generate_data.py

"""Generate kenya-data.ts from shapefile ward JSON + constituency CSV."""
import json

# County ID to name mapping (IEBC official order)
COUNTY_MAP = {
    1: "Baringo", 2: "Bomet", 3: "Bungoma", 4: "Busia",
    5: "Elgeyo-Marakwet", 6: "Embu", 7: "Garissa", 8: "Homa Bay",
    9: "Isiolo", 10: "Kajiado", 11: "Kakamega", 12: "Kericho",
    13: "Kiambu", 14: "Kilifi", 15: "Kirinyaga", 16: "Kisii",
    17: "Kisumu", 18: "Kitui", 19: "Kwale", 20: "Laikipia",
    21: "Lamu", 22: "Machakos", 23: "Makueni", 24: "Mandera",
    25: "Marsabit", 26: "Meru", 27: "Migori", 28: "Mombasa",
    29: "Muranga", 30: "Nairobi", 31: "Nakuru", 32: "Nandi",
    33: "Narok", 34: "Nyamira", 35: "Nyandarua", 36: "Nyeri",
    37: "Samburu", 38: "Siaya", 39: "Taita Taveta", 40: "Tana River",
    41: "Tharaka-Nithi", 42: "Trans Nzoia", 43: "Turkana",
    44: "Uasin Gishu", 45: "Vihiga", 46: "Wajir", 47: "West Pokot",
}

