uweziegenhagen.de

import pandas as pd
import Levenshtein
 
df = pd.read_excel('Daten.xlsx')
df = df.sort_values(by=['Name'])
df = df.reset_index(drop=True)
 
dfs= df.shift() # Shift df by one row
dfs = dfs.rename(columns={'Name': 'Nameshifted'})
 
df_combined = pd.concat([df,dfs],axis=1) # combine original and shifted df
df_combined = df_combined.fillna('') # remove NaNs
 
for index, row in df_combined.iterrows():
    df_combined.loc[index,'Ratio'] = (Levenshtein.ratio(row['Name'], row['Nameshifted']))
    df_combined.loc[index,'Distance'] = (Levenshtein.distance(row['Name'], row['Nameshifted']))    
 
print(df_combined)

import os
 
for (root,dirs,files) in os.walk('.'):
 
    for file in files:
        fullpath = os.path.join(root,file)
 
        if fullpath.endswith('.txt'):
            newpath = root+'\\'+root[2:].replace('\\','_')+'_'+file
            print(newpath)
            os.rename(fullpath, newpath)

files = ['f:/willich.txt', 'f:/willich.txt',  'f:/willich.txt']
 
output = 'F:/kombiniert.txt'
filecount = len(files)
 
print(f'Processing {filecount} files')
 
with open(output, 'w') as outputfile: # Ausgabe öffnen
 
    for counter, file in enumerate(files):
        print(counter, file)
 
        with open(file, 'r') as fin:
            data = fin.read().splitlines(True)
 
        if counter == 0: # Erste Datei: alles bis auf die letzte Zeile
            outputfile.writelines(data[:-1])
 
        elif counter == filecount - 1: # letzte Datei, alles bis auf die ersten zwei Zeilen
            outputfile.writelines(data[2:])
 
        else: # die Dateien zwischen erster und letzter Datei, nicht die beiden ersten und die letzte Zeile
            outputfile.writelines(data[2:-1])

import sys
print(sys.executable)

import matplotlib.pyplot as plt
import numpy as np
 
ax = plt.gca()
plt.gca().set_aspect('equal')
 
ax.set_xticks(range(-6,6,1))
ax.set_yticks(range(-6,6,1))
ax.set_xlim([-5, 5])
ax.set_ylim([-5, 5])
 
ax.spines['top'].set_color('none')
ax.spines['bottom'].set_position('zero')
ax.spines['left'].set_position('zero')
ax.spines['right'].set_color('none')
 
x = np.linspace(-5,5,100)
y = 2*x+1
y2 = -0.5*x-2
 
plt.plot(x, y,  'r', label='2*x+1')
plt.plot(x, y2, 'g', label='-0.5*x-2')
 
plt.title('Linear Plots')
 
plt.legend(loc='upper left')
 
plt.grid()
plt.show()

<?xml version='1.0' encoding='UTF-8'?>
	<table name="Tablename">
	{% for _,row in data.iterrows() %}
	<ROW>
    <COLUMN1>{{row['column1']}}</COLUMN1>
    <COLUMN2>{{row['column2']}}</COLUMN2>
    <COLUMN3>{{row['column3']}}</COLUMN3>
	</ROW>
	{% endfor %}
</table>

import pandas as pd # data wrangling
import jinja2 # template engine
import os # for file-related stuff
 
# create jinja env that can load template from filesystem
jinja_env = jinja2.Environment(loader = jinja2.FileSystemLoader(os.path.abspath('.')))
 
