meta-edc 1.0.6__py3-none-any.whl → 1.0.7__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.
- meta_analytics/dataframes/__init__.py +3 -0
- meta_analytics/dataframes/constants.py +1 -1
- meta_analytics/dataframes/enrolled/__init__.py +0 -1
- meta_analytics/dataframes/get_eos_df.py +15 -2
- meta_analytics/dataframes/get_glucose_df.py +149 -0
- meta_analytics/dataframes/get_glucose_fbg_df.py +27 -0
- meta_analytics/dataframes/get_glucose_fbg_ogtt_df.py +22 -0
- meta_analytics/dataframes/glucose_endpoints/endpoint_by_date.py +106 -120
- meta_analytics/dataframes/glucose_endpoints/glucose_endpoints_by_date.py +36 -227
- meta_analytics/dataframes/utils.py +18 -4
- meta_analytics/notebooks/hiv_regimens.ipynb +425 -0
- meta_analytics/notebooks/monitoring_report.ipynb +1561 -0
- meta_analytics/notebooks/pharmacy.ipynb +971 -0
- meta_analytics/utils.py +81 -0
- {meta_edc-1.0.6.dist-info → meta_edc-1.0.7.dist-info}/METADATA +4 -3
- {meta_edc-1.0.6.dist-info → meta_edc-1.0.7.dist-info}/RECORD +32 -18
- {meta_edc-1.0.6.dist-info → meta_edc-1.0.7.dist-info}/WHEEL +1 -1
- meta_edc-1.0.7.dist-info/licenses/AUTHORS.rst +8 -0
- meta_reports/migrations/0054_auto_20250422_2003.py +81 -0
- meta_reports/migrations/0055_alter_glucosesummary_table.py +17 -0
- meta_reports/migrations/0056_auto_20250422_2214.py +54 -0
- meta_reports/migrations/0057_auto_20250422_2224.py +54 -0
- meta_reports/migrations/0058_auto_20250422_2232.py +54 -0
- meta_reports/models/dbviews/glucose_summary/unmanaged_model.py +13 -1
- meta_reports/models/dbviews/glucose_summary/view_definition.py +8 -5
- meta_subject/form_validators/glucose_form_validator.py +16 -1
- meta_subject/forms/study_medication_form.py +5 -3
- meta_subject/migrations/0221_auto_20250402_1913.py +42 -0
- meta_subject/migrations/0222_alter_historicalstudymedication_stock_codes_and_more.py +46 -0
- meta_analytics/dataframes/enrolled/get_glucose_df.py +0 -122
- /meta_edc-1.0.6.dist-info/AUTHORS → /meta_analytics/dataframes/glucose_endpoints/utils.py +0 -0
- {meta_edc-1.0.6.dist-info → meta_edc-1.0.7.dist-info/licenses}/LICENSE +0 -0
- {meta_edc-1.0.6.dist-info → meta_edc-1.0.7.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,425 @@
|
|
|
1
|
+
{
|
|
2
|
+
"cells": [
|
|
3
|
+
{
|
|
4
|
+
"metadata": {},
|
|
5
|
+
"cell_type": "code",
|
|
6
|
+
"source": [
|
|
7
|
+
"%%capture\n",
|
|
8
|
+
"import os\n",
|
|
9
|
+
"from pathlib import Path\n",
|
|
10
|
+
"import pandas as pd\n",
|
|
11
|
+
"from dj_notebook import activate\n",
|
|
12
|
+
"\n",
|
|
13
|
+
"env_file = os.environ[\"META_ENV\"]\n",
|
|
14
|
+
