Pandas 复习2

import pandas as pd
import numpy as np 
food_info = pd.read_csv('food_info.csv')
1.处理缺失值(可使用平均数，众数填充)
    查看非缺失值的数据：
        price_is_null = pd.isnull(food_info["Price"])
        price = food_info["Price"][price_is_null==False]
    使用 fillna 填充
        food_info['Price'].fillna(food_info['Price'].mean(),inplace = True)
2.求平均值
    food_info["Price"].mean()
3.查看每一个 index 级,values 的平均值
    food_info.pivot(index = "",values = "",aggfunc = np.mean)
4.查看总人数
    food_info.pivot(index = "",values = ["",""],aggfunc = np.sum)
5.丢弃缺失值
    dropna_columns = food_info.dropna(axis = 1)
    将 Price 和 Time 列存在 NaN 的行去掉
        new_food_info = food_info.dropna(axis = 0,subset = ["Price","Time"])
6.定位具体值到 83 
    row_index_83_price = food_info.loc[83,"Price"]
7.进行排序(sort_values 默认升序)
    new_food_info.sort_values("Price")
8.将索引值重新排序，使用 reset_index
    new_food_info.reset_index(drop = True)
9.使用 apply 函数
    new_food_info.apply(函数名)
10.查看缺失值的个数
    def not_null_count(column):
        column_null = pd.isnull(column)
        # column_null 为空的布尔类型
        null = column[column_null]
        # 将为空值的列表传递给 null 
        return len(null)
    column_null_count = food_info.apply(not_null_count)
11.划分等级：年龄 成绩
    def which_class(row):
        pclass = row["Pclass"]
        if pd.isnull(pclass):
            return "未知等级"
        elif pclass == 1:
            return "第一级"
        elif pclass == 2:
            return "第二级"
        elif pclass == 3:
            return "第三级"
    new_food_info.apply(which_class,axis = 1)
12.使用 pivot_table 展示透视表
    new_food_info.pivot_table(index = " ",values=" ")

---

2020-04-11