数据分析处理库
import pandas as pd
df=pd.read_csv("./pandas/data/titanic.csv")
df.head(N) 读取数据的前N行
df.head(6)
df.info() 获取DataFrame的简要摘要
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 PassengerId 891 non-null int64
1 Survived 891 non-null int64
2 Pclass 891 non-null int64
3 Name 891 non-null object
4 Sex 891 non-null object
5 Age 714 non-null float64
6 SibSp 891 non-null int64
7 Parch 891 non-null int64
8 Ticket 891 non-null object
9 Fare 891 non-null float64
10 Cabin 204 non-null object
11 Embarked 889 non-null object
dtypes: float64(2), int64(5), object(5)
memory usage: 83.7+ KB
df.index 查看索引
df.index
RangeIndex(start=0, stop=891, step=1)
df.columns 查看所有列名
df.columns
Index(['PassengerId', 'Survived', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp',
'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked'],
dtype='object')
df.dtypes 查看每一列的字段类型
df.dtypes
PassengerId int64
Survived int64
Pclass int64
Name object
Sex object
Age float64
SibSp int64
Parch int64
Ticket object
Fare float64
Cabin object
Embarked object
dtype: object
df.values查看所有数据
df.values
array([[1, 0, 3, ..., 7.25, nan, 'S'],
[2, 1, 1, ..., 71.2833, 'C85', 'C'],
[3, 1, 3, ..., 7.925, nan, 'S'],
...,
[889, 0, 3, ..., 23.45, nan, 'S'],
[890, 1, 1, ..., 30.0, 'C148', 'C'],
[891, 0, 3, ..., 7.75, nan, 'Q']], dtype=object)
df['Name']
0 Braund, Mr. Owen Harris
1 Cumings, Mrs. John Bradley (Florence Briggs Th...
2 Heikkinen, Miss. Laina
3 Futrelle, Mrs. Jacques Heath (Lily May Peel)
4 Allen, Mr. William Henry
...
886 Montvila, Rev. Juozas
887 Graham, Miss. Margaret Edith
888 Johnston, Miss. Catherine Helen "Carrie"
889 Behr, Mr. Karl Howell
890 Dooley, Mr. Patrick
Name: Name, Length: 891, dtype: object
df=df.set_index('Name')
df
查询Age列的前8列数据
df['Age'][:8]
Name
Braund, Mr. Owen Harris 22.0
Cumings, Mrs. John Bradley (Florence Briggs Thayer) 38.0
Heikkinen, Miss. Laina 26.0
Futrelle, Mrs. Jacques Heath (Lily May Peel) 35.0
Allen, Mr. William Henry 35.0
Moran, Mr. James NaN
McCarthy, Mr. Timothy J 54.0
Palsson, Master. Gosta Leonard 2.0
Name: Age, dtype: float64
对单列数据的操作
age=df['Age']
age
Name
Braund, Mr. Owen Harris 22.0
Cumings, Mrs. John Bradley (Florence Briggs Thayer) 38.0
Heikkinen, Miss. Laina 26.0
Futrelle, Mrs. Jacques Heath (Lily May Peel) 35.0
Allen, Mr. William Henry 35.0
...
Montvila, Rev. Juozas 27.0
Graham, Miss. Margaret Edith 19.0
Johnston, Miss. Catherine Helen "Carrie" NaN
Behr, Mr. Karl Howell 26.0
Dooley, Mr. Patrick 32.0
Name: Age, Length: 891, dtype: float64
# 每一个Age统一加10
age=age+10
age
Name
Braund, Mr. Owen Harris 32.0
Cumings, Mrs. John Bradley (Florence Briggs Thayer) 48.0
Heikkinen, Miss. Laina 36.0
Futrelle, Mrs. Jacques Heath (Lily May Peel) 45.0
Allen, Mr. William Henry 45.0
...
Montvila, Rev. Juozas 37.0
Graham, Miss. Margaret Edith 29.0
Johnston, Miss. Catherine Helen "Carrie" NaN
Behr, Mr. Karl Howell 36.0
Dooley, Mr. Patrick 42.0
Name: Age, Length: 891, dtype: float64
# Age的最大值
age.max()
90.0
# Age的最小值
age.min()
10.42
# Age的平均值
age.mean()
39.69911764705882
describe得到数据的基本统计特征
df.describe()
只查询某集几列
df[['Age','Fare']][:5]
通过索引或者标签查询数据
# 通过索引查看某一行的数据
df.iloc[0]
# 查询前4行数据
df.iloc[0:5]
# 查询前4行前3列的数据
df.iloc[0:5,1:3]
# 通过索引列值读取某一行的数据
df.loc['Futrelle, Mrs. Jacques Heath (Lily May Peel)']
# 查询某行某列的某个值
df.loc['Futrelle, Mrs. Jacques Heath (Lily May Peel)','Age']
# 查询某几行的数某几列的数据
df.loc['Braund, Mr. Owen Harris':'Graham, Miss. Margaret Edith','Sex':'Age']
# 修改某个值
df.loc['Heikkinen, Miss. Laina','Age']=2000
bool运算
# 查询Age大于50的前5行数据
df[df['Age']>50][:5]
# 查询Sex为female的数据
df[df['Sex']=='female']
# 计算Sex为male,Age的平均值
df.loc[df['Sex']=='male','Age'].mean()
# 计算Age大于50的年龄和
(df['Age']>50).sum()
65
DataFrame groupby数据分组
dff=pd.DataFrame({'key':['A','B','C','A','B','C','A','B','C'],'value':[0,5,10,5,10,15,10,15,20]})
dff
按照key分组求和
dff.groupby('key').sum()
import numpy as np
dff.groupby('key').aggregate(np.mean)
# 按照Sex分组,计算Age的平均值
df.groupby('Sex')['Age'].mean()
Sex
female 35.478927
male 30.726645
Name: Age, dtype: float64
数值运算
df1=pd.DataFrame([[1,2,3,4],[3,4,5,6]],index=['a','b'],columns=['A','B','C','D'])
df1
# 每一列求值
df1.sum()
df1.sum(axis=0)
A 4
B 6
C 8
D 10
dtype: int64
# 每一行求和
df1.sum(axis=1)
a 10
b 18
dtype: int64
# 每一列求平均值
df1.mean(axis=0)
A 2.0
B 3.0
C 4.0
D 5.0
dtype: float64
# 每一行求平均值
df1.mean(axis=1)
a 2.5
b 4.5
dtype: float64
df
# 协方差
df.cov()
# 相关性
df.corr()
# 统计某一个每一个值出现的次数
df['Age'].value_counts()
24.00 30
22.00 27
18.00 26
28.00 25
19.00 25
..