"reports_folder = Path(os.environ[\"META_REPORTS_FOLDER\"])\n",
|
|
15
|
+
"analysis_folder = Path(os.environ[\"META_ANALYSIS_FOLDER\"])\n",
|
|
16
|
+
"pharmacy_folder = Path(os.environ[\"META_PHARMACY_FOLDER\"])\n",
|
|
17
|
+
"plus = activate(dotenv_file=env_file)\n",
|
|
18
|
+
"pd.set_option('future.no_silent_downcasting', True)"
|
|
19
|
+
],
|
|
20
|
+
"id": "5c3bc2c5cc22e357",
|
|
21
|
+
"outputs": [],
|
|
22
|
+
"execution_count": null
|
|
23
|
+
},
|
|
24
|
+
{
|
|
25
|
+
"metadata": {},
|
|
26
|
+
"cell_type": "code",
|
|
27
|
+
"source": [
|
|
28
|
+
"from edc_pdutils.dataframes import get_crf, get_subject_visit\n",
|
|
29
|
+
"from edc_constants.constants import YES\n",
|
|
30
|
+
"from edc_appointment.analytics import get_appointment_df\n",
|
|
31
|
+
"from datetime import datetime"
|
|
32
|
+
],
|
|
33
|
+
"id": "4067e6257bf1c657",
|
|
34
|
+
"outputs": [],
|
|
35
|
+
"execution_count": null
|
|
36
|
+
},
|
|
37
|
+
{
|
|
38
|
+
"metadata": {},
|
|
39
|
+
"cell_type": "code",
|
|
40
|
+
"source": [
|
|
41
|
+
"cutoff_datetime = datetime(2026,3,1)\n",
|
|
42
|
+
"df_patienthistory = get_crf(\"meta_subject.patienthistory\", subject_visit_model=\"meta_subject.subjectvisit\")\n",
|
|
43
|
+
"df_followup_examination = get_crf(\"meta_subject.FollowupExamination\", subject_visit_model=\"meta_subject.subjectvisit\")"
|
|
44
|
+
],
|
|
45
|
+
"id": "5a00d10dadc9d7f8",
|
|
46
|
+
"outputs": [],
|
|
47
|
+
"execution_count": null
|
|
48
|
+
},
|
|
49
|
+
{
|
|
50
|
+
"metadata": {},
|
|
51
|
+
"cell_type": "code",
|
|
52
|
+
"source": [
|
|
53
|
+
"replacements = {\n",
|
|
54
|
+
" \"ABC+ 3TC+ DTG\": \"ABC + 3TC + DTG\",\n",
|
|
55
|
+
" \"ABC+3TC+DTG\": \"ABC + 3TC + DTG\",\n",
|
|
56
|
+
" \"ABC, 3TC, DTG\":\"ABC + 3TC + DTG\",\n",
|
|
57
|
+
" \"ABC, EFV, DTG\": \"ABC + EFV + DTG\",\n",
|
|
58
|
+
" \"TDF+FTC+DTG\": \"TDF + FTC + DTG\",\n",
|
|
59
|
+
" \"AZT+3TC+DTG\": \"AZT + 3TC + DTG\",\n",
|
|
60
|
+
" \"AZT + 3 TC + DTG\":\"AZT + 3TC + DTG\",\n",
|
|
61
|
+
" \"TDF+3TC+DTG\": \"TDF + 3TC + DTG\",\n",
|
|
62
|
+
"}\n",
|
|
63
|
+
"\n",
|
|
64
|
+
"df_patienthistory[\"other_current_arv_regimen\"] = (\n",
|
|
65
|
+
" df_patienthistory[\"other_current_arv_regimen\"]\n",
|
|
66
|
+
" .replace(replacements)\n",
|
|
67
|
+
")"
|
|
68
|
+
],
|
|
69
|
+
"id": "cc2958e795b6c83f",
|
|
70
|
+
"outputs": [],
|
|
71
|
+
"execution_count": null
|
|
72
|
+
},
|
|
73
|
+
{
|
|
74
|
+
"metadata": {},
|
|
75
|
+
"cell_type": "code",
|
|
76
|
+
"source": [
|
|
77
|
+
"df_patienthistory['regimen'] = df_patienthistory[\"current_arv_regimen\"]\n",
|
|
