pandas 2

2020年3月2日

2.3.10 pandas 1

import numpy as np
import pandas as pd
%matplotlib inline

pd.__version__

'1.0.1'

2.3.1 Object creation

s = pd.Series([1, 3, 5, np.nan, 6, 8])

s

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

dates = pd.date_range('20130101', periods=6)

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')

 df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list('ABCD'))

df

df2 = pd.DataFrame({'A':1.0,'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'})

df2

df2.dtypes

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

df2.A

0    1.0
1    1.0
2    1.0
3    1.0
Name: A, dtype: float64

df2.bool

<bound method NDFrame.bool of      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>

2.3.2 Viewing data

df.head()

df.tail(3)

df.index

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

df.columns

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

df.to_numpy()

array([[ 0.10944515,  0.75507818, -0.39212779,  0.68661786],
       [ 0.8199961 ,  1.13307764,  1.24042756, -0.59855844],
       [-0.51722489,  1.06057526,  1.95910122,  0.62497238],
       [-0.63022037, -0.68633565,  0.39642911, -2.25482556],
       [ 1.6858012 , -1.21305901,  1.21406631,  0.4222287 ],
       [ 0.41159282,  0.67259021,  0.69013212,  0.28446607]])

df3 = df.to_numpy()

df3

array([[ 0.10944515,  0.75507818, -0.39212779,  0.68661786],
       [ 0.8199961 ,  1.13307764,  1.24042756, -0.59855844],
       [-0.51722489,  1.06057526,  1.95910122,  0.62497238],
       [-0.63022037, -0.68633565,  0.39642911, -2.25482556],
       [ 1.6858012 , -1.21305901,  1.21406631,  0.4222287 ],
       [ 0.41159282,  0.67259021,  0.69013212,  0.28446607]])

df3.dtype

dtype('float64')

df22 = df2.to_numpy()

df22.dtype

dtype('O')

df22

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)

df.describe()

df.T

Follow me!