=True)
X_null = null_transform.fit_transform(X_csr)
assert_array_equal(X_null.data, X_csr.data)
X_orig = null_transform.inverse_transform(X_null)
assert_array_equal(X_orig.data, X_csr.data)
scaler = StandardScaler(with_mean=False).fit(X)
X_scaled = scaler.transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
scaler_csr = StandardScaler(with_mean=False).fit(X_csr)
X_csr_scaled = scaler_csr.transform(X_csr, copy=True)
assert_false(np.any(np.isnan(X_csr_scaled.data)))
scaler_csc = StandardScaler(with_mean=False).fit(X_csc)
X_csc_scaled = scaler_csr.transform(X_csc, copy=True)
assert_false(np.any(np.isnan(X_csc_scaled.data)))
assert_equal(scaler.mean_, scaler_csr.mean_)
assert_array_almost_equal(scaler.std_, scaler_csr.std_)
assert_equal(scaler.mean_, scaler_csc.mean_)
assert_array_almost_equal(scaler.std_, scaler_csc.std_)
assert_array_almost_equal(X_scaled.mean(axis=0),
[0., -0.01, 2.24, -0.35, -0.78], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
X_csr_scaled_mean, X_csr_scaled_std = mean_variance_axis0(X_csr_scaled)
assert_array_almost_equal(X_csr_scaled_mean, X_scaled.mean(axis=0))
assert_array_almost_equal(X_csr_scaled_std, X_scaled.std(axis=0))
# Check that X has not been modified (copy)
assert_true(X_scaled is not X)
assert_true(X_csr_scaled is not X_csr)
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_true(X_scaled_back is not X)
assert_true(X_scaled_back is not X_scaled)
assert_array_almost_equal(X_scaled_back, X)
X_csr_scaled_back = scaler_csr.inverse_transform(X_csr_scaled)
assert_true(X_csr_scaled_back is not X_csr)
assert_true(X_csr_scaled_back is not X_csr_scaled)
assert_array_almost_equal(X_csr_scaled_back.toarray(), X)
X_csc_scaled_back = scaler_csr.inverse_transform(X_csc_scaled.tocsc())
assert_true(X_csc_scaled_back is not X_csc)
assert_true(X_csc_scaled_back is not X_csc_scaled)
assert_array_almost_equal(X_csc_scaled_back.toarray(), X)
def main():
args = parse()
n_rollout = args.nrollout
n_epoch = args.epoch
savename = args.savename if args.savename is not None else 'model-' + str(
n_rollout) + 'unroll'
np.random.seed(1098)
path = args.filename
names = ['target_pos', 'target_speed', 'pos', 'vel', 'effort']
with h5py.File(path, 'r') as f:
(target_pos, target_speed, pos, vel,
effort) = [[np.array(val) for val in f[name].values()]
for name in names]
x_target = np.array(target_pos)
x_first = np.array([pos_[0] for pos_ in pos])
x_speed = np.array(target_speed).reshape((-1, 1))
aux_output = [np.ones(eff.shape[0]).reshape((-1, 1)) for eff in effort]
x = np.concatenate((x_target, x_first, x_speed), axis=1)
input_scaler = StandardScaler()
x = input_scaler.fit_transform(x)
output_scaler = StandardScaler()
effort_concat = np.concatenate([a for a in effort], axis=0)
output_scaler.fit(effort_concat)
effort = [output_scaler.transform(eff) for eff in effort]
y = pad_sequences(effort, padding='post', value=0.)
aux_output = pad_sequences(aux_output, padding='post', value=0.)