78
|
+
"df_patienthistory.loc[df_patienthistory[\"current_arv_regimen\"]==\"Other, specify ...\", \"regimen\"] = df_patienthistory[\"other_current_arv_regimen\"]"
|
|
79
|
+
],
|
|
80
|
+
"id": "41a0202e91442199",
|
|
81
|
+
"outputs": [],
|
|
82
|
+
"execution_count": null
|
|
83
|
+
},
|
|
84
|
+
{
|
|
85
|
+
"metadata": {},
|
|
86
|
+
"cell_type": "code",
|
|
87
|
+
"source": [
|
|
88
|
+
"df_followup_examination[\"art_new_regimen_other\"] = (\n",
|
|
89
|
+
" df_followup_examination[\"art_new_regimen_other\"]\n",
|
|
90
|
+
" .replace(replacements)\n",
|
|
91
|
+
")"
|
|
92
|
+
],
|
|
93
|
+
"id": "29ee66d690a550b",
|
|
94
|
+
"outputs": [],
|
|
95
|
+
"execution_count": null
|
|
96
|
+
},
|
|
97
|
+
{
|
|
98
|
+
"metadata": {},
|
|
99
|
+
"cell_type": "code",
|
|
100
|
+
"source": [
|
|
101
|
+
"df_followup_examination['regimen'] = pd.NA\n",
|
|
102
|
+
"df_followup_examination.loc[(df_followup_examination[\"art_change\"]==YES) & (df_followup_examination.art_new_regimen_other.notna()), \"regimen\"] = df_followup_examination[\"art_new_regimen_other\"]\n",
|
|
103
|
+
"df_followup_examination.loc[(df_followup_examination[\"art_change\"]==YES) & (df_followup_examination.art_new_regimen_other.isna()), \"regimen\"] = \"CHANGE_NOT_REPORTED\""
|
|
104
|
+
],
|
|
105
|
+
"id": "3356b70f9415f8cf",
|
|
106
|
+
"outputs": [],
|
|
107
|
+
"execution_count": null
|
|
108
|
+
},
|
|
109
|
+
{
|
|
110
|
+
"metadata": {},
|
|
111
|
+
"cell_type": "code",
|
|
112
|
+
"source": [
|
|
113
|
+
"df_regimen = pd.concat([df_patienthistory[[\"subject_identifier\", \"visit_datetime\", \"regimen\"]], df_followup_examination[[\"subject_identifier\", \"visit_datetime\", \"regimen\"]]])\n",
|
|
114
|
+
"df_regimen[\"regimen\"] = df_regimen[\"regimen\"].replace({\"Other second line\": \"CHANGE_NOT_REPORTED\"})\n",
|
|
115
|
+
"df_regimen[\"regimen\"] = pd.Categorical(df_regimen[\"regimen\"], categories=list(df_regimen.query(\"regimen.notna()\").regimen.unique()), ordered=False)\n",
|
|
116
|
+
"df_regimen = df_regimen.sort_values([\"subject_identifier\", \"visit_datetime\"])\n",
|
|
117
|
+
"df_regimen = df_regimen.reset_index(drop=True)"
|
|
118
|
+
],
|
|
119
|
+
"id": "bfa119a47ab4827e",
|
|
120
|
+
"outputs": [],
|
|
121
|
+
"execution_count": null
|
|
122
|
+
},
|
|
123
|
+
{
|
|
124
|
+
"metadata": {},
|
|
125
|
+
"cell_type": "code",
|
|
126
|
+
"source": [
|
|
127
|
+
"df_pivot = df_regimen.pivot_table(values=\"visit_datetime\", columns=\"regimen\", index=\"subject_identifier\", observed=True)\n",
|
|
128
|
+
"df_pivot = df_pivot.reset_index()"
|
|
129
|
+
