Medium-20210509-4.py

Medium-20210509-4.py

# names of the comparison column
check_colnames= [s + '_c' for s in columnnames1]

# initialize an empty dataframe for the log
logdf=pd.DataFrame(index=[True,False])

for column in check_colnames:
    t=comparison[column].value_counts() # returns a series
    tt=pd.DataFrame(t) # makes a DF out of the series
    logdf = logdf.join(tt,how='outer') # join the two dfs

# transpose for better readability
logdf = logdf.transpose()

# Ensure fixed sequence of the columns
logdf=logdf.reindex(sorted(logdf.columns),axis=1)

# write to disk
logdf.to_excel('logfile.xlsx')

# for better viewing on the screen
logdf.fillna('-',inplace=True)
pd.options.display.float_format = '{:,.0f}'.format

print(logdf)