| 1 |
===== LCHC req from Dana to take an XLS of dob and other pii data and pivot by deduplicated user name =====
|
| 2 |
|
| 3 |
>>> docIDMatrix = {}
|
| 4 |
>>> mrnMatrix = {}
|
| 5 |
>>> ccaidMatrix = {}
|
| 6 |
>>> dobMatrix = {}
|
| 7 |
>>> ssnMatrix = {}
|
| 8 |
>>> otherIDMatrix = {}
|
| 9 |
>>> otherPIIMatrix = {}
|
| 10 |
>>> contents = open(r"C:\Temp\LCHC - Consolidated Master_For Scripting_02.17.21.csv").readlines()
|
| 11 |
>>> contents[0]
|
| 12 |
'Doc ID:|MRN|CCAID|DOB|Name|SSN|Other Identifiable Info.|Other PII|Multiple Doc IDs (Used for Consolidation Only)\n'
|
| 13 |
>>> contents = contents[1:]
|
| 14 |
>>> for line in contents:
|
| 15 |
... line = line.replace("\n","")
|
| 16 |
... line = line.split("|")
|
| 17 |
... name = line[4]
|
| 18 |
... name = name.upper()
|
| 19 |
... name = name.lstrip()
|
| 20 |
... name = name.rstrip()
|
| 21 |
... if name in docIDMatrix.keys():
|
| 22 |
... if line[0] in docIDMatrix[name]:
|
| 23 |
... pass
|
| 24 |
... else:
|
| 25 |
... docIDMatrix[name].append(line[0])
|
| 26 |
... else:
|
| 27 |
... docIDMatrix[name] = [line[0],]
|
| 28 |
...
|
| 29 |
>>> len(docIDMatrix.keys())
|
| 30 |
66183
|
| 31 |
>>> docIDMatrix['ABAD HIRALDO, PASCUAL']
|
| 32 |
['REV00118844', 'REV00215151']
|
| 33 |
>>> for line in contents:
|
| 34 |
... line = line.replace("\n","")
|
| 35 |
... line = line.split("|")
|
| 36 |
... name = line[4]
|
| 37 |
... name = name.upper()
|
| 38 |
... name = name.lstrip()
|
| 39 |
... name = name.rstrip()
|
| 40 |
... if line[1]:
|
| 41 |
... if name in mrnMatrix.keys():
|
| 42 |
... if line[1] in mrnMatrix[name]:
|
| 43 |
... pass
|
| 44 |
... else:
|
| 45 |
... mrnMatrix[name].append(line[1])
|
| 46 |
... else:
|
| 47 |
... mrnMatrix[name] = [line[1],]
|
| 48 |
...
|
| 49 |
>>> len(mrnMatrix.keys())
|
| 50 |
3534
|
| 51 |
>>> for line in contents:
|
| 52 |
... line = line.replace("\n","")
|
| 53 |
... line = line.split("|")
|
| 54 |
... name = line[4]
|
| 55 |
... name = name.upper()
|
| 56 |
... name = name.lstrip()
|
| 57 |
... name = name.rstrip()
|
| 58 |
... if line[2]:
|
| 59 |
... if name in ccaidMatrix.keys():
|
| 60 |
... if line[2] in ccaidMatrix[name]:
|
| 61 |
... pass
|
| 62 |
... else:
|
| 63 |
... ccaidMatrix[name].append(line[2])
|
| 64 |
... else:
|
| 65 |
... ccaidMatrix[name] = [line[2],]
|
| 66 |
...
|
| 67 |
>>> len(ccaidMatrix.keys())
|
| 68 |
3
|
| 69 |
>>> for line in contents:
|
| 70 |
... line = line.replace("\n","")
|
| 71 |
... line = line.split("|")
|
| 72 |
... name = line[4]
|
| 73 |
... name = name.upper()
|
| 74 |
... name = name.lstrip()
|
| 75 |
... name = name.rstrip()
|
| 76 |
... if line[5]:
|
| 77 |
... if name in ssnMatrix.keys():
|
| 78 |
... if line[5] in ssnMatrix[name]:
|
| 79 |
... pass
|
| 80 |
... else:
|
| 81 |
... ssnMatrix[name].append(line[5])
|
| 82 |
... else:
|
| 83 |
... ssnMatrix[name] = [line[5],]
|
| 84 |
...
