Pandas 常见操作(一)

Pandas 常见操作(一)

# 导入 pandas 和 numpy 两个常用数据处理包，并缩写。
import numpy as np
import pandas as pd

# 创建一个 Series 
s = pd.Series([1, 3, 6, np.nan, 44, 2]) # 默认给出索引
s

result:

0     1.0
1     3.0
2     6.0
3     NaN
4    44.0
5     2.0
dtype: float64

# 用 DataFrame创建表格，给出行索引和列索引
dates = pd.date_range('20200101', periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=['a', 'b', 'c','d'])

result

a	b	c	d
2020-01-01	-2.003205	-0.386903	-1.964165	1.819738
2020-01-02	-1.312786	-1.822615	1.488771	-1.288448
2020-01-03	-0.128299	-0.523143	0.076266	-0.262308
2020-01-04	0.012361	-0.094343	-0.070053	2.136403
2020-01-05	-1.320334	-0.157720	-0.183065	0.124426
2020-01-06	1.469395	0.506660	0.961168	0.390255

# 按照某一列索引,也会有它对应的行索引出来
df['b']
result
2020-01-01   -0.386903
2020-01-02   -1.822615
2020-01-03   -0.523143
2020-01-04   -0.094343
2020-01-05   -0.157720
2020-01-06    0.506660
Freq: D, Name: b, dtype: float64	

#若 DataFrame 不给定行列索引，那么就默认整数索引
df1 = pd.DataFrame(np.arange(12).reshape((3, 4)))

ruesult:

	0	1	2	3
0	0	1	2	3
1	4	5	6	7
2	8	9	10	11

# 还可以用字典的形式创建表格
df2 = pd.DataFrame({'A' : 1.,
                    'B' : pd.Timestamp('20130102'),
                    'C' : pd.Series(1,index=np.arange(4),dtype='float32'),
                    'D' : np.array([3] * 4,dtype='int32'),
                    'E' : pd.Categorical(["test","train","test","train"]),
                    'F' : 'foo'})

result:

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

# 查看表格的数据类型
df2.dtypes

result:

A           float64
B    datetime64[ns]
C           float32
D             int32
E          category
F            object
dtype: object

# 默认 index 为行索引
df2.index

result:

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

# 列索引
df2.columns

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

# 查看表格中所有的值，不要索引
df2.values

array([[1.0, Timestamp('2013-01-02 00:00:00'), 1.0, 3, 'test', 'foo'],
       [1.0, Timestamp('2013-01-02 00:00:00'), 1.0, 3, 'train', 'foo'],
       [1.0, Timestamp('2013-01-02 00:00:00'), 1.0, 3, 'test', 'foo'],
       [1.0, Timestamp('2013-01-02 00:00:00'), 1.0, 3, 'train', 'foo']],
      dtype=object)

# 查看表格的总体描述，包括个数，均值，标准差，最小值，最大值
# 如果是某个数据类型的属性则不需要括号，若是它的方法，则需要括号。
df2.describe()

reuslt:

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

# 将表格旋转 90 度，转置
df2.T
df2

reuslt:

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

# 将表格按照索引来降序排列, axis 确定是行还是列，0 为行，1 为列
# ascending = False 表示降序，True为升序
df2.sort_index(axis=1, ascending=False)

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

# 对表格数值排序
df2.sort_values(by='E')

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