53.00 1
55.50 1
70.50 1
23.50 1
0.42 1
Name: Age, Length: 89, dtype: int64
# 统计某一个每一个值出现的次数,次数由少到多排列
df['Age'].value_counts(ascending=True)
0.42 1
23.50 1
70.50 1
55.50 1
53.00 1
..
19.00 25
28.00 25
18.00 26
22.00 27
24.00 30
Name: Age, Length: 89, dtype: int64
对象操作(Series一行或者一列)
data=[1,2,3,4]
index=['a','b','c','d']
s=pd.Series(index=index,data=data)
# 查询第一行
s[0]
# 查询1到3行
s[1:3]
# 掩码操作 只显示a c行
mask=[True,False,True,False]
s[mask]
#修改某个值
s['a']=200
# 值替换将3替换为300
s.replace(to_replace=3,value=300,inplace=True)
# 修改列名
s.rename(index={'a':'A'},inplace=True)
# 添加数据
s1=pd.Series(index=['e','f'],data=[5,6])
s3=s.append(s1)
# 删除A行数据
del s3['A']
# 一次删除多行数据
s3.drop(['c','d'],inplace=True)
s3
b 2
e 5
f 6
dtype: int64
DataFrame的增删改查操作
# 构造一个DataFrame
data=[[1,2,3,4],[5,6,7,8]]
index=['a','b']
columns=['A','B','C','D']
dff=pd.DataFrame(data=data,index=index,columns=columns)
|
A |
B |
C |
D |
| a |
1 |
2 |
3 |
4 |
| b |
5 |
6 |
7 |
8 |
# 通过loc(‘索引值’)和iloc(索引数值)查询
dff1=dff.iloc[1]
dff1=dff.loc['a']
dff1
A 1
B 2
C 3
D 4
Name: a, dtype: int64
# 修改值
dff.loc['a']['A']=1000
dff
|
A |
B |
C |
D |
| a |
1000 |
2 |
3 |
4 |
| b |
5 |
6 |
7 |
8 |
# 修改索引
dff.index=['m','n']
dff
|
A |
B |
C |
D |
| m |
1000 |
2 |
3 |
4 |
| n |
5 |
6 |
7 |
8 |
# 添加一行数据
dff.loc['o']=[10,11,12,13]
dff
|
A |
B |
C |
D |
| m |
1000 |
2 |
3 |
4 |
| n |
5 |
6 |
7 |
8 |
| o |
10 |
11 |
12 |
13 |
# 添加一列数据
dff['E']=[5,9,14]
dff
|
A |
B |
C |
D |
E |
| m |
1000 |
2 |
3 |
4 |
5 |
| n |
5 |
6 |
7 |
8 |
9 |
| o |
10 |
11 |
12 |
13 |
14 |
# 批量添加多列数据
df4=pd.DataFrame([[6,10,15],[7,11,16],[8,12,17]],index=['m','n','o'],columns=['F','M','N'])
df5=pd.concat([dff,df4],axis=1)
df5
|
A |
B |
C |
D |
E |
F |
M |
N |
| m |
1000 |
2 |
3 |
4 |
5 |
6 |
10 |
15 |
| n |
5 |
6 |
7 |
8 |
9 |
7 |
11 |
16 |
| o |
10 |
11 |
12 |
13 |
14 |
8 |
12 |
17 |
# 删除一行数据
df5.drop(['o'],axis=0,inplace=True)
df5
|
A |
B |
C |
D |
E |
F |
M |
N |
| m |
1000 |
2 |
3 |
4 |
5 |
6 |
10 |
15 |
| n |
5 |
6 |
7 |
8 |
9 |
7 |
11 |
16 |
# 删除列
df5.drop(['E','F'],axis=1,inplace=True)
df5
|
A |
B |
C |
D |
M |
N |
| m |
1000 |
2 |
3 |
4 |
10 |
15 |
| n |
5 |
6 |
7 |
8 |
11 |
16 |
