Created
July 7, 2018 05:48
-
-
Save Llibyddap/1f609587562a96ce8159a9658162042b to your computer and use it in GitHub Desktop.
SO response
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import re | |
import numpy as np | |
data= [['Empty','CMI-General Liability | 05-9632','Empty','Empty'],['Empty','Central Operations','Empty','Empty'],['Empty','Alarm Central 05-8642','Empty','Empty'],['Empty','Market 466','Empty','Empty'],['Empty','Talent, Experience','Empty','Empty'],['Empty','Food Division','Empty','Empty'],['Empty','Quality WMCC','Empty','Empty'],['Empty','Modular Execution Team | 01-9700','Empty','Empty'],['Empty','US Central Operations','Empty','Empty'],['Empty','CE - Engineering - US','Empty','Empty'],['Empty','Fresh, Freezer & Cooler - 18-8110','Empty','Empty'],['Empty','9701','Empty','Empty'],['Empty','Contact Center','Empty','Empty'],['Empty','Central Operations','Empty','Empty'],['Empty','US Central Operations','Empty','Empty'],['Empty','Private Brands GM - 01-8683','Empty','Empty']] | |
df2=pd.DataFrame(data,columns=['JobTitle','Department','TrueDepartment','Dept_Function']) | |
data5 = [[1,'TRUCKING, MARCY, NY','Empty','Empty'],[2,'TRUCKING-GREENVILLE,TN','Empty','Empty'],[3,'DC 40, HOPE MILLS, NC','Empty','Empty'],[4,'TRUCKING, SHARON SPRINGS','Empty','Empty'],[5,'DISP PAULS VALLEY OK FDC','Empty','Empty'],[6,'COLDWATER, MI','Empty','Empty'],[7,'AMERICOLD LOGISTICS','Empty','Empty'],[8,'DFW3N FORT WORTH FC WHS.COM','Empty','Empty'],[9,'PCCC CURRENTLY BEING REVIEWED','Empty','Empty'],[466,'Springfield, MO','Empty','Empty'],[8110,'Fresh Dept','Empty','Empty'],[8642,'Security','Security & Compliance','Empty'],[8683,'General Merchandise','Empty','Empty'],[9362,'General Liability','Empty','Empty'],[9700,'Execution Team','Empty','Empty'],[9701,'Produce TN','Empty','Empty']] | |
df5=pd.DataFrame(data5,columns=['Dept_Nbr','Dept_Desc_good','Dept_Desc_better','Dept_Abrv']) | |
numbers = df5['Dept_Nbr'].tolist() | |
df5['Dept_Nbr'] = [int(i) for i in df5['Dept_Nbr']] | |
df5 = df5.set_index('Dept_Nbr') #<-- need to actually set df5 to the new index | |
for n in numbers: | |
for i in range(len(df5.index)): #<-- you want to iterate through the number of elements not the elements themselves | |
if str(n) == df2.loc[i, 'Department'][-4:]: #<-- convert n to str and slice df2 string for the last 4 chars | |
if df5.loc[n, 'Dept_Desc_better'] != "Empty": #<-- you're actually checking against a string, not a NaN | |
df2.loc[i, 'TrueDepartment'] = df5.loc[n, 'Dept_Desc_better'] #<-- use .loc not .at | |
else: | |
df2.loc[i, 'TrueDepartment'] = df5.loc[n, 'Dept_Desc_good'] | |
df2 = df2.replace(to_replace="Empty", value="") | |
print(df2) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment