1.导入包
2.创建向量
3.创建DataFrame
- DataFrame创建矩阵用法一
- DataFrame创建矩阵用法二
4.查看数据
5.选择数据
6.改变DataFrame数据

新手必备，10分钟学pandas

1.导入包

导入包

import numpy as np
import pandas as pd

2.创建向量

使用Series函数让pandas创建默认的整数索引

import numpy as np 
import pandas as pd 
s = pd.Series([1, 3, 5, np.nan, 6, 8])
print(s)

0 1.0 1 3.0 2 5.0 3 NaN 4 6.0 5 8.0 dtype: float64

import numpy as np 
import pandas as pd 
s = pd.Series([1, 3, 5, np.nan, 6, 8])
print(s[0], s[2])

1.0 5.0

3.创建DataFrame

通过Numpy array创建一个有日期和标记的列的数据框架

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)        %使用data_range创建连续的向量
print(dates)

DatetimeIndex([‘2013-01-01’, ‘2013-01-02’, ‘2013-01-03’, ‘2013-01-04’, ‘2013-01-05’, ‘2013-01-06’], dtype=’datetime64[ns]’, freq=’D’)

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
print(dates[2])

2013-01-03 00:00:00

DataFrame创建矩阵用法一

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
%使用DataFrame创建矩阵，columns(矩阵的行标头),index(矩阵的列标头)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))        
print(df)

                       A              B             C               D
2013-01-01 0.652211 0.351307 -0.047034 0.233530 2013-01-02 -0.997980 0.292630 -1.312628 0.222933 2013-01-03 -0.733029 0.878319 0.789346 0.547204 2013-01-04 -2.428614 -1.820740 -0.884209 0.454380 2013-01-05 0.500799 0.293417 0.384024 1.294105 2013-01-06 0.257280 -0.692720 0.376611 -1.718606

DataFrame创建矩阵用法二

import numpy as np 
import pandas as pd 
# dates = pd.date_range('20130101', periods=6)
# df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
#使用字典创建DataFrame
df = pd.DataFrame({
    'A': 1,
    'B': pd.Timestamp('20130102'),
    'C': pd.Series(1, index=list(range(4)), dtype='float32'),
    'D': np.array([3]*4, dtype='int32'),
    'E': pd.Categorical(['test', 'train', 'test', 'train']),
    'F': 'foo'
    })
print(df)

A         B           C   D     E    F
0 1 2013-01-02 1.0 3 test foo 1 1 2013-01-02 1.0 3 train foo 2 1 2013-01-02 1.0 3 test foo 3 1 2013-01-02 1.0 3 train foo

从结果可以看出，DataFrame的行标头默认为数字，我们用字典赋值的是列标头
查看这个df的每列的数据类型

A int64 B datetime64[ns] C float32

D int32

E category

F object

dtype: object

4.查看数据

df.head()

import numpy as np 
import pandas as pd 
# dates = pd.date_range('20130101', periods=6)
# df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
df = pd.DataFrame({
    'A': 1,
    'B': pd.Timestamp('20130102'),
    'C': pd.Series(1, index=list(range(4)), dtype='float32'),
    'D': np.array([3]*4, dtype='int32'),
    'E': pd.Categorical(['test', 'train', 'test', 'train']),
    'F': 'foo'
    })
print(df.head())        %查看所有数据

A          B           C  D      E    F
0 1 2013-01-02 1.0 3 test foo

1 1 2013-01-02 1.0 3 train foo

2 1 2013-01-02 1.0 3 test foo

3 1 2013-01-02 1.0 3 train foo

df.tail()

print(df.tail(2))        %查看最后的两行数据

A          B           C  D      E    F
2 1 2013-01-02 1.0 3 test foo

3 1 2013-01-02 1.0 3 train foo

df.index

print(df.index)        %查看DataFrame的行标头

Int64Index([0, 1, 2, 3], dtype=’int64’)

df.columns

print(df.columns)        %查看DataFrame的列标头

Index([‘A’, ‘B’, ‘C’, ‘D’, ‘E’, ‘F’], dtype=’object’)

df.to_numpy()

注意：使用df.to_numpy()将DataFrame转换为Numpy是需要很高的代价的。这是因为：Numpy arrays对于整个矩阵而言只会有一个数据类型，而DataFrame每列都可为不同的数据类型。这就很可能导致，Numpy arrys中的数据最终只有一个父类： object类型。

import numpy as np 
import pandas as pd 
# dates = pd.date_range('20130101', periods=6)
# df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
df = pd.DataFrame({
    'A': 1,
    'B': pd.Timestamp('20130102'),
    'C': pd.Series(1, index=list(range(4)), dtype='float32'),
    'D': np.array([3]*4, dtype='int32'),
    'E': pd.Categorical(['test', 'train', 'test', 'train']),
    'F': 'foo'
    })
nf = df.to_numpy()        %转换为numpy类型的时候没有行表头和列表头
print(nf)

[[1 Timestamp(‘2013-01-02 00:00:00’) 1.0 3 ‘test’ ‘foo’]

[1 Timestamp(‘2013-01-02 00:00:00’) 1.0 3 ‘train’ ‘foo’]

