Python Pandas 结构之 Series 和 DataFrame

1 概述

1.1 Pandas 安装

• 安装命令：pip install pandas

import pandas as pd

print(f'查看 pandas 版本：{pd.__version__}')

1.2 Series 和 DataFrame 结构

2 Series：一维数组

2.1 创建 Series 对象

# 语法格式
import pandas as pd

s = pd.Series(data, index, dtype)

2.1.1 创建

import pandas as pd

data = [10, 20, 30, 40, 50]

s = pd.Series(data)

print(s)
# 0    10
# 1    20
# 2    30
# 3    40
# 4    50
# dtype: int64

2.1.2 创建并指定标签索引

import pandas as pd

data = [10, 20, 30, 40, 50]
index = ['a', 'b', 'c', 'd', 'e']

s = pd.Series(data, index)

print(s)
# a    10
# b    20
# c    30
# d    40
# e    50
# dtype: int64

2.1.3 创建并指定数据类型

import pandas as pd

data = [10, 20, 30, 40, 50]

s = pd.Series(data, dtype=float)

print(s)
# 0    10.0
# 1    20.0
# 2    30.0
# 3    40.0
# 4    50.0
# dtype: float64

2.2 访问 Series 数据

2.2.1 按位置索引访问

import pandas as pd

data = [10, 20, 30, 40, 50]

s = pd.Series(data)

print(s[0])  # 通过索引
print(s[0:2])  # 通过索引切片
# 10
#
# 0    10
# 1    20
# dtype: int64

2.2.2 按标签索引访问

import pandas as pd

data = [10, 20, 30, 40, 50]
index = ['a', 'b', 'c', 'd', 'e']

s = pd.Series(data, index)

print(s['a'])  # 10

2.3 常用属性

2.3.1 index: 标签索引

import pandas as pd

data = [10, 20, 30, 40, 50]

s = pd.Series(data)

print(s.index)
# RangeIndex(start=0, stop=5, step=1)

2.3.2 values: 数据值

import pandas as pd

data = [10, 20, 30, 40, 50]

s = pd.Series(data)

print(s.values)
# [10 20 30 40 50]

2.3.3 dtype: 数据值类型

import pandas as pd

data = [10, 20, 30, 40, 50]

s = pd.Series(data)

print(s.dtype)  # int64

2.3.4 size: 对象的大小

import pandas as pd

data = [10, 20, 30, 40, 50]

s = pd.Series(data)

print(s.size)  # 5

2.3.5 empty: 判断对象是否为空

import pandas as pd

data = []

s = pd.Series(data)

print(s.empty)  # True

2.4 常用方法

2.4.1 head(): 查看前 n 行数据

import pandas as pd

data = [10, 20, 30, 40, 50]

s = pd.Series(data)

print(s.head(3))
# 0    10
# 1    20
# 2    30
# dtype: int64

2.4.2 tail(): 查看后 n 行数据

import pandas as pd

data = [10, 20, 30, 40, 50]

s = pd.Series(data)

print(s.tail(3))
# 2    30
# 3    40
# 4    50
# dtype: int64

2.4.3 isnull(): 检测是否缺失

import pandas as pd

data = [10, 20, 30, 40, 50, None]

s = pd.Series(data)

print(s.isnull())
# 0    False
# 1    False
# 2    False
# 3    False
# 4    False
# 5     True
# dtype: bool

2.4.4 notnull(): 检测是否不缺失

import pandas as pd

data = [10, 20, 30, 40, 50, None]

s = pd.Series(data)

print(s.notnull())
# 0    False
# 1    False
# 2    False
# 3    False
# 4    False
# 5     True
# dtype: bool

3 DataFrame：二维数组

3.1 创建 DataFrame 对象

# 语法格式
import pandas as pd

s = pd.DataFrame(data, index, columns, dtype)

3.1.1 创建

示例1：一维数组

import pandas as pd

data = [10, 20, 30, 40, 50]

df = pd.DataFrame(data)

print(df)

示例2：二维数组

import pandas as pd

data = [['张三', 10], ['李四', 20], ['王五', 30]]
columns = ['Name', 'Age']

df = pd.DataFrame(data, columns=columns)

print(df)
#     Name  Age
# 0   张三   10
# 1   李四   20
# 2   王五   30

3.1.2 创建并指定索引标签

import pandas as pd

data = [['张三', 10], ['李四', 20], ['王五', 30]]
index = ['a', 'b', 'c']
columns = ['Name', 'Age']

df = pd.DataFrame(data, index, columns)

print(df)
#     Name  Age
# a   张三   10
# b   李四   20
# c   王五   30

3.1.3 创建并指定数据类型

import pandas as pd

data = [['张三', 10], ['李四', 20], ['王五', 30]]
columns = ['Name', 'Age']

df = pd.DataFrame(data, columns=columns, dtype=str)

print(df)
#     Name  Age
# a   张三   10
# b   李四   20
# c   王五   30n

3.2 访问 DataFrame 数据

3.2.1 按行索引访问

import pandas as pd

data = [['张三', 10], ['李四', 20], ['王五', 30]]
columns = ['Name', 'Age']

df = pd.DataFrame(data, columns=columns)

print(df.loc[0])
# Name    张三
# Age     10
# Name: 0, dtype: object

3.2.2 按列索引访问

import pandas as pd

data = [['张三', 10], ['李四', 20], ['王五', 30]]
columns = ['Name', 'Age']

df = pd.DataFrame(data, columns=columns)

print(df['Name'])
# 0    张三
# 1    李四
# 2    王五
# Name: Name, dtype: object

3.3 常用属性和方法

常用属性和方法同 Series 类似，以下仅列举独属于 DataFrame

3.3.1 T：行列互换

• T：Transpose，转换

import pandas as pd

data = [['张三', 10], ['李四', 20], ['王五', 30]]
columns = ['Name', 'Age']

df = pd.DataFrame(data, columns=columns)

print(df.T)
#        0   1   2
# Name  张三  李四  王五
# Age   10  20  30