deidkit 0.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (45) hide show
  1. deidkit/__init__.py +74 -0
  2. deidkit/__main__.py +6 -0
  3. deidkit/api.py +316 -0
  4. deidkit/cli.py +399 -0
  5. deidkit/config.py +285 -0
  6. deidkit/data/NOTICES.md +25 -0
  7. deidkit/data/context_triggers_en.txt +17 -0
  8. deidkit/data/context_triggers_es.txt +36 -0
  9. deidkit/data/en_given_names.txt +203 -0
  10. deidkit/data/en_surnames.txt +118 -0
  11. deidkit/data/es_given_names.txt +273 -0
  12. deidkit/data/es_surnames.txt +168 -0
  13. deidkit/data/honorifics_en.txt +22 -0
  14. deidkit/data/honorifics_es.txt +35 -0
  15. deidkit/data/medical_stoplist_en.txt +345 -0
  16. deidkit/data/medical_stoplist_es.txt +499 -0
  17. deidkit/data/medical_vocab.txt +21445 -0
  18. deidkit/dates.py +229 -0
  19. deidkit/detect/__init__.py +19 -0
  20. deidkit/detect/checksums.py +160 -0
  21. deidkit/detect/context.py +137 -0
  22. deidkit/detect/gazetteer.py +158 -0
  23. deidkit/detect/patterns.py +147 -0
  24. deidkit/detect/pipeline.py +234 -0
  25. deidkit/detect/spacy_ner.py +53 -0
  26. deidkit/detect/types.py +53 -0
  27. deidkit/engine.py +644 -0
  28. deidkit/generators/__init__.py +4 -0
  29. deidkit/generators/names.py +111 -0
  30. deidkit/generators/surrogates.py +76 -0
  31. deidkit/io.py +184 -0
  32. deidkit/learn.py +83 -0
  33. deidkit/mapping.py +108 -0
  34. deidkit/report.py +219 -0
  35. deidkit/resources.py +100 -0
  36. deidkit/schema.py +234 -0
  37. deidkit/secret.py +77 -0
  38. deidkit/textnorm.py +66 -0
  39. deidkit/version.py +3 -0
  40. deidkit-0.1.0.dist-info/METADATA +768 -0
  41. deidkit-0.1.0.dist-info/RECORD +45 -0
  42. deidkit-0.1.0.dist-info/WHEEL +5 -0
  43. deidkit-0.1.0.dist-info/entry_points.txt +2 -0
  44. deidkit-0.1.0.dist-info/licenses/LICENSE +21 -0
  45. deidkit-0.1.0.dist-info/top_level.txt +1 -0
@@ -0,0 +1,25 @@
1
+ # Data notices — bundled medical safe-vocabulary
2
+
3
+ `medical_vocab.txt` is a DERIVED list of single word-tokens (accent-folded,
4
+ lowercased) used only to keep medical terms from being flagged as person names.
5
+ It contains no codes, no mappings, and no patient data. Known person names and
6
+ common medical eponyms (e.g. Parkinson) are excluded so real patient names are
7
+ not suppressed.
8
+
9
+ Derived from:
10
+
11
+ - **ICD-10-CM** — International Classification of Diseases, 10th Revision,
12
+ Clinical Modification. U.S. public domain (CMS / CDC / NCHS).
13
+ - **RxNorm** — U.S. National Library of Medicine (NLM). The prescribe subset is
14
+ freely redistributable; see the RxNorm terms. This product uses publicly
15
+ available data courtesy of the U.S. NLM; it is not endorsed or certified by
16
+ the NLM.
17
+
18
+ Not bundled (add locally via `--extra-stoplist-file` / the vocab builder):
19
+
20
+ - **LOINC** — © Regenstrief Institute, Inc. Free to use under the LOINC license;
21
+ redistribution requires including the LOINC license/notice, so it is not
22
+ bundled here. Provide `Loinc.csv` to `tools/build_medical_vocab.py --loinc`.
23
+ - **SNOMED CT / UMLS / MedDRA** — license-gated; load locally, do not bundle.
24
+
25
+ Rebuild with `tools/build_medical_vocab.py` pointing at your local files.
