use codebooks database for label_names, num_dicts

label_dicts.py

@@ -1,1086 +1,50 @@
-CAP_MEDIA2_LABEL_NAMES = {
-    1: 'Macroeconomics',
-    2: 'Civil Rights',
-    3: 'Health',
-    4: 'Agriculture',
-    5: 'Labor',
-    6: 'Education',
-    7: 'Environment',
-    8: 'Energy',
-    9: 'Immigration',
-    10: 'Transportation',
-    12: 'Law and Crime',
-    13: 'Social Welfare',
-    14: 'Housing',
-    15: 'Banking, Finance, and Domestic Commerce',
-    16: 'Defense',
-    17: 'Technology',
-    18: 'Foreign Trade',
-    19: 'International Affairs',
-    20: 'Government Operations',
-    21: 'Public Lands',
-    23: 'Culture',
-    24: 'State and Local Government Administration',
-    25: 'Weather',
-    26: 'Fires, emergencies and natural disasters',
-    27: 'Crime and trials',
-    28: 'Arts, culture, entertainment and history',
-    29: 'Style and fashion',
-    30: 'Food',
-    31: 'Travel',
-    32: 'Wellbeing and learning',
-    33: 'Personal finance and real estate',
-    34: 'Personal technology and popular science',
-    35: 'Churches and Religion',
-    36: 'Celebrities and human interest',
-    37: 'Obituaries and death notices',
-    38: 'Sports',
-    39: 'Crosswords, puzzles, comics',
-    40: 'Media production/internal, letters',
-    41: 'Advertisements',
-    998: 'No Policy and No Media Content'
-}
-
-CAP_MEDIA2_NUM_DICT = {
-    0: 1,
-    1: 2,
-    2: 3,
-    3: 4,
-    4: 5,
-    5: 6,
-    6: 7,
-    7: 8,
-    8: 9,
-    9: 10,
-    10: 12,
-    11: 13,
-    12: 14,
-    13: 15,
-    14: 16,
-    15: 17,
-    16: 18,
-    17: 19,
-    18: 20,
-    19: 21,
-    20: 23,
-    21: 24,
-    22: 25,
-    23: 26,
-    24: 27,
-    25: 28,
-    26: 29,
-    27: 30,
-    28: 31,
-    29: 32,
-    30: 33,
-    31: 34,
-    32: 35,
-    33: 36,
-    34: 37,
-    35: 38,
-    36: 39,
-    37: 40,
-    38: 41,
-    39: 998
-}
-
-CAP_NUM_DICT = {
-    0: 1,
-    1: 2,
-    2: 3,
-    3: 4,
-    4: 5,
-    5: 6,
-    6: 7,
-    7: 8,
-    8: 9,
-    9: 10,
-    10: 12,
-    11: 13,
-    12: 14,
-    13: 15,
-    14: 16,
-    15: 17,
-    16: 18,
-    17: 19,
-    18: 20,
-    19: 21,
-    20: 23,
-    21: 999,
-    22: 999, # had to do this because of some language-domain models (e.g. english media)
-}
-
-CAP_MEDIA_LABEL_NAMES = {
-    1: "Macroeconomics",
-    2: "Civil Rights",
-    3: "Health",
-    4: "Agriculture",
-    5: "Labor",
-    6: "Education",
-    7: "Environment",
-    8: "Energy",
-    9: "Immigration",
-    10: "Transportation",
-    12: "Law and Crime",
-    13: "Social Welfare",
-    14: "Housing",
-    15: "Domestic Commerce",
-    16: "Defense",
-    17: "Technology",
-    18: "Foreign Trade",
-    19: "International Affairs",
-    20: "Government Operations",
-    21: "Public Lands",
-    23: "Culture",
-    24: "State and Local Government Administration",
-    26: "Weather and Natural Disasters",
-    27: "Fires",
-    29: "Sports and Recreation",
-    30: "Death Notices",
-    31: "Churches and Religions",
-    99: "Other, Miscellaneous, and Human Interest",
-    998: "No Policy or Media Content"
-}
-
-CAP_MEDIA_NUM_DICT = {