],
|
|
130
|
+
"id": "10d8f6687f35b5e4",
|
|
131
|
+
"outputs": [],
|
|
132
|
+
"execution_count": null
|
|
133
|
+
},
|
|
134
|
+
{
|
|
135
|
+
"metadata": {},
|
|
136
|
+
"cell_type": "code",
|
|
137
|
+
"source": [
|
|
138
|
+
"subject_identifier = \"105-20-0050-0\"\n",
|
|
139
|
+
"df_pivot[df_pivot.subject_identifier==subject_identifier].melt().query(\"value.notna() and regimen!='subject_identifier'\").sort_values(\"value\", ascending=False)"
|
|
140
|
+
],
|
|
141
|
+
"id": "d3b3a1a80436cc1d",
|
|
142
|
+
"outputs": [],
|
|
143
|
+
"execution_count": null
|
|
144
|
+
},
|
|
145
|
+
{
|
|
146
|
+
"metadata": {},
|
|
147
|
+
"cell_type": "code",
|
|
148
|
+
"source": "df_melt = df_pivot.melt(id_vars=[\"subject_identifier\"]).query(\"value.notna()\")",
|
|
149
|
+
"id": "b82ea4629050675e",
|
|
150
|
+
"outputs": [],
|
|
151
|
+
"execution_count": null
|
|
152
|
+
},
|
|
153
|
+
{
|
|
154
|
+
"metadata": {},
|
|
155
|
+
"cell_type": "code",
|
|
156
|
+
"source": [
|
|
157
|
+
"df_melt[\"max_date\"] = df_melt.groupby(\"subject_identifier\")[\"value\"].transform(\"max\")\n",
|
|
158
|
+
"df_melt[\"current_regimen\"] = df_melt[df_melt.value==df_melt.max_date][\"regimen\"]"
|
|
159
|
+
],
|
|
160
|
+
"id": "46906641b5f8e73b",
|
|
161
|
+
"outputs": [],
|
|
162
|
+
"execution_count": null
|
|
163
|
+
},
|
|
164
|
+
{
|
|
165
|
+
"metadata": {},
|
|
166
|
+
"cell_type": "code",
|
|
167
|
+
"source": "df_current_regimens = df_melt.query(\"current_regimen.notna()\")[[\"subject_identifier\", \"max_date\", \"current_regimen\"]].copy()",
|
|
168
|
+
"id": "c297749df4c7397c",
|
|
169
|
+
"outputs": [],
|
|
170
|
+
"execution_count": null
|
|
171
|
+
},
|
|
172
|
+
{
|
|
173
|
+
"metadata": {},
|
|
174
|
+
"cell_type": "code",
|
|
175
|
+
"source": [
|
|
176
|
+
"df_visit = get_subject_visit(model=\"meta_subject.subjectvisit\")\n",
|
|
177
|
+
"df_visit = df_visit[df_visit.visit_code==1000.0].copy()"
|
|
178
|
+
],
|
|
179
|
+
"id": "ce1f8d3dacba2d99",
|
|
180
|
+
"outputs": [],
|
|
181
|
+
"execution_count": null
|
|
182
|
+
},
|
|
183
|
+
{
|
|
184
|
+
"metadata": {},
|
|
185
|
+
"cell_type": "code",
|
|
186
|
+
"source": [
|
|
187
|
+
"df_appointment = get_appointment_df()\n",
|
|
188
|
+
"df_appointment_next = (\n",
|
|
189
|
+
" df_appointment\n",
|
|
190
|
+
" .groupby(by=[\"subject_identifier\", \"next_appt_datetime\", \"next_visit_code\"])\n",
|
|
191
|
+
" .size()\n",
|
|
192
|
+
" .copy()\n",
|
|
193
|
+
" .reset_index()\n",
|
|
194
|
+
")"
|
|
195
|
+
],
|
|
196
|
+
"id": "72c7862945e8a25e",
|
|
197
|
+
"outputs": [],
|
|
198
|
+
