A Python Dictionary to translate US States to Two letter codes

us_state_abbrev.py

# United States of America Python Dictionary to translate States,
# Districts & Territories to Two-Letter codes and vice versa.
#
# Canonical URL: https://gist.github.com/rogerallen/1583593
#
# Dedicated to the public domain.  To the extent possible under law,
# Roger Allen has waived all copyright and related or neighboring
# rights to this code.  Data originally from Wikipedia at the url:
# https://en.wikipedia.org/wiki/ISO_3166-2:US
#
# Automatically Generated 2024-10-08 07:45:06 via Jupyter Notebook from
# https://gist.github.com/rogerallen/d75440e8e5ea4762374dfd5c1ddf84e0 

us_state_to_abbrev = {
    "Alabama": "AL",
    "Alaska": "AK",
    "Arizona": "AZ",
    "Arkansas": "AR",
    "California": "CA",
    "Colorado": "CO",
    "Connecticut": "CT",
    "Delaware": "DE",
    "Florida": "FL",
    "Georgia": "GA",
    "Hawaii": "HI",
    "Idaho": "ID",
    "Illinois": "IL",
    "Indiana": "IN",
    "Iowa": "IA",
    "Kansas": "KS",
    "Kentucky": "KY",
    "Louisiana": "LA",
    "Maine": "ME",
    "Maryland": "MD",
    "Massachusetts": "MA",
    "Michigan": "MI",
    "Minnesota": "MN",
    "Mississippi": "MS",
    "Missouri": "MO",
    "Montana": "MT",
    "Nebraska": "NE",
    "Nevada": "NV",
    "New Hampshire": "NH",
    "New Jersey": "NJ",
    "New Mexico": "NM",
    "New York": "NY",
    "North Carolina": "NC",
    "North Dakota": "ND",
    "Ohio": "OH",
    "Oklahoma": "OK",
    "Oregon": "OR",
    "Pennsylvania": "PA",
    "Rhode Island": "RI",
    "South Carolina": "SC",
    "South Dakota": "SD",
    "Tennessee": "TN",
    "Texas": "TX",
    "Utah": "UT",
    "Vermont": "VT",
    "Virginia": "VA",
    "Washington": "WA",
    "West Virginia": "WV",
    "Wisconsin": "WI",
    "Wyoming": "WY",
    "District of Columbia": "DC",
    "American Samoa": "AS",
    "Guam": "GU",
    "Northern Mariana Islands": "MP",
    "Puerto Rico": "PR",
    "United States Minor Outlying Islands": "UM",
    "Virgin Islands, U.S.": "VI",
}
    
# invert the dictionary
abbrev_to_us_state = dict(map(reversed, us_state_to_abbrev.items()))

Those east of the Mississippi River:
['AL', 'CT', 'DE', 'FL', 'GA', 'IL', 'IN', 'KY', 'ME', 'MD', 'MA', 'MI', 'MS', 'NH', 'NJ', 'NY', 'NC', 'OH', 'PA', 'RI', 'SC', 'TN', 'VT', 'VA', 'WV', 'WI']

Just what I need, cheers for creating this and sharing it!

Hereby an auto enumerator.

from enum import IntEnum, auto

class US_States(IntEnum):
    AL = auto() # Alabama
    AK = auto() # Alaska
    AS = auto() # American Samoa
    AZ = auto() # Arizona
    AR = auto() # Arkansas
    CA = auto() # California
    CO = auto() # Colorado
    CT = auto() # Connecticut
    DE = auto() # Delaware
    DC = auto() # District of Columbia
    FL = auto() # Florida
    GA = auto() # Georgia
    GU = auto() # Guam
    HI = auto() # Hawaii
    ID = auto() # Idaho
    IL = auto() # Illinois
    IN = auto() # Indiana
    IA = auto() # Iowa
    KS = auto() # Kansas
    KY = auto() # Kentucky
    LA = auto() # Louisiana
    ME = auto() # Maine
    MD = auto() # Maryland
    MA = auto() # Massachusetts
    MI = auto() # Michigan
    MN = auto() # Minnesota
    MS = auto() # Mississippi
    MO = auto() # Missouri
    MT = auto() # Montana
    NE = auto() # Nebraska
    NV = auto() # Nevada
    NH = auto() # New Hampshire
    NJ = auto() # New Jersey
    NM = auto() # New Mexico
    NY = auto() # New York
    NC = auto() # North Carolina
    ND = auto() # North Dakota
    MP = auto() # Northern Mariana Islands
    OH = auto() # Ohio
    OK = auto() # Oklahoma
    OR = auto() # Oregon
    PA = auto() # Pennsylvania
    PR = auto() # Puerto Rico
    RI = auto() # Rhode Island
    SC = auto() # South Carolina
    SD = auto() # South Dakota
    TN = auto() # Tennessee
    TX = auto() # Texas
    UT = auto() # Utah
    VT = auto() # Vermont
    VI = auto() # Virgin Islands
    VA = auto() # Virginia
    WA = auto() # Washington
    WV = auto() # West Virginia
    WI = auto() # Wisconsin
    WY = auto() # Wyoming

