-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathmatch_skeds_to_committees.py
247 lines (185 loc) · 10.3 KB
/
match_skeds_to_committees.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
""" the raw contribution files only give an id for the committee name; match them to the committee file. """
import csv
import settings
COMMITTEE_FILES = ['data/22/cm.txt', 'data/20/cm.txt', 'data/18/cm.txt', 'data/16/cm.txt', 'data/14/cm.txt', 'data/12/cm.txt', 'data/10/cm.txt', 'data/08/cm.txt']
CANDIDATE_FILES = ['data/22/cn.txt', 'data/20/cn.txt', 'data/18/cn.txt', 'data/16/cn.txt', 'data/14/cn.txt', 'data/12/cn.txt', 'data/10/cn.txt', 'data/08/cn.txt']
SKEDA_PROCESSED = settings.SCHEDULE_A_OUTFILE
SKEDA_OUTFILE = SKEDA_PROCESSED.replace(".csv", "_annotated.csv")
SKEDB_PROCESSED = settings.SCHEDULE_B_OUTFILE
SKEDB_OUTFILE = SKEDB_PROCESSED.replace(".csv", "_annotated.csv")
COMMITTEE_HEADERS = ['CMTE_ID', 'CMTE_NM', 'TRES_NM', 'CMTE_ST1', 'CMTE_ST2', 'CMTE_CITY', 'CMTE_ST', 'CMTE_ZIP', 'CMTE_DSGN', 'CMTE_TP', 'CMTE_PTY_AFFILIATION', 'CMTE_FILING_FREQ', 'ORG_TP', 'CONNECTED_ORG_NM', 'CAND_ID']
CANDIDATE_HEADERS = ['CAND_ID','CAND_NAME','CAND_PTY_AFFILIATION','CAND_ELECTION_YR','CAND_OFFICE_ST','CAND_OFFICE','CAND_OFFICE_DISTRICT','CAND_ICI','CAND_STATUS','CAND_PCC','CAND_ST1','CAND_ST2','CAND_CITY','CAND_ST','CAND_ZIP']
SKEDA_HEADERS = ['filing_number','line_sequence','form_type','filer_committee_id_number','transaction_id','back_reference_tran_id_number','back_reference_sched_name','entity_type','contributor_organization_name','contributor_name','contributor_last_name','contributor_first_name','contributor_middle_name','contributor_prefix','contributor_suffix','contributor_street_1','contributor_street_2','contributor_city','contributor_state','contributor_zip_code','election_code','election_other_description','contribution_date','contribution_amount','contribution_aggregate','contribution_purpose_descrip','contributor_employer','contributor_occupation','donor_committee_fec_id','donor_committee_name','donor_candidate_fec_id','donor_candidate_last_name','donor_candidate_first_name','donor_candidate_middle_name','donor_candidate_prefix','donor_candidate_suffix','donor_candidate_office','donor_candidate_state','donor_candidate_district','conduit_name','conduit_street1','conduit_street2','conduit_city','conduit_state','conduit_zip_code','memo_code','memo_text_description','reference_code']
SKEDA_RESULT_HEADERS = SKEDA_HEADERS + ['year','CMTE_NM', 'CMTE_ST1','CMTE_ST2','CMTE_CITY', 'CMTE_ST', 'CMTE_ZIP', 'CAND_ID', 'CAND_NAME']
SKEDB_HEADERS = ['filing_number','line_sequence','form_type','filer_committee_id_number','transaction_id_number','back_reference_tran_id_number','back_reference_sched_name','entity_type','payee_organization_name','payee_name', 'payee_last_name','payee_first_name','payee_middle_name','payee_prefix','payee_suffix','payee_street_1','payee_street_2','payee_city','payee_state','payee_zip_code','election_code','election_other_description','expenditure_date','expenditure_amount','semi_annual_refunded_bundled_amt','expenditure_purpose_descrip','category_code','beneficiary_committee_fec_id','beneficiary_committee_name','beneficiary_candidate_fec_id','beneficiary_candidate_last_name','beneficiary_candidate_first_name','beneficiary_candidate_middle_name','beneficiary_candidate_prefix','beneficiary_candidate_suffix','beneficiary_candidate_office','beneficiary_candidate_state','beneficiary_candidate_district','conduit_name','conduit_street_1','conduit_street_2','conduit_city','conduit_state','conduit_zip_code','memo_code','memo_text_description','reference_to_si_or_sl_system_code_that_identifies_the_account']
SKEDB_RESULT_HEADERS = SKEDB_HEADERS + ['year', 'CMTE_NM', 'CMTE_ST1','CMTE_ST2','CMTE_CITY', 'CMTE_ST', 'CMTE_ZIP', 'CAND_ID', 'CAND_NAME']
COMMITTEE_DICT_KEY = "%s-%s"
CANDIDATE_DICT_KEY = "%s-%s"
MIN_YEAR = 2021
def dictify_row(line, headers):
line = line.rstrip("\n")
line_array = line.split("|")
dict = {}
for i, header in enumerate(headers):
try:
dict[header]=line_array[i]
except IndexError:
dict[header] = None
return dict
def get_committee_dict():
print("Making committee dictionary")
comdict = {}
i=0
for committee_file in COMMITTEE_FILES:
year = committee_file.split("/")[1]
infile = open(committee_file, 'r')
while True:
i+=1
this_line = infile.readline()
if not this_line:
break
linedict = dictify_row(this_line, COMMITTEE_HEADERS)
committee_key = COMMITTEE_DICT_KEY % (linedict['CMTE_ID'], year)
comdict[committee_key] = {
'NAME':linedict['CMTE_NM'],
