norm/Gainsight
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Walmart script in production! And more notes.

Browse Source
This commit is contained in:
Norm Rasmussen
2023-02-01 18:11:39 -05:00
parent 55eb10b0f5
commit 3fd15aee52
102 changed files with 2729 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
Scripts/TalkspaceUsers/usercomparison.py
View File

@ -6,43 +6,49 @@ import sys
peopleCsv = "/Users/normrasmussen/Downloads/TalkspaceAllLearners.csv"
def readCsv(peopleCsv):
people = []
readExport = pd.read_csv(
peopleCsv,
usecols=['Learner Full Name', 'Email'],
skipinitialspace=True,
#index_col=True,
)
people.extend(readExport['Email'].tolist())
peopleCsv,
usecols=["Learner Full Name", "Email"],
skipinitialspace=True,
# index_col=True,
)
people.extend(readExport["Email"].tolist())
startCompare(peopleCsv, people, readExport)
# 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.
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
# 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)
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',
)
"/Users/normrasmussen/Downloads/TalkspaceDupes_singlechange.csv",
)
if __name__ == "__main__":
readCsv(peopleCsv)