非理工科编程零基础文科生秒懂python学习笔记：pandas库dataframe核心基础数据选取loc与iloc

 

#本数据纯属虚构，如有雷同实属巧合

本次拜读的是:

 

目录

创建

读取

 使用loc索引读取dataframe：

使用iloc读取数据表格dataframe

---

""" dataframe是python数据分析基础中的核心， 这位按字面意义可理解为数据表格、数据框架， 她跟excel的table很相似， 由三部分组成： 行索引，称为index； 列索引，称为column； 数据内容。 她的每一列都是一个series对象。 """

创建

使用字典创建dataframe，并设置索引号

import pandas as pd #导入pandas库，缩写为pd
print("\n使用字典创建dataframe，并设置索引号：")
characters01 = pd.DataFrame({
        "name" : ["zhongli","yanfei", "jiangjun","tuoma","xinhai","chongyun","xingqiu","anbo","xiangling"],
        "age" : [17,18,19,21,29,15,19,14,17],
        "score" : [98780,36895,54100,20523,36895,54100,20523,36895,54100]
}, index = [1,2,3,4,"num5","第6",7,8,9])
print(characters01)

 

索引index的结果对应第一列，如果不设置index的参数，默认使用整数类型

print("\n\n索引index的结果对应第一列，如果不设置index的参数，默认使用整数类型：")
characters02 = pd.DataFrame({
        "name" : ["zhongli","yanfei", "jiangjun","tuoma","xinhai","chongyun","xingqiu","anbo","xiangling"],
        "age" : [17,18,19,21,29,15,19,14,17],
        "score" : [98780,36895,54100,20523,36895,54100,20523,36895,54100]
})
print(characters02)

 

可以使用columns参数定义列名

print("\n\n可以使用columns参数定义列名：")
characters03 = pd.DataFrame({
        "name" : ["zhongli","yanfei", "jiangjun","tuoma","xinhai","chongyun","xingqiu","anbo","xiangling"],
        "age" : [17,18,19,21,29,15,19,14,17],
        "score" : [98780,36895,54100,20523,36895,54100,20523,36895,54100]
}, index = [1,2,3,4,"num5","第6",7,8,9], columns=["score", "name", "age", "newcol"])
print(characters03)

 

如果某一字段没有数据会自动变成NaN

print("\n\n如果某一字段没有数据会自动变成NaN：")
gdp = pd.DataFrame({
    '2018': {'GDP': "1%", '人口': 3},
    '2019': {'GDP': "3%", '人口': 2},
    '2020': {'GDP': "2%", '人口': 1},
    '2021': {'人口': 1},
    '2022': {'GDP': "4%"}
})
print(gdp)

 

实现多层嵌套索引

print("\n\n实现多层嵌套索引：")
values = [
    [10, "A"], [11, "B"],  [13, "C"], [10, "D"],  [12, "E"], [12, "F"],
]
salesData = pd.DataFrame(values, columns=["销量", "型号"], index=[
    ["一月", "一月", "二月", "二月", "三月", "三月"],
    ["huawei", "apple", "huawei", "apple", "huawei", "apple"],
])
print(salesData)

 

通过元组直接实现MultiIndex多层嵌套索引

print("\n\n通过元组直接实现MultiIndex多层嵌套索引：")
index = pd.MultiIndex.from_tuples([('f', 1), ('f', 2), ('w', 2)], names=['e', 'c'])
df01 = pd.DataFrame({
    "a01": [400, 500, 600],
    "b02": [702, 805, 903],
    "c03": [101, 110, 120]
}, index=index)
print(df01)

 读取

使用索引读取dataframe

 

