notebook.community



In [54]:

    
import pandas as pd

from pandas.api.types import CategoricalDtype



In [55]:

    
pd.__version__









    Out[55]:





'1.0.3'



In [56]:

    
df = pd.DataFrame({'country': ['russia', 'germany', 'australia','korea','germany']})
df









    Out[56]:







  
    
      
      country
    
  
  
    
      0
      russia
    
    
      1
      germany
    
    
      2
      australia
    
    
      3
      korea
    
    
      4
      germany

One-hot encoding a column in a Pandas Dataframe



In [57]:

    
df = pd.DataFrame({'country': ['russia', 'germany', 'australia','korea','germany']})
pd.get_dummies(df,prefix=['country'])









    Out[57]:







  
    
      
      country_australia
      country_germany
      country_korea
      country_russia
    
  
  
    
      0
      0
      0
      0
      1
    
    
      1
      0
      1
      0
      0
    
    
      2
      1
      0
      0
      0
    
    
      3
      0
      0
      1
      0
    
    
      4
      0
      1
      0
      0

One-hot encoding vs Dummy variables



In [58]:

    
df = pd.DataFrame({'country': ['russia', 'germany', 'australia','korea','germany']})
pd.get_dummies(df["country"], prefix='country', drop_first=True)









    Out[58]:







  
    
      
      country_germany
      country_korea
      country_russia
    
  
  
    
      0
      0
      0
      1
    
    
      1
      1
      0
      0
    
    
      2
      0
      0
      0
    
    
      3
      0
      1
      0
    
    
      4
      1
      0
      0

Add columns for categories that only appear in the test set



In [59]:

    
df = pd.DataFrame({'country': ['russia', 'germany', 'australia','korea','germany']})
df["country"] = df["country"].astype(CategoricalDtype(["australia","germany","korea","russia","japan"]))



In [60]:

    
df









    Out[60]:







  
    
      
      country
    
  
  
    
      0
      russia
    
    
      1
      germany
    
    
      2
      australia
    
    
      3
      korea
    
    
      4
      germany



In [61]:

    
pd.get_dummies(df["country"],prefix='country')









    Out[61]:







  
    
      
      country_australia
      country_germany
      country_korea
      country_russia
      country_japan
    
  
  
    
      0
      0
      0
      0
      1
      0
    
    
      1
      0
      1
      0
      0
      0
    
    
      2
      1
      0
      0
      0
      0
    
    
      3
      0
      0
      1
      0
      0
    
    
      4
      0
      1
      0
      0
      0

Add dummy columns to dataframe



In [62]:

    
import pandas as pd

# df now has two columns: name and country
df = pd.DataFrame({
        'name': ['josef','michael','john','bawool','klaus'],
        'country': ['russia', 'germany', 'australia','korea','germany']
    })

# use pd.concat to join the new columns with your original dataframe
df = pd.concat([df,pd.get_dummies(df['country'], prefix='country')],axis=1)

# now drop the original 'country' column (you don't need it anymore)
df.drop(['country'],axis=1, inplace=True)



In [63]:

    
df









    Out[63]:







  
    
      
      name
      country_australia
      country_germany
      country_korea
      country_russia
    
  
  
    
      0
      josef
      0
      0
      0
      1
    
    
      1
      michael
      0
      1
      0
      0
    
    
      2
      john
      1
      0
      0
      0
    
    
      3
      bawool
      0
      0
      1
      0
    
    
      4
      klaus
      0
      1
      0
      0

Treat Nulls/NaNs as a separate category



In [64]:

    
import numpy as np



In [65]:

    
df = pd.DataFrame({
    'country': ['germany',np.nan,'germany','united kingdom','america','united kingdom']
})
df









    Out[65]:







  
    
      
      country
    
  
  
    
      0
      germany
    
    
      1
      NaN
    
    
      2
      germany
    
    
      3
      united kingdom
    
    
      4
      america
    
    
      5
      united kingdom



In [66]:

    
pd.get_dummies(df["country"],dummy_na=True)









    Out[66]:







  
    
      
      america
      germany
      united kingdom
      NaN
    
  
  
    
      0
      0
      1
      0
      0
    
    
      1
      0
      0
      0
      1
    
    
      2
      0
      1
      0
      0
    
    
      3
      0
      0
      1
      0
    
    
      4
      1
      0
      0
      0
    
    
      5
      0
      0
      1
      0

one-hot encode a single column



In [67]:

    
df = pd.DataFrame({
    'has_dogs':[True,False,True,True,False,True],
    'country': ['germany',np.nan,'germany','united kingdom','america','united kingdom']
})



In [68]:

    
pd.get_dummies(df)









    Out[68]:







  
    
      
      has_dogs
      country_america
      country_germany
      country_united kingdom
    
  
  
    
      0
      True
      0
      1
      0
    
    
      1
      False
      0
      0
      0
    
    
      2
      True
      0
      1
      0
    
    
      3
      True
      0
      0
      1
    
    
      4
      False
      1
      0
      0
    
    
      5
      True
      0
      0
      1



In [69]:

    
df = pd.DataFrame({'country': ['russia', 'germany', 'australia','korea','germany']})

pd.get_dummies(df,prefix=['country'], drop_first=True)









    Out[69]:







  
    
      
      country_germany
      country_korea
      country_russia
    
  
  
    
      0
      0
      0
      1
    
    
      1
      1
      0
      0
    
    
      2
      0
      0
      0
    
    
      3
      0
      1
      0
    
    
      4
      1
      0
      0