'CAND_ID':linedict['CAND_ID'],
'CMTE_ST1':linedict['CMTE_ST1'],
'CMTE_ST2':linedict['CMTE_ST2'],
'CMTE_CITY':linedict['CMTE_CITY'],
'CMTE_ST':linedict['CMTE_ST'],
'CMTE_ZIP':linedict['CMTE_ZIP'],
}
#print("adding key %s" % committee_key)
infile.close()
print("Created committee lookup with %s keys" % i)
return comdict
def get_candidate_dict():
print("Making candidate dictionary")
candict = {}
i=0
for candidate_file in CANDIDATE_FILES:
year = candidate_file.split("/")[1]
infile = open(candidate_file, 'r')
while True:
i+=1
this_line = infile.readline()
if not this_line:
break
linedict = dictify_row(this_line, CANDIDATE_HEADERS)
candidate_key = CANDIDATE_DICT_KEY % (linedict['CAND_ID'], year)
candict[candidate_key] = {
'CAND_NAME':linedict['CAND_NAME'],
}
#print("adding key %s %s" % (candidate_key, candict[candidate_key]))
infile.close()
print("Created candidate lookup with %s keys" % i)
return candict
def process_sked_a(committeedict, candidatedict, year):
f = open(SKEDA_OUTFILE % year, 'w')
dw = csv.DictWriter(f, fieldnames=SKEDA_RESULT_HEADERS)
dw.writeheader()
infile = open(SKEDA_PROCESSED % year, 'r')
reader = csv.DictReader(infile)
for (i,row) in enumerate(reader):
CMTE_NAME = ''
CMTE_ID = row['filer_committee_id_number']
raw_year = row['contribution_date']
year = 0
try:
year = int(raw_year[:4])
except ValueError:
#print("no year in %s line %s: %s" % (row['filing_number'], row['line_sequence'], raw_year))
continue
if year < MIN_YEAR:
continue
row['year'] = year
if year % 2 ==1:
year += 1
year_string = str(year)[-2:]
# add the committee name
committee_key = COMMITTEE_DICT_KEY % (CMTE_ID, year_string)
try:
thisdict = committeedict[committee_key]
#print("Got committee dict %s" % thisdict)
row['CMTE_NM'] = thisdict['NAME']
row['CAND_ID'] = thisdict['CAND_ID']
row['CMTE_ST1'] = thisdict['CMTE_ST1']
row['CMTE_ST2'] = thisdict['CMTE_ST2']
row['CMTE_CITY'] = thisdict['CMTE_CITY']
row['CMTE_ST'] = thisdict['CMTE_ST']
row['CMTE_ZIP'] = thisdict['CMTE_ZIP']
#print("Found match * %s %s" % (row['CMTE_NM'], committee_key))
except KeyError:
print("line %s: missing %s" % (i, committee_key))
dw.writerow(row)
continue
# add the candidate name, if applicable
if row['CAND_ID']:
candidate_key = CANDIDATE_DICT_KEY % (row['CAND_ID'], year_string)
try:
thisdict = candidatedict[candidate_key]
row['CAND_NAME'] = thisdict['CAND_NAME']
#print("Found match * %s %s" % (row['CMTE_NM'], committee_key))
except KeyError:
print("line %s: missing %s" % (i, committee_key))
pass
dw.writerow(row)
def process_sked_b(committeedict, candidatedict, year):
f = open(SKEDB_OUTFILE % year, 'w')
dw = csv.DictWriter(f, fieldnames=SKEDB_RESULT_HEADERS)
dw.writeheader()
infile = open(SKEDB_PROCESSED % year, 'r')
reader = csv.DictReader(infile)
for (i,row) in enumerate(reader):
CMTE_NAME = ''
CMTE_ID = row['filer_committee_id_number']
raw_year = row['expenditure_date']
year = 0
try:
year = int(raw_year[:4])
except ValueError:
#print("no year in %s line %s: %s" % (row['filing_number'], row['line_sequence'], raw_year))
continue
if year < MIN_YEAR:
continue
row['year'] = year
if year % 2 ==1:
year += 1
year_string = str(year)[-2:]
# add the committee name
committee_key = COMMITTEE_DICT_KEY % (CMTE_ID, year_string)
try:
thisdict = committeedict[committee_key]
#print("Got committee dict %s" % thisdict)
row['CMTE_NM'] = thisdict['NAME']
row['CAND_ID'] = thisdict['CAND_ID']
row['CMTE_ST1'] = thisdict['CMTE_ST1']
row['CMTE_ST2'] = thisdict['CMTE_ST2']
row['CMTE_CITY'] = thisdict['CMTE_CITY']
row['CMTE_ST'] = thisdict['CMTE_ST']
row['CMTE_ZIP'] = thisdict['CMTE_ZIP']
#print("Found match * %s %s" % (row['CMTE_NM'], committee_key))
except KeyError:
print("line %s: committee missing %s" % (i, committee_key))
dw.writerow(row)
continue
# add the candidate name, if applicable
if row['CAND_ID']:
candidate_key = CANDIDATE_DICT_KEY % (row['CAND_ID'], year_string)
try:
thisdict = candidatedict[candidate_key]
row['CAND_NAME'] = thisdict['CAND_NAME']
#print("Found match * %s %s" % (row['CMTE_NM'], committee_key))
except KeyError:
print("line %s: candidate missing %s" % (i, committee_key))
dw.writerow(row)
if __name__ == '__main__':
committeedict = get_committee_dict()
candidatedict = get_candidate_dict()
# YEARS = [2007, 2008, 2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018]
#YEARS = [2009, 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018]
YEARS = [2021, 2022, 2023]
for year in YEARS:
process_sked_a(committeedict, candidatedict, year)
process_sked_b(committeedict, candidatedict, year)
# TK F132.