forked from munibanust/febrl
-
Notifications
You must be signed in to change notification settings - Fork 0
/
project-standardise.py
367 lines (309 loc) · 16.7 KB
/
project-standardise.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
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
# =============================================================================
# project-standardise.py - Configuration for a standardisation project.
#
# Freely extensible biomedical record linkage (Febrl) Version 0.2.2
# See http://datamining.anu.edu.au/projects/linkage.html
#
# =============================================================================
# AUSTRALIAN NATIONAL UNIVERSITY OPEN SOURCE LICENSE (ANUOS LICENSE)
# VERSION 1.1
#
# The contents of this file are subject to the ANUOS License Version 1.1 (the
# "License"); you may not use this file except in compliance with the License.
# Software distributed under the License is distributed on an "AS IS" basis,
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License for
# the specific language governing rights and limitations under the License.
# The Original Software is "project-standardise.py".
# The Initial Developers of the Original Software are Dr Peter Christen
# (Department of Computer Science, Australian National University) and Dr Tim
# Churches (Centre for Epidemiology and Research, New South Wales Department
# of Health). Copyright (C) 2002, 2003 the Australian National University and
# others. All Rights Reserved.
# Contributors:
#
# =============================================================================
"""Module project-standardise.py - Configuration for a standardisation project.
Briefly, what needs to be defined for a standardisation project is:
- A Febrl object, a project, plus a project logger
- One input data set (initialised in read access mode)
- One output data set (initialised in write or append access mode)
- Lookup tables to be used
- Standardisers for names, addresses and dates
and then the 'standardise' method can be called.
For more information see chapter
"Configuration and Running Febrl using a Module derived from 'project.py'"
in the Febrl manual.
This project module will standardised the example data set 'dataset1.csv'
given in the directory 'dbgen' into a data set 'dataset1clean.csv'.
"""
# =============================================================================
# Imports go here
import sys
import time
from febrl import * # Main Febrl classes
from dataset import * # Data set routines
from standardisation import * # Standardisation routines
from comparison import * # Comparison functions
from lookup import * # Look-up table routines
from indexing import * # Indexing and blocking routines
from simplehmm import * # Hidden Markov model (HMM) routines
from classification import * # Classifiers for weight vectors
# =============================================================================
# Set up Febrl and create a new project (or load a saved project)
myfebrl = Febrl(description = 'Example standardisation Febrl instance',
febrl_path = '.')
myproject = myfebrl.new_project(name = 'example-std',
description = 'Standardise example data set 1',
file_name = 'example-standardise.fbr',
block_size = 1000,
parallel_write = 'host')
# =============================================================================
# Define a project logger
mylog = ProjectLog(file_name = 'example-std.log',
project = myproject,
log_level = 1,
verbose_level = 1,
clear_log = True,
no_warn = False,
parallel_print = 'host')
# =============================================================================
# Define original input data set
#
indata = DataSetCSV(name = 'example1in',
description = 'Example data set 1',
access_mode = 'read',
header_lines = 1,
file_name = './dbgen/dataset1.csv',
fields = {'rec_id':0,
'given_name':1,
'surname':2,
'street_num':3,
'address_part_1':4,
'address_part_2':5,
'suburb':6,
'postcode':7,
'state':8,
'date_of_birth':9,
'soc_sec_id':10},
fields_default = '',