Here is one to encode US states based on their population ranking (might be usefull for some further correlation analysis):
us_state_to_population_ranking_encoding = {
"CA": 52, "TX": 51, "FL": 50, "NY": 49, "PA": 48, "IL": 47,
"OH": 46, "GA": 45, "NC": 44, "MI": 43, "NJ": 42, "VA": 41,
"WA": 40, "AZ": 39, "TN": 38, "MA": 37, "IN": 36, "MO": 35,
"MD": 34, "CO": 33, "WI": 32, "MN": 31, "SC": 30, "AL": 29,
"LA": 28, "KY": 27, "OR": 26, "OK": 25, "CT": 24, "UT": 23,
"PR": 22, "NV": 21, "IA": 20, "AR": 19, "MS": 18, "KS": 17,
"NM": 16, "NE": 15, "ID": 14, "WV": 13, "HI": 12, "NH": 11,
"ME": 10, "MT": 9, "RI": 8, "DE": 7, "SD": 6, "ND": 5,
"AK": 4, "DC": 3, "VT": 2, "WY": 1
}

Thank you!

Thank you!! And Happy New Year!

I just came in today to parse legal data from all US states and this came very in handy! Thanks buddy!

us_state_to_abbrev = {
"Alabama": "AL",
"Alaska": "AK",
"Arizona": "AZ",
"Arkansas": "AR",
"California": "CA",
"Colorado": "CO",
"Connecticut": "CT",
"Delaware": "DE",
"Florida": "FL",
"Georgia": "GA",
"Hawaii": "HI",
"Idaho": "ID",
"Illinois": "IL",
"Indiana": "IN",
"Iowa": "IA",
"Kansas": "KS",
"Kentucky": "KY",
"Louisiana": "LA",
"Maine": "ME",
"Maryland": "MD",
"Massachusetts": "MA",
"Michigan": "MI",
"Minnesota": "MN",
"Mississippi": "MS",
"Missouri": "MO",
"Montana": "MT",
"Nebraska": "NE",
"Nevada": "NV",
"New Hampshire": "NH",
"New Jersey": "NJ",
"New Mexico": "NM",
"New York": "NY",
"North Carolina": "NC",
"North Dakota": "ND",
"Ohio": "OH",
"Oklahoma": "OK",
"Oregon": "OR",
"Pennsylvania": "PA",
"Rhode Island": "RI",
"South Carolina": "SC",
"South Dakota": "SD",
"Tennessee": "TN",
"Texas": "TX",
"Utah": "UT",
"Vermont": "VT",
"Virginia": "VA",
"Washington": "WA",
"West Virginia": "WV",
"Wisconsin": "WI",
"Wyoming": "WY",
"District of Columbia": "DC",
"American Samoa": "AS",
"Guam": "GU",
"Northern Mariana Islands": "MP",
"Puerto Rico": "PR",
"United States Minor Outlying Islands": "UM",
"U.S. Virgin Islands": "VI",
"AL": "AL",
"AK": "AK",
"AZ": "AZ",
"AR": "AR",
"CA": "CA",
"CO": "CO",
"CT": "CT",
"DE": "DE",
"FL": "FL",
"GA": "GA",
"HI": "HI",
"ID": "ID",
"IL": "IL",
"IN": "IN",
"IA": "IA",
"KS": "KS",
"KY": "KY",
"LA": "LA",
"ME": "ME",
"MD": "MD",
"MA": "MA",
"MI": "MI",
"MN": "MN",
"MS": "MS",
"MO": "MO",
"MT": "MT",
"NE": "NE",
"NV": "NV",
"NH": "NH",
"NJ": "NJ",
"NM": "NM",
"NY": "NY",
"NC": "NC",
"ND": "ND",
"OH": "OH",
"OK": "OK",
"OR": "OR",
"PA": "PA",
"RI": "RI",
"SC": "SC",
"SD": "SD",
"TN": "TN",
"TX": "TX",
"UT": "UT",
"VT": "VT",
"VA": "VA",
"WA": "WA",
"WV": "WV",
"WI": "WI",
"WY": "WY",
"DC": "DC",
"AS": "AS",
"GU": "GU",
"MP": "MP",
"PR": "PR",
"UM": "UM",
"VI": "VI",
}

needed this for standardizing the column where some values were full names and some were abbreviations

@pnojai take a look at : https://pypi.org/project/us/

thanks a lot

Thank you for sharing this information
@sandlerj It's worked very well, and thank you

Thank you!

Commenting as well, so everyone gets spam on this gist! haha

Everyone who contributed to this I hope nothing but the best for you! Thank you!

Updated with latest results from Wikipedia-scraping script. Only change was to Virgin Islands.