| 1 |
+ |
--- NEW --- |
| 2 |
+ |
"""In this project, Rawlings data check,old format I was asked to take two spreadsheets and using last name and the last 4 dig of ssn, |
| 3 |
+ |
cross ref and give them a list of what matched""" |
| 4 |
+ |
|
| 5 |
+ |
>>> matrix = {} |
| 6 |
+ |
>>> contents = open(r"\\BSTDD967DTW1\Users\eborges\Box Sync\Client\Narco\schedule a - list of pe claims to be paid Q3.csv").readlines() |
| 7 |
+ |
# First I made a matrix with {fullname,full_ssn}, this came from the schedule a list |
| 8 |
+ |
>>> for line in contents: |
| 9 |
+ |
... line = line.split("|") |
| 10 |
+ |
... name = line[0] |
| 11 |
+ |
... matrix[name] = line[1] |
| 12 |
+ |
|
| 13 |
+ |
# Then I made a matrix of {lastName,[fullname,fullname,fullname]}, so that I could first search by last name and then per |
| 14 |
+ |
# name test the ssn |
| 15 |
+ |
>>> lastNameMatrix = {} |
| 16 |
+ |
>>> for line in contents: |
| 17 |
+ |
... line = line.split("|") |
| 18 |
+ |
... name = line[0] |
| 19 |
+ |
... lastName = name.split(",")[0] |
| 20 |
+ |
... lastName = lastName.upper() |
| 21 |
+ |
... if lastName in lastNameMatrix.keys(): |
| 22 |
+ |
... lastNameMatrix[lastName].append(name) |
| 23 |
+ |
... else: |
| 24 |
+ |
... lastNameMatrix[lastName] = [name,] |
| 25 |
+ |
|
| 26 |
+ |
# Finally, going through the other file, I tested firs the last name and then, if that was found, checked the ssn per |
| 27 |
+ |
# last name found. |
| 28 |
+ |
contents = open(r"\\BSTDD967DTW1\Users\eborges\Box Sync\Client\Narco\NARCO Trust Claims Master File 11042014.csv").readlines() |
| 29 |
+ |
>>> outputFile = open(r"\\BSTDD967DTW1\Users\eborges\Box Sync\Client\Narco\Matched.txt",'w') |
| 30 |
+ |
>>> errFile = open(r"\\BSTDD967DTW1\Users\eborges\Box Sync\Client\Narco\NotFound.txt",'w') |
| 31 |
+ |
>>> for line in contents: |
| 32 |
+ |
... newLine = line.split("|") |
| 33 |
+ |
... lastName = newLine[4] |
| 34 |
+ |
... lastName = lastName.strip() |
| 35 |
+ |
... ssn = newLine[5] |
| 36 |
+ |
... if len(ssn) > 8: |
| 37 |
+ |
... ssnPart = ssn[-4:] |
| 38 |
+ |
... if lastName.upper() in lastNameMatrix.keys(): |
| 39 |
+ |
... for ln in lastNameMatrix[lastName.upper()]: |
| 40 |
+ |
... if ssnPart == matrix[ln][-4:]: |
| 41 |
+ |
... outputFile.write("%s | %s"%(matrix[ln],line)) |
| 42 |
+ |
... else: |
| 43 |
+ |
... errFile.write(line) |
| 44 |
+ |
... else: |
| 45 |
+ |
... errFile.write(line) |
| 46 |
+ |
... |
| 47 |
+ |
>>> outputFile.close() |
| 48 |
+ |
>>> errFile.close() |
| 49 |
+ |
|
| 50 |
+ |
|
| 51 |
+ |
--- END --- |
| 52 |
+ |
--- ALTERNATE --- |
| 53 |
+ |
""" new format""" |
| 54 |
+ |
>>> matrix = {} |
| 55 |
+ |
>>> contents = open(r"C:\Users\eborges\Box Sync\Client\Narco\New_Sched_A.csv").readlines() |
| 56 |
+ |
# First I made a matrix with {fullname[full_ssn,full_ssn]}, this came from the schedule a list |
| 57 |
+ |
>>> for line in contents: |