-    0: 1,
-    1: 2,
-    2: 3,
-    3: 4,
-    4: 5,
-    5: 6,
-    6: 7,
-    7: 8,
-    8: 9,
-    9: 10,
-    10: 12,
-    11: 13,
-    12: 14,
-    13: 15,
-    14: 16,
-    15: 17,
-    16: 18,
-    17: 19,
-    18: 20,
-    19: 21,
-    20: 23,
-    21: 24,
-    22:26,
-    23:27,
-    24:29,
-    25:30,
-    26:31,
-    27:99,
-    28:998
-}
-
-CAP_MIN_NUM_DICT = {
-    0: 100,
-    1: 101,
-    2: 103,
-    3: 104,
-    4: 105,
-    5: 107,
-    6: 108,
-    7: 110,
-    8: 199,
-    9: 200,
-    10: 201,
-    11: 202,
-    12: 204,
-    13: 205,
-    14: 206,
-    15: 207,
-    16: 208,
-    17: 209,
-    18: 299,
-    19: 300,
-    20: 301,
-    21: 302,
-    22: 321,
-    23: 322,
-    24: 323,
-    25: 324,
-    26: 325,
-    27: 331,
-    28: 332,
-    29: 333,
-    30: 334,
-    31: 335,
-    32: 341,
-    33: 342,
-    34: 398,
-    35: 399,
-    36: 400,
-    37: 401,
-    38: 402,
-    39: 403,
-    40: 404,
-    41: 405,
-    42: 408,
-    43: 498,
-    44: 499,
-    45: 500,
-    46: 501,
-    47: 502,
-    48: 503,
-    49: 504,
-    50: 505,
-    51: 506,
-    52: 529,
-    53: 599,
-    54: 600,
-    55: 601,
-    56: 602,
-    57: 603,
-    58: 604,
-    59: 606,
-    60: 607,
-    61: 698,
-    62: 699,
-    63: 700,
-    64: 701,
-    65: 703,
-    66: 704,
-    67: 705,
-    68: 707,
-    69: 708,
-    70: 709,
-    71: 711,
-    72: 798,
-    73: 799,
-    74: 800,
-    75: 801,
-    76: 802,
-    77: 803,
-    78: 805,
-    79: 806,
-    80: 807,
-    81: 898,
-    82: 899,
-    83: 900,
-    84: 1000,
-    85: 1001,
-    86: 1002,
-    87: 1003,
-    88: 1005,
-    89: 1007,
-    90: 1010,
-    91: 1098,
-    92: 1099,
-    93: 1200,
-    94: 1201,
-    95: 1202,
-    96: 1203,
-    97: 1204,
-    98: 1205,
-    99: 1206,
-    100: 1207,
-    101: 1208,
-    102: 1210,
-    103: 1211,
-    104: 1227,
-    105: 1299,
-    106: 1300,
-    107: 1302,
-    108: 1303,
-    109: 1304,
-    110: 1305,
-    111: 1308,
-    112: 1399,
-    113: 1400,
-    114: 1401,
-    115: 1403,
-    116: 1404,
-    117: 1405,
-    118: 1406,
-    119: 1407,
-    120: 1408,
-    121: 1409,
-    122: 1498,
-    123: 1499,
-    124: 1500,
-    125: 1501,
-    126: 1502,
-    127: 1504,
-    128: 1505,
-    129: 1507,
-    130: 1520,
-    131: 1521,
-    132: 1522,
-    133: 1523,
-    134: 1524,
-    135: 1525,
-    136: 1526,
-    137: 1598,
-    138: 1599,
-    139: 1600,
-    140: 1602,
-    141: 1603,
-    142: 1604,
-    143: 1605,
-    144: 1606,
-    145: 1608,
-    146: 1610,
-    147: 1611,
-    148: 1612,
-    149: 1614,
-    150: 1615,
-    151: 1616,
-    152: 1617,
-    153: 1619,
-    154: 1620,
-    155: 1698,
-    156: 1699,
-    157: 1700,
-    158: 1701,
-    159: 1704,
-    160: 1705,
-    161: 1706,
-    162: 1707,
-    163: 1708,
-    164: 1709,
-    165: 1798,
-    166: 1799,
-    167: 1800,
-    168: 1802,
-    169: 1803,
-    170: 1804,
-    171: 1806,
-    172: 1807,
-    173: 1808,
-    174: 1899,
-    175: 1900,
-    176: 1901,
-    177: 1902,
-    178: 1905,
-    179: 1906,
-    180: 1910,
-    181: 1921,
-    182: 1925,
