blog2_2_20190723-mlb-feature-processing.py

# Add days of the week 
msft_proc['day_of_week'] = msft_proc['timestamp'].dt.day_name()

# create dummy variables
dummies = pd.get_dummies(msft_proc['day_of_week'])

# drop original days of the week column from the original dataframe
msft_proc.drop(columns=['day_of_week'], inplace=True)

# add two dataframes together
msft_proc = pd.concat([msft_proc, 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
msft_proc.drop(columns=['timestamp', 'open', 'high', 'low', 'close', 
                        'adjusted_close','dividend_amount', 'split_coefficient'], 
               inplace=True)
msft_proc.head()