|
| 85 |
>>> len(ssnMatrix.keys())
|
| 86 |
521
|
| 87 |
>>> for line in contents:
|
| 88 |
... line = line.replace("\n","")
|
| 89 |
... line = line.split("|")
|
| 90 |
... name = line[4]
|
| 91 |
... name = name.upper()
|
| 92 |
... name = name.lstrip()
|
| 93 |
... name = name.rstrip()
|
| 94 |
... if line[6]:
|
| 95 |
... if name in otherIDMatrix.keys():
|
| 96 |
... if line[6] in otherIDMatrix[name]:
|
| 97 |
... pass
|
| 98 |
... else:
|
| 99 |
... otherIDMatrix[name].append(line[6])
|
| 100 |
... else:
|
| 101 |
... otherIDMatrix[name] = [line[6],]
|
| 102 |
...
|
| 103 |
>>> len(otherIDMatrix.keys())
|
| 104 |
24636
|
| 105 |
>>> for line in contents:
|
| 106 |
... line = line.replace("\n","")
|
| 107 |
... line = line.split("|")
|
| 108 |
... name = line[4]
|
| 109 |
... name = name.upper()
|
| 110 |
... name = name.lstrip()
|
| 111 |
... name = name.rstrip()
|
| 112 |
... if line[7]:
|
| 113 |
... if name in otherPIIMatrix.keys():
|
| 114 |
... if line[7] in otherPIIMatrix[name]:
|
| 115 |
... pass
|
| 116 |
... else:
|
| 117 |
... otherPIIMatrix[name].append(line[7])
|
| 118 |
... else:
|
| 119 |
... otherPIIMatrix[name] = [line[7],]
|
| 120 |
...
|
| 121 |
>>> len(otherPIIMatrix.keys())
|
| 122 |
1351
|
| 123 |
>>> effFile = open(r"C:\Temp\LCHC - dobTestLog.txt",'w')
|
| 124 |
>>> for line in contents:
|
| 125 |
... line = line.replace("\n","")
|
| 126 |
... line = line.split("|")
|
| 127 |
... name = line[4]
|
| 128 |
... name = name.upper()
|
| 129 |
... name = name.lstrip()
|
| 130 |
... name = name.rstrip()
|
| 131 |
... rawDob = line[3]
|
| 132 |
... if len(line[3]) >5:
|
| 133 |
... if "/" in rawDob:
|
| 134 |
... rawDob = datetime.datetime.strptime(rawDob, '%m/%d/%Y')
|
| 135 |
... dob = rawDob.strftime("%m/%d/%Y")
|
| 136 |
... else:
|
| 137 |
... rawDob = datetime.datetime.strptime(rawDob, '%Y%m%d')
|
| 138 |
... dob = rawDob.strftime("%m/%d/%Y")
|
| 139 |
... effFile.write("%s changed to %s for docID %s\n"% (line[3], dob, line[0]))
|
| 140 |
... if name in dobMatrix.keys():
|
| 141 |
... if dob in dobMatrix[name]:
|
| 142 |
... pass
|
| 143 |
... else:
|
| 144 |
... dobMatrix[name].append(dob)
|
| 145 |
... else:
|
| 146 |
... dobMatrix[name] = [dob,]
|
| 147 |
... else:
|
| 148 |
... if line[3]:
|
| 149 |
... effFile.write("ERROR: %s is too small to parse!!!\n"% line[3])
|
| 150 |
...
|
| 151 |
>>> effFile.close()
|
| 152 |
>>> len(dobMatrix.keys())
|
| 153 |
64145
|
| 154 |
>>> patientList = docIDMatrix.keys()
|
| 155 |
>>> patientList.sort()
|
| 156 |
>>> patientList[0]
|
| 157 |
''
|
| 158 |
>>> patientList[1]
|
| 159 |
'A., A.'
