In [1]:

    

import pandas as pd


    

In [2]:

    

# Read stage 2
gr_15 = pd.read_csv('grant_15.csv')
gr_16 = pd.read_csv('grant_16.csv')


    

In [3]:

    

# Only use important values and properly name them
gr_15 = gr_15.loc[:, ["BauerID", "Gesamt", "Ökologischer Landbau"]]
gr_16 = gr_16.loc[:, ["BauerID", "Gesamt", "Ökologischer Landbau"]]
gr_15.rename(columns={'Gesamt': '2015', "Ökologischer Landbau": 'Öko_2015'}, inplace=True)
gr_16.rename(columns={'Gesamt': '2016', "Ökologischer Landbau": 'Öko_2016'}, inplace=True)


    

In [4]:

    

# Debug Information
#print(gr_15.columns.values)
#print(gr_16.columns.values)


    

In [5]:

    

# Merge both years and fill NaN
organic = pd.merge(gr_15, gr_16, how='outer', on=['BauerID'])
organic.fillna(0, inplace=True)


    

In [6]:

    

# Generate is organic column
organic['Öko'] = organic['Öko_2015'] + organic['Öko_2016']
organic['Öko'] = organic['Öko'].map(lambda a: 1 if a > 0 else 0)


    

In [7]:

    

# Print amount of farmers
conv = organic.shape[0]
orga = organic['Öko'].sum()
print(conv)
print(orga)
print(str((orga/conv)*100) + " %")


    

    




297841
15983
5.36628603852 %

In [8]:

    

# Print amount of money
conv_m = organic['2016'].sum()
orga_m = organic['Öko_2016'].sum()
print(conv_m/(10**6))
print(orga_m/(10**6))
print(str((orga_m/conv_m)*100) + " %")


    

    




5737.57592941
187.02608467
3.25967075593 %

In [9]:

    

# Save insight
organic.to_csv('insights/organic.csv', encoding='utf-8', index=False)