DV,Walmart, API Tests

Scripts/TalkspaceUsers/usercomparison.py

@@ -1,15 +1,48 @@
 import csv
 from Levenshtein import distance as lev
+import pandas as pd
+import itertools
 import sys
 
-x = lev("nrasmussen", "mrasmussen")
-print(x)
+peopleCsv = "/Users/normrasmussen/Downloads/TalkspaceAllLearners.csv"
 
-#def readSpreadsheet():
-#    with open('talkspace.csv', rb) as csvfile:
-#        for line in csvfile.readlines():
-#            array = line.split(',')
-#            emailcol = array[3]
+def readCsv(peopleCsv):
+    people = []
+    readExport = pd.read_csv(
+            peopleCsv,
+            usecols=['Learner Full Name', 'Email'],
+            skipinitialspace=True,
+            #index_col=True,
+            )
+    people.extend(readExport['Email'].tolist())
+    startCompare(peopleCsv, people, readExport)
 
-#def compareemails():
-#    levenshtein.distance(email1, email2)
+# itertools combinations
+def startCompare(peopleCsv, people, readExport):
+    email1 = []
+    email2 = []
+    for name1, name2, in itertools.combinations(people, 2):
+        #print(name1, name2) - prints all pairs, working so far. 
+        distance = lev(name1, name2)
+        #print(distance) - successfully returns numbers
+        if distance > 0 and distance < 2:
+            email1.append(name1)
+            email2.append(name2)
+    writenewColumn(email1, email2, peopleCsv, readExport)
+
+def writenewColumn(email1, email2, peopleCsv, readExport):
+    df = pd.DataFrame(readExport)
+    print(df)
+    df['Email1'] = pd.Series(email1)
+    df['Email2'] = pd.Series(email2)
+    df.drop_duplicates('Email1', inplace=True)
+    df.drop_duplicates('Email2', inplace=True)
+    df.drop_duplicates(
+            subset=['Email1', 'Email2'])
+            #keep = 'last').reset_index(drop=True)
+    writeLst = df.to_csv(
+            '/Users/normrasmussen/Downloads/TalkspaceDupes_singlechange.csv',
+            )
+
+if __name__ == "__main__":
+    readCsv(peopleCsv)

Scripts/WalmartExcel/walmart_numeric.py

@@ -40,9 +40,11 @@ def copytoDash(latestdownload, currentDash):
                 regex="Unname"
                 ),axis=1, 
                 inplace=True)
+
+def progressFormat(latestdownload, currentDash, readExport):
+   df = pd.DataFrame(readExport)
     readExport['Progress_replace'] = readExport['Progress'].str.replace('%','')
     readExport['Progress_replace'] = pd.to_numeric(readExport['Progress_replace'])
-    copiedData = readExport.copy()
     bringtoExcel(latestdownload, currentDash, copiedData)
     #cleanitUp(latestdownload, currentDash, copiedData)