@@ -0,0 +1,17 @@
1
+ patient
2
+ companion
3
+ guardian
4
+ mother
5
+ father
6
+ son
7
+ daughter
8
+ spouse
9
+ relative
10
+ caregiver
11
+ name
12
+ surname
13
+ signed
14
+ signature
15
+ sincerely
16
+ referred
17
+ attended
@@ -0,0 +1,36 @@
1
+ paciente
2
+ acompanante
3
+ responsable
4
+ madre
5
+ padre
6
+ hijo
7
+ hija
8
+ esposo
9
+ esposa
10
+ familiar
11
+ informante
12
+ cuidador
13
+ cuidadora
14
+ tutor
15
+ tutora
16
+ atendido
17
+ atendida
18
+ remitido
19
+ remite
20
+ valorado
21
+ valorada
22
+ nombre
23
+ apellido
24
+ firma
25
+ atentamente
26
+ cordialmente
27
+ refiere
28
+ acude
29
+ solicita
30
+ elabora
31
+ realiza
32
+ diligencia
33
+ nombres
34
+ apellidos
35
+ suscribe
36
+ firmado
@@ -0,0 +1,203 @@
1
+ aaron m
2
+ abigail f
3
+ adam m
4
+ alan m
5
+ albert m
6
+ alexander m
7
+ alexis f
8
+ alice f
9
+ amanda f
10
+ amber f
11
+ amy f
12
+ andrea f
13
+ andrew m
14
+ angela f
15
+ ann f
16
+ anna f
17
+ anthony m
18
+ arthur m
19
+ ashley f
20
+ austin m
21
+ barbara f
22
+ benjamin m
23
+ betty f
24
+ beverly f
25
+ billy m
26
+ bobby m
27
+ bradley m
28
+ brandon m
29
+ brenda f
30
+ brian m
31
+ brittany f
32
+ bruce m
33
+ bryan m
34
+ caleb m
35
+ cameron m
36
+ carl m
37
+ carol f
38
+ carolyn f
39
+ catherine f
40
+ charles m
41
+ charlotte f
42
+ cheryl f
43
+ christian m
44
+ christina f
45
+ christine f
46
+ christopher m
47
+ cody m
48
+ cynthia f
49
+ daniel m
50
+ danielle f
51
+ david m
52
+ deborah f
53
+ debra f
54
+ denise f
55
+ dennis m
56
+ diana f
57
+ diane f
58
+ donald m
59
+ donna f
60
+ doris f
61
+ dorothy f
62
+ douglas m
63
+ dylan m
64
+ edward m
65
+ elizabeth f
66
+ emily f
67
+ emma f
68
+ eric m
69
+ ethan m
70
+ eugene m
71
+ evelyn f
72
+ frances f
73
+ frank m
74
+ gabriel m
75
+ gary m
76
+ george m
77
+ gerald m
78
+ gloria f
79
+ grace f
80
+ gregory m
81
+ hannah f
82
+ harold m
83
+ heather f
84
+ helen f
85
+ henry m
86
+ isabella f
87
+ jack m
88
+ jacob m
89
+ jacqueline f
90
+ james m
91
+ janet f
92
+ janice f
93
+ jason m
94
+ jean f
95
+ jeffrey m
96
+ jennifer f
97
+ jeremy m
98
+ jerry m
99
+ jesse m
100
+ jessica f
101
+ joan f
102
+ joe m
103
+ john m
104
+ johnny m
105
+ jonathan m
106
+ jordan m
107
+ joseph m
108
+ joshua m
109
+ joyce f
110
+ judith f
111
+ judy f
112
+ julia f
113
+ julie f
114
+ justin m
115
+ karen f
116
+ katherine f
117
+ kathleen f
118
+ kathryn f
119
+ kayla f
120
+ keith m
121
+ kelly f
122
+ kenneth m
123
+ kevin m
124
+ kimberly f
125
+ kyle m
126
+ larry m
127
+ laura f
128
+ lauren f
129
+ lawrence m
130
+ linda f
131
+ lisa f
132
+ logan m
133
+ lori f
134
+ louis m
135
+ madison f
136
+ margaret f
137
+ marie f
138
+ marilyn f
139
+ mark m
140
+ martha f
141
+ mary f
142
+ matthew m
143
+ megan f
144
+ melissa f
145
+ michael m
146
+ michelle f
147
+ nancy f
148
+ natalie f
149
+ nathan m
150
+ nathaniel m
151
+ nicholas m
152
+ nicole f
153
+ noah m
154
+ olivia f
155
+ pamela f
156
+ patricia f
157
+ patrick m
158
+ paul m
159
+ peter m
160
+ philip m
161
+ rachel f
162
+ ralph m
163
+ randy m
