Code:
import pandas as pd
import numpy as np
print("Generate sequence")
s = pd.Series([1, 3, 6, np.nan, 44, 1])
print(s)
dates = pd.date_range('20160101', periods=6)
print(dates)
operation result:
Generate sequence
0 1.0
1 3.0
2 6.0
3 NaN
4 44.0
5 1.0
dtype: float64
DatetimeIndex(['2016-01-01', '2016-01-02', '2016-01-03', '2016-01-04',
'2016-01-05', '2016-01-06'],
dtype='datetime64[ns]', freq='D')
Code:
# Law one
print("法一")
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=['a', 'b', 'c', 'd'])
print(df)
print("Method 2")
# Law two
df1 = pd.DataFrame(np.arange(12).reshape((3, 4)))
print(df1)
# Law three
print("Method three")
df2 = pd.DataFrame({'A': pd.Series([1,2,3,4]),
'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(df2)
operation result:
law one
a b c d
2016-01-01 0.754096 1.030924 1.122601 -0.945364
2016-01-02 0.678263 1.597405 -0.570131 1.778779
2016-01-03 -2.048156 -0.824976 1.497493 0.865702
2016-01-04 0.095282 0.790544 -0.623735 -0.560488
2016-01-05 -0.369227 -0.463738 -1.496183 -0.421661
2016-01-06 0.271562 -0.709889 0.012280 1.094913
Law II
0 1 2 3
0 0 1 2 3
1 4 5 6 7
2 8 9 10 11
Law three
A B C D E F
0 1 2013-01-02 1.0 3 test foo
1 2 2013-01-02 1.0 3 train foo
2 3 2013-01-02 1.0 3 test foo
3 4 2013-01-02 1.0 3 train foo
Code:
# Attributes
print(df2.dtypes)
# print the subscript order of all lines
print(df2.index)
# output column
print(df2.columns)
# output values
print("output values")
print(df2.values)
operation result:
A int64
B datetime64[ns]
C float32
D int32
E category
F object
dtype: object
RangeIndex(start=0, stop=4, step=1)
Index(['A', 'B', 'C', 'D', 'E', 'F'], dtype='object')
output values
[[1 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo']
[2 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']
[3 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo']
[4 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']]
Code:
# describe print(df2.describe()) # Transpose print(df2.T) # sort print(df2.sort_index(axis=1, ascending=False)) # Reverse by column print(df2.sort_index(axis=0, ascending=False)) # Reverse row by row # sort values print(df2.sort_values(by='E'))
operation result:
A C D
count 4.000000 4.0 4.0
mean 2.500000 1.0 3.0
std 1.290994 0.0 0.0
min 1.000000 1.0 3.0
25% 1.750000 1.0 3.0
50% 2.500000 1.0 3.0
75% 3.250000 1.0 3.0
max 4.000000 1.0 3.0
0 1 2 \
A 1 2 3
B 2013-01-02 00:00:00 2013-01-02 00:00:00 2013-01-02 00:00:00
C 1 1 1
D 3 3 3
E test train test
F foo foo foo
3
A 4
B 2013-01-02 00:00:00
C 1
D 3
E train
F foo
F E D C B A
0 foo test 3 1.0 2013-01-02 1
1 foo train 3 1.0 2013-01-02 2
2 foo test 3 1.0 2013-01-02 3
3 foo train 3 1.0 2013-01-02 4
A B C D E F
3 4 2013-01-02 1.0 3 train foo
2 3 2013-01-02 1.0 3 test foo
1 2 2013-01-02 1.0 3 train foo
0 1 2013-01-02 1.0 3 test foo
A B C D E F
0 1 2013-01-02 1.0 3 test foo
2 3 2013-01-02 1.0 3 test foo
1 2 2013-01-02 1.0 3 train foo
3 4 2013-01-02 1.0 3 train foo