format.py

# Formattinng data
data['state'] = data['state'].str.upper() # Capitalize the whole thing
data['state'] = data['state'].replace( # Changing the format of the string
                                      to_replace=["CA", "C.A", "CALI"], 
                                      value=["CALIFORNIA", "CALIFORNIA", "CALIFORNIA"])

# Dates and times are quite common in large datasets
# Converting all strings to datetime objects is good standardisation practice
# Here, the data["time"] strings will look like "2019-01-15", which is exactly
# how we set the "format" variable below
data["time"] = pd.to_datetime(data["time"], format='%Y-%m-%d', errors='ignore')

# Discretising continous variables
# Height is in inches and we make a few bins with labels
data["height"] = pd.cut(data['height'],
                        bins=[0, 48, 60, 66, 72, 78, 100], 
                        labels=["Super Short","Short", "Average", "Above Average","Tall","Super Tall"])

# Replace string values with some floats that our 
# ML models will be able to handle
mapping = {'Adult Woman': 1, 'Adult Man': 2, "Child": 3}
data"Person" = data["Person"].replace(mapping)