print("\n\n使用索引读取dataframe：")
characters04 = pd.DataFrame({
        "name" : ["zhongli","yanfei", "jiangjun","tuoma","xinhai","chongyun","xingqiu","anbo","xiangling"],
        "age" : [17,18,19,21,29,15,19,14,17],
        "score" : [98780,36895,54100,20523,36895,54100,20523,36895,54100]
}, index = [1,2,3,4,5,6,7,8,9])
print("\n\n读取name列：\n", characters04['name'])
print("\n\n读取name和age列：\n", characters04[['name', 'age']])
print("\n\n读取前两行的所有内容：\n", characters04[:2])
print("\n\n使用loc索引读取dataframe：")
print("\n\n使用loc索引第一行所有内容\n", characters04.loc[1])
print("\n\n使用loc索引同行多列内容\n", characters04.loc[1, ['name',  "age"]])
print("\n\n使用loc索引多行同列内容\n", characters04.loc[[1, 3], "name"])
print("\n\n使用loc索引多行多列内容\n", characters04.loc[1:2])
print("\n\n使用lambda表达式，获取索引号是偶数的行\n", characters04.loc[lambda x: x.index % 2 == 0])
print("\n\n获取年龄大于18的对应值\n", characters04.loc[lambda x: x['age'] > 18 ])
print("\n\n逗号前写筛选条件，逗号后显示对应值\n", characters04.loc[characters04['age'] > 17, 'name'])
print("\n\n逗号前写筛选条件，逗号后获取对应值的相关字段信息：\n", characters04.loc[characters04['age'] > 17, ['name', 'score']])

 

 

 使用loc索引读取dataframe：

 

 

 

 

使用loc读取多层索引dataframe

print("\n\n使用loc读取多成索引dataframe：")
salesData = pd.DataFrame([
    [10, "A"], [11, "B"],  [13, "C"], [10, "D"],  [12, "E"], [12, "F"],
], columns=["销量", "型号"], index=[
    ["六月", "六月", "七月", "七月", "八月", "八月"],
    ["huawei", "apple", "huawei", "apple", "huawei", "apple"],
])
print("\n\n输出整个表：\n",salesData)
print("\n\n输出六月相关：\n",salesData.loc['六月'])
print("\n\n输出六月huawei相关：\n",salesData.loc['六月', 'huawei'])

 

 

 

使用iloc读取数据表格dataframe

print("\n\n使用iloc读取数据表格dataframe：")
df001 = pd.DataFrame( [[39,35940,8,703], [51,45468,4,815], [84, 83694, 4, 894], [57, 46540, 2, 973], [19, 20316, 3, 436], [46, 53104, 6, 735]] ,
   index=list(range(0, 12, 2)), #定义显示行索引起始为0，结束为12，步长为2
   columns=list(range(0, 8, 2)))#定义显示列索引起始为0，结束为8，步长为2
print("\n\n输出整个表：\n",df001)
print("\n\n输出第二行，默认索引为1，显示索引为2：\n",df001.iloc[1])
print("\n\n使用切片运算输出前三行：\n",df001.iloc[:3])
print("\n\n使用切片超出范围也不会报错：\n",df001.iloc[3:100])
# print("\n\n但如果读取某个不存在的索引会报错：\n",df001.iloc[4, 8, 9])
print("\n\n选择第二行第二列的一个数据：\n",df001.iloc[1, 1])
print("\n\n连续选择第二到五行的第三到第四列的数据：\n",df001.iloc[1:5, 2:4])
print("\n\n跳选第二、四、六行的第二、四列的数据：\n",df001.iloc[[1, 3, 5], [1, 3]])
print("\n\n使用冒号表示获取一整行：\n",df001.iloc[1:3, :])
print("\n\n使用冒号表示获取一整列：\n",df001.iloc[:, 1:3])

 

 

 

 

 

使用iterrows遍历读取每一行

print("\n\n使用iterrows遍历读取每一行：")
characters05 = pd.DataFrame({
        "name" : ["zhongli","yanfei", "jiangjun","tuoma","xinhai","chongyun","xingqiu","anbo","xiangling"],
        "age" : [17,18,19,21,29,15,19,14,17],
        "score" : [98780,36895,54100,20523,36895,54100,20523,36895,54100]
}, index = [1,2,3,4,5,6,7,8,9])
for index, row in characters05.iterrows():
    print("索引index: {0}".format(index))
    print("角色{0}, 年龄{1}, 分数{2}".format(row['name'], row['age'], row['score']))

 

使用items遍历读取每一列

print("\n\n使用items遍历读取每一列：")
characters06 = pd.DataFrame({
        "name" : ["zhongli","yanfei", "jiangjun","tuoma","xinhai","chongyun","xingqiu","anbo","xiangling"],
        "age" : [17,18,19,21,29,15,19,14,17],
        "score" : [98780,36895,54100,20523,36895,54100,20523,36895,54100]
}, index = [1,2,3,4,5,6,7,8,9])
for label, item in characters06.items():
    print(label)
    print(item)