"execution_count": null
|
|
199
|
+
},
|
|
200
|
+
{
|
|
201
|
+
"metadata": {},
|
|
202
|
+
"cell_type": "code",
|
|
203
|
+
"source": [
|
|
204
|
+
"df_appointment_last = (\n",
|
|
205
|
+
" df_appointment[df_appointment.appt_datetime<cutoff_datetime][[\"subject_identifier\", \"appt_datetime\", \"visit_code\"]]\n",
|
|
206
|
+
" .sort_values([\"subject_identifier\", \"appt_datetime\", \"visit_code\"])\n",
|
|
207
|
+
" .groupby(by=[\"subject_identifier\"])\n",
|
|
208
|
+
" .agg([\"last\"])\n",
|
|
209
|
+
" .reset_index() )\n",
|
|
210
|
+
"df_appointment_last.columns = [\"_\".join(col).strip() for col in df_appointment_last.columns.values]\n",
|
|
211
|
+
"df_appointment_last = (\n",
|
|
212
|
+
" df_appointment_last\n",
|
|
213
|
+
" .rename(columns={\n",
|
|
214
|
+
" \"subject_identifier_\":\"subject_identifier\",\n",
|
|
215
|
+
" \"appt_datetime_last\":\"last_appt_datetime\",\n",
|
|
216
|
+
" \"visit_code_last\":\"last_visit_code\"\n",
|
|
217
|
+
" }\n",
|
|
218
|
+
" )\n",
|
|
219
|
+
")"
|
|
220
|
+
],
|
|
221
|
+
"id": "cecd662f3a76a4ac",
|
|
222
|
+
"outputs": [],
|
|
223
|
+
"execution_count": null
|
|
224
|
+
},
|
|
225
|
+
{
|
|
226
|
+
"metadata": {},
|
|
227
|
+
"cell_type": "code",
|
|
228
|
+
"source": [
|
|
229
|
+
"df = df_current_regimens.merge(df_visit[[ \"subject_identifier\", \"baseline_datetime\", \"endline_visit_datetime\", \"endline_visit_code\"]], on=\"subject_identifier\", how=\"left\")\n",
|
|
230
|
+
"df = df.reset_index(drop=True)\n",
|
|
231
|
+
"df[\"changed\"] = False\n",
|
|
232
|
+
"df.loc[df.max_date != df.baseline_datetime, \"changed\"] = True"
|
|
233
|
+
],
|
|
234
|
+
"id": "46700ad09717a89f",
|
|
235
|
+
"outputs": [],
|
|
236
|
+
"execution_count": null
|
|
237
|
+
},
|
|
238
|
+
{
|
|
239
|
+
"metadata": {},
|
|
240
|
+
"cell_type": "code",
|
|
241
|
+
"source": [
|
|
242
|
+
"df = df.merge(df_appointment_next[[\"subject_identifier\", \"next_appt_datetime\", \"next_visit_code\"]], on=\"subject_identifier\", how=\"left\")\n",
|
|
243
|
+
"df = df.merge(df_appointment_last[[\"subject_identifier\", \"last_appt_datetime\", \"last_visit_code\"]], on=\"subject_identifier\", how=\"left\")"
|
|
244
|
+
],
|
|
245
|
+
"id": "21a77db6b3d342ad",
|
|
246
|
+
"outputs": [],
|
|
247
|
+
"execution_count": null
|
|
248
|
+
},
|
|
249
|
+
{
|
|
250
|
+
"metadata": {},
|
|
251
|
+
"cell_type": "code",
|
|
252
|
+
"source": [
|
|
253
|
+
"# from last seen to final scheduled appt\n",
|
|
254
|
+
"df[\"remaining_delta_from_last_seen\"] = df.last_appt_datetime - df.endline_visit_datetime\n",
|
|
255
|
+