-    183: 1926,
-    184: 1927,
-    185: 1929,
-    186: 1999,
-    187: 2000,
-    188: 2001,
-    189: 2002,
-    190: 2003,
-    191: 2004,
-    192: 2005,
-    193: 2006,
-    194: 2007,
-    195: 2008,
-    196: 2009,
-    197: 2010,
-    198: 2011,
-    199: 2012,
-    200: 2013,
-    201: 2014,
-    202: 2015,
-    203: 2030,
-    204: 2099,
-    205: 2100,
-    206: 2101,
-    207: 2102,
-    208: 2103,
-    209: 2104,
-    210: 2105,
-    211: 2199,
-    212: 2300,
-    213: 999
-}
-CAP_LABEL_NAMES = {
-    1: "Macroeconomics",
-    2: "Civil Rights",
-    3: "Health",
-    4: "Agriculture",
-    5: "Labor",
-    6: "Education",
-    7: "Environment",
-    8: "Energy",
-    9: "Immigration",
-    10: "Transportation",
-    12: "Law and Crime",
-    13: "Social Welfare",
-    14: "Housing",
-    15: "Domestic Commerce",
-    16: "Defense",
-    17: "Technology",
-    18: "Foreign Trade",
-    19: "International Affairs",
-    20: "Government Operations",
-    21: "Public Lands",
-    23: "Culture",
-    999: "No Policy Content"
-}
-
-CAP_MIN_MEDIA_NUM_DICT = {0: 100,
-     1: 101,
-     2: 103,
-     3: 104,
-     4: 105,
-     5: 107,
-     6: 108,
-     7: 110,
-     8: 199,
-     9: 200,
-     10: 201,
-     11: 202,
-     12: 204,
-     13: 205,
-     14: 206,
-     15: 207,
-     16: 208,
-     17: 209,
-     18: 299,
-     19: 300,
-     20: 301,
-     21: 302,
-     22: 321,
-     23: 322,
-     24: 323,
-     25: 324,
-     26: 325,
-     27: 331,
-     28: 332,
-     29: 333,
-     30: 334,
-     31: 335,
-     32: 341,
-     33: 342,
-     34: 398,
-     35: 399,
-     36: 400,
-     37: 401,
-     38: 402,
-     39: 403,
-     40: 404,
-     41: 405,
-     42: 408,
-     43: 498,
-     44: 499,
-     45: 500,
-     46: 501,
-     47: 502,
-     48: 503,
-     49: 504,
-     50: 505,
-     51: 506,
-     52: 529,
-     53: 599,
-     54: 600,
-     55: 601,
-     56: 602,
-     57: 603,
-     58: 604,
-     59: 606,
-     60: 607,
-     61: 698,
-     62: 699,
-     63: 700,
-     64: 701,
-     65: 703,
-     66: 704,
-     67: 705,
-     68: 707,
-     69: 708,
-     70: 709,
-     71: 711,
-     72: 798,
-     73: 799,
-     74: 800,
-     75: 801,
-     76: 802,
-     77: 803,
-     78: 805,
-     79: 806,
-     80: 807,
-     81: 898,
-     82: 899,
-     83: 900,
-     84: 1000,
-     85: 1001,
-     86: 1002,
-     87: 1003,
-     88: 1005,
-     89: 1007,
-     90: 1010,
-     91: 1098,
-     92: 1099,
-     93: 1200,
-     94: 1201,
-     95: 1202,
-     96: 1203,
-     97: 1204,
-     98: 1205,
-     99: 1206,
-     100: 1207,
-     101: 1208,
-     102: 1210,
-     103: 1211,
-     104: 1227,
-     105: 1299,
-     106: 1300,
-     107: 1302,
-     108: 1303,
-     109: 1304,
-     110: 1305,
-     111: 1308,
-     112: 1399,
-     113: 1400,
-     114: 1401,
-     115: 1403,
-     116: 1404,
-     117: 1405,
-     118: 1406,
-     119: 1407,
-     120: 1408,
-     121: 1409,
-     122: 1498,
-     123: 1499,
-     124: 1500,
-     125: 1501,
-     126: 1502,
-     127: 1504,
-     128: 1505,
-     129: 1507,
-     130: 1520,
-     131: 1521,
