def test_make_single_prediction():
data = pd.read_csv(config.TRAINING_DATA_FILE)
drop_duplicate = pp.DropDuplicateValues()
data = drop_duplicate.fit_transform(data)
drop_missing = pp.DropMissingValues()
data = drop_missing.fit_transform(data)
create_polarity = pp.CreatePolarityFeature()
data = create_polarity.fit_transform(data)
X_train, X_test, y_train, y_test = train_test_split(
data[config.INPUT_FEATURES],
data[config.TARGET],
test_size=0.3,
random_state=42)
# Given
single_test_json = X_test[0:1].to_json(orient='records')
# When
subject = make_prediction(input_data=single_test_json)
# Then
assert subject is not None
def run_training():
"""Train the model."""
# read training data
data = pd.read_csv(config.TRAINING_DATA_FILE)
data = data.sample(n=100000)
drop_duplicate = pp.DropDuplicateValues()
data = drop_duplicate.fit_transform(data)
drop_missing = pp.DropMissingValues()
data = drop_missing.fit_transform(data)
create_polarity = pp.CreatePolarityFeature()
data = create_polarity.fit_transform(data)
# divide train and test
X_train, X_test, y_train, y_test = train_test_split(
data[config.INPUT_FEATURES],
data[config.TARGET],
test_size=0.1,
random_state=42) # we are setting the seed here
pipeline.review_pipe.fit(X_train[config.INPUT_FEATURES], y_train)
joblib.dump(pipeline.review_pipe, config.PIPELINE_NAME)
results = _pipe_price.predict(input_data)
return results
if __name__ == '__main__':
# test pipeline
data = pd.read_csv(config.TRAINING_DATA_FILE)
drop_duplicate = pp.DropDuplicateValues()
data = drop_duplicate.fit_transform(data)
drop_missing = pp.DropMissingValues()
data = drop_missing.fit_transform(data)
create_polarity = pp.CreatePolarityFeature()
data = create_polarity.fit_transform(data)
X_train, X_test, y_train, y_test = train_test_split(
data[config.INPUT_FEATURES],
data[config.TARGET],
test_size=0.1,
random_state=42)
pred = make_prediction(X_test)
# determine mse and rmse
print('test precision_score: {}'.format(precision_score(y_test, pred)))