x, x_test, y, y_test, y_aux, y_aux_test = train_test_split(x,
y,
aux_output,
test_size=0.2)
y_mask, y_test_mask = [this_y[:, :, 0] for this_y in (y_aux, y_aux_test)]
y_aux_mask, y_aux_test_mask = [
np.ones(this_y.shape[:2]) for this_y in (y_aux, y_aux_test)
]
model = MyModel(train=[x, [y, y_aux]],
val=[x_test, [y_test, y_aux_test]],
train_mask=[y_mask, y_aux_mask],
val_mask=[y_test_mask, y_aux_test_mask],
max_unroll=n_rollout,
name=savename)
if not os.path.exists('save'):
os.makedirs('save')
if args.train:
model.fit(nb_epoch=n_epoch, batch_size=32)
elif args.resume:
model.resume(nb_epoch=n_epoch, batch_size=32)
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_scaler_without_copy():
"""Check that StandardScaler.fit does not change input"""
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
X_csr = sparse.csr_matrix(X)
X_copy = X.copy()
StandardScaler(copy=False).fit(X)
assert_array_equal(X, X_copy)
X_csr_copy = X_csr.copy()
StandardScaler(with_mean=False, copy=False).fit(X_csr)
assert_array_equal(X_csr.toarray(), X_csr_copy.toarray())
def test_scale_sparse_with_mean_raise_exception():
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X_csr = sparse.csr_matrix(X)
# check scaling and fit with direct calls on sparse data
assert_raises(ValueError, scale, X_csr, with_mean=True)
assert_raises(ValueError, StandardScaler(with_mean=True).fit, X_csr)
# check transform and inverse_transform after a fit on a dense array
scaler = StandardScaler(with_mean=True).fit(X)
assert_raises(ValueError, scaler.transform, X_csr)
X_transformed_csr = sparse.csr_matrix(scaler.transform(X))
assert_raises(ValueError, scaler.inverse_transform, X_transformed_csr)
def prepare_time_data(data):
data_scaler = StandardScaler()
data_concat = np.concatenate(data, axis=0)
data_scaler.fit(data_concat)
new_data = [data_scaler.transform(data_) for data_ in data]
return data_scaler, new_data
def boston_DBSCAN(class_num=0):
'''给出Boston房价数据集中class_num类，数据形式为归一化数据列
:parameter
————
class_num:类号，读取函数所返回的类别号
:returns
————
x_boston:波士顿数据集中class_num类的自变量，归一化数据列，共13列
y_boston:波士顿数据集中class_num类自变量，归一化数据列，共1列
'''
# 读取全数据集
bostondata = load_boston()
boston_X = bostondata.data
boston_y = bostondata.target
boston_full = np.c_[boston_X, boston_y]
# 进行全数据集归一化
scale = StandardScaler()
boston_full = scale.fit_transform(boston_full)
# 数据集降维为3维，方便可视化调参。
pca = PCA(n_components=3)
boston_full3 = pca.fit_transform(boston_full)
# 分类
clt = DBSCAN(eps=0.8, min_samples=5, n_jobs=4)
label3 = clt.fit_predict(X=boston_full3)
# 给定输出数据
group0_boston = boston_full[label3 == 0]
x_boston = group0_boston[:, 0:-2]
y_boston = group0_boston[:, -1]
return x_boston, y_boston
def fit(self, x_train, y_train):
self.processing_steps = [StandardScaler()]
ann = MLPRegressor()
params = {
'hidden_layer_sizes': sp_randint(20, 150),
'alpha': sp_uniform(0, 100),
'max_iter': sp_randint(100, 2000),
'solver': ['lbfgs'],
# 'identity', 'logistic', 'tanh', 'relu'
'activation': ['relu']
}
if 'hidden_layer_sizes' in self.kwargs:
self.kwargs['hidden_layer_sizes'] = self.parsefunction(
self.kwargs['hidden_layer_sizes'])
params.update(self.kwargs)
clf = RandomizedSearchCV(estimator=ann,
param_distributions=params,
n_iter=10,
scoring=self.score['function'],
cv=3,
iid=True)
self._update_pipeline_and_fit(x_train, y_train, [clf])
def fit(self, x_train, y_train):
self.processing_steps = [StandardScaler()]
svr = SVR(kernel='rbf', gamma=0.1)
# http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf
# C = [2**i for i in np.arange(start=-5, stop=16, step=2)]
# gamma = [2**i for i in np.arange(start=-15, stop=4, step=2)]
# https://stats.stackexchange.com/questions/43943/
# which-search-range-for-determining-svm-optimal-c-
# and-gamma-parameters
C = [2**i for i in [-3, -2, -1, 0, 1, 2, 3, 4, 5]]
gamma = [2**i for i in [-5, -4, -3, -2, -1, 0, 1, 2, 3]]
params = {"C": sp_uniform(0.125, 32), "gamma": sp_uniform(0.03125, 8)}
params.update(self.kwargs)
reg = RandomizedSearchCV(estimator=svr,
param_distributions=params,
n_iter=10,
scoring=self.score['function'],
cv=3,
iid=True)
clf = MultiOutputRegressor(reg)
self._update_pipeline_and_fit(x_train, y_train, [clf])
def make_model(classifier, **params):
pipeline = Pipeline([
('feature_extractor', FeatureExtractor()),
('scaler', StandardScaler()),
('model', classifier(**params)),
])
return pipeline
def fit(self, data, args):
self.model = StandardScaler()
with Timer() as t:
self.model.fit(data.X_train, data.y_train)
return t.interval
def test_fit_transform():
rng = np.random.RandomState(0)
X = rng.random_sample((5, 4))
for obj in ((StandardScaler(), Normalizer(), Binarizer())):
X_transformed = obj.fit(X).transform(X)
X_transformed2 = obj.fit_transform(X)
assert_array_equal(X_transformed, X_transformed2)
def normalize_features(self, scaler: StandardScaler=None) \
-> StandardScaler:
'''
Normalizes the features of the dataset using a StandardScaler
(subtract mean, divide by standard deviation).