"df[\"remaining_delta_from_last_seen\"] = df[\"remaining_delta_from_last_seen\"].apply(lambda x: 0 if x.total_seconds()<0 else x)\n",
|
|
256
|
+
"df[\"remaining_delta_from_last_seen\"] = pd.to_timedelta(df[\"remaining_delta_from_last_seen\"])\n",
|
|
257
|
+
"df[\"remaining_days_last_seen_to_final\"] = df[\"remaining_delta_from_last_seen\"].dt.days\n",
|
|
258
|
+
"\n",
|
|
259
|
+
"# from now to final scheduled appt\n",
|
|
260
|
+
"df[\"remaining_delta_from_now\"] = 0.0\n",
|
|
261
|
+
"df[\"remaining_delta_from_now\"] = df[df.remaining_days_last_seen_to_final>0].last_appt_datetime - datetime.now()\n",
|
|
262
|
+
"df[\"remaining_delta_from_now\"] = df[\"remaining_delta_from_now\"].apply(lambda x: 0 if x.total_seconds()<0 else x)\n",
|
|
263
|
+
"df[\"remaining_delta_from_now\"] = pd.to_timedelta(df[\"remaining_delta_from_now\"])\n",
|
|
264
|
+
"df[\"remaining_days_now_to_final\"] = df[\"remaining_delta_from_now\"].dt.days\n",
|
|
265
|
+
"\n",
|
|
266
|
+
"# from next appointment to final scheduled appt\n",
|
|
267
|
+
"df[\"remaining_delta_from_next\"] = 0.0\n",
|
|
268
|
+
"df[\"remaining_delta_from_next\"] = df[df.remaining_days_last_seen_to_final>0].last_appt_datetime - df[df.remaining_days_last_seen_to_final>0].next_appt_datetime\n",
|
|
269
|
+
"df[\"remaining_delta_from_next\"] = df[\"remaining_delta_from_next\"].apply(lambda x: 0 if x.total_seconds()<0 else x)\n",
|
|
270
|
+
"df[\"remaining_delta_from_next\"] = pd.to_timedelta(df[\"remaining_delta_from_next\"])\n",
|
|
271
|
+
"df[\"remaining_days_next_to_final\"] = df[\"remaining_delta_from_next\"].dt.days"
|
|
272
|
+
],
|
|
273
|
+
"id": "46455533d4c928a5",
|
|
274
|
+
"outputs": [],
|
|
275
|
+
"execution_count": null
|
|
276
|
+
},
|
|
277
|
+
{
|
|
278
|
+
"metadata": {},
|
|
279
|
+
"cell_type": "code",
|
|
280
|
+
"source": [
|
|
281
|
+
"df_final = (\n",
|
|
282
|
+
" df\n",
|
|
283
|
+
" .rename(columns={\n",
|
|
284
|
+
" \"max_date\": \"current_regimen_date\",\n",
|
|
285
|
+
" \"endline_visit_code\": \"last_attended_visit_code\",\n",
|
|
286
|
+
" \"endline_visit_datetime\": \"last_attended_visit_datetime\",\n",
|
|
287
|
+
" })\n",
|
|
288
|
+
" .copy()\n",
|
|
289
|
+
")\n",
|
|
290
|
+
"df_final = df_final[[\n",
|
|
291
|
+
" \"subject_identifier\",\n",
|
|
292
|
+
" \"current_regimen\",\n",
|
|
293
|
+
" \"current_regimen_date\",\n",
|
|
294
|
+
" \"changed\",\n",
|
|
295
|
+
" \"baseline_datetime\",\n",
|
|
296
|
+
" \"last_attended_visit_code\",\n",
|
|
297
|
+
" \"last_attended_visit_datetime\",\n",
|
|
298
|
+
" \"next_visit_code\",\n",
|
|
299
|
+
" \"next_appt_datetime\",\n",