# Constituency CSV data (id,name,county_id)
CONSTITUENCIES_RAW = """1,CHANGAMWE,28
2,JOMVU,28
3,KISAUNI,28
4,NYALI,28
5,LIKONI,28
6,MVITA,28
7,MSAMBWENI,19
8,LUNGALUNGA,19
9,MATUGA,19
10,KINANGO,19
11,KILIFI NORTH,14
12,KILIFI SOUTH,14
13,KALOLENI,14
14,RABAI,14
15,GANZE,14
16,MALINDI,14
17,MAGARINI,14
18,GARSEN,40
19,GALOLE,40
20,BURA,40
21,LAMU EAST,21
22,LAMU WEST,21
23,TAVETA,39
24,WUNDANYI,39
25,MWATATE,39
26,VOI,39
27,GARISSA TOWNSHIP,7
28,BALAMBALA,7
29,LAGDERA,7
30,DADAAB,7
31,FAFI,7
32,IJARA,7
33,WAJIR NORTH,46
34,WAJIR EAST,46
35,TARBAJ,46
36,WAJIR WEST,46
37,ELDAS,46
38,WAJIR SOUTH,46
39,MANDERA WEST,24
40,BANISSA,24
41,MANDERA NORTH,24
42,MANDERA SOUTH,24
43,MANDERA EAST,24
44,LAFEY,24
45,MOYALE,25
46,NORTH HORR,25
47,SAKU,25
48,LAISAMIS,25
49,ISIOLO NORTH,9
50,ISIOLO SOUTH,9
51,IGEMBE SOUTH,26
52,IGEMBE CENTRAL,26
53,IGEMBE NORTH,26
54,TIGANIA WEST,26
55,TIGANIA EAST,26
56,NORTH IMENTI,26
57,BUURI,26
58,CENTRAL IMENTI,26
59,SOUTH IMENTI,26
60,MAARA,41
61,CHUKA/IGAMBANG'OMBE,41
62,THARAKA,41
63,MANYATTA,6
64,RUNYENJES,6
65,MBEERE SOUTH,6
66,MBEERE NORTH,6
67,MWINGI NORTH,18
68,MWINGI WEST,18
69,MWINGI CENTRAL,18
70,KITUI WEST,18
71,KITUI RURAL,18
72,KITUI CENTRAL,18
73,KITUI EAST,18
74,KITUI SOUTH,18
75,MASINGA,22
76,YATTA,22
77,KANGUNDO,22
78,MATUNGULU,22
79,KATHIANI,22
80,MAVOKO,22
81,MACHAKOS TOWN,22
82,MWALA,22
83,MBOONI,23
84,KILOME,23
85,KAITI,23
86,MAKUENI,23
87,KIBWEZI WEST,23
88,KIBWEZI EAST,23
89,KINANGOP,35
90,KIPIPIRI,35
91,OL KALOU,35
92,OL JOROK,35
93,NDARAGWA,35
94,TETU,36
95,KIENI,36
96,MATHIRA,36
97,OTHAYA,36
98,MUKURWEINI,36
99,NYERI TOWN,36
100,MWEA,15
101,GICHUGU,15
102,NDIA,15
103,KIRINYAGA CENTRAL,15
104,KANGEMA,29
105,MATHIOYA,29
106,KIHARU,29
107,KIGUMO,29
108,MARAGWA,29
109,KANDARA,29
110,GATANGA,29
111,GATUNDU SOUTH,13
112,GATUNDU NORTH,13
113,JUJA,13
114,THIKA TOWN,13
115,RUIRU,13
116,GITHUNGURI,13
117,KIAMBU,13
118,KIAMBAA,13
119,KABETE,13
120,KIKUYU,13
121,LIMURU,13
122,LARI,13
123,TURKANA NORTH,43
124,TURKANA WEST,43
125,TURKANA CENTRAL,43
126,LOIMA,43
127,TURKANA SOUTH,43
128,TURKANA EAST,43
129,KAPENGURIA,47
130,SIGOR,47
131,KACHELIBA,47
132,POKOT SOUTH,47
133,SAMBURU WEST,37
134,SAMBURU NORTH,37
135,SAMBURU EAST,37
136,KWANZA,42
137,ENDEBESS,42
138,SABOTI,42
139,KIMININI,42
140,CHERANGANY,42
141,SOY,44
142,TURBO,44
143,MOIBEN,44
144,AINABKOI,44
145,KAPSERET,44
146,KESSES,44
147,MARAKWET EAST,5
148,MARAKWET WEST,5
149,KEIYO NORTH,5
150,KEIYO SOUTH,5
151,TINDERET,32
152,ALDAI,32
153,NANDI HILLS,32
154,CHESUMEI,32
155,EMGWEN,32
156,MOSOP,32
157,TIATY,1
158,BARINGO NORTH,1
159,BARINGO CENTRAL,1
160,BARINGO SOUTH,1
161,MOGOTIO,1
162,ELDAMA RAVINE,1
163,LAIKIPIA WEST,20
164,LAIKIPIA EAST,20
165,LAIKIPIA NORTH,20
166,MOLO,31
167,NJORO,31
168,NAIVASHA,31
169,GILGIL,31
170,KURESOI SOUTH,31
171,KURESOI NORTH,31
172,SUBUKIA,31
173,RONGAI,31
174,BAHATI,31
175,NAKURU TOWN WEST,31
176,NAKURU TOWN EAST,31
177,KILGORIS,33
178,EMURUA DIKIRR,33
179,NAROK NORTH,33
180,NAROK EAST,33
181,NAROK SOUTH,33
182,NAROK WEST,33
183,KAJIADO NORTH,10
184,KAJIADO CENTRAL,10
185,KAJIADO EAST,10
186,KAJIADO WEST,10
187,KAJIADO SOUTH,10
188,KIPKELION EAST,12
189,KIPKELION WEST,12
190,AINAMOI,12
191,BURETI,12
192,BELGUT,12
193,SIGOWET/SOIN,12
194,SOTIK,2
195,CHEPALUNGU,2
196,BOMET EAST,2
197,BOMET CENTRAL,2
198,KONOIN,2
199,LUGARI,11
200,LIKUYANI,11
201,MALAVA,11
202,LURAMBI,11
203,NAVAKHOLO,11
204,MUMIAS WEST,11
205,MUMIAS EAST,11
206,MATUNGU,11
207,BUTERE,11
208,KHWISERO,11
209,SHINYALU,11
210,IKOLOMANI,11
211,VIHIGA,45
212,SABATIA,45
213,HAMISI,45
214,LUANDA,45
215,EMUHAYA,45
216,MT. ELGON,3
217,SIRISIA,3
218,KABUCHAI,3
219,BUMULA,3
220,KANDUYI,3
221,WEBUYE EAST,3
222,WEBUYE WEST,3
223,KIMILILI,3
224,TONGAREN,3
225,TESO NORTH,4
226,TESO SOUTH,4
227,NAMBALE,4
228,MATAYOS,4
229,BUTULA,4
230,FUNYULA,4
231,BUDALANGI,4
232,UGENYA,38
233,UGUNJA,38
234,ALEGO USONGA,38
235,GEM,38
236,BONDO,38
237,RARIEDA,38
238,KISUMU EAST,17
239,KISUMU WEST,17
240,KISUMU CENTRAL,17
241,SEME,17
242,NYANDO,17
243,MUHORONI,17
244,NYAKACH,17
245,KASIPUL,8
246,KABONDO KASIPUL,8
247,KARACHUONYO,8
248,RANGWE,8
249,HOMA BAY TOWN,8
250,NDHIWA,8
251,SUBA NORTH,8
252,SUBA SOUTH,8
253,RONGO,27
254,AWENDO,27
255,SUNA EAST,27
256,SUNA WEST,27
257,URIRI,27
258,NYATIKE,27
259,KURIA WEST,27
260,KURIA EAST,27
261,BONCHARI,16
262,SOUTH MUGIRANGO,16
263,BOMACHOGE BORABU,16
264,BOBASI,16
265,BOMACHOGE CHACHE,16
266,NYARIBARI MASABA,16
267,NYARIBARI CHACHE,16
268,KITUTU CHACHE NORTH,16
269,KITUTU CHACHE SOUTH,16
270,KITUTU MASABA,34
271,WEST MUGIRANGO,34
272,NORTH MUGIRANGO,34
273,BORABU,34
274,WESTLANDS,30
275,DAGORETTI NORTH,30
276,DAGORETTI SOUTH,30
277,LANGATA,30
278,KIBRA,30
279,ROYSAMBU,30
280,KASARANI,30
281,RUARAKA,30
282,EMBAKASI SOUTH,30
283,EMBAKASI NORTH,30
284,EMBAKASI CENTRAL,30
285,EMBAKASI EAST,30
286,EMBAKASI WEST,30
287,MAKADARA,30
288,KAMUKUNJI,30
289,STAREHE,30
290,MATHARE,30"""

