Pandas的基础操作（一）——矩阵表的创建及其属性

---

Pandas的基础操作（一）——矩阵表的创建及其属性

（注：记得在文件开头导入import numpy as np以及import pandas as pd）

---

 import pandas as pd
 import numpy as np

 #创建一个Pandas序列

 s = pd.Series([1, 3, 6, np.nan, 44, 1])
 # print(s)
 # 0     1.0
 # 1     3.0
 # 2     6.0
 # 3     NaN
 # 4    44.0
 # 5     1.0
 # dtype: float64

 #创建一个矩阵式的DataFrame
 dates = pd.date_range('', periods=6)
 # print(dates)
 # DatetimeIndex(['2019-07-10', '2019-07-11', '2019-07-12', '2019-07-13',
 #                '2019-07-14', '2019-07-15'],
 #               dtype='datetime64[ns]', freq='D')

 #行的标签是 dates ；列的标签是：columns
 df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=['a', 'b', 'c', 'd'])
 # print(df)
 #                    a         b         c         d
 # 2019-07-10 -0.953463 -2.588401  1.680335  0.258889
 # 2019-07-11 -2.183960 -1.559565 -0.119690  2.474845
 # 2019-07-12  0.246754  0.237245  0.555891 -2.291064
 # 2019-07-13  1.365473 -0.520804  2.351753 -0.650416
 # 2019-07-14  0.160255 -0.665578 -1.330720 -0.502632
 # 2019-07-15  1.427740 -0.386175 -0.102600  0.280338

 #采用默认的行列标签方式，行和列的标签号都是从0开始
 df1 = pd.DataFrame(np.arange(12).reshape((3,4)))
 # print(df1)
 #    0  1   2   3
 # 0  0  1   2   3
 # 1  4  5   6   7
 # 2  8  9  10  11

 #利用字典创建pandas矩阵表
 df2 = pd.DataFrame({
     'A':1.,
     'B':pd.Timestamp(''),
     '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)
 #      A          B    C  D      E    F
 # 0  1.0 2019-07-10  1.0  3   test  foo
 # 1  1.0 2019-07-10  1.0  3  train  foo
 # 2  1.0 2019-07-10  1.0  3   test  foo
 # 3  1.0 2019-07-10  1.0  3  train  foo
 #

 #常用属性介绍(PS:因为是属性所以不用添加括号)

 #1 df.dtypes 查看每一列的数据类型
 print(df2.dtypes)
 # A           float64
 # B    datetime64[ns]
 # C           float32
 # D             int32
 # E          category
 # F            object
 # dtype: object

 #2 df.index 查看矩阵表所有每一行的标签号
 print(df2.index)
 # Int64Index([0, 1, 2, 3], dtype='int64')

 #3 df.columns 查看矩阵表所有每一列的标签号
 print(df2.columns)
 # Index(['A', 'B', 'C', 'D', 'E', 'F'], dtype='object')

 #4 df.values 查看矩阵表中所有的值
 print(df2.values)
 # [[1.0 Timestamp('2019-07-10 00:00:00') 1.0 3 'test' 'foo']
 #  [1.0 Timestamp('2019-07-10 00:00:00') 1.0 3 'train' 'foo']
 #  [1.0 Timestamp('2019-07-10 00:00:00') 1.0 3 'test' 'foo']
 #  [1.0 Timestamp('2019-07-10 00:00:00') 1.0 3 'train' 'foo']]

 #5 df.describe() 描述矩阵表中float int 数据类型的均值、方差等参数
 print(df2.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

 #6 df.T 将矩阵表转置
 print(df2.T)
 # A                    1  ...                    1
 # B  2019-07-10 00:00:00  ...  2019-07-10 00:00:00
 # C                    1  ...                    1
 # D                    3  ...                    3
 # E                 test  ...                train
 # F                  foo  ...                  foo

 #7 df.sort_index() 对矩阵表进行排序

 #按照索引标签进行排序，axis=1 --> 行位置不变，列位置变化，ascending=False，进行反排序
 print(df2.sort_index(axis=1, ascending=False))
 #      F      E  D    C          B    A
 # 0  foo   test  3  1.0 2019-07-10  1.0
 # 1  foo  train  3  1.0 2019-07-10  1.0
 # 2  foo   test  3  1.0 2019-07-10  1.0
 # 3  foo  train  3  1.0 2019-07-10  1.0

 #按照索引标签进行排序，axis=0 --> 行位置变化，列位置不变，ascending=False，进行反排序
 print(df2.sort_index(axis=0, ascending=False))
 #      A          B    C  D      E    F
 # 3  1.0 2019-07-10  1.0  3  train  foo
 # 2  1.0 2019-07-10  1.0  3   test  foo
 # 1  1.0 2019-07-10  1.0  3  train  foo
 # 0  1.0 2019-07-10  1.0  3   test  foo

 #8 df.sort_values() 根据矩阵表中的值进行排序
 print(df2.sort_values(by='E'))      #对第"E"列的值进行排序
 #      A          B    C  D      E    F
 # 0  1.0 2019-07-10  1.0  3   test  foo
 # 2  1.0 2019-07-10  1.0  3   test  foo
 # 1  1.0 2019-07-10  1.0  3  train  foo
 # 3  1.0 2019-07-10  1.0  3  train  foo

---