uweziegenhagen.de

import pandas as pd
import numpy as np
from openpyxl import Workbook
from openpyxl.utils.cell import get_column_letter
from openpyxl.utils.dataframe import dataframe_to_rows
from openpyxl.worksheet.table import Table, TableStyleInfo
 
 
dataframe = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), columns=['a', 'b', 'c'])
rows = dataframe_to_rows(dataframe, index=False, header=True)
 
wb = Workbook()
ws = wb.active
 
for r_idx, row in enumerate(rows, 1):
    for c_idx, value in enumerate(row, 1):
        ws.cell(row=r_idx, column=c_idx, value=value)
 
# Set column widths based on title width or fixed number
widths = {}
for column in ws.columns:
    if column[0].value is None: # no column header => Fixed with
        widths[column[0].column] = 10.5
    else: # if column header is present => min width resp. maximum
        widths[column[0].column] = max(len(str(column[0].value)) * 1.45, 10.5)
 
ws.column_dimensions[get_column_letter(column[0].column)].width = widths[column[0].column]
 
# Insert formatted table from A1 to max column/max row
tab = Table(displayName="MeineTabelle", ref='A1:' + get_column_letter(ws.max_column) + str(ws.max_row))
style = TableStyleInfo(name="TableStyleLight9", showFirstColumn=False,
                       showLastColumn=False, showRowStripes=True, showColumnStripes=True)
tab.tableStyleInfo = style
ws.add_table(tab)
 
wb.save('05.xlsx')
wb.close()

import pandas as pd
import numpy as np
from openpyxl import Workbook
from openpyxl.utils.dataframe import dataframe_to_rows
 
dataframe = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), columns=['a', 'b', 'c'])
rows = dataframe_to_rows(dataframe, index=False, header=True)
 
wb = Workbook()
ws = wb.active
 
for r_idx, row in enumerate(rows, 1):
    for c_idx, value in enumerate(row, 1):
        ws.cell(row=r_idx, column=c_idx, value=value)
 
# Set column widths based on title width or fixed number
widths = {}
for column in ws.columns:
    if column[0].value is None: # no column header => Fixed with
        widths[column[0].column] = 10.5
    else: # if column header is present => min width resp. maximum
        widths[column[0].column] = max(len(str(column[0].value)) * 1.45, 10.5)
 
ws.column_dimensions[get_column_letter(column[0].column)].width = widths[column[0].column]
 
wb.save('04.xlsx')
wb.close()

import pandas as pd
import numpy as np
from openpyxl import Workbook
from openpyxl.utils.dataframe import dataframe_to_rows
 
dataframe = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), columns=['a', 'b', 'c'])
rows = dataframe_to_rows(dataframe, index=False, header=True)
 
wb = Workbook()
ws = wb.active
 
for r_idx, row in enumerate(rows, 1):
    for c_idx, value in enumerate(row, 1):
        ws.cell(row=r_idx, column=c_idx, value=value)
 
ws.column_dimensions['A'].width = 5
ws.column_dimensions['B'].width = 10
ws.column_dimensions['C'].width = 15
 
wb.save('03.xlsx')
wb.close()

import pandas as pd
import numpy as np
from openpyxl import Workbook
from openpyxl.utils.dataframe import dataframe_to_rows
 
dataframe = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), columns=['a', 'b', 'c'])
rows = dataframe_to_rows(dataframe, index=False, header=True)
 
wb = Workbook()
ws = wb.active
 
for r_idx, row in enumerate(rows, 1):
    for c_idx, value in enumerate(row, 1):
        ws.cell(row=r_idx, column=c_idx, value=value)
 
wb.save('02.xlsx')
wb.close()

# -*- coding: utf-8 -*-
"""
Created on Sat Mar 18 10:04:40 2017
 
@author: Uwe Ziegenhagen
"""
import pandas as pd
from math import floor
 
def russianPeasantMultiply(a, b):
    assert a > 1
    assert b > 0    
    data = pd.DataFrame([[a, b]], columns=list('ab'))
    while a > 1:
        a = floor(a/2)
        b = b + b
        data.loc[len(data)]=[a, b]
    data = data[data['a'] % 2 == 1]    
    return(data.b.sum())
 
print(russianPeasantMultiply(63, 17))

# -*- coding: utf-8 -*-
 
import pandas as pd
 
data = pd.read_excel('meltdata.xlsx')
 
print(data.shape[1], 'columns and', data.shape[0], 'rows')
 
print(list(data))
 
melted = pd.melt(data, id_vars=['Name', 'ColumnB', 'ColumnC'], 
                 value_vars=['Januar', 'Februar', 'März', 'April', 'Mai', 
                 'Juni', 'Juli', 'August', 'September', 'Oktober', 
                 'November', 'Dezember'])
 
print(melted)

# -*- coding: utf-8 -*-
import pandas as pd
 
def unique(liste):
    """ takes a list of elements, separated by comma and returns sorted string of unique items separated by comma """
    a = liste.split(',')
    b = sorted(set(a))
    return ','.join(b)
 
df = pd.read_excel('groupb_Beispiel.xlsx')
print(df)
 
grouped = df.groupby(['Key1','Key2'],as_index=False)['Bar'].agg(lambda col: ','.join(col))
grouped = pd.DataFrame(grouped)
 
grouped['Unique'] = grouped['Bar'].apply(unique)
 
print(grouped)
 
grouped.to_excel('result.xlsx')

import pandas as pd
 
# Lade die Daten
daten = pd.read_excel('combine.xlsx')
# Erstelle leeren Dataframe mit den Spaltennamen aus den Excelzeilen 
verarbeitet = pd.DataFrame(columns=['ColA','ColB','ColC'])
 
# Iteriere über die Daten
for i, row in daten.iterrows():
    # ganzzahliges Teilen, um die Zeile zu bestimmen
    # in die die Zelle gehört, Spalte ergibt sich aus dem Wert in 'Spalte'
    verarbeitet.loc[i // 3,row['Spalte']] = row['Wert']
 
print(verarbeitet)

import pandas as pd
 
data = {'A': ["cola", "colb", "colc", "cola", "colb", "colc"], "B": [1, 2, 3, 4, 5, 6]}
data = pd.DataFrame(data)
gb = data.groupby('A')
res = pd.DataFrame()
for key in gb.groups:
    res[key] = gb.get_group(key)['B'].values.flatten()
 
print(res)