def test_score_samples(self):
X = self.iris['data']
y = self.iris['target']
param_grid = {'classifier__n_estimators': [100, 50]}
steps = [('classifier', RandomForestClassifier(random_state=42))]
pipe = Pipeline(steps).train()
tmp = GridSearchCV(
estimator=pipe,
param_grid=param_grid,
scoring='accuracy',
verbose=1,
)
tmp.fit(X, y)
def test_score_samples(self):
#Apply transforms, and score_samples of the final estimator.
pipe = Pipeline(self.kde_pipe).fit(self.data.df_devices)
tmp = pipe.score_samples(self.data.df_devices)
print(tmp)
def test_score(self):
#Apply transforms, and score with the final estimator
pipe = Pipeline(self.rf_pipe).fit(self.data.df_devices,
self.data.df_activities)
tmp = pipe.score(self.data.df_devices, self.data.df_activities)
print(tmp)
def test_predict_proba(self):
#Apply transforms, and predict_proba of the final estimator
pipe = Pipeline(self.rf_pipe).fit(self.data.df_devices,
self.data.df_activities)
tmp = pipe.predict_proba(self.data.df_devices)
print(tmp)
def test_get_params(self):
#Get parameters for this estimator.
pipe = Pipeline(self.rf_pipe)
tmp = pipe.get_params()
def test_fit_transform(self):
#Fit the model and transform with the final estimator
pipe = Pipeline(self.rf_pipe)
tmp = pipe.fit_transform(self.data.df_devices, self.data.df_activities)
def test_fit_predict(self):
# Applies fit_predict of last step in pipeline after transforms.
pipe = Pipeline(self.rf_pipe)
tmp = pipe.fit_predict(self.data.df_devices, self.data.df_activities)
print(tmp)
def test_fit(self):
pipe = Pipeline(self.rf_pipe)
tmp = pipe.fit(self.data.df_devices, self.data.df_activities)
split='leave_one_day_out')
"""
Example: Cross Validation
"""
ts = TimeSeriesSplit(n_splits=5)
scores = []
# cross validation on train set
for train_int, val_int in ts.split(X_train):
steps = [('enc', BinaryEncoder(encode='raw')),
('lbl', TrainOrEvalOnlyWrapper(LabelEncoder(idle=True))),
('drop_val', TrainOnlyWrapper(CVSubset(train_int))),
('drop_train', EvalOnlyWrapper(CVSubset(val_int))),
('drop_time_idx', DropTimeIndex()),
('classifier', RandomForestClassifier(random_state=42))]
pipe = Pipeline(steps).train()
pipe.fit(X_train, y_train)
# evaluate
pipe = pipe.eval()
scores.append(pipe.score(X_train, y_train))
print('scores of the pipeline: {}'.format(str(scores)))
print('mean score: {:.3f}'.format(np.array(scores).mean()))
"""
Simple Example Gridsearch
"""
from pyadlml.model_selection import GridSearchCV
param_grid = {
'encode_devices__encode': ['changepoint', 'raw', 'lastfired'],
('time_bin', TimeBinExtractor(one_hot_encoding=True)),
('pass_through', IdentityTransformer())
])
#('time_diff', TimeDifferenceExtractor())]
steps = [('encode_devices', BinaryEncoder()),
('fit_labels', TrainOrEvalOnlyWrapper(LabelEncoder())),
('feature_extraction', feature_extraction),
('select_train_set', TrainOnlyWrapper(CVSubset())),
('select_val_set', EvalOnlyWrapper(CVSubset())),
('drop_time_idx', DropTimeIndex()),
('drop_duplicates', TrainOnlyWrapper(DropDuplicates())),
('classifier', RandomForestClassifier(random_state=42))]
cv = KFold(n_splits=5)
pipe = Pipeline(steps).train()
with open('my_estimator.html', 'w') as f:
f.write(estimator_html_repr(pipe))
param_grid = {
#'encode_devices__encode': ['changepoint', 'raw', 'lastfired'],
'encode_devices__encode': ['raw'],
#'fit_labels__wr__idle': [True, False],
#'feature_extraction__time_bin__resolution': ['2h', '1h'],
#'feature_extraction__skip_day_of_week': [True, False]
}
tmp = steps[2][1]
pipe = Pipeline(steps).train()