-     132: 1522,
-     133: 1523,
-     134: 1524,
-     135: 1525,
-     136: 1526,
-     137: 1598,
-     138: 1599,
-     139: 1600,
-     140: 1602,
-     141: 1603,
-     142: 1604,
-     143: 1605,
-     144: 1606,
-     145: 1608,
-     146: 1610,
-     147: 1611,
-     148: 1612,
-     149: 1614,
-     150: 1615,
-     151: 1616,
-     152: 1617,
-     153: 1619,
-     154: 1620,
-     155: 1698,
-     156: 1699,
-     157: 1700,
-     158: 1701,
-     159: 1704,
-     160: 1705,
-     161: 1706,
-     162: 1707,
-     163: 1708,
-     164: 1709,
-     165: 1798,
-     166: 1799,
-     167: 1800,
-     168: 1802,
-     169: 1803,
-     170: 1804,
-     171: 1806,
-     172: 1807,
-     173: 1808,
-     174: 1899,
-     175: 1900,
-     176: 1901,
-     177: 1902,
-     178: 1905,
-     179: 1906,
-     180: 1910,
-     181: 1921,
-     182: 1925,
-     183: 1926,
-     184: 1927,
-     185: 1929,
-     186: 1999,
-     187: 2000,
-     188: 2001,
-     189: 2002,
-     190: 2003,
-     191: 2004,
-     192: 2005,
-     193: 2006,
-     194: 2007,
-     195: 2008,
-     196: 2009,
-     197: 2010,
-     198: 2011,
-     199: 2012,
-     200: 2013,
-     201: 2014,
-     202: 2015,
-     203: 2030,
-     204: 2099,
-     205: 2100,
-     206: 2101,
-     207: 2102,
-     208: 2103,
-     209: 2104,
-     210: 2105,
-     211: 2300,
-     212: 99, # do not use separate 9999 and 99 labels
-     213: 24,
-     214: 26,
-     215: 27,
-     216: 29,
-     217: 30,
-     218: 31,
-     219: 99}
-     
-MANIFESTO_NUM_DICT = {
-    0: 0,
-    1: 101,
-    2: 102,
-    3: 103,
-    4: 104,
-    5: 105,
-    6: 106,
-    7: 107,
-    8: 108,
-    9: 109,
-    10: 110,
-    11: 201,
-    12: 202,
-    13: 203,
-    14: 204,
-    15: 301,
-    16: 302,
-    17: 303,
-    18: 304,
-    19: 305,
-    20: 401,
-    21: 402,
-    22: 403,
-    23: 404,
-    24: 405,
-    25: 406,
-    26: 407,
-    27: 408,
-    28: 409,
-    29: 410,
-    30: 411,
-    31: 412,
-    32: 413,
-    33: 414,
-    34: 415,
-    35: 416,
-    36: 501,
-    37: 502,
-    38: 503,
-    39: 504,
-    40: 505,
-    41: 506,
-    42: 507,
-    43: 601,
-    44: 602,
-    45: 603,
-    46: 604,
-    47: 605,
-    48: 606,
-    49: 607,
-    50: 608,
-    51: 701,
-    52: 702,
-    53: 703,
-    54: 704,
-    55: 705,
-    56: 706
-}
-
-CAP_MIN_LABEL_NAMES = {
-    # 1. Macroeconomics
-    100: "General",
-    101: "Interest Rates",
-    103: "Unemployment Rate",
-    104: "Monetary Policy",
-    105: "National Budget",
-    107: "Tax Code",
-    108: "Industrial Policy",
-    110: "Price Control",
-    199: "Other",
-    # 2. Civil Rights
-    200: "General",
-    201: "Minority Discrimination",
-    202: "Gender Discrimination",
-    204: "Age Discrimination",
-    205: "Handicap Discrimination",
-    206: "Voting Rights",
-    207: "Freedom of Speech",
-    208: "Right to Privacy",
-    209: "Anti-Government",
-    299: "Other",
-    # 3. Health
-    300: "General",
-    301: "Health Care Reform",
-    302: "Insurance",
-    321: "Drug Industry",
-    322: "Medical Facilities",
-    323: "Insurance Providers",
