Python - Basics - Pandas

import pandas as pd

pwd

# read file from file system

df=pd.read_csv('bevolkerung.csv’)

# read file from github

from pandas import Series, DataFrame

url1 = 'https://raw.githubusercontent.com/spribylova/Data/master/Assets.csv'

assets = pd.read_csv(url1,index_col=0)

url2 = 'https://raw.githubusercontent.com/spribylova/Data/master/Firmen.csv'

firmen = pd.read_csv(url2,index_col=0)

banks = pd.merge(assets, firmen, on='IN')

banks.describe()

banks

import matplotlib.pyplot as plt

import numpy as np

# summary statistics to describe numeric fields of uploaded file

# data is file are for 2 years /January 1998 - December 1999/ , provided is number of inhaitants in Zurich, Month, Day, Gender, Age group, Origin, District name, District code, number of inhabitants

df.describe()

df.groupby(['StichtagDatJahr', 'KreisCd'])['AnzBestWir'].sum().reset_index()

df3=df.groupby(['KreisCd'])['AnzBestWir'].sum().reset_index()

df3.sort_values(by=['KreisCd’])

df3.plot.bar(x="KreisCd", y="AnzBestWir”);

# Chart the ratio of foreigners within the total population in Kreis 2 over time # vorbereitet filter fur Kreis 2

filt2 = df2['KreisCd'] == 2

df2=df.groupby(['KreisCd', 'HerkunftLang'])['AnzBestWir'].sum().reset_index()

df2.where(filt2, inplace = True)

# using dropna() function

df4=df2.dropna(how = 'all’)

df4

# using dropna() function

df2.dropna(how = 'all’)