|
| 160 |
>>> patientList[2]
|
| 161 |
'A., JESSE'
|
| 162 |
>>> patientList[3]
|
| 163 |
'A., JOHN'
|
| 164 |
|
| 165 |
=== Now we write it out ===
|
| 166 |
>>> dobPatientList = dobMatrix.keys()
|
| 167 |
>>> mrnPatientList = mrnMatrix.keys()
|
| 168 |
>>> ccaidPatientList = ccaidMatrix.keys()
|
| 169 |
>>> ssnPatientList = ssnMatrix.keys()
|
| 170 |
>>> otherIDPatientList = otherIDMatrix.keys()
|
| 171 |
>>> otherPIIPatientList = otherPIIMatrix.keys()
|
| 172 |
|
| 173 |
>>> outputFile = open(r"C:\Temp\LCHC - Consolidated Master_For Scripting_02.17.21-OUTPUT.DAT",'w')
|
| 174 |
>>> outputFile.write("Name|DOB|MRN|CCAID|SSN|OtherIDInfo|OtherPII|DodIDs\n")
|
| 175 |
>>> for pt in patientList:
|
| 176 |
... dob = ""
|
| 177 |
... docID = ""
|
| 178 |
... mrn = ""
|
| 179 |
... ccaid = ""
|
| 180 |
... ssn = ""
|
| 181 |
... otherID = ""
|
| 182 |
... otherPII = ""
|
| 183 |
... outputFile.write("%s|"%pt)
|
| 184 |
... if pt in dobPatientList:
|
| 185 |
... dobs = dobMatrix[pt]
|
| 186 |
... if len(dobs) > 1:
|
| 187 |
... for d in dobs:
|
| 188 |
... dob = dob + d + ";"
|
| 189 |
... else:
|
| 190 |
... dob = dobs[0]
|
| 191 |
... outputFile.write("%s|"%dob)
|
| 192 |
... if pt in mrnPatientList:
|
| 193 |
... mrns = mrnMatrix[pt]
|
| 194 |
... if len(mrns) >1:
|
| 195 |
... for m in mrns:
|
| 196 |
... mrn = mrn + m + ";"
|
| 197 |
... else:
|
| 198 |
... mrn = mrns[0]
|
| 199 |
... outputFile.write("%s|"%mrn)
|
| 200 |
... if pt in ccaidPatientList:
|
| 201 |
... ccaids = ccaidMatrix[pt]
|
| 202 |
... if len(ccaids) >1:
|
| 203 |
... for c in ccaids:
|
| 204 |
... ccaid = ccaid + c + ";"
|
| 205 |
... else:
|
| 206 |
... ccaid = ccaids[0]
|
| 207 |
... outputFile.write("%s|"%ccaid)
|
| 208 |
... if pt in ssnPatientList:
|
| 209 |
... ssns = ssnMatrix[pt]
|
| 210 |
... if len(ssns) >1:
|
| 211 |
... for s in ssns:
|
| 212 |
... ssn = ssn + s + ";"
|
| 213 |
... else:
|
| 214 |
... ssn = ssns[0]
|
| 215 |
... outputFile.write("%s|"%ssn)
|
| 216 |
... if pt in otherIDPatientList:
|
| 217 |
... otherIDs = otherIDMatrix[pt]
|
| 218 |
... if len(otherIDs) >1:
|
| 219 |
... for i in otherIDs:
|
| 220 |
... otherID = otherID + i + ";"
|
| 221 |
... else:
|
| 222 |
... otherID = otherIDs[0]
|
| 223 |
... outputFile.write("%s|"%otherID)
|
| 224 |
... if pt in otherPIIPatientList:
|
| 225 |
... otherPIIs = otherPIIMatrix[pt]
|
| 226 |
... if len(otherPIIs) >1:
|
| 227 |
... for p in otherPIIs:
|
| 228 |
... otherPII = otherPII + p + ";"
|
| 229 |
... else:
|
| 230 |
... otherPII = otherPIIs[0]
|
| 231 |
... outputFile.write("%s|"%otherPII)
|
| 232 |
... docIDs = docIDMatrix[pt]
|
| 233 |
... if len(docIDs) >1:
|
| 234 |
... for rev in docIDs:
|
| 235 |
... docID = docID + rev + ";"
|
| 236 |
... else:
|
| 237 |
... docID = docIDs[0]
|
| 238 |
... outputFile.write("%s\n"%docID)
|
| 239 |
...
