python的论文_分类 python 下的文章

one_hot_encoder和label_encoder可以处理类别类型的特征。import pandas as pd

from sklearn.preprocessing import LabelEncoder

def one_hot_encoder(df, nan_as_category = True):

original_columns = list(df.columns)

categorical_columns = [col for col in df.columns if df[col].dtype == 'object']

df = pd.get_dummies(df, columns = categorical_columns, dummy_na = nan_as_category)

new_columns = [c for c in df.columns if c not in original_columns]

return df, new_columns

def label_encoder(df):

original_columns = list(df.columns)

categorical_columns = [col for col in df.columns if df[col].dtype == 'object']

for col in categorical_columns:

df[col] = LabelEncoder().fit_transform(df[col].astype('str'))

new_columns = [c for c in df.columns if c not in original_columns]

return df, categorical_columns