strip_fields = True,
missing_values = ['','missing'])
# =============================================================================
# Define the output data set
outdata = DataSetCSV(name = 'example1out',
description = 'Standardised example data set 1',
access_mode = 'write',
write_header = True,
file_name = './dbgen/dataset1clean.csv',
write_quote_char = '',
fields = {'title':1,
'gender_guess':2,
'given_name':3,
'alt_given_name':4,
'surname':5,
'alt_surname':6,
'wayfare_number':7,
'wayfare_name':8,
'wayfare_qualifier':9,
'wayfare_type':10,
'unit_number':11,
'unit_type':12,
'property_name':13,
'institution_name':14,
'institution_type':15,
'postaddress_number':16,
'postaddress_type':17,
'locality_name':18,
'locality_qualifier':19,
'postcode':20,
'territory':21,
'country':22,
'dob_day':23,
'dob_month':24,
'dob_year':25,
# The following are output fields that are passed without standardisation
'rec_id':0,
'soc_sec_id':26,
# The last output field contains the probability of the address HMM
'address_hmm_prob':27,
},
missing_values = ['','missing'])
# =============================================================================
# Define and load lookup tables
name_lookup_table = TagLookupTable(name = 'Name lookup table',
default = '')
name_lookup_table.load(['./data/givenname_f.tbl',
'./data/givenname_m.tbl',
'./data/name_prefix.tbl',
'./data/name_misc.tbl',
'./data/saints.tbl',
'./data/surname.tbl',
'./data/title.tbl'])
name_correction_list = CorrectionList(name = 'Name correction list')
name_correction_list.load('./data/name_corr.lst')
surname_freq_table = FrequencyLookupTable(name = 'Surname frequency table',
default = 1)
surname_freq_table.load('./data/surname_nsw_freq.csv')
address_lookup_table = TagLookupTable(name = 'Address lookup table',
default = '')
address_lookup_table.load(['./data/country.tbl',
'./data/address_misc.tbl',
'./data/address_qual.tbl',
'./data/institution_type.tbl',
'./data/locality_name_act.tbl',
'./data/locality_name_nsw.tbl',
'./data/post_address.tbl',
'./data/postcode_act.tbl',
'./data/postcode_nsw.tbl',
'./data/saints.tbl',
'./data/territory.tbl',
'./data/unit_type.tbl',
'./data/wayfare_type.tbl'])
address_correction_list = CorrectionList(name = 'Address correction list')
address_correction_list.load('./data/address_corr.lst')
pc_geocode_table = GeocodeLookupTable(name = 'NSW postcode locations',
default = [])
pc_geocode_table.load('./data/postcode_nsw_geocode.csv')
# =============================================================================
# Define and load hidden Markov models (HMMs)
name_states = ['titl','baby','knwn','andor','gname1','gname2','ghyph',
'gopbr','gclbr','agname1','agname2','coma','sname1','sname2',
'shyph','sopbr','sclbr','asname1','asname2','pref1','pref2',
'rubb']
name_tags = ['NU','AN','TI','PR','GF','GM','SN','ST','SP','HY','CO','NE','II',
'BO','VB','UN','RU']
myname_hmm = hmm('Name HMM', name_states, name_tags)
myname_hmm.load_hmm('./hmm/name-absdiscount.hmm')
# myname_hmm.load_hmm('./hmm/name.hmm')
# myname_hmm.load_hmm('./hmm/name-laplace.hmm')
address_states = ['wfnu','wfna1','wfna2','wfql','wfty','unnu','unty','prna1',
'prna2','inna1','inna2','inty','panu','paty','hyph','sla',
'coma','opbr','clbr','loc1','loc2','locql','pc','ter1',
'ter2','cntr1','cntr2','rubb']
address_tags = ['PC','N4','NU','AN','TR','CR','LN','ST','IN','IT','LQ','WT',
'WN','UT','HY','SL','CO','VB','PA','UN','RU']
myaddress_hmm = hmm('Address HMM', address_states, address_tags)
myaddress_hmm.load_hmm('./hmm/address-absdiscount.hmm')
# myaddress_hmm.load_hmm('./hmm/address.hmm')
# myaddress_hmm.load_hmm('./hmm/address-laplace.hmm')
# =============================================================================
# Define a list of date parsing format strings
date_parse_formats = ['%d %m %Y', # 24 04 2002 or 24 4 2002
'%d %B %Y', # 24 Apr 2002 or 24 April 2002
'%m %d %Y', # 04 24 2002 or 4 24 2002
'%B %d %Y', # Apr 24 2002 or April 24 2002
'%Y %m %d', # 2002 04 24 or 2002 4 24
'%Y %B %d', # 2002 Apr 24 or 2002 April 24
