def test_complex_grid_search():
# build a pipeline
pipe = Pipeline([
('dropper', FeatureFilter()), # won't drop any
('collinearity', MultiCorrFilter(threshold=0.85)),
('imputer', SelectiveImputer()), # pass through since all full
('scaler', SelectiveMaxAbsScaler()),
('boxcox', BoxCoxTransformer(suppress_warnings=True)),
('nzv', NearZeroVarianceFilter()),
('pca', SelectivePCA(n_components=0.9)),
('custom', make_transformer(subtract_k, k=1)),
('model', RandomForestClassifier(n_jobs=1))
])
# let's define a set of hyper-parameters over which to search
hp = {
'collinearity__threshold': uniform(loc=.8, scale=.15),
'collinearity__method': ['pearson', 'kendall', 'spearman'],
'pca__n_components': uniform(loc=.75, scale=.2),
'pca__whiten': [True, False],
'custom__k': [1, 2, 3],
'custom__func': [subtract_k, add_k],
'model__n_estimators': randint(5, 10),
'model__max_depth': randint(2, 5),
'model__min_samples_leaf': randint(1, 5),
'model__max_features': uniform(loc=.5, scale=.5),
'model__max_leaf_nodes': randint(10, 15)
}
# define the gridsearch
search = RandomizedSearchCV(
pipe,
hp,
n_iter=2, # just to test it even works
scoring='accuracy',
cv=cv,
random_state=42,
# in parallel so we are testing pickling of the classes
n_jobs=2)
# fit the search
search.fit(X_train, y_train)
# Show we can profile the best estimator
profile_estimator(search.best_estimator_)
# Assert that it's persistable
assert_persistable(pipe, "location.pkl", X_train, y_train)
def test_haversine_persistable():
assert_persistable(
HaversineFeatures(cols=[('from_lat', 'from_lon'), ('to_lat',
'to_lon')]),
"location.pkl", X)
def test_schema_persistable():
assert_persistable(SchemaNormalizer(schema), "location.pkl", X)
def test_date_transformer_persistable():
assert_persistable(
DateTransformer(cols=["b", "c", "d"],
date_format=["%m/%d/%Y", None, None]), "location.pkl",
df)
def test_all_persistable():
for est in (BoxCoxTransformer, YeoJohnsonTransformer):
assert_persistable(est(), "location.pkl", X)
def test_all_persistable():
for est in (SelectiveStandardScaler, SelectiveRobustScaler,
SelectiveMinMaxScaler, SelectiveMaxAbsScaler):
assert_persistable(est(), "location.pkl", X)
def test_all_persistable():
for est in (SelectivePCA, SelectiveTruncatedSVD, SelectiveNMF,
SelectiveKernelPCA, SelectiveIncrementalPCA):
assert_persistable(est(), location="location.pkl", X=X)
def test_all_persistable():
for est in (FeatureFilter, SparseFeatureFilter, MultiCorrFilter,
NearZeroVarianceFilter):
assert_persistable(est(), location="loc.pkl", X=iris)
def test_classifier_imputers_persistable():
for est in (BaggedClassifierImputer, ):
assert_persistable(est(cols=['label'], random_state=42),
"location.pkl", Y)
def test_regressor_imputers_persistable():
for est in (SelectiveImputer, BaggedRegressorImputer):
assert_persistable(est(), "location.pkl", X)
def test_binning_persistable():
assert_persistable(BinningTransformer(), "location.pkl", iris)
def test_interaction_persistable():
assert_persistable(InteractionTermTransformer(cols=['a', 'b']),
location='loc.pkl',
X=X_pd)
def test_combos_persistable():
assert_persistable(LinearCombinationFilter(), location="loc.pkl", X=X)
def test_time_deltas_persistable():
assert_persistable(TimeDeltaFeatures(cols=['b', 'c']),
location='loc.pkl',
X=df2)
def test_date_factorizer_persistable():
assert_persistable(DateFactorizer(cols=['b']), location="loc.pkl", X=df)
def test_dummy_persistable():
assert_persistable(DummyEncoder(cols=iris.columns.tolist()),
"location.pkl", iris)
