def test_categorical_indicators(self):
self.data['categorical'] = map(str, range(10))
model_def = ModelDefinition(features=[Map('categorical', list), F('a'), Map('b', np.abs)],
target='y',
categorical_indicators=False)
x, ff = build_featureset_safe(model_def.features, self.data)
self.assertEqual(len(x.columns), len(model_def.features))
self.data['categorical'] = map(str, range(10))
model_def = ModelDefinition(features=[Map('categorical', np.abs), F('a'), Map('b', np.abs)],
target='y',
categorical_indicators=True)
x, ff = build_featureset_safe(model_def.features, self.data)
self.assertEqual(len(x.columns), len(model_def.features) + 9)
def generate_train(model_def, data, prep_index=None, train_index=None):
# create training set
data, prep_index, train_index = filter_data_and_indexes(model_def, data, prep_index, train_index)
x_train, fitted_features = build_featureset_safe(model_def.features, data, prep_index, train_index)
y_train, fitted_target = build_target_safe(model_def.target, data, prep_index, train_index)
x_train = x_train.reindex(train_index)
y_train = y_train.reindex(train_index)
return x_train, y_train, fitted_features, fitted_target
def generate_train(model_def, data, prep_index=None, train_index=None):
# create training set
data, prep_index, train_index = filter_data_and_indexes(
model_def, data, prep_index, train_index)
x_train, fitted_features = build_featureset_safe(model_def.features, data,
prep_index, train_index)
y_train, fitted_target = build_target_safe(model_def.target, data,
prep_index, train_index)
x_train = x_train.reindex(train_index)
y_train = y_train.reindex(train_index)
return x_train, y_train, fitted_features, fitted_target
def fit_model(model_def, data, prep_index=None, train_index=None):
# create training set
x_train, fitted_features = build_featureset_safe(model_def.features, data, prep_index, train_index)
y_train, fitted_target = build_target_safe(model_def.target, data, prep_index, train_index)
# fit estimator
model_def.estimator.fit(x_train, y_train)
# unnecesary?
fitted_estimator = FittedEstimator(model_def.estimator, x_train, y_train)
fitted_model = FittedModel(model_def, fitted_features, fitted_target, fitted_estimator)
return x_train, y_train, fitted_model
def test_categorical_indicators(self):
self.data['categorical'] = map(str, range(10))
model_def = ModelDefinition(
features=[Map('categorical', str),
F('a'),
Map('b', np.abs)],
target='y',
categorical_indicators=False)
x, ff = build_featureset_safe(model_def.features, self.data)
self.assertEqual(len(x.columns), len(model_def.features))
self.data['categorical'] = map(str, range(10))
model_def = ModelDefinition(
features=[Map('categorical', str),
F('a'),
Map('b', np.abs)],
target='y',
categorical_indicators=True)
print model_def.features
x, ff = build_featureset_safe(model_def.features, self.data)
print x
for f in ff:
print f.feature
self.assertEqual(len(x.columns), len(model_def.features) + 9)
def generate_train(model_def, data, prep_index=None, train_index=None):
# create training set
x_train, fitted_features = build_featureset_safe(model_def.features, data, prep_index, train_index)
y_train, fitted_target = build_target_safe(model_def.target, data, prep_index, train_index)
return x_train, y_train, fitted_features, fitted_target