# Parse constituencies
county_constituencies = {}
for line in CONSTITUENCIES_RAW.strip().split('\n'):
    parts = line.split(',')
    cid = int(parts[0])
    name = parts[1].strip()
    county_id = int(parts[2])
    county_name = COUNTY_MAP[county_id]
    if county_name not in county_constituencies:
        county_constituencies[county_name] = []
    county_constituencies[county_name].append(name.title())

# Load ward data from shapefile extraction
with open(r'D:\CEKA\ceka v010\report-malpractice\kenya_wards_raw.json', 'r') as f:
    ward_data = json.load(f)

# Build TypeScript output
lines = []
lines.append('// Auto-generated from:')
lines.append('// 1. Kenya_Wards shapefile (D:\\CEKA\\NASAKA\\NASAKA CONTEXT\\KENYA\\WARDS\\Kenya_Wards\\kenya_wards.shp)')
lines.append('// 2. IEBC Constituency CSV (290 constituencies)')
lines.append('// 47 Counties, 290 Constituencies, 1450 Wards')
lines.append('')
lines.append('export interface Ward {')
lines.append('  name: string;')
lines.append('}')
lines.append('')
lines.append('export interface Constituency {')
lines.append('  name: string;')
lines.append('  wards: string[];')
lines.append('}')
lines.append('')
lines.append('export interface County {')
lines.append('  name: string;')
lines.append('  constituencies: Constituency[];')
lines.append('}')
lines.append('')
lines.append('export const KENYA_LOCATIONS: County[] = [')

for county_name in sorted(COUNTY_MAP.values()):
    lines.append('  {')
    lines.append(f'    name: "{county_name}",')
    lines.append('    constituencies: [')
    
    constituencies = county_constituencies.get(county_name, [])
    subcounties = ward_data.get(county_name, {})
    
    for const_name in sorted(constituencies):
        # Try to find matching subcounty wards
        wards = []
        const_upper = const_name.upper()
        for sc_name, sc_wards in subcounties.items():
            sc_upper = sc_name.upper()
            # Match subcounty to constituency (fuzzy match)
            if (sc_upper == const_upper or
                sc_upper in const_upper or
                const_upper in sc_upper or
                sc_upper.replace(' ', '') == const_upper.replace(' ', '') or
                sc_upper.split()[0] == const_upper.split()[0]):
                wards.extend(sc_wards)
        
        # Deduplicate and sort wards
        wards = sorted(set(wards))
        ward_strs = ', '.join([f'"{w}"' for w in wards])
        
        lines.append('      {')
        lines.append(f'        name: "{const_name}",')
        lines.append(f'        wards: [{ward_strs}],')
        lines.append('      },')
    
    lines.append('    ],')
    lines.append('  },')

lines.append('];')
lines.append('')
lines.append('export const getCounties = (): string[] => KENYA_LOCATIONS.map(c => c.name);')
lines.append('')
lines.append('export const getConstituencies = (county: string): string[] => {')
lines.append('  const loc = KENYA_LOCATIONS.find(c => c.name === county);')
lines.append('  return loc ? loc.constituencies.map(c => c.name) : [];')
lines.append('};')
lines.append('')
lines.append('export const getWards = (county: string, constituency: string): string[] => {')
lines.append('  const loc = KENYA_LOCATIONS.find(c => c.name === county);')
lines.append('  if (!loc) return [];')
lines.append('  const con = loc.constituencies.find(c => c.name === constituency);')
lines.append('  return con ? con.wards : [];')
lines.append('};')

output_path = r'D:\CEKA\ceka v010\report-malpractice\src\lib\kenya-data.ts'
with open(output_path, 'w', encoding='utf-8') as f:
    f.write('\n'.join(lines) + '\n')

# Stats
total_const = sum(len(v) for v in county_constituencies.values())
total_wards_mapped = 0
for county_name in COUNTY_MAP.values():
    constituencies = county_constituencies.get(county_name, [])
    subcounties = ward_data.get(county_name, {})
    for const_name in constituencies:
        const_upper = const_name.upper()
        for sc_name, sc_wards in subcounties.items():
            sc_upper = sc_name.upper()
            if (sc_upper == const_upper or sc_upper in const_upper or const_upper in sc_upper or
                sc_upper.replace(' ', '') == const_upper.replace(' ', '') or
                sc_upper.split()[0] == const_upper.split()[0]):
                total_wards_mapped += len(sc_wards)

print(f'Written: {output_path}')
print(f'Counties: {len(COUNTY_MAP)}')
print(f'Constituencies: {total_const}')
print(f'Wards mapped: {total_wards_mapped}')