def test_trees(self):
(train, label) = get_X_y(train_file, label_column, sep=',')
(test, label1) = get_X_y(test_file, label_column, sep=',')
pipeline = Pipeline([OneHotVectorizer() << categorical_columns,
FastTreesBinaryClassifier()])
pipeline.fit(train, label)
out_data = pipeline.predict(test)
check_accuracy(test_file, label_column, out_data, 0.65)
def test_trees_file(self):
pipeline = Pipeline([OneHotVectorizer() << categorical_columns,
FastTreesBinaryClassifier() << {
'Label': label_column}])
train_stream = FileDataStream(train_file, schema=file_schema)
pipeline.fit(train_stream, label_column)
test_stream = FileDataStream(test_file, schema=file_schema)
out_data = pipeline.predict(test_stream)
check_accuracy(test_file, label_column, out_data, 0.65)
def test_linear_with_train_test_schema(self):
(train, label) = get_X_y(train_file, label_column, sep=',')
(test, label1) = get_X_y(test_file, label_column, sep=',')
pipeline = Pipeline([OneHotVectorizer() << categorical_columns,
FastLinearBinaryClassifier(train_threads=1,
shuffle=False)])
pipeline.fit(train, label)
out_data = pipeline.predict(test)
check_accuracy(test_file, label_column, out_data, 0.65)
def test_linear_file_role(self):
pipeline = Pipeline([OneHotVectorizer() << categorical_columns,
FastLinearBinaryClassifier(train_threads=1,
shuffle=False)])
train_stream = FileDataStream(train_file, schema=file_schema)
train_stream._set_role('Label', label_column)
pipeline.fit(train_stream)
test_stream = FileDataStream(test_file, schema=file_schema)
out_data = pipeline.predict(test_stream)
check_accuracy(test_file, label_column, out_data, 0.65)
def test_linear_file(self):
pipeline = Pipeline([OneHotVectorizer() << categorical_columns,
FastLinearBinaryClassifier(train_threads=1,
shuffle=False)])
train_stream = FileDataStream(train_file, schema=file_schema)
assert 'sep' in train_stream.schema.options
assert 'header' in train_stream.schema.options
pipeline.fit(train_stream, label_column)
test_stream = FileDataStream(test_file, schema=file_schema)
out_data = pipeline.predict(test_stream)
check_accuracy(test_file, label_column, out_data, 0.65)