-    324: "Medical Liability",
-    325: "Manpower",
-    331: "Disease Prevention",
-    332: "Infants and Children",
-    333: "Mental Health",
-    334: "Long-term Care",
-    335: "Drug Coverage and Cost",
-    341: "Tobacco Abuse",
-    342: "Drug and Alcohol Abuse",
-    398: "R&D",
-    399: "Other",
-    # 4. Agriculture
-    400: "General",
-    401: "Trade",
-    402: "Subsidies to Farmers",
-    403: "Food Inspection & Safety",
-    404: "Food Marketing & Promotion",
-    405: "Animal and Crop Disease",
-    408: "Fisheries & Fishing",
-    498: "R&D",
-    499: "Other",
-    # 5. Labor
-    500: "General",
-    501: "Worker Safety",
-    502: "Employment Training",
-    503: "Employee Benefits",
-    504: "Labor Unions",
-    505: "Fair Labor Standards",
-    506: "Youth Employment",
-    529: "Migrant and Seasonal",
-    599: "Other",
-    # 6. Education
-    600: "General",
-    601: "Higher",
-    602: "Elementary & Secondary",
-    603: "Underprivileged",
-    604: "Vocational",
-    606: "Special",
-    607: "Excellence",
-    698: "R&D",
-    699: "Other",
-    # 7. Environment
-    700: "General",
-    701: "Drinking Water",
-    703: "Waste Disposal",
-    704: "Hazardous Waste",
-    705: "Air Pollution",
-    707: "Recycling",
-    708: "Indoor Hazards",
-    709: "Species & Forest",
-    711: "Land and Water Conservation",
-    798: "R&D",
-    799: "Other",
-    # 8. Energy
-    800: "General",
-    801: "Nuclear",
-    802: "Electricity",
-    803: "Natural Gas & Oil",
-    805: "Coal",
-    806: "Alternative & Renewable",
-    807: "Conservation",
-    898: "R&D",
-    899: "Other",
-    # 9. Immigration
-    900: "Immigration",
-    # 10. Transportation
-    1000: "General",
-    1001: "Mass",
-    1002: "Highways",
-    1003: "Air Travel",
-    1005: "Railroad Travel",
-    1007: "Maritime",
-    1010: "Infrastructure",
-    1098: "R&D",
-    1099: "Other",
-    # 12. Law and Crime
-    1200: "General",
-    1201: "Agencies",
-    1202: "White Collar Crime",
-    1203: "Illegal Drugs",
-    1204: "Court Administration",
-    1205: "Prisons",
-    1206: "Juvenile Crime",
-    1207: "Child Abuse",
-    1208: "Family Issues",
-    1210: "Criminal & Civil Code",
-    1211: "Crime Control",
-    1227: "Police",
-    1299: "Other",
-    # 13. Social Welfare
-    1300: "General",
-    1302: "Low-Income Assistance",
-    1303: "Elderly Assistance",
-    1304: "Disabled Assistance",
-    1305: "Volunteer Associations",
-    1308: "Child Care",
-    1399: "Other",
-    # 14. Housing
-    1400: "General",
-    1401: "Community Development",
-    1403: "Urban Development",
-    1404: "Rural Housing",
-    1405: "Rural Development",
-    1406: "Low-Income Assistance",
-    1407: "Veterans",
-    1408: "Elderly",
-    1409: "Homeless",
-    1498: "R&D",
-    1499: "Other",
-    # 15. Domestic Commerce
-    1500: "General",
-    1501: "Banking",
-    1502: "Securities & Commodities",
-    1504: "Consumer Finance",
-    1505: "Insurance Regulation",
-    1507: "Bankruptcy",
-    1520: "Corporate Management",
-    1521: "Small Businesses",
