python——pandas

pandas常用数据类型：

1. Series一维，带标签数组(标签即索引)

2. DataFrame二维，Series容器

import pandas as pd
import numpy as np
import string

# 数组形式创建
demo = pd.Series(np.arange(10),index=list(string.ascii_uppercase[:10]))
print(demo)


"""
A    0
B    1
C    2
D    3
E    4
F    5
G    6
H    7
I    8
J    9
dtype: int32
"""


#字典形式创建

dataDic = {"name":"goodDog", "age": 12, "sex": "1"}
demo2 = pd.Series(dataDic)
print(demo2)

"""
name    goodDog
age          12
sex           1
dtype: object
"""

# 修改数据类型
demo1 = demo.astype(float)
print(demo1.dtype)  # float64


# 标签索引
print(demo2["age"]) # 12
# 位置索引
print(demo2[1]) # 12
# bool索引
print(demo[demo>5])
"""
G    6
H    7
I    8
J    9
dtype: int32
"""

# 取出索引
demo.index
# 取出值
demo.values

# 切片
##连续
print(demo2[:2])
"""
name    goodDog
age          12
dtype: object
"""
##离散
print(demo2[[1,2]]) #/ print(demo2[["age", "sex"]])
"""
age    12
sex     1
dtype: object
"""

import pandas as pd
import numpy as np

#数组创建
demo = pd.DataFrame(np.arange(12).reshape(3,4))
print(demo)
"""
   0  1   2   3 # columns 列索引 axis = 1
0  0  1   2   3
1  4  5   6   7
2  8  9  10  11
#
index axis = 0
行
索
引
"""



demo1 = pd.DataFrame(np.arange(12).reshape(3,4),index=list("abc"),columns=list("WXYZ"))
print(demo1)
"""
   W  X   Y   Z
a  0  1   2   3
b  4  5   6   7
c  8  9  10  11
"""

# 字典创建
dataDic = {"name": ["xiaoming", "xiaohong"], "age": [18,18], "tel":[10086,10010]}
demo2 = pd.DataFrame(dataDic)
print(demo2)
"""
       name  age    tel
0  xiaoming   18  10086
1  xiaohong   18  10010
"""

dataDic1 = [{"name":"xiaoming",  "age": 18, "tel":10086}, {"name":"xiaohong",  "age": 18, "tel":10010}]
demo3 = pd.DataFrame(dataDic1)
print(demo3)
"""
       name  age    tel
0  xiaoming   18  10086
1  xiaohong   18  10010
"""

# 行索引
demo3.index
# 列索引
demo3.columns
#值
demo3.values

# 维度
print(demo3.ndim) # 2

#DataFrame整体查询

# 前几行，默认五行 head()
demo3.head(2) #前两行
# 末尾几行，默认五行tail()
demo3.tail(2) #后两行

#展示概况
print(demo3.info())
"""
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2 entries, 0 to 1
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype 
---  ------  --------------  ----- 
 0   name    2 non-null      object
 1   age     2 non-null      int64 
 2   tel     2 non-null      int64 
dtypes: int64(2), object(1)
memory usage: 176.0+ bytes
"""

# describe()对数字类型快速进行统计
print(demo3.describe())
"""
        age           tel
count   2.0      2.000000
mean   18.0  10048.000000
std     0.0     53.740115
min    18.0  10010.000000
25%    18.0  10029.000000
50%    18.0  10048.000000
75%    18.0  10067.000000
max    18.0  10086.000000
"""

pandas读取外部数据

import pandas as pd

filePath = r" "
#读取CSV文件
data = pd.read_csv(filePath)

#读取excel文件
data1 = pd.read_excel(filePath)

# 读取剪切板中的数据
data2 = pd.read_clipboard()

# 读取MYSQL中的数据
data3 = pd.read_sql()

pandas取行取列

1. df.loc通过标签索引行数据

2. df.iloc通过位置获取行数据

#取前20行
df[:20]
# 取列
df["name"]

#取行取列
df[:20]["name"]

import pandas as pd
import numpy as np
demo1 = pd.DataFrame(np.arange(12).reshape(3,4),index=list("abc"),columns=list("WXYZ"))
print(demo1)
"""
   W  X   Y   Z
a  0  1   2   3
b  4  5   6   7
c  8  9  10  11
"""
print(demo1.loc["a", "Z"]) # 3
print(demo1.loc["a"]) #/print(demo1.loc["a",:]) /demo1.iloc[1]
"""
W    0
X    1
Y    2
Z    3
"""
print(demo1.loc[:,"Y"]) /demo1.iloc[:,2]
"""
a     2
b     6
c    10
"""

# 取多行多列
# 不连续
print(demo1.loc[["a", "c"],["W", "Z"]]) /demo1.iloc[[0, 2], [0, 3]]
"""
     W   Z
a  0   3
c  8  11
"""

# 连续
print(demo1.loc["a":"c","W":"Y"])/demo1.iloc[0:2, 0:2]
"""
   W  X   Y
a  0  1   2
b  4  5   6
c  8  9  10
"""

# bool索引
# 大于3小于8
demo1[(demo1["W"] > 3)&(demo1["W"] < 8)]

pandas缺失数据的处理

一种是空，None等，在pandas是NaN；另外一种是0。

 

import pandas as pd
import numpy as np
demo1 = pd.DataFrame(np.arange(12).reshape(3,4),index=list("abc"),columns=list("WXYZ"))
print(demo1)
"""
   W  X   Y   Z
a  0  1   2   3
b  4  5   6   7
c  8  9  10  11
"""
# 是NaN
print(pd.isnull(demo1))
"""
       W      X      Y      Z
a  False  False  False  False
b  False  False  False  False
c  False  False  False  False
"""
# 不是NaN
print(pd.notnull(demo1))

#选取W列不为NaN的行
print(demo1[pd.notnull(demo1["W"])])
"""
   W  X   Y   Z
a  0  1   2   3
b  4  5   6   7
c  8  9  10  11
"""

print(pd.notnull(demo1["W"]))
"""
a    True
b    True
c    True
Name: W, dtype: bool
"""

填充数据：