| 58 |
+ |
... line = line.split("|") |
| 59 |
+ |
... lastName = line[1] |
| 60 |
+ |
... firstName = line[2] |
| 61 |
+ |
... if line[3]: |
| 62 |
+ |
... midName = line[3] |
| 63 |
+ |
... else: |
| 64 |
+ |
... midName = None |
| 65 |
+ |
... if midName: |
| 66 |
+ |
... name = "%s, %s %s"% (lastName, firstName, midName) |
| 67 |
+ |
... else: |
| 68 |
+ |
... name = "%s, %s"% (lastName, firstName) |
| 69 |
+ |
... if name in matrix.keys(): |
| 70 |
+ |
... matrix[name].append(line[4]) |
| 71 |
+ |
... else: |
| 72 |
+ |
... matrix[name] = [line[4],] |
| 73 |
+ |
|
| 74 |
+ |
# Then I made a matrix of {lastName,[fullname,fullname,fullname]}, so that I could first search by last name and then per |
| 75 |
+ |
# name test the ssn |
| 76 |
+ |
>>> lastNameMatrix = {} |
| 77 |
+ |
# do this again each time... |
| 78 |
+ |
>>> contents = open(r"C:\Users\eborges\Box Sync\Client\Narco\New_Sched_A.csv").readlines() |
| 79 |
+ |
>>> for line in contents: |
| 80 |
+ |
... line = line.split("|") |
| 81 |
+ |
... lastName = line[1] |
| 82 |
+ |
... lastName = lastName.strip() |
| 83 |
+ |
... lastName = lastName.upper() |
| 84 |
+ |
... if lastName in lastNameMatrix.keys(): |
| 85 |
+ |
... lastNameMatrix[lastName].append(name) |
| 86 |
+ |
... else: |
| 87 |
+ |
... lastNameMatrix[lastName] = [name,] |
| 88 |
+ |
... |
| 89 |
+ |
|
| 90 |
+ |
# Finally, going through the other file, I tested first the last name and then, if that was found, checked the ssn per |
| 91 |
+ |
# last name found and per ssn found |
| 92 |
+ |
contents = open(r"\\BSTDD967DTW1\Users\eborges\Box Sync\Client\Narco\NARCO Trust Claims Master File 11042014.csv").readlines() |
| 93 |
+ |
>>> outputFile = open(r"\\BSTDD967DTW1\Users\eborges\Box Sync\Client\Narco\Matched_2.txt",'w') |
| 94 |
+ |
>>> errFile = open(r"\\BSTDD967DTW1\Users\eborges\Box Sync\Client\Narco\NotFound_2.txt",'w') |
| 95 |
+ |
>>> for line in contents: |
| 96 |
+ |
... newLine = line.split("|") |
| 97 |
+ |
... lastName = newLine[4] |
| 98 |
+ |
... lastName = lastName.strip() |
| 99 |
+ |
... ssn = newLine[5] |
| 100 |
+ |
... if len(ssn) > 8: |
| 101 |
+ |
... ssnPart = ssn[-4:] |
| 102 |
+ |
... if lastName.upper() in lastNameMatrix.keys(): |
| 103 |
+ |
... for ln in lastNameMatrix[lastName.upper()]: |
| 104 |
+ |
... for fl_SSN in matrix[ln]: |
| 105 |
+ |
... if ssnPart == fl_SSN[-4:]: |
| 106 |
+ |
... outputFile.write("%s | %s"%(fl_SSN,line)) |
| 107 |
+ |
... else: |
| 108 |
+ |
... errFile.write(line) |
| 109 |
+ |
... else: |
| 110 |
+ |
... errFile.write(line) |
| 111 |
+ |
>>> outputFile.close() |
| 112 |
+ |
>>> errFile.close() |
| 113 |
+ |
--- END --- |
| 114 |
+ |
|
| 115 |
+ |
----------------------------------------- |
| 116 |
|
""" In this project, I was asked to compare teh ssn column to two ssn columns in a separate sheet. |
| 117 |
|
I also had to normalize the ssn to look for hyphens""" |
| 118 |
|
|
