Go from a 2 letter state abbreviation to the region. Territories included https://en.wikipedia.org/wiki/List_of_U.S._state_and_territory_abbreviations. Regions defined here: https://www2.census.gov/geo/pdfs/maps-data/maps/reference/us_regdiv.pdf

us_state_to_region.py

# full name to abbreviation here: https://gist.github.com/mshafrir/2646763

ste_to_reg = {
        'AA': 'Other',
        'AE': 'Other',
        'AP': 'Other',
        'AK': 'West',
        'AL': 'South',
        'AR': 'South',
        'AS': 'Other',
        'AZ': 'West',
        'CA': 'West',
        'CO': 'West',
        'CT': 'Northeast',
        'DC': 'South',
        'DE': 'South',
        'FL': 'South',
        'FM': 'Other',
        'GA': 'South',
        'GU': 'Other',
        'HI': 'West',
        'IA': 'Midwest',
        'ID': 'West',
        'IL': 'Midwest',
        'IN': 'Midwest',
        'KS': 'Midwest',
        'KY': 'South',
        'LA': 'South',
        'MA': 'Northeast',
        'MD': 'South',
        'ME': 'Northeast',
        'MH': 'Other',
        'MI': 'Midwest',
        'MN': 'Midwest',
        'MO': 'Midwest',
        'MP': 'Other',
        'MS': 'South',
        'MT': 'West',
        'NA': 'Other',
        'NC': 'South',
        'ND': 'Midwest',
        'NE': 'Midwest',
        'NH': 'Northeast',
        'NJ': 'Northeast',
        'NM': 'West',
        'NV': 'West',
        'NY': 'Northeast',
        'OH': 'Midwest',
        'OK': 'South',
        'OR': 'West',
        'PA': 'Northeast',
        'PR': 'Other',
        'PR': 'Other',
        'RI': 'Northeast',
        'SC': 'South',
        'SD': 'Midwest',
        'TN': 'South',
        'TX': 'South',
        'UM': 'Other',
        'UT': 'West',
        'VA': 'South',
        'VI': 'Other',
        'VT': 'Northeast',
        'WA': 'West',
        'WI': 'Midwest',
        'WV': 'South',
        'WY': 'West'
}

# pandas transform from list of 2 letter abbreviations to regions
df["region"] = df["state"].apply(lambda x: ste_to_reg[x])

# or if you want as a list
midwest = ['IA', 'IL', 'IN', 'KS', 'MI', 'MN', 'MO', 'ND', 'NE', 'OH', 'SD', 'WI']
northeast = ['CT', 'MA', 'ME', 'NH', 'NJ', 'NY', 'PA', 'RI', 'VT']
west = ['AK', 'AZ', 'CA', 'CO', 'HI', 'ID', 'MT', 'NM', 'NV', 'OR', 'UT', 'WA', 'WY']
other = ['AA', 'AE', 'AP', 'AS', 'FM', 'GU', 'MH', 'MP', 'NA', 'PR', 'UM', 'VI']
south = ['AL', 'AR', 'DC', 'DE', 'FL', 'GA', 'KY', 'LA', 'MD', 'MS', 'NC', 'OK', 'SC', 'TN', 'TX', 'VA', 'WV']