'%Y%m%d', # 20020424 ISO standard
'%d%m%Y', # 24042002
'%m%d%Y', # 04242002
'%d %m %y', # 24 04 02 or 24 4 02
'%d %B %y', # 24 Apr 02 or 24 April 02
'%y %m %d', # 02 04 24 or 02 4 24
'%y %B %d', # 02 Apr 24 or 02 April 24
'%m %d %y', # 04 24 02 or 4 24 02
'%B %d %y', # Apr 24 02 or April 24 02
'%y%m%d', # 020424
'%d%m%y', # 240402
'%m%d%y', # 042402
]
# =============================================================================
# Define standardisers for dates
dob_std = DateStandardiser(name = 'DOB-std',
description = 'Date of birth standardiser',
input_fields = 'date_of_birth',
output_fields = ['dob_day','dob_month', 'dob_year'],
parse_formats = date_parse_formats)
# =============================================================================
# Define a standardiser for names based on rules
name_rules_std = NameRulesStandardiser(name = 'Name-Rules',
input_fields = ['given_name','surname'],
output_fields = ['title',
'gender_guess',
'given_name',
'alt_given_name',
'surname',
'alt_surname'],
name_corr_list = name_correction_list,
name_tag_table = name_lookup_table,
male_titles = ['mr'],
female_titles = ['ms'],
field_separator = ' ',
check_word_spill = True)
# =============================================================================
# Define a standardiser for names based on HMM
name_hmm_std = NameHMMStandardiser(name = 'Name-HMM',
input_fields = ['given_name','surname'],
output_fields = ['title',
'gender_guess',
'given_name',
'alt_given_name',
'surname',
'alt_surname'],
name_corr_list = name_correction_list,
name_tag_table = name_lookup_table,
male_titles = ['mr'],
female_titles = ['ms'],
name_hmm = myname_hmm,
field_separator = ' ',
check_word_spill = True)
# =============================================================================
# Define a standardiser for addresses based on HMM
address_hmm_std = AddressHMMStandardiser(name = 'Address-HMM',
input_fields = ['street_num','address_part_1',
'address_part_2','suburb',
'postcode', 'state'],
output_fields = ['wayfare_number',
'wayfare_name',
'wayfare_qualifier',
'wayfare_type',
'unit_number',
'unit_type',
'property_name',
'institution_name',
'institution_type',
'postaddress_number',
'postaddress_type',
'locality_name',
'locality_qualifier',
'postcode',
'territory',
'country',
'address_hmm_prob'],
address_corr_list = address_correction_list,
address_tag_table = address_lookup_table,
address_hmm = myaddress_hmm)
# =============================================================================
# Define a pass field standardiser for all fields that should be passed from
# the input to the output data set without any cleaning or standardisdation.
pass_fields = PassFieldStandardiser(name = 'Pass fields',
input_fields = ['rec_id',
'soc_sec_id'],
output_fields = ['rec_id',
'soc_sec_id'])
# =============================================================================
# Define record standardiser(s) (one for each data set)
comp_stand = [dob_std, name_rules_std, address_hmm_std, pass_fields]
# The HMM based name standardisation is not used in the above standardiser,
# uncomment the lines below (and comment the ones above) to use HMM
# standardisation for names.
#
#comp_stand = [dob_std, name_hmm_std, address_hmm_std, pass_fields]
example_standardiser = RecordStandardiser(name = 'Example-std',
description = 'Example standardiser',
input_dataset = indata,
output_dataset = outdata,
comp_std = comp_stand)
# =============================================================================
# Start the standardisation task
# - If 'first_record' is set to 'None' then it will be set to 0
# - If 'number_records' is set to 'None' then it will be set to the total
# number of records in the input data set.
myproject.standardise(input_dataset = indata,
output_dataset = outdata,
rec_standardiser = example_standardiser,
first_record = 0,
number_records = 1000)
# =============================================================================
myfebrl.finalise()
# =============================================================================