[1 Timestamp(‘2013-01-02 00:00:00’) 1.0 3 ‘test’ ‘foo’]

[1 Timestamp(‘2013-01-02 00:00:00’) 1.0 3 ‘train’ ‘foo’]]

descirbe()

describe() ：展示了数据的统计结果

import numpy as np 
import pandas as pd 
# dates = pd.date_range('20130101', periods=6)
# df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
df = pd.DataFrame({
    'A': 1,
    'B': pd.Timestamp('20130102'),
    'C': pd.Series(1, index=list(range(4)), dtype='float32'),
    'D': np.array([3]*4, dtype='int32'),
    'E': pd.Categorical(['test', 'train', 'test', 'train']),
    'F': 'foo'
    })
print(df.describe())

          A    C    D
count 4.0 4.0 4.0

mean 1.0 1.0 3.0

std 0.0 0.0 0.0

min 1.0 1.0 3.0

25% 1.0 1.0 3.0

50% 1.0 1.0 3.0

75% 1.0 1.0 3.0

max 1.0 1.0 3.0

df.T

df.T：DataFrame转置

import numpy as np 
import pandas as pd 
# dates = pd.date_range('20130101', periods=6)
# df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
df = pd.DataFrame({
    'A': 1,
    'B': pd.Timestamp('20130102'),
    'C': pd.Series(1, index=list(range(4)), dtype='float32'),
    'D': np.array([3]*4, dtype='int32'),
    'E': pd.Categorical(['test', 'train', 'test', 'train']),
    'F': 'foo'
    })
print(df.T)

                               0  ...                                    3
A 1 … 1

B 2013-01-02 00:00:00 … 2013-01-02 00:00:00

C 1 … 1

D 3 … 3

E test … train

F foo … foo

[6 rows x 4 columns]

sort_index()

import numpy as np 
import pandas as pd 
# dates = pd.date_range('20130101', periods=6)
# df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
df = pd.DataFrame({
    'A': 1,
    'B': pd.Timestamp('20130102'),
    'C': pd.Series(1, index=list(range(4)), dtype='float32'),
    'D': np.array([3]*4, dtype='int32'),
    'E': pd.Categorical(['test', 'train', 'test', 'train']),
    'F': 'foo'
    })
print(df)
print(df.sort_index(axis=1, ascending=False))

sort_values()

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
df = pd.DataFrame({
    'A': 1,
    'B': pd.Timestamp('20130102'),
    'C': pd.Series(1, index=list(range(4)), dtype='float32'),
    'D': np.array(np.random.rand(4), dtype='float32'),
    'E': pd.Categorical(['test', 'train', 'test', 'train']),
    'F': 'foo'
    })
print(df)
print(df.sort_values(by='D'))

5.选择数据

列


import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
df = pd.DataFrame({
    'A': 1,
    'B': pd.Timestamp('20130102'),
    'C': pd.Series(1, index=list(range(4)), dtype='float32'),
    'D': np.array(np.random.rand(4), dtype='float32'),
    'E': pd.Categorical(['test', 'train', 'test', 'train']),
    'F': 'foo'
    })
print(df)
print(df['A'])

行

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
df = pd.DataFrame({
    'A': 1,
    'B': pd.Timestamp('20130102'),
    'C': pd.Series(1, index=list(range(4)), dtype='float32'),
    'D': np.array(np.random.rand(4), dtype='float32'),
    'E': pd.Categorical(['test', 'train', 'test', 'train']),
    'F': 'foo'
    })
print(df)
print(df[0: 2])

loc函数

不带标头的第一行

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
# df = pd.DataFrame({
#     'A': 1,
#     'B': pd.Timestamp('20130102'),
#     'C': pd.Series(1, index=list(range(4)), dtype='float32'),
#     'D': np.array(np.random.rand(4), dtype='float32'),
#     'E': pd.Categorical(['test', 'train', 'test', 'train']),
#     'F': 'foo'
#     })
print(df)
print(df.loc[dates[0]])

特定列数据

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
print(df)
print(df.loc[:, ['A', 'B']])

iloc函数

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
print(df)
print(df.iloc[3])

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
print(df)
print(df.iloc[2: 4, 0: 2])

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
print(df)
print(df.iloc[[2, 4], [0, 2]])

iat函数

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
print(df)
print(df.iat[1, 1])

逻辑判断，找到符合条件的数据

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
print(df)
print(df[df['A'] > 0])

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
print(df)
print(df > 0)
print(df[df > 0])

isin函数

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
df2 = df.copy()
df2['E'] = ['one', 'one', 'two', 'three', 'four', 'three']
print(df2)
print(df[df2['E'].isin(['two', 'three'])])

6.改变DataFrame数据

import numpy as np 
import pandas as pd 
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))
s1 = pd.Series(np.arange(6)+1, index=pd.date_range('20130102', periods=6))
print(df)
df['F'] = s1
df.at[dates[0], 'A'] = 0
df.iat[0, 1] = 0
df.loc[:, 'D'] = np.array([5] * len(df))
print(df)

深度学习

§ 10分钟学pandas