详解Pandas的三大利器(map,apply,applymap)

import pandas as pd
import numpy as np

boolean = [True, False]
gender = ["男","女"]
color = ["white","black","red"]

# 好好学习如何生成模拟数据：非常棒的例子
# 学会使用random模块中的randint方法

df = pd.DataFrame({"height":np.random.randint(160,190,100),
                     "weight":np.random.randint(60,90,100),
                     "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(20,60,100),
                     "color":[color[x] for x in np.random.randint(0,len(color),100)]
                    })
df.head()

map(function, iterable)

# 方式1：通过字典映射实现
dic = {"男":1, "女":0}  # 通过字典映射
df1 = df.copy()   # 副本，不破坏原来的数据df
df1["gender"] = df1["gender"].map(dic)
df1

# 方式2：通过函数实现
def map_gender(x):
    gender = 1 if x == "男" else 0
    return gender

df2 = df.copy()
# 将df["gender"]这个S型数据中的每个数值传进去
df2["gender"] = df2["gender"].map(map_gender)
df2

def apply_age(x,bias):
    return x + bias

df4 = df.copy()
# df4["age"]当做第一个值传给apply_age函数，args是第二个参数
df4["age"] = df4["age"].apply(apply_age,args=(-3,))

# 实现计算BMI指数：体重/身高的平方(kg/m^2)
def BMI(x):
    weight = x["weight"]
    height = x["height"] / 100
    BMI = weight / (height **2)

    return BMI

df5 = df.copy()
df5["BMI"] = df5.apply(BMI,axis=1)  # df5现在就相当于BMI函数中的参数x；axis=1表示在列上操作
df5