| 1 |
+ |
=== Here I was asked to group dup documents using a field where they are putting in the |
| 2 |
+ |
dup values === |
| 3 |
+ |
== First I made the matrix, flatening the data into “groups” == |
| 4 |
+ |
>>> matrix = {} |
| 5 |
+ |
>>> contents = open(r"/Users/ninoborges/Dropbox/Misc/359.txt").readlines() |
| 6 |
+ |
>>> matrix2 = {} |
| 7 |
+ |
>>> count = 1 |
| 8 |
+ |
>>> for line in contents: |
| 9 |
+ |
line = line.replace("\n","") |
| 10 |
+ |
line = line.replace("\r","") |
| 11 |
+ |
line = line.split("|") |
| 12 |
+ |
test = None |
| 13 |
+ |
for docID in line: |
| 14 |
+ |
if docID in matrix.keys(): |
| 15 |
+ |
test = matrix[docID] |
| 16 |
+ |
if test: |
| 17 |
+ |
pass |
| 18 |
+ |
else: |
| 19 |
+ |
test = count |
| 20 |
+ |
count = count + 1 |
| 21 |
+ |
for docID in line: |
| 22 |
+ |
matrix[docID] = test |
| 23 |
+ |
|
| 24 |
+ |
>>> len(matrix.keys()) |
| 25 |
+ |
>>> for begNo in matrix.keys(): |
| 26 |
+ |
group = matrix[begNo] |
| 27 |
+ |
if group in matrix2.keys(): |
| 28 |
+ |
if begNo in matrix2[group]: |
| 29 |
+ |
pass |
| 30 |
+ |
else: |
| 31 |
+ |
matrix2[group].append(begNo) |
| 32 |
+ |
else: |
| 33 |
+ |
matrix2[group] = [begNo,] |
| 34 |
+ |
|
| 35 |
+ |
>>> outputFile = open(r"/Users/ninoborges/Dropbox/Misc/359_export.txt",'w') |
| 36 |
+ |
>>> for i in matrix2.keys(): |
| 37 |
+ |
outputFile.write(str(matrix2[i])+"\n") |
| 38 |
+ |
|
| 39 |
+ |
|
| 40 |
+ |
>>> outputFile.close() |
| 41 |
+ |
>>> len(matrix2.keys()) |
| 42 |
+ |
== Now use a list as the prefered “original” list == |
| 43 |
+ |
>>> contents = open(r"/Users/ninoborges/Dropbox/Misc/originals_list.dat").readlines() |
| 44 |
+ |
>>> origList = [] |
| 45 |
+ |
>>> for line in contents: |
| 46 |
+ |
line = line.replace("\n","") |
| 47 |
+ |
origList.append(line) |
| 48 |
+ |
|
| 49 |
+ |
|
| 50 |
+ |
>>> len(origList) |
| 51 |
+ |
|
| 52 |
+ |
== now unpack and if it’s in the orig list, use that, if not use the smaller one. == |
| 53 |
+ |
>>> outputFile = open(r"/Users/ninoborges/Dropbox/Misc/finalReport.txt",'w') |
| 54 |
+ |
>>> for k in matrix2.keys(): |
| 55 |
+ |
group = matrix2[k] |
| 56 |
+ |
group.sort() |
| 57 |
+ |
parent = None |
| 58 |
+ |
for orig in origList: |
| 59 |
+ |
if orig in group: |
| 60 |
+ |
parent = orig |
| 61 |
+ |
if parent: |
| 62 |
+ |
outputFile.write(parent + "|") |
| 63 |
+ |
for i in group: |
| 64 |
+ |
if i == parent: |
| 65 |
+ |
pass |
| 66 |
+ |
else: |
| 67 |
+ |
outputFile.write(i+",") |
| 68 |
+ |
else: |
| 69 |
+ |
outputFile.write(group[0]+"|") |
| 70 |
+ |
for i in group[1:]: |
| 71 |
+ |
outputFile.write(i+",") |
| 72 |
+ |
outputFile.write('\n') |
| 73 |
+ |
|
| 74 |
+ |
|
| 75 |
+ |
>>> outputFile.close() |
| 76 |
+ |
===end=== |
| 77 |
+ |
|
| 78 |
|
=== Here I was asked to make a report of the relates to but using priority tags === |
| 79 |
|
== First I take the priority scale that they gave me into a dict == |
| 80 |
|
contents = open(r"C:\Users\eborges\Box Sync\Client\Honeywell\Perligo\Project_RelatesTo_Priority\Group A\GroupA_pri.txt").readlines() |
