Python - data frame columns rename with capital letter after the '.'

Question

I have some columns that follow the pattern 'abc.def' and I'm trying to change it to 'abcDef' with a function. I can do it with df.rename(columns={'abc.def': 'abcDef'}, inplace = True) but looking for a more generic approach that can be applied to different data frames. I did it for the simple string and I do not know how to apply it to the column names. I have tried to get column names to the list and append the function to the list but that did not work either.

My df is:

import pandas as pd
import re
            
            
data = {'end.date': ['01/10/2020 15:23', '01/10/2020 16:31', '01/10/2020 16:20', '01/10/2020 11:00'],
                  'start.date': ['01/10/2020 13:38', '01/10/2020 14:49', '01/10/2020 14:30','01/10/2020 14:30']
                  }
            
df = pd.DataFrame(data, columns = ['end.Date','start.date'])

# below is my go at the text.             
text = 'abs.d'
splitFilter = re.compile('([.!?]\s*)')
splitColumnName = splitFilter.split(text)
print(splitColumnName)
        
final = ''.join([i.capitalize() for i in splitColumnName])
final = final.replace('.', '')
print(final)

Answer 1

I think you want something like that ?

import pandas as pd
import re
            
            
data = {'end.date': ['01/10/2020 15:23', '01/10/2020 16:31', '01/10/2020 16:20', '01/10/2020 11:00'],
                  'start.date': ['01/10/2020 13:38', '01/10/2020 14:49', '01/10/2020 14:30','01/10/2020 14:30']
                  }
            
df = pd.DataFrame(data, columns = ['end.Date','start.date'])

# below is my go at the text.   
def formatColumn(column) :
  splitFilter = re.compile('([.!?]\s*)')
  splitColumnName = splitFilter.split(column)
          
  final = ''.join([i.capitalize() for i in splitColumnName])
  final = final.replace('.', '')
  return final[0].lower() + final[1:] 

df.rename(columns=dict(zip(df.columns, [formatColumn(c) for c in df.columns])))

Answer 2

I used the answers from @Arne and from @LeMorse and compiled what I needed. Thanks again!

import pandas as pd
import re
            
            
data = {'end.date': ['01/10/2020 15:23', '01/10/2020 16:31', '01/10/2020 16:20', '01/10/2020 11:00'],
                  'start.date': ['01/10/2020 13:38', '01/10/2020 14:49', '01/10/2020 14:30','01/10/2020 14:30']
                  }
            
df = pd.DataFrame(data, columns = ['end.Date','start.date'])

# below is my go at the text.   
def formatColumn(column) :
  splitFilter = re.compile('([.!?]\s*)')
  splitColumnName = splitFilter.split(column)
          
  final = ''.join([i.capitalize() for i in splitColumnName])
  final = final.replace('.', '')
  return final[0].lower() + final[1:] 

df.columns = [formatColumn(col) for col in df.columns]

Answer 3

You could put your code to transform an individual string into a function and then apply this function to every column name, eg with a list comprehension:

def camelCase(text):
    splitFilter = re.compile('([.!?]\s*)')
    splitColumnName = splitFilter.split(text)
    final = ''.join([i.capitalize() for i in splitColumnName])
    final = final.replace('.', '')
    return final

df.columns = [camelCase(col) for col in df.columns]

Note that currently your code capitalizes the first letter too.

Answer 4

def splitAndRenameColumns(df, splitSignal):
 # get all the columns in a list
 columnNameList = df.columns.values.tolist()
 # create a map to rename columns
 # mapping is old.columnname : newColumnname
 newColNames = {}
 # loop pver all column names
 for clm in columnNameList :
    # split the column names on "provided split signal i.e dot in this case"
    tempStore = clm.split(splitSignal)
    # store the first word before dot in temparory string  
    newString = tempStore[0]
    # loop over all other string values we got after splitting  
    for index in range(1,len(tempStore)):
        # capitalise first character to upper case and concatenate all the strings 
        newString += tempStore[index][0].upper()+tempStore[index][1:]
    # create the mapping 
    # i.e {'end.Date.gate': 'endDateGate', 'start.date.bate': 'startDateBate'}
    newColNames[clm] = newString
 return newColNames


df = df.rename(columns=splitAndRenameColumns(df, "."))
print(df)

It's almost similar to other answers but It's more generic in-terms of split signals and explains the process with comments clearly. Let me know if you still need more comments on the code