def test_run():
for m in [rfc, dtc]:
print(model_name(m))
m.fit(x_train, y_train)
print('score in and out of sample', m.score(x_train, y_train),
m.score(x_test, y_test))
y_proba = m.predict_proba(x_test)[:, 1]
print(roc_auc_score(y_test, y_proba))
def test_run():
for m in [rfc, dtc, logit]:
print(model_name(m))
m.fit(x_train, y_train)
print(m.classes_)
print('score in and out of sample', m.score(x_train, y_train),
m.score(x_test, y_test))
y_proba = m.predict_proba(x_test)
print(roc_auc_score(y2_test, y_proba, None))
def test_run():
for m in [rfc, dtc, logit]:
print(model_name(m))
print(cross_val_score(m, x, y, scoring="accuracy", cv=cv))
print(cross_val_score(m, x, y, scoring=accuracy_at_proba(1 / 3),
cv=cv))
print(cross_val_score(m, x, y, scoring=coverage_at_proba(1 / 3),
cv=cv))
print(cross_val_score(m, x, y, scoring="avg_roc_auc_macro", cv=cv))
print(cross_val_score(m, x, y, scoring="avg_roc_auc_micro", cv=cv))
def test_run():
for m in models:
reg, n_iter, params = m
gs = RandomizedSearchCV(reg,
param_distributions=params,
cv=cvs.split(x),
verbose=1,
n_iter=n_iter)
gs.fit(x, y)
print(model_name(reg), gs.best_score_)
def get_pipeline(est, is_tree, is_regressor, params):
name = model_name(est)
if name.startswith('Dummy'):
ppl = Pipeline([
('ft', FunctionTransformer()),
('mo', est)
])
params['ft__func'] = [lambda x:x[numeric_cols(x)]]
params['ft__validate'] = [False]
elif is_tree:
ppl = Pipeline([
('da', DateEncoder()),
('du', OrdinalEncoder()),
('ft', FunctionTransformer()),
('se', SelectKBest2()),
('mo', est)
])
params['da__ascategory'] = [False]
params['du__drop_invariant'] = [True]
params['ft__func'] = [lambda x:x.fillna(-999)]
params['ft__validate'] = [False]
params['se__score_func'] = get_selector(is_regressor, is_tree)
params['se__k'] = [0.2, 0.5, 0.8, 1000, 1000]
else:
ppl = Pipeline([
('da', DateEncoder()),
('en', FeatureUnion([
('nu', Pipeline([('ft', FunctionTransformer()), ('in', Imputer()), ('sc', TransformerWrap(StandardScaler()))])),
('ca', Pipeline([('ft', FunctionTransformer()), ('sc', SparseCatEncoder())]))
])),
('fu', FeatureUnion([('se', SelectKBest2()), ('dr', TruncatedSVD2())])),
('mo', est)
])
params['en__nu__ft__func'] = [lambda x:x[numeric_cols(x)]]
params['en__nu__ft__validate'] = [False]
params['en__ca__ft__func'] = [lambda x:x[object_cols(x)]]
params['en__ca__ft__validate'] = [False]
params['fu__se__score_func'] = get_selector(is_regressor, is_tree)
params['fu__se__k'] = [0.2, 0.5, 0.8, 1000]
params['fu__dr__k'] = [0.2, 0.5, 0.8, 1000]
return name, ppl, params