One Hot Encoding

one method converting categorical variables to convenient variables (e.g. 0-1) using dummy variables

Pandas

Get dummy columns

dummies = pd.get_dummies(df.town)

merged = pd.concat([df, dummies], axis='columns')

Drop one of the variables

防止变量出现完全共线性情况使参数无法估计

final = merged.drop(['town', 'west windsor'], axis='columns')

Sklearn

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()

dfle = df
dfle.town = le.fit_transform(dfle.town)

X = dfle[['town', 'area']].values
y = dfle.price

from sklearn.preprocessing import OneHotEncoder
ohe = OneHotEncoder(categorical_features=[0])

"""
报错如下：
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In [28], line 2
      1 from sklearn.preprocessing import OneHotEncoder
----> 2 ohe = OneHotEncoder(categorical_features=[0])

TypeError: __init__() got an unexpected keyword argument 'categorical_features'

原因：新版sklearn删去了"categorical_features"参数

解决：from sklearn.compose import ColumnTransformer
"""

from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
ohe = ColumnTransformer([('encoder', OneHotEncoder(), [0])], remainder='passthrough')

X = ohe.fit_transform(X)

X = X[:,1:] # Take all the rows and drop 0th column