|
| 240 |
>>> outputFile.close()
|
| 241 |
|
| 242 |
|
| 243 |
|
| 244 |
|
| 245 |
|
| 246 |
|
| 247 |
|
| 248 |
====== OLD BELOW THIS LINE, DO NOT USE ======
|
| 249 |
|
| 250 |
PythonWin 2.7.17 (v2.7.17:c2f86d86e6, Oct 19 2019, 20:49:36) [MSC v.1500 32 bit (Intel)] on win32.
|
| 251 |
Portions Copyright 1994-2018 Mark Hammond - see 'Help/About PythonWin' for further copyright information.
|
| 252 |
>>> docIDMatrix = {}
|
| 253 |
>>> mrnMatrix = {}
|
| 254 |
>>> ccaidMatrix = {}
|
| 255 |
>>> dobMatrix = {}
|
| 256 |
>>> ssnMatrix = {}
|
| 257 |
>>> otherIDMatrix = {}
|
| 258 |
>>> otherPIIMatrix = {}
|
| 259 |
>>> contents = open(r"C:\Temp\LCHC - Consolidated Master_For Scripting_02.17.21.csv").readlines()
|
| 260 |
>>> contents[0]
|
| 261 |
'Doc ID:|MRN|CCAID|DOB|Name|SSN|Other Identifiable Info.|Other PII|Multiple Doc IDs (Used for Consolidation Only)\n'
|
| 262 |
>>> contents = contents[1:]
|
| 263 |
>>> import datetime
|
| 264 |
>>> test = '20210122'
|
| 265 |
>>> test2 = datetime.datetime.strptime(test, '%Y%m%d")
|
| 266 |
>>> test = '20210122'
|
| 267 |
>>> test2 = datetime.datetime.strptime(test, '%Y%m%d')
|
| 268 |
>>> test2.strftime("%m/%d/%Y")
|
| 269 |
'01/22/2021'
|
| 270 |
>>> for line in contents:
|
| 271 |
... line = line.replace("\n","")
|
| 272 |
... line = line.split("|")
|
| 273 |
... name = line[4]
|
| 274 |
... name = name.upper()
|
| 275 |
... if name in docIDMatrix.keys():
|
| 276 |
... if line[0] in docIDMatrix[name]:
|
| 277 |
... pass
|
| 278 |
... else:
|
| 279 |
... docIDMatrix[name].append(line[0])
|
| 280 |
... else:
|
| 281 |
... docIDMatrix[name] = [line[0],]
|
| 282 |
...
|
| 283 |
>>> len(docIDMatrix.keys()
|
| 284 |
... )
|
| 285 |
66433
|
| 286 |
|
| 287 |
>>> len(docIDMatrix['ABAD HIRALDO, PASCUAL'])
|
| 288 |
2
|
| 289 |
>>> docIDMatrix['ABAD HIRALDO, PASCUAL']
|
| 290 |
['REV00118844', 'REV00215151']
|
| 291 |
|
| 292 |
>>> for line in contents:
|
| 293 |
... line = line.replace("\n","")
|
| 294 |
... line = line.split("|")
|
| 295 |
... name = line[4]
|
| 296 |
... name = name.upper()
|
| 297 |
... if line[1]:
|
| 298 |
... if name in mrnMatrix.keys():
|
| 299 |
... if line[1] in mrnMatrix[name]:
|
| 300 |
... pass
|
| 301 |
... else:
|
| 302 |
... mrnMatrix[name].append(line[1])
|
| 303 |
... else:
|
| 304 |
... mrnMatrix[name] = [line[1],]
|
| 305 |
...
