一、Pandas —— 基本介绍

 

import  pandas as pd
import  numpy as np
print("************Series*************")
print("=========从Array 生成 Series===========")
#数据类型 dtype: float64，行 列名字默认 0-n 的数字
s = pd.Series([1, 3, 6, np.nan, 44, 1])
print(s)
#数据类型 dtype='datetime64[ns]'，生成从指定日期 20190101 开始的 6 的日期
# DatetimeIndex(['2019-01-01', '2019-01-02', '2019-01-03', '2019-01-04',
'2019-01-05', '2019-01-06'], dtype='datetime64[ns]', freq='D')
dates = pd.date_range('20190101',periods= 6)
print(dates)
print("************DataFrame*************")
print("==========从矩阵生成DataFrame=============")
#index 指定行名，columns指定列名，的dataframe
df = pd.DataFrame(np.random.randn(6, 4), index= dates, columns=['a', 'b', 'c', 'd'])
print(df)
#                    a         b         c         d
# 2019-01-01  1.909770  0.182445  1.301455  0.866027
# 2019-01-02  0.580548 -2.191395  0.668358 -0.866770
# 2019-01-03  1.937158 -0.715154 -0.476099  0.379382
# 2019-01-04 -0.402467  0.821941 -0.322327  0.583404
# 2019-01-05 -0.961753  1.265157  0.917990  0.454411
# 2019-01-06 -1.617632 -1.184158 -0.348426 -0.396559
print("==========从Map字典生成 DataFrame=============")
df1 = 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', 'trait', 'test', 'train']),
                    'F': 'foo'
                    })
print(df1)
#      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  trait  foo
# 2  1.0 2013-01-02  1.0  3   test  foo
# 3  1.0 2013-01-02  1.0  3  train  foo
print(df1.dtypes)
# A           float64
# B    datetime64[ns]
# C           float32
# D             int32
# E          category
# F            object
# dtype: object
print("=======打印行名、列名、值=========")
print(df1.index)#Int64Index([0, 1, 2, 3], dtype='int64')
print(df1.columns)#Index(['A', 'B', 'C', 'D', 'E', 'F'], dtype='object')
print(df1.values)
# [[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 'trait' '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']]
print("=============DataFrame 的基本描述==================")
print(df1.describe())#列数，均值，方差，最小值等等，会忽略非数字的值
#          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
print("==========DataFrame转置============")
print(df1.T)
print("==========DataFrame排序，按照列名、行名 、 值排序============")
#对
print(df1.sort_index(axis=1, ascending=False))# 1 表示列,False表示倒序，从大到小
#      F      E  D    C          B    A
# 0  foo   test  3  1.0 2013-01-02  1.0
# 1  foo  trait  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
#
print(df1.sort_values(by= 'E'))# by 指定列名
#      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
# 3  1.0 2013-01-02  1.0  3  train  foo
# 1  1.0 2013-01-02  1.0  3  trait  foo