-    1522: "Copyrights and Patents",
-    1523: "Disaster Relief",
-    1524: "Tourism",
-    1525: "Consumer Safety",
-    1526: "Sports Regulation",
-    1598: "R&D",
-    1599: "Other",
-    # 16. Defense
-    1600: "General",
-    1602: "Alliances",
-    1603: "Intelligence",
-    1604: "Readiness",
-    1605: "Nuclear Arms",
-    1606: "Military Aid",
-    1608: "Personnel Issues",
-    1610: "Procurement",
-    1611: "Installations & Land",
-    1612: "Reserve Forces",
-    1614: "Hazardous Waste",
-    1615: "Civil",
-    1616: "Civilian Personnel",
-    1617: "Contractors",
-    1619: "Foreign Operations",
-    1620: "Claims against Military",
-    1698: "R&D",
-    1699: "Other",
-    # 17. Technology
-    1700: "General",
-    1701: "Space",
-    1704: "Commercial Use of Space",
-    1705: "Science Transfer",
-    1706: "Telecommunications",
-    1707: "Broadcast",
-    1708: "Weather Forecasting",
-    1709: "Computers",
-    1798: "R&D",
-    1799: "Other",
-    # 18. Foreign Trade
-    1800: "General",
-    1802: "Trade Agreements",
-    1803: "Exports",
-    1804: "Private Investments",
-    1806: "Competitiveness",
-    1807: "Tariff & Imports",
-    1808: "Exchange Rates",
-    1899: "Other",
-    # 19. International Affairs
-    1900: "General",
-    1901: "Foreign Aid",
-    1902: "Resources Exploitation",
-    1905: "Developing Countries",
-    1906: "International Finance",
-    1910: "Western Europe",
-    1921: "Specific Country",
-    1925: "Human Rights",
-    1926: "Organizations",
-    1927: "Terrorism",
-    1929: "Diplomats",
-    1999: "Other",
-    # 20. Government Operations
-    2000: "General",
-    2001: "Intergovernmental Relations",
-    2002: "Bureaucracy",
-    2003: "Postal Service",
-    2004: "Employees",
-    2005: "Appointments",
-    2006: "Currency",
-    2007: "Procurement & Contractors",
-    2008: "Property Management",
-    2009: "Tax Administration",
-    2010: "Scandals",
-    2011: "Branch Relations",
-    2012: "Political Campaigns",
-    2013: "Census & Statistics",
-    2014: "Capital City",
-    2015: "Claims against the government",
-    2030: "National Holidays",
-    2099: "Other",
-    # 21. Public Lands
-    2100: "General",
-    2101: "National Parks",
-    2102: "Indigenous Affairs",
-    2103: "Public Lands",
-    2104: "Water Resources",
-    2105: "Dependencies & Territories",
-    2199: "Other",
-    # 23. Culture
-    2300: "General",
-    # NPC
-    999: "No Policy Content",
-    9999: "No Policy Content",
-}
-
-MANIFESTO_LABEL_NAMES = {
-    0: "No Policy Goal",
-    999: "No Policy Goal",
-    101: "Foreign Special Relationships: Positive",
-    102: "Foreign Special Relationships: Negative",
-    103: "Anti-Imperialism",
-    104: "Military: Positive",
-    105: "Military: Negative",
-    106: "Peace",
-    107: "Internationalism: Positive",
-    108: "European Community/Union: Positive",
-    109: "Internationalism: Negative",
-    110: "European Community/Union: Negative",
-    201: "Freedom and Human Rights",
-    202: "Democracy",
-    203: "Constitutionalism: Positive",