|
| 306 |
>>> len(mrnMatrix.keys())
|
| 307 |
3535
|
| 308 |
>>> for line in contents:
|
| 309 |
... line = line.replace("\n","")
|
| 310 |
... line = line.split("|")
|
| 311 |
... name = line[4]
|
| 312 |
... name = name.upper()
|
| 313 |
... if line[2]:
|
| 314 |
... if name in ccaidMatrix.keys():
|
| 315 |
... if line[2] in ccaidMatrix[name]:
|
| 316 |
... pass
|
| 317 |
... else:
|
| 318 |
... ccaidMatrix[name].append(line[2])
|
| 319 |
... else:
|
| 320 |
... ccaidMatrix[name] = [line[2],]
|
| 321 |
...
|
| 322 |
>>> len(ccaidMatrix.keys())
|
| 323 |
3
|
| 324 |
>>> for line in contents:
|
| 325 |
... line = line.replace("\n","")
|
| 326 |
... line = line.split("|")
|
| 327 |
... name = line[4]
|
| 328 |
... name = name.upper()
|
| 329 |
... if line[5]:
|
| 330 |
... if name in ssnMatrix.keys():
|
| 331 |
... if line[5] in ssnMatrix[name]:
|
| 332 |
... pass
|
| 333 |
... else:
|
| 334 |
... ssnMatrix[name].append(line[5])
|
| 335 |
... else:
|
| 336 |
... ssnMatrix[name] = [line[5],]
|
| 337 |
...
|
| 338 |
>>> len(ssnMatrix.keys())
|
| 339 |
522
|
| 340 |
>>> for line in contents:
|
| 341 |
... line = line.replace("\n","")
|
| 342 |
... line = line.split("|")
|
| 343 |
... name = line[4]
|
| 344 |
... name = name.upper()
|
| 345 |
... if line[6]:
|
| 346 |
... if name in otherIDMatrix.keys():
|
| 347 |
... if line[6] in otherIDMatrix[name]:
|
| 348 |
... pass
|
| 349 |
... else:
|
| 350 |
... otherIDMatrix[name].append(line[6])
|
| 351 |
... else:
|
| 352 |
... otherIDMatrix[name] = [line[6],]
|
| 353 |
...
|
| 354 |
>>> len(otherIDMatrix.keys())
|
| 355 |
24639
|
| 356 |
>>> for line in contents:
|
| 357 |
... line = line.replace("\n","")
|
| 358 |
... line = line.split("|")
|
| 359 |
... name = line[4]
|
| 360 |
... name = name.upper()
|
| 361 |
... if line[7]:
|
| 362 |
... if name in otherPIIMatrix.keys():
|
| 363 |
... if line[7] in otherPIIMatrix[name]:
|
| 364 |
... pass
|
| 365 |
... else:
|
| 366 |
... otherPIIMatrix[name].append(line[7])
|
| 367 |
... else:
|
| 368 |
... otherPIIMatrix[name] = [line[7],]
|
| 369 |
...