If a scaler is provided, uses that scaler to perform the normalization.
Otherwise fits a scaler to the features in the dataset and then
performs the normalization.
:param scaler: A fitted StandardScaler. Used if provided.
Otherwise a StandardScaler is fit on this dataset and is then used.
:param replace_nan_token: What to replace nans with.
:return: A fitted StandardScaler. If a scaler is provided, this is the
same scaler. Otherwise, this is a scaler fit on this dataset.
'''
if not self.data or not self.data[0].features:
return None
if not scaler:
scaler = StandardScaler()
features = np.vstack([d.features for d in self.data])
scaler.fit(features)
for d in self.data:
d.set_features(scaler.transform(d.features.reshape(1, -1))[0])
return scaler
def load_UCI_Credit_Card_data(infile=None, balanced=True, seed=5):
X = []
y = []
sids = []
with open(infile, "r") as fi:
fi.readline()
reader = csv.reader(fi)
for row in reader:
sids.append(row[0])
X.append(row[1:-1])
y0 = int(row[-1])
if y0 == 0:
y0 = -1
y.append(y0)
y = np.array(y)
if balanced:
X, y = balance_X_y(X, y, seed)
X = np.array(X, dtype=np.float32)
y = np.array(y, dtype=np.float32)
encoder = OneHotEncoder(categorical_features=[1, 2, 3])
encoder.fit(X)
X = encoder.transform(X).toarray()
X, y = shuffle_X_y(X, y, seed)
scale_model = StandardScaler()
X = scale_model.fit_transform(X)
return X, np.expand_dims(y, axis=1)
def get_data(args, logger, debug):
'''Get data.'''
# Get data:
train_data, val_data, test_data = _get_data(args, logger)
debug(f'train size = {len(train_data):,} | val size = {len(val_data):,} |'
f' test size = {len(test_data):,}')
if args.dataset_type == 'classification':
class_sizes = get_class_sizes(args.data_df)
debug('Class sizes')
debug(class_sizes)
# Scale features:
if args.features_scaling:
features_scaler = train_data.normalize_features()
val_data.normalize_features(features_scaler)
test_data.normalize_features(features_scaler)
else:
features_scaler = None
# Initialise scaler and scale training targets by subtracting mean and
# dividing standard deviation (regression only):
if args.dataset_type == 'regression':
debug('Fitting scaler')
scaler = StandardScaler()
targets = scaler.fit_transform(train_data.targets())
train_data.set_targets(targets)
else:
scaler = None
return train_data, val_data, test_data, scaler, features_scaler
def test_scaler_2d_arrays():
"""Test scaling of 2d array along first axis"""
rng = np.random.RandomState(0)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
scaler = StandardScaler()
X_scaled = scaler.fit(X).transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has been copied
assert_true(X_scaled is not X)
# check inverse transform
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_true(X_scaled_back is not X)
assert_true(X_scaled_back is not X_scaled)
assert_array_almost_equal(X_scaled_back, X)
X_scaled = scale(X, axis=1, with_std=False)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=1), 4 * [0.0])
X_scaled = scale(X, axis=1, with_std=True)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=1), 4 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=1), 4 * [1.0])
# Check that the data hasn't been modified
assert_true(X_scaled is not X)
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert_true(X_scaled is X)
X = rng.randn(4, 5)
X[:, 0] = 1.0 # first feature is a constant, non zero feature
scaler = StandardScaler()
X_scaled = scaler.fit(X).transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert_true(X_scaled is not X)
def _create_scaler(self, positivity):
self.scaler_positivity = positivity
if positivity is True:
eps = 1e-9
self._scaler = MinMaxScaler(feature_range=(eps, 1))
else:
self._scaler = StandardScaler()
self.scaler_is_fitted = False
def __stdScaler(self):
all_cols = list(self.data_df.columns.values)
for col in all_cols:
if col not in self.non_numeric_cols and col != 'time_to_failure':
stdScaler = StandardScaler()
stdScaler.fit(self.data_df[[col]])
self.data_df[col] = stdScaler.transform(self.data_df[[col]])
print('Standard Scaler applied ... ')
def preprocess(self):
sc = StandardScaler()
sc.fit(self.X_train)
X_train_std = sc.transform(self.X_train)
X_test_std = sc.transform(self.X_test)
self.train_dataset = self.Dataset(data=X_train_std,
target=self.y_train)
self.test_dataset = self.Dataset(data=X_test_std, target=self.y_test)
def test_theanets_regression():
check_regression(
TheanetsRegressor(layers=[3],
trainers=[dict(algo='rmsprop', **impatient)]),
**regressor_params)
check_regression(
TheanetsRegressor(scaler=StandardScaler(),
trainers=[dict(algo='rmsprop', **impatient)]),
**regressor_params)
def test_theanets_regression():
check_regression(
TheanetsRegressor(layers=[20],
trainers=[{
'optimize': 'rmsprop',
'min_improvement': 0.1
}]), **regressor_params)
check_regression(TheanetsRegressor(scaler=StandardScaler()),
**regressor_params)
def test_theanets_regression():
check_regression(
TheanetsRegressor(layers=[3],
trainers=[{
'algo': 'rmsprop',
'learning_rate': 0.1
}]), **regressor_params)
check_regression(TheanetsRegressor(scaler=StandardScaler()),
**regressor_params)
def load_scalers(path: str) -> Tuple[StandardScaler, StandardScaler]:
'''
Loads the scalers a model was trained with.
