import pandas as pd
train_file = './data/train.csv'
train_data = pd.read_csv(train_file)
# 删除需要的列
train_data.drop(['PID', 'Name'], axis=1, inplace=True)
# 弹出Label列
label_data = train_data.pop('Label')
# 补全缺失值(用中位数)
age_median = train_data['Age'].median()
train_data['Age'].fillna(age_median, inplace=True)
# 有大小关系的用编码映射
size_map = {'S': 1, 'M': 2, 'L': 3}
train_data['Size'] = train_data['Size'].map(size_map)
# 无大小顺序的用One-hot编码
train_data = pd.get_dummies(train_data)
print(train_data.head(20))
PS:自用的 不做解释 作者:一个吃货帅锅