UweZiegenhagen

\documentclass{article}

\usepackage[T1]{fontenc}
\usepackage{graphicx}
\usepackage{csquotes}
\usepackage{xcolor}
\usepackage{tikz}
\usetikzlibrary{positioning}
\usetikzlibrary{calc}

UweZiegenhagen

\documentclass{article}

\usepackage[T1]{fontenc}
\usepackage{graphicx}
\usepackage{csquotes}
\usepackage{xcolor}
\usepackage{tikz}

\begin{document}

UweZiegenhagen

\documentclass[21pt]{scrartcl}
\usepackage[left=2cm,right=2cm, top=2cm,bottom=2cm,a3paper]{geometry}

\usepackage{forloop}
\setlength{\parindent}{0pt}
\usepackage{tikz}

\newcounter{ct} 
\usepackage{pgfpages}
 

UweZiegenhagen

import sys
import collections
import pandas as pd

file1 = pd.read_csv('file1.csv', sep=';', encoding='UTF-8')
file2 = pd.read_csv('file2.csv', sep=';', encoding='UTF-8')

columnnames1 = list(file1)
columnnames2 = list(file2)

UweZiegenhagen

# 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

UweZiegenhagen

	A_c	A_e	A_t	B_c	B_e	B_t	C_c	C_e	C_t	D_c	D_e	D_t	Key_c	Key_e	Key_t
0	False	1	nan	False	A	nan	False	1	nan	False	J	nan	False	1	nan
1	True	1	1	False	A	B	True	2	2	False	J	N	True	2	2
2	True	1	1	True	A	A	True	3	3	True	J	J	True	3	3
3	False	1	2	True	A	A	False	4	6	True	J	J	True	4	4
4	True	1	1	True	A	A	True	5	5	True	J	J	True	5	5
5	False	nan	1	False	nan	A	False	nan	1	False	nan

UweZiegenhagen

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

# add suffixes to distinguish between actual and expected in the merger
file1 = file1.add_suffix('_e') # expected
file2 = file2.add_suffix('_t') # actual, true result

# merge them using the given key, use outer join
comparison = pd.merge(file1,file2, how='outer',
                      left_on=['Key_e'],

UweZiegenhagen

# load both files into separate dataframes
file1 = pd.read_csv('file1.csv', sep=';', encoding='UTF-8')
file2 = pd.read_csv('file2.csv', sep=';', encoding='UTF-8')

# save the list of column names for each dataset
columnnames1 = list(file1)
columnnames2 = list(file2)

# check if the columns match
if collections.Counter(columnnames1) == collections.Counter(columnnames2):

UweZiegenhagen

import sys
import collections
import pandas as pd

UweZiegenhagen

# -*- coding: utf-8 -*-
"""
Created 20200215

@author: Uwe Ziegenhagen, ziegenhagen@gmail.com

Initial version, needs heavy refactoring

See https://github.com/jemmyw/Qif/blob/master/QIF_references for info
"""