:param path: Path where model checkpoint is saved.
:return: A tuple with the data scaler and the features scaler.
'''
state = torch.load(path, map_location=lambda storage, loc: storage)
scaler = StandardScaler(state['data_scaler']['means'],
state['data_scaler']['stds']) \
if state['data_scaler'] else None
features_scaler = StandardScaler(state['features_scaler']['means'],
state['features_scaler']['stds']) \
if state['features_scaler'] else None
return scaler, features_scaler
def _proccess_input(self, target_pos, target_speed, pos, vel, effort):
x_target = np.array(target_pos)
x_first = np.array([pos_[0] for pos_ in pos])
x_speed = np.array(target_speed).reshape((-1, 1))
aux_output = [np.ones(eff.shape[0]).reshape((-1, 1)) for eff in effort]
x = np.concatenate((x_target, x_first, x_speed), axis=1)
input_scaler = StandardScaler()
x = input_scaler.fit_transform(x)
output_scaler = StandardScaler()
effort_concat = np.concatenate([a for a in effort], axis=0)
output_scaler.fit(effort_concat)
effort = [output_scaler.transform(eff) for eff in effort]
y = pad_sequences(effort, padding='post', value=0.)
aux_output = pad_sequences(aux_output, padding='post', value=0.)
x, x_test, y, y_test, y_aux, y_aux_test = train_test_split(x, y, aux_output, test_size=0.2)
return x, x_test, y, y_test, y_aux, y_aux_test
def test_warning_scaling_integers():
"""Check warning when scaling integer data"""
X = np.array([[1, 2, 0], [0, 0, 0]], dtype=np.uint8)
w = "assumes floating point values as input, got uint8"
clean_warning_registry()
assert_warns_message(UserWarning, w, scale, X)
assert_warns_message(UserWarning, w, StandardScaler().fit, X)
assert_warns_message(UserWarning, w, MinMaxScaler().fit, X)
def imputeAndScale(X_train,X_test):
imp= Imputer()
X_train=imp.fit_transform(X_train)
X_test=imp.transform(X_test)
scaler= StandardScaler().fit(X_train)
X_test=scaler.transform(X_test)
X_train= scaler.transform(X_train)
return X_train, X_test
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)
def test_warning_scaling_integers():
"""Check warning when scaling integer data"""
X = np.array([[1, 2, 0], [0, 0, 0]], dtype=np.uint8)
with warnings.catch_warnings(record=True):
warnings.simplefilter("always")
assert_warns(UserWarning, StandardScaler().fit, X)
with warnings.catch_warnings(record=True):
warnings.simplefilter("always")
assert_warns(UserWarning, MinMaxScaler().fit, X)
def scale_vars(df, mapper=None):
# TODO Try RankGauss: https://www.kaggle.com/c/porto-seguro-safe-driver-prediction/discussion/44629
warnings.filterwarnings('ignore',
category=sklearn.exceptions.DataConversionWarning)
if mapper is None:
# is_numeric_dtype will exclude categorical columns
map_f = [([n], StandardScaler()) for n in df.columns
if is_numeric_dtype(df[n])]
mapper = DataFrameMapper(map_f).fit(df)
df[mapper.transformed_names_] = mapper.transform(df).astype(np.float32)
return mapper
