DAY8字典的简单介绍

字典的简单介绍

字典就是键值对

标签编码

实现映射操作

import pandas as pd
data = pd.read_csv('data.csv')
data
data["Home Ownership"].value_counts()
# 定义映射字典
mapping = {
        "Own Home": 1,
        "Rent": 0,
        "Have Mortgage": 2,
        "Home Mortgage": 3
    
}
data["Home Ownership"] = data["Home Ownership"].map(mapping)
data["Home Ownership"].head()

也可以一个函数实现两个映射

import pandas as pd

# 重新读取数据
data = pd.read_csv("data\data.csv")
# 嵌套映射字典
mapping = {
    "Term": {
        "Short Term": 1,
        "Long Term": 0
    },
    "Home Ownership": {
        "Rent": 0,
        "Own Home": 1,
        "Have Mortgage  ": 2,
        "Home Mortgage": 3
    }
}

连续变量的处理

归一化和标准化，直接sklearn中的归一化和标准化函数。

# 借助sklearn库进行归一化处理

from sklearn.preprocessing import StandardScaler, MinMaxScaler
data = pd.read_csv("data\data.csv")# 重新读取数据


# 归一化处理
min_max_scaler = MinMaxScaler() # 实例化 MinMaxScaler类，之前课上也说了如果采取这种导入函数的方式，不需要申明库名
data['Annual Income'] = min_max_scaler.fit_transform(data[['Annual Income']])

data['Annual Income'].head()

# 标准化处理
data = pd.read_csv("data\data.csv")# 重新读取数据
scaler = StandardScaler() # 实例化 StandardScaler，
data['Annual Income'] = scaler.fit_transform(data[['Annual Income']])
data['Annual Income'].head()

@浙大疏锦行