-    204: "Constitutionalism: Negative",
-    301: "Federalism",
-    302: "Centralisation",
-    303: "Governmental and Administrative Efficiency",
-    304: "Political Corruption",
-    305: "Political Authority",
-    401: "Free Market Economy",
-    402: "Incentives",
-    403: "Market Regulation",
-    404: "Economic Planning",
-    405: "Corporatism/Mixed Economy",
-    406: "Protectionism: Positive",
-    407: "Protectionism: Negative",
-    408: "Economic Goals",
-    409: "Keynesian Demand Management",
-    410: "Economic Growth: Positive",
-    411: "Technology and Infrastructure",
-    412: "Controlled Economy",
-    413: "Nationalisation",
-    414: "Economic Orthodoxy",
-    415: "Marxist Analysis: Positive",
-    416: "Anti-Growth Economy: Positive",
-    501: "Environmental Protection: Positive",
-    502: "Culture: Positive",
-    503: "Equality: Positive",
-    504: "Welfare State Expansion",
-    505: "Welfare State Limitation",
-    506: "Education Expansion",
-    507: "Education Limitation",
-    601: "National Way of Life: Positive",
-    602: "National Way of Life: Negative",
-    603: "Traditional Morality: Positive",
-    604: "Traditional Morality: Negative",
-    605: "Law and Order: Positive",
-    606: "Civic Mindedness: Positive",
-    607: "Multiculturalism: Positive",
-    608: "Multiculturalism: Negative",
-    701: "Labour Groups: Positive",
-    702: "Labour Groups: Negative",
-    703: "Agriculture and Farmers: Positive",
-    704: "Middle Class and Professional Groups",
-    705: "Underprivileged Minority Groups",
-    706: "Non-economic Demographic Groups"
-}
-
-ILLFRAMES_MIGRATION_LABEL_NAMES = {
-    901: "Culture Under Attack",
-    902: "Economic Burden",
-    903: "Illegals and Fraudsters",
-    904: "Extradition Necessity",
-    905: "Nation tate Should Decide",
-    906: "Administrative Burden",
-    907: "General System Failure",
-    908: "Security Threat",
-    909: "Criminals",
-    910: "Welfare State Overload",
-    999: "None of Them",
-}
-
-ILLFRAMES_COVID_LABEL_NAMES = {
-    310: "Skepticism",
-    311: "Great Reset and Elite Control",
-    312: "Undermining the Economy",
-    313: "Medical Choice",
-    314: "Media Fabrication",
-    315: "Threatening Way of Life",
-    399: "None of Them",
-}
-
-ILLFRAMES_WAR_LABEL_NAMES = {
-    101: 'Identity and Cultural Threat',
-    102: 'Economic Fallout/Domestic Welfare Neglected',
-    103: 'Violation of Russian Sovereignty/Western geopolitical meddling',
-    104: 'Illegitimate and corrupt Ukraine leadership',
-    105: 'Ukrainians and Ukraine are a military threat and agressive war-mongerer that threaten EU stability and security',
-    107: 'Western Propaganda and Civilian Suffering',
-    108: 'Historical Betrayal of Russia',
-    109: 'Ukraine/Nazi Allegation',
-    110: "None of Them"
-}
-
-ONTOLISST_LABEL_NAMES = {
-    0: 'Demographics',
-    1: 'Housing and local environment (Housing and environment)',
-    2: 'Physical health',
-    3: 'Mental health and mental processes',
-    4: 'Healthcare',
-    5: 'Health behaviour (Health and lifestyle)',
-    6: 'Family and social networks',