|
| 370 |
>>> len(otherPIIMatrix.keys())
|
| 371 |
1352
|
| 372 |
>>> test = '7/15/1974'
|
| 373 |
>>> test2 = datetime.datetime.strptime(test, '%m/%d/%Y')
|
| 374 |
>>> test2.strftime("%m/%d/%Y")
|
| 375 |
'07/15/1974'
|
| 376 |
>>> for line in contents:
|
| 377 |
... line = line.replace("\n","")
|
| 378 |
... line = line.split("|")
|
| 379 |
... name = line[4]
|
| 380 |
... name = name.upper()
|
| 381 |
... if line[3]:
|
| 382 |
... if name in dobMatrix.keys():
|
| 383 |
... if line[3] in dobMatrix[name]:
|
| 384 |
... pass
|
| 385 |
... else:
|
| 386 |
... dobMatrix[name].append(line[3])
|
| 387 |
... else:
|
| 388 |
... dobMatrix[name] = [line[3],]
|
| 389 |
|
| 390 |
>>> for line in contents:
|
| 391 |
... line = line.replace("\n","")
|
| 392 |
... line = line.split("|")
|
| 393 |
... name = line[4]
|
| 394 |
... name = name.upper()
|
| 395 |
... if line[3]:
|
| 396 |
... if "/" in rawDob:
|
| 397 |
... rawDob = datetime.datetime.strptime(rawDob, '%m/%d/%Y')
|
| 398 |
... dob = rawDob.strftime("%m/%d/%Y")
|
| 399 |
... else:
|
| 400 |
... rawDob = datetime.datetime.strptime(rawDob, '%Y%m%d')
|
| 401 |
... dob = rawDob.strftime("%m/%d/%Y")
|
| 402 |
... if name in dobMatrix.keys():
|
| 403 |
... if dob in dobMatrix[name]:
|
| 404 |
... pass
|
| 405 |
... else:
|
| 406 |
... dobMatrix[name].append(dob)
|
| 407 |
... else:
|
| 408 |
... dobMatrix[name] = [dob,]
|
| 409 |
...
|
| 410 |
>>> effFile = open(r"C:\Temp\LCHC - dobTestLog.txt",'w')
|
| 411 |
|
| 412 |
|
| 413 |
>>> dobMatrix = {}
|
| 414 |
>>> effFile = open(r"C:\Temp\LCHC - dobTestLog.txt",'w')
|
| 415 |
>>> for line in contents:
|
| 416 |
... line = line.replace("\n","")
|
| 417 |
... line = line.split("|")
|
| 418 |
... name = line[4]
|
| 419 |
... name = name.upper()
|
| 420 |
... rawDob = line[3]
|
| 421 |
... if len(line[3]) >5:
|
| 422 |
... if "/" in rawDob:
|
| 423 |
... rawDob = datetime.datetime.strptime(rawDob, '%m/%d/%Y')
|
| 424 |
... dob = rawDob.strftime("%m/%d/%Y")
|
| 425 |
... else:
|
| 426 |
... rawDob = datetime.datetime.strptime(rawDob, '%Y%m%d')
|
| 427 |
... dob = rawDob.strftime("%m/%d/%Y")
|
| 428 |
... effFile.write("%s changed to %s for docID %s\n"% (line[3], dob, line[0]))
|
| 429 |
... if name in dobMatrix.keys():
|
| 430 |
... if dob in dobMatrix[name]:
|
| 431 |
... pass
|
| 432 |
... else:
|
| 433 |
... dobMatrix[name].append(dob)
|
| 434 |
... else:
|
| 435 |
... dobMatrix[name] = [dob,]
|
| 436 |
... else:
|
| 437 |
... if line[3]:
|
| 438 |
... effFile.write("ERROR: %s is too small to parse!!!\n"% line[3])
|
| 439 |
...
|
| 440 |
>>> effFile.close()
|
| 441 |
>>> len(dobMatrix.keys())
|
| 442 |
64385
|
| 443 |
>>> outputFile = open(r"C:\Temp\LCHC - Consolidated Master_For Scripting_02.17.21-OUTPUT.DAT",'w')
|
| 444 |
>>> patientList = docIDMatrix.keys()
|
| 445 |
>>> patientList.sort()
|
| 446 |
>>> patientList[0]
|
| 447 |
''
|
| 448 |
>>> patientList[1]
|
| 449 |
' CAMPUZANO, JACGP'
|
| 450 |
>>> patientList[2]
|
| 451 |
' LEVESQUE, JENNIFER'
|
| 452 |
>>> patientList[3]
|
| 453 |
' OLIVER, CRUZ'
|
| 454 |
>>> patientList[1].lstrip()
|
| 455 |
'CAMPUZANO, JACGP'
|
| 456 |
>>> patientList[1].rstrip()
|
| 457 |
' CAMPUZANO, JACGP'
|
| 458 |
>>> |