|
|
300
|
+
" \"last_visit_code\",\n",
|
|
301
|
+
" \"last_appt_datetime\",\n",
|
|
302
|
+
" \"remaining_days_last_seen_to_final\",\n",
|
|
303
|
+
" \"remaining_days_now_to_final\",\n",
|
|
304
|
+
" \"remaining_days_next_to_final\",\n",
|
|
305
|
+
"]].copy()\n",
|
|
306
|
+
"\n",
|
|
307
|
+
"df_final = (\n",
|
|
308
|
+
" df_final\n",
|
|
309
|
+
" .sort_values(\"subject_identifier\")\n",
|
|
310
|
+
" .reset_index(drop=True)\n",
|
|
311
|
+
")\n",
|
|
312
|
+
"df_final[\"remaining_days_last_seen_to_final\"] = df_final[\"remaining_days_last_seen_to_final\"].astype(\"float64\").fillna(0)\n",
|
|
313
|
+
"df_final[\"remaining_days_now_to_final\"] = df_final[\"remaining_days_now_to_final\"].astype(\"float64\").fillna(0)\n",
|
|
314
|
+
"df_final[\"remaining_days_next_to_final\"] = df_final[\"remaining_days_next_to_final\"].astype(\"float64\").fillna(0)\n",
|
|
315
|
+
"df_final"
|
|
316
|
+
],
|
|
317
|
+
"id": "c32993c296d84def",
|
|
318
|
+
"outputs": [],
|
|
319
|
+
"execution_count": null
|
|
320
|
+
},
|
|
321
|
+
{
|
|
322
|
+
"metadata": {},
|
|
323
|
+
"cell_type": "code",
|
|
324
|
+
"source": [
|
|
325
|
+
"# need from now until end of study\n",
|
|
326
|
+
"df_summary1 = (pd.merge(\n",
|
|
327
|
+
" df_final.groupby(by=[\"current_regimen\"]).remaining_days_now_to_final.sum(),\n",
|
|
328
|
+
" df_final.groupby(by=[\"current_regimen\"]).subject_identifier.count(), on=\"current_regimen\")\n",
|
|
329
|
+
" .rename(columns={\n",
|
|
330
|
+
" \"remaining_days_now_to_final\": \"days_medication_needed\",\n",
|
|
331
|
+
" \"subject_identifier\": \"subjects\"\n",
|
|
332
|
+
" })\n",
|
|
333
|
+
" .sort_values(\"days_medication_needed\", ascending=False)\n",
|
|
334
|
+
" .reset_index()\n",
|
|
335
|
+
")\n",
|
|
336
|
+
"df_summary1"
|
|
337
|
+
],
|
|
338
|
+
"id": "3b8b54a63bc67608",
|
|
339
|
+
"outputs": [],
|
|
340
|
+
"execution_count": null
|
|
341
|
+
},
|
|
342
|
+
{
|
|
343
|
+
"metadata": {},
|
|
344
|
+
"cell_type": "code",
|
|
345
|
+
"source": [
|
|
346
|
+
"# need from last seen to end of study\n",
|
|
347
|
+
"df_summary2 = (pd.merge(\n",
|
|
348
|
+
" df_final.groupby(by=[\"current_regimen\"]).remaining_days_last_seen_to_final.sum(),\n",
|
|
349
|
+
" df_final.groupby(by=[\"current_regimen\"]).subject_identifier.count(), on=\"current_regimen\")\n",
|
|
350
|
+
" .rename(columns={\n",
|
|
351
|
+
" \"remaining_days_last_seen_to_final\": \"days_medication_needed\",\n",
|
|
352
|
+
" \"subject_identifier\": \"subjects\"\n",
|
|
353
|
+
" })\n",
|
|
354
|
+
" .sort_values(\"days_medication_needed\", ascending=False)\n",
