获取库及数据
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from IPython.display import Image
%matplotlib inline
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
plt.rcParams['figure.figsize'] = (10, 6) # 设置输出图片大小
# 读取训练数集
train = pd.read_csv('C:/Users/Administrator/LC python/datawhale/data analysis/unit 3/train.csv')
train.shape
(891, 12)
train.head()
预处理
缺失值填充
- 对分类变量缺失值:填充某个缺失值字符(NA)、用最多类别的进行填充
- 对连续变量缺失值:填充均值、中位数、众数
# 对分类变量进行填充
train['Cabin'] = train['Cabin'].fillna('NA')
train['Embarked'] = train['Embarked'].fillna('S')
# 对连续变量进行填充
train['Age'] = train['Age'].fillna(train['Age'].mean())
# 检查缺失值比例
train.isnull().mean().sort_values(ascending=False)
编码分类变量
# 取出所有的输入特征
data = train[['Pclass',