164
+ raymond m
165
+ rebecca f
166
+ richard m
167
+ robert m
168
+ roger m
169
+ ronald m
170
+ roy m
171
+ russell m
172
+ ruth f
173
+ ryan m
174
+ samantha f
175
+ samuel m
176
+ sandra f
177
+ sara f
178
+ sarah f
179
+ scott m
180
+ sean m
181
+ sharon f
182
+ shirley f
183
+ sophia f
184
+ stephanie f
185
+ stephen m
186
+ steven m
187
+ susan f
188
+ teresa f
189
+ terry m
190
+ theresa f
191
+ thomas m
192
+ tiffany f
193
+ timothy m
194
+ travis m
195
+ tyler m
196
+ victoria f
197
+ vincent m
198
+ virginia f
199
+ walter m
200
+ wayne m
201
+ william m
202
+ willie m
203
+ zachary m
@@ -0,0 +1,118 @@
1
+ smith
2
+ johnson
3
+ williams
4
+ brown
5
+ jones
6
+ garcia
7
+ miller
8
+ davis
9
+ rodriguez
10
+ martinez
11
+ hernandez
12
+ lopez
13
+ gonzalez
14
+ wilson
15
+ anderson
16
+ thomas
17
+ taylor
18
+ moore
19
+ jackson
20
+ martin
21
+ lee
22
+ perez
23
+ thompson
24
+ white
25
+ harris
26
+ sanchez
27
+ clark
28
+ ramirez
29
+ lewis
30
+ robinson
31
+ walker
32
+ young
33
+ allen
34
+ king
35
+ wright
36
+ scott
37
+ torres
38
+ nguyen
39
+ hill
40
+ flores
41
+ green
42
+ adams
43
+ nelson
44
+ baker
45
+ hall
46
+ rivera
47
+ campbell
48
+ mitchell
49
+ carter
50
+ roberts
51
+ gomez
52
+ phillips
53
+ evans
54
+ turner
55
+ diaz
56
+ parker
57
+ cruz
58
+ edwards
59
+ collins
60
+ reyes
61
+ stewart
62
+ morris
63
+ morales
64
+ murphy
65
+ cook
66
+ rogers
67
+ gutierrez
68
+ ortiz
69
+ morgan
70
+ cooper
71
+ peterson
72
+ bailey
73
+ reed
74
+ kelly
75
+ howard
76
+ ramos
77
+ kim
78
+ cox
79
+ ward
80
+ richardson
81
+ watson
82
+ brooks
83
+ chavez
84
+ wood
85
+ james
86
+ bennett
87
+ gray
88
+ mendoza
89
+ ruiz
90
+ hughes
91
+ price
92
+ alvarez
93
+ castillo
94
+ sanders
95
+ patel
96
+ myers
97
+ long
98
+ ross
99
+ foster
100
+ jimenez
101
+ powell
102
+ jenkins
103
+ perry
104
+ russell
105
+ sullivan
106
+ bell
107
+ coleman
108
+ butler
109
+ henderson
110
+ barnes
111
+ gonzales
112
+ fisher
113
+ vasquez
114
+ simmons
115
+ romero
116
+ jordan
117
+ patterson
118
+ alexander
@@ -0,0 +1,273 @@
1
+ adrian m
2
+ adriana f
3
+ agustin m
4
+ alba f
5
+ albeiro m
6
+ alberto m
7
+ alejandra f
8
+ alejandro m
9
+ alexander m
10
+ alfonso m
11
+ alicia f
12
+ alvaro m
13
+ amelia f
14
+ amparo f
15
+ ana f
16
+ anderson m
17
+ andrea f
18
+ andres m
19
+ angel m
20
+ angela f
21
+ angie f
22
+ anibal m
23
+ antonia f
24
+ antonio m
25
+ araceli f
26
+ aristides m
27
+ armando m
28
+ arturo m
29
+ aurelio m
30
+ aurora f
31
+ beatriz f
32
+ benjamin m
33
+ bernardo m
34
+ blanca f
35
+ brandon m
36
+ brayan m
37
+ brenda f
38
+ bruno m
39
+ camila f
40
+ camilo m
41
+ carlos m
42
+ carmen f
43
+ carolina f
44
+ catalina f
45
+ cecilia f
46
+ cesar m
47
+ ciro m
48
+ claudia f
49
+ consuelo f
50
+ cristhian m
51
+ cristian m
52
+ cristina f
53
+ damian m
54
+ daniel m
55
+ daniela f
56
+ dario m
57
+ david m
58
+ dayana f
59
+ deisy f
60
+ diana f
61
+ diego m
62
+ dolores f
63
+ dora f
64
+ duvan m
65
+ dylan m
66
+ eduardo m
67
+ edwin m
68
+ efrain m
69
+ elena f
70
+ elias m
71
