pandas数据分析的常用方法map和apply

一、方法map的使用

import numpy as np
import pandas as pd
boolean = [True, False]
gender = ["男","女"]
color = ['white','black','yellow']
data = pd.DataFrame({
    'height':np.random.randint(150,190,100),
    'weight':np.random.randint(40,90,100),
    'smoker':[boolean[x] for x in np.random.randint(0,2,100)],
    'gender':[gender[x] for x in np.random.randint(0,2,100)],
    'age':np.random.randint(15,90,100),
    'color':[color[x] for x in np.random.randint(0,len(color),100)]
})

将性别映射为0/1

def gender_map(x):
    gender = 1 if x == "男" else 0
    return gender
data['gender'] = data['gender'].map(gender_map)
# 直接简历字典进行映射（等效上面）
data['gender'] = data['gender'].map({"男":1,"女":0})

二、方法apply的使用

（一）增加一列BMI指标

def BMI(series):
    weight = series['weight']
    height = series['height']/100
    BMI = weight/height**2
    return BMI

data['BMI'] = data.apply(BMI,axis=1)

（二）年龄整体减小3岁

def apply_age(x,bias):
    return x + bias
data['age'] = data['age'].apply(apply_age, args=(-3,))