blog2_function2.py

# put data processing code into function
def process_alphavantage_data_create_dow_dummies(raw_data_file):
    raw_data_file['timestamp'] = pd.to_datetime(raw_data_file['timestamp'])
    raw_data_file['day_of_week'] = raw_data_file['timestamp'].dt.day_name()
    dummies = pd.get_dummies(raw_data_file['day_of_week'])
    raw_data_file.drop(columns=['day_of_week'], inplace=True)
    raw_data_file = pd.concat([raw_data_file, dummies], axis=1)
    # we are only interested in running a regression of volume against the dummy 
    # variables for days of the week. Because of this we will drop the remaining 
    # variables before importing it to our processed data folder
    raw_data_file.drop(columns=['timestamp', 'open', 'high', 'low', 'close', 
                                'adjusted_close', 'dividend_amount', 
                                'split_coefficient'], inplace=True)
    return raw_data_file

# Let's save our file
msft_proc.to_csv('../data/03_processed/msft_proc.csv', index=False)