-    7: 'Education',
-    8: 'Employment and income (Employment and pensions)',
-    9: 'Expectation, attitudes and beliefs (Attitudes and beliefs)',
-    10: 'Child development',
-    11: 'Life events',
-    12: 'Omics',
-    13: 'Pregnancy',
-    14: 'Administration',
-    15: 'COVID19'
-}
-
-EMOTION6_LABEL_NAMES = {
-    0: "Anger",
-    1: "Fear",
-    2: "Disgust",
-    3: "Sadness",
-    4: "Joy",
-    5: "None of Them"
-}
-
-EMOTION9_LABEL_NAMES = {
-    0: "Anger",
-    1: "Fear",
-    2: "Disgust",
-    3: "Sadness",
-    4: "Joy",
-    5: "Enthusiasm",
-    6: "Hope",
-    7: "Pride",
-    8: "None of Them",
-}
-
-EMOTION9_V2_LABEL_NAMES = {
-    0:  "Anger",
-    1:	"Fear",
-    2:	"Disgust",
-    3:	"Sadness",
-    4:	"Joy",
-    5:	"None of them",
-    6:	"Enthusiasm",
-    7:	"Hope",
-    8:	"Pride"
-}
+import os
+import json
+import pandas as pd
+from google.cloud import bigquery
+
+service_account_info = json.loads(os.environ["GCP_SERVICE_ACCOUNT_JSON"])
+client = bigquery.Client.from_service_account_info(service_account_info)
+query = "SELECT * FROM `upheld-magpie-314312.codebooks.codebooks_full`"
+query_job = client.query(query)
+df_codebooks = query_job.result().to_dataframe()
+
+
+def get_label_names(df, task):
+    task_df = df[df["task"] == task].sort_values(by="index")
+    label_names_dict = dict(zip(task_df["code"], task_df["name"]))
+    return label_names_dict
+
+
+def get_num_dict(df, task):
+    task_df = df[df["task"] == task].sort_values(by="index")
+    num_dict = dict(zip(task_df["index"], task_df["code"]))
+    return num_dict
+
+# NOTE: this is the same logic as in the Babel pipeline (different vairable names!)
+# key: task type (as in codebooks.codebooks_full)
+# value: (tuple) name of label_names, num_dict variables
+# TO-DO: we could replace all of these variables with one dict-like object
+
+task_names = {
+    "CAP": ("CAP_LABEL_NAMES", "CAP_NUM_DICT"),
+    "CAP_MINOR": ("CAP_MIN_LABEL_NAMES", "CAP_MIN_NUM_DICT"),
+    "CAP_MEDIA": ("CAP_MEDIA_LABEL_NAMES", "CAP_MEDIA_NUM_DICT"),
+    "CAP_MEDIA2": ("CAP_MEDIA2_LABEL_NAMES", "CAP_MEDIA2_DICT"),
+    "CAP_MINOR_MEDIA": ("CAP_MIN_MEDIA_LABEL_NAMES", "CAP_MIN_MEDIA_DICT"),
+    "MANIFESTO": ("MANIFESTO_LABEL_NAMES", "MANIFESTO_NUM_DICT"),
+    "SENTIMENT": ("SENTIMENT_LABEL_NAMES", "SENTIMENT_NUM_DICT"),
+    "EMOTION6": ("EMOTION_LABEL_NAMES", "EMOTION_NUM_DICT"),
+    "EMOTION9": ("EMOTION9_V2_LABEL_NAMES", "EMOTION9_V2_NUM_DICT"),
+    "EMOTION9_LEGACY": ("EMOTION9_LABEL_NAMES", "EMOTION9_NUM_DICT"),
+    "ILLFRAMES_MIGRATION": ("ILLFRAMES_MIGRATION_LABEL_NAMES", "ILLFRAMES_MIGRATION_NUM_DICT"),
+    "ILLFRAMES_COVID": ("ILLFRAMES_COVID_LABEL_NAMES", "ILLFRAMES_COVID_NUM_DICT"),
+    "ILLFRAMES_WAR": ("ILLFRAMES_WAR_LABEL_NAMES", "ILLFRAMES_WAR_NUM_DICT"),
+    "ONTOLISST": ("ONTOLISST_LABEL_NAMES", "ONTOLISST_NUM_DICT"),
+}
+
+for task, var_names in task_names.items():
+    label_name_var = var_names[0]
+    num_dict_var = var_names[1]
+    globals()[label_name_var] = get_label_names(df_codebooks, task)
+    globals()[num_dict_var] = get_num_dict(df_codebooks, task)