|
|
355
|
+
" .reset_index()\n",
|
|
356
|
+
")\n",
|
|
357
|
+
"df_summary2"
|
|
358
|
+
],
|
|
359
|
+
"id": "9fcf09fbc781845b",
|
|
360
|
+
"outputs": [],
|
|
361
|
+
"execution_count": null
|
|
362
|
+
},
|
|
363
|
+
{
|
|
364
|
+
"metadata": {},
|
|
365
|
+
"cell_type": "code",
|
|
366
|
+
"source": [
|
|
367
|
+
"# need from next to end of study\n",
|
|
368
|
+
"df_summary3 = (pd.merge(\n",
|
|
369
|
+
" df_final.groupby(by=[\"current_regimen\"]).remaining_days_next_to_final.sum(),\n",
|
|
370
|
+
" df_final.groupby(by=[\"current_regimen\"]).subject_identifier.count(), on=\"current_regimen\")\n",
|
|
371
|
+
" .rename(columns={\n",
|
|
372
|
+
" \"remaining_days_next_to_final\": \"days_medication_needed\",\n",
|
|
373
|
+
" \"subject_identifier\": \"subjects\"\n",
|
|
374
|
+
" })\n",
|
|
375
|
+
" .sort_values(\"days_medication_needed\", ascending=False)\n",
|
|
376
|
+
" .reset_index()\n",
|
|
377
|
+
")\n",
|
|
378
|
+
"\n",
|
|
379
|
+
"df_summary3"
|
|
380
|
+
],
|
|
381
|
+
"id": "9d4bebb0a52a8457",
|
|
382
|
+
"outputs": [],
|
|
383
|
+
"execution_count": null
|
|
384
|
+
},
|
|
385
|
+
{
|
|
386
|
+
"metadata": {},
|
|
387
|
+
"cell_type": "code",
|
|
388
|
+
"source": [
|
|
389
|
+
"with pd.ExcelWriter(\n",
|
|
390
|
+
" analysis_folder / \"hiv_medication.xlsx\",\n",
|
|
391
|
+
" date_format=\"YYYY-MM-DD\",\n",
|
|
392
|
+
" datetime_format=\"YYYY-MM-DD HH:MM:SS\"\n",
|
|
393
|
+
") as writer:\n",
|
|
394
|
+
" df_final.to_excel(writer, sheet_name=\"subjects\", index=False)\n",
|
|
395
|
+
" df_summary1.to_excel(writer, sheet_name=\"now to final\", index=False)\n",
|
|
396
|
+
" df_summary2.to_excel(writer, sheet_name=\"last seen to final\", index=False)\n",
|
|
397
|
+
" df_summary3.to_excel(writer, sheet_name=\"next to final\", index=False)\n"
|
|
398
|
+
],
|
|
399
|
+
"id": "e344164f67b3cc46",
|
|
400
|
+
"outputs": [],
|
|
401
|
+
"execution_count": null
|
|
402
|
+
}
|
|
403
|
+
],
|
|
404
|
+
"metadata": {
|
|
405
|
+
"kernelspec": {
|
|
406
|
+
"display_name": "Python 3",
|
|
407
|
+
"language": "python",
|
|
408
|
+
"name": "python3"
|
|
409
|
+
},
|
|
410
|
+
"language_info": {
|
|
411
|
+
"codemirror_mode": {
|
|
412
|
+
"name": "ipython",
|
|
413
|
+
"version": 2
|
|
414
|
+
},
|
|
415
|
+
"file_extension": ".py",
|
|
416
|
+
"mimetype": "text/x-python",
|
|
417
|
+
"name": "python",
|
|
418
|
+
"nbconvert_exporter": "python",
|
|
419
|
+
"pygments_lexer": "ipython2",
|
|
420
|
+
"version": "2.7.6"
|
|
421
|
+
}
|
|
422
|
+
},
|
|
423
|
+
"nbformat": 4,
|
|
424
|
+
"nbformat_minor": 5
|
|
425
|
+
}
|