def get_test_data():
'''
Input: None
Output: DataFrame - data from test set
'''
df = load_data(train=False)
df = transform_data(df)
X, ids = prep_for_modeling(df, column='id', columns_to_drop=columns_to_drop[:-1])
return X, ids
def make_model(df, model, model_name):
'''
Input: DataFrame, Model Instance - implementing fit method, Str - of name for pickled model file
Output: None
'''
df = transform_data(df)
X, y = prep_for_modeling(df, column='country_destination', columns_to_drop=columns_to_drop)
model.fit(X, y)
with open(model_path.format(model_name), 'w+') as model_file:
pickle.dump(model, model_file)
def modeling_exclaimation_point(df):
'''
Input: DataFrame
Output: NpArray - scores from k-fold tests on current data transformation
Function to quickly test engineered features.
'''
df = transform_data(df)
X, y = prep_for_modeling(df, column='country_destination', columns_to_drop=columns_to_drop)
rfc = RandomForestClassifier(n_estimators=100, n_jobs=-1)
scores = ndcg_cross_val_score(rfc, X, y)
return scores