学习笔记 - pandas: 数据结构基本知识

Series

• 初识Series

# -*- coding: utf-8 -*-

import pandas as pd

"""
生成第一个Series(按照默认的index)
"""
s1 = pd.Series([1,2,3,4])
print(s1)

"""
自定义index
"""
s2 = pd.Series([1,2,3,4], index=['a','b','c','d'])
print(s2)

"""
Series的一些属性
"""
# 打印索引（标签）
print(s2.index)
# 打印值
print(s2.values)

0    1
1    2
2    3
3    4
dtype: int64
a    1
b    2
c    3
d    4
dtype: int64
Index(['a', 'b', 'c', 'd'], dtype='object')
[1 2 3 4]

• 操作Series

# -*- coding: utf-8 -*-

import pandas as pd

"""
增删查改
"""
s1 = pd.Series([1,2,3,4])
s2 = pd.Series([1,2,3,4], index=['a','b','c','d'])

# 查
"""
（1）通过标签访问
"""
# 访问某个元素
print(s2['a'])
# 访问多个元素(Series的切片)
print(s2['a':'d'])
# 访问多个元素（不连续）
print(s2[['a','c']])
"""
(2)通过索引访问
"""
print(s2[0])
# 访问多个的情况与上面类似

# 增
a = pd.Series([5],index=['e'])
s2 = s2.append(a)
print(s2)

b = pd.Series([5,6],index=['e1','e2'])
s2 = s2.append(b)
print(s2)

# 删除
s2 = s2.drop('e1')
print(s2)
"""
判断某个值是否在Series中
"""
print('a' != s2.values)

# 改
s2['e2'] = 22
print(s2)
"""
批量修改
"""
s2[['b','c']] = 333
s2[['a','d']] = [111,99]
print(s2)

# 创建Series(使用字典)
dic1 = {"Tom":12,"Alice":11,"Bob":22}
s3 = pd.Series(dic1)
print(s3)

# 重置索引
s2.index = range(0,len(s2))
print(s2)

DataFrame

• 初识dataFrame

# -*- coding: utf-8 -*-

import pandas as pd

df1 = pd.DataFrame({"age":[1,2,3,4,5],"name":['a','b','c','d','e']}, 
                    index=['s1','s2','s3','s4','s5'])
print(df1)

"""
Dataframe属性
"""
# 索引
print(df1.index)
# 列名
print(df1.columns)
# 值
print(df1.values)

    age name
s1    1    a
s2    2    b
s3    3    c
s4    4    d
s5    5    e
Index(['s1', 's2', 's3', 's4', 's5'], dtype='object')
Index(['age', 'name'], dtype='object')
[[1 'a']
 [2 'b']
 [3 'c']
 [4 'd']
 [5 'e']]

• 简单操作dataFrame

import pandas as pd

df1 = pd.DataFrame({"age":[1,2,3,4,5],"name":['a','b','c','d','e']}, 
                    index=['s1','s2','s3','s4','s5'])
"""
修改列名
"""
#df1.columns = range(0,len(df1.columns))
#print(df1)
"""
列名精准修改
"""
df1.rename(columns = {"age":"年龄","name":"姓名"}, inplace=True)
print(df1)

"""
修改行名
"""
df1.index = range(0,len(df1.index))

"""
增加一列
"""
# 在最后添加一列
df1["rank"] = [1,2,4,3,5]
print(df1)
# 在任意位置添加一列
df1.insert(0,'number',[101,102,103,104,105])
print(df1)