df = pd.read_excel('Daten.xlsx')
template = jinja_env.get_template('template.xml')
 
with open('FertigesXML.xml','w') as output:
    output.write(template.render(data=df))

import xml.etree.ElementTree as ET
import urllib.request 
 
root = ET.parse(urllib.request.urlopen('http://www.ecb.europa.eu/stats/eurofxref/eurofxref-daily.xml')).getroot()
 
for child in root[2][0]:
    curr = child.get('currency')
    rate = child.get('rate')
    print(curr, rate)

from urllib.request import urlopen
import pandas as pd
 
df = pd.read_xml(urlopen('http://www.ecb.europa.eu/stats/eurofxref/eurofxref-daily.xml'),xpath='//*[@currency]')
 
print(df)

import sys
import collections
import pandas as pd
from tabulate import tabulate
 
 
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)
 
if collections.Counter(columnnames1) == collections.Counter(columnnames2):
    print ("Number of columns and Names match, Comparison possible...\n\n")
else:
    print ("Number of columns and Names are not matching!!! Please check the input!")
    sys.exit('Error!')
 
# add suffixes to distinguish between actual and expected in the merger
file1 = file1.add_suffix('_e') # expected
file2 = file2.add_suffix('_t') # t
 
 
# merge them using the given key, use outer join
comparison = pd.merge(file1,file2, how='outer',
                      left_on=['Key_e'],
                      right_on=['Key_t'])
 
# create the columnwise comparison
for col in columnnames1:
    comparison[(col + '_c')] = comparison[(col + '_t')] == comparison[(col + '_e')]
 
# reorder the columns
comparison=comparison.reindex(sorted(comparison.columns),axis=1)
 
print(tabulate(comparison, tablefmt="pipe", headers="keys"))
 
 
# save the result as Excel file
comparison.to_excel('result.xlsx')
 
# 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(tabulate(logdf, tablefmt="pipe", headers="keys"))

import pandas
import pandas_datareader.data as web
 
YAHOO_TODAY="http://download.finance.yahoo.com/d/quotes.csv?s=%s&f=sd1ohgl1vl1"
 
history = web.DataReader('AAPL', "yahoo", start="2021-1-1")
history.to_latex('aapl.tex')

\documentclass[12pt,ngerman]{scrartcl}
\usepackage[a4paper, top=1cm,bottom=1cm,left=1cm, right=1cm]{geometry}
\usepackage[T1]{fontenc}
\usepackage{booktabs}
 
\makeatletter
\newcommand{\testfileexists}[1]{%
  \IfFileExists{#1}%
    {\def\inputtestedfile{\@@input #1 }}
    {\let\inputtestedfile\@empty}%
}
\makeatother
 
\begin{document}
 
\write18{python runpy.py}
 
  \testfileexists{aapl}
      \inputtestedfile
 
 
\end{document}

#!/usr/bin/env python
# coding: utf-8
 
import seaborn as sns
import pandas as pd
import requests
from bs4 import BeautifulSoup
from io import StringIO
import matplotlib.pylab as plt
 
headers = {
    'Access-Control-Allow-Origin': '*',
    'Access-Control-Allow-Methods': 'GET',
    'Access-Control-Allow-Headers': 'Content-Type',
    'Access-Control-Max-Age': '3600',
    'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:52.0) Gecko/20100101 Firefox/52.0'
}
 
url = "http://www.statistics4u.com/fundstat_eng/data_fluriedw.html"
req = requests.get(url, headers)
soup = BeautifulSoup(req.content, 'html.parser')
 
 
data=soup.find('pre').contents[0]
 
str_object = StringIO(data)
 
df = pd.read_csv(str_object,engine='python',skiprows=5,delim_whitespace=True)
 
# Banknotes BN1 to BN100 are genuine, all others are counterfeit
df['Type'] = 'Counterfeit'
df.loc[df.index[:100], 'Type'] = 'Genuine'
 
print(df)
 
sns.set(style="whitegrid", palette="muted")
 
#df = df[['Left', 'Diagonal', 'Type']]
df = pd.melt(df, "Type", var_name="Variable")
 
sp = sns.stripplot(x="value", 
              y="Variable", 
              hue="Type",
              data=df, 
              dodge=True, 
              alpha=.75, 
              zorder=1)
 
#sp.set(xlim=(127, 143)) 
 
sp.legend_.remove()
plt.show()