import pandas as pd
d = {'sales': [100000,222000,1000000,522000,111111,222222,1111111,20000,75000,90000,1000000,10000],
'city': ['Tampa','Tampa','Orlando','Jacksonville','Miami','Jacksonville','Miami','Miami','Orlando','Orlando','Orlando','Orlando'],
'size': ['Small', 'Medium','Large','Large','Small','Medium','Large','Small','Medium','Medium','Medium','Small',]}
df = pd.DataFrame(data=d)
df
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import OrdinalEncoder
ohe = OneHotEncoder(sparse_output=False)
ode = OrdinalEncoder()
from sklearn.compose import make_column_transformer
ct = make_column_transformer(
(OneHotEncoder, ['city']),
(OrdinalEncoder, ['size']),
remainder='drop')
ct.set_output(transform="pandas")
df_pandas = ct.fit_transform(df)
df_pandas
#drop
ct2 = make_column_transformer(
(ohe, [1]),
(ode, [2]),
sparse_threshold=0,
remainder='drop')
ct2.set_output(transform="pandas")
df_pandas2 = ct2.fit_transform(df)
df_pandas2
#Example Passthrough some columns, drop offthers
ct3 = make_column_transformer(
(ohe, ['city']),
('passthrough', ['size']),
sparse_threshold=0,
remainder='drop')
ct3.set_output(transform="pandas")
df_pandas3 = ct3.fit_transform(df)
df_pandas3