+ eliecer m
72
+ elizabeth f
73
+ emiliano m
74
+ emilio m
75
+ emma f
76
+ emmanuel m
77
+ enzo m
78
+ ernesto m
79
+ esperanza f
80
+ esteban m
81
+ estefania f
82
+ estela f
83
+ esther f
84
+ euclides m
85
+ eugenia f
86
+ ezequiel m
87
+ fabian m
88
+ fabiola f
89
+ facundo m
90
+ federico m
91
+ felipe m
92
+ fernanda f
93
+ fernando m
94
+ flor f
95
+ francisca f
96
+ francisco m
97
+ franco m
98
+ gabriel m
99
+ gabriela f
100
+ gael m
101
+ geraldine f
102
+ german m
103
+ gilberto m
104
+ gloria f
105
+ graciela f
106
+ gregorio m
107
+ guadalupe f
108
+ guillermo m
109
+ gustavo m
110
+ harold m
111
+ heidy f
112
+ heriberto m
113
+ hernan m
114
+ hilda f
115
+ hugo m
116
+ humberto m
117
+ ian m
118
+ ignacio m
119
+ ines f
120
+ irene f
121
+ isaac m
122
+ isabella f
123
+ isidro m
124
+ ivan m
125
+ ivonne f
126
+ jacqueline f
127
+ jaime m
128
+ jairo m
129
+ javier m
130
+ jenny f
131
+ jessica f
132
+ jesus m
133
+ jheison m
134
+ jhon m
135
+ jhonatan m
136
+ joaquin m
137
+ joel m
138
+ johan m
139
+ johana f
140
+ jorge m
141
+ jose m
142
+ josefina f
143
+ juan m
144
+ juana f
145
+ julian m
146
+ juliana f
147
+ karen f
148
+ katherine f
149
+ kelly f
150
+ kevin m
151
+ laura f
152
+ leidy f
153
+ leon m
154
+ leonardo m
155
+ leopoldo m
156
+ leticia f
157
+ liliana f
158
+ lina f
159
+ lorenzo m
160
+ lourdes f
161
+ lucia f
162
+ luciana f
163
+ luis m
164
+ luisa f
165
+ luz f
166
+ mabel f
167
+ magdalena f
168
+ maicol m
169
+ maite f
170
+ manuel m
171
+ manuela f
172
+ marcela f
173
+ marcelo m
174
+ marcos m
175
+ margarita f
176
+ maria f
177
+ mariana f
178
+ maribel f
179
+ marino m
180
+ mario m
181
+ marisol f
182
+ martha f
183
+ martin m
184
+ mateo m
185
+ matias m
186
+ mauricio m
187
+ maximiliano m
188
+ mayra f
189
+ melissa f
190
+ mercedes f
191
+ michelle f
192
+ miguel m
193
+ milena f
194
+ moises m
195
+ monica f
196
+ nancy f
197
+ natalia f
198
+ nataly f
199
+ nelson m
200
+ nicolas m
201
+ nidia f
202
+ nolberto m
203
+ norma f
204
+ nubia f
205
+ octavio m
206
+ olga f
207
+ omaira f
208
+ orlando m
209
+ oscar m
210
+ osvaldo m
211
+ pablo m
212
+ paola f
213
+ patricia f
214
+ patricio m
215
+ paula f
216
+ pedro m
217
+ pilar f
218
+ rafael m
219
+ ramon m
220
+ raquel f
221
+ raul m
222
+ reinaldo m
223
+ ricardo m
224
+ roberto m
225
+ rocio f
226
+ rodrigo m
227
+ rosa f
228
+ ruben m
229
+ ruth f
230
+ salome f
231
+ salvador m
232
+ samuel m
233
+ sandra f
234
+ santiago m
235
+ sara f
236
+ saul m
237
+ sebastian m
238
+ sergio m
239
+ silvia f
240
+ sirley f
241
+ socorro f
242
+ sofia f
243
+ soledad f
244
+ stella f
245
+ tatiana f
246
+ teodoro m
247
+ teresa f
248
+ thiago m
249
+ tobias m
250
+ tomas m
251
+ ulises m
252
+ valentin m
253
+ valentina f
254
+ valeria f
255
+ veronica f
256
+ vicente m
257
+ victor m
258
+ victoria f
259
+ viviana f
260
+ walter m
261
+ wilfredo m
262
+ wilmer m
263
+ wilson m
264
+ ximena f
265
+ yaneth f
266
+ yeison m
267
+ yenny f
268
+ yesica f
269
+ yesid m
270
+ yolanda f
271
+ yonatan m
272
+ yuliana f
273
+ zulma f