0-2 pandas 复习

2022-01-12 23:30:56 阅读：144 来源： 互联网

标签：02 01 1.0 复习 df pandas print 2010

1-1 初识pandas

创建序列

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
"""

创建日期型数据，并增长六个日期

date = pd.date_range('2016-01-01', periods = 6)
print(date)
"""
DatetimeIndex(['2016-01-01', '2016-01-02', '2016-01-03', '2016-01-04',
               '2016-01-05', '2016-01-06'],
              dtype='datetime64[ns]', freq='D')
"""

创建有索引和字符串的数据

df = pd.DataFrame(np.random.rand(6,4), index=date, columns=['a', 'b', 'c', 'd'])
print(df)
"""
                   a         b         c         d
2016-01-01  0.113951  0.583000  0.167336  0.917897
2016-01-02  0.632843  0.950597  0.280311  0.946806
2016-01-03  0.367501  0.313236  0.475095  0.889570
2016-01-04  0.653676  0.444720  0.091550  0.272699
2016-01-05  0.448919  0.328602  0.644945  0.196358
2016-01-06  0.656723  0.355628  0.886951  0.688788
"""

不加索引的矩阵

df1 = pd.DataFrame(np.arange(12).reshape((3,4)))
print(df1)

# 创建决定各个数值的矩阵 categorical 明确的，确定的
df2 = pd.DataFrame({'A':1,
                    'B':pd.Timestamp('20120202'),
                    '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 2012-02-02  1.0  3   test  foo
1  1 2012-02-02  1.0  3  train  foo
2  1 2012-02-02  1.0  3   test  foo
3  1 2012-02-02  1.0  3  train  foo
"""
# df2 的dtype
print(df2.dtypes)
"""
A             int64
B    datetime64[ns]
C           float32
D             int32
E          category
F            object
dtype: object
"""
# 列标
print(df2.columns)
"Index(['A', 'B', 'C', 'D', 'E', 'F'], dtype='object')"
# 值
print(df2.values)
"""
[[1 Timestamp('2012-02-02 00:00:00') 1.0 3 'test' 'foo']
 [1 Timestamp('2012-02-02 00:00:00') 1.0 3 'train' 'foo']
 [1 Timestamp('2012-02-02 00:00:00') 1.0 3 'test' 'foo']
 [1 Timestamp('2012-02-02 00:00:00') 1.0 3 'train' 'foo']]
"""
# 描述
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
"""
# 转置
print(df2.T)
# 按列或者行排序
print(df2.sort_index(axis=1, ascending=False))
"""
     F      E  D    C          B  A
0  foo   test  3  1.0 2012-02-02  1
1  foo  train  3  1.0 2012-02-02  1
2  foo   test  3  1.0 2012-02-02  1
3  foo  train  3  1.0 2012-02-02  1
"""
# 输出部分索引的值并排序
print(df2.sort_values(by='E'))
"""
   A          B    C  D      E    F
0  1 2012-02-02  1.0  3   test  foo
2  1 2012-02-02  1.0  3   test  foo
1  1 2012-02-02  1.0  3  train  foo
3  1 2012-02-02  1.0  3  train  foonn 
"""

1-2 数据处理

# 先创建数据备用
date = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)), index=date, columns=['A', 'B', 'C', 'D'])
print(df)
# 多种方式打印
print(df['A'])
print(df.A)
# 打印前三行
print(df[0:3])
# print('\n'*1)
# 打印后三行
print(df['2013-01-04':'2013-01-06'])
# select by label:loc
print(df.loc['2013-01-06'])
"""
A    20
B    21
C    22
D    23
Name: 2013-01-06 00:00:00, dtype: int32
"""
print(df.loc[:,['A', 'B']])
"""
             A   B
2013-01-01   0   1
2013-01-02   4   5
2013-01-03   8   9
2013-01-04  12  13
2013-01-05  16  17
2013-01-06  20  21
"""
print(df.loc['2013-01-03', ['A', 'B']])
"""
A    8
B    9
Name: 2013-01-03 00:00:00, dtype: int32
"""

# select by of position：iloc
print(df.iloc[[1, 3, 5], 1:3])
"""
             B   C
2013-01-02   5   6
2013-01-04  13  14
2013-01-06  21  22
"""
# select mixed: ix
# print(df.ix[:3, ['A', 'B', 'C']])

# boolean indexing
print(df)
print(df<8)
print(df[df.A<8])
"""
                A      B      C      D
2013-01-01   True   True   True   True
2013-01-02   True   True   True   True
2013-01-03  False  False  False  False
2013-01-04  False  False  False  False
2013-01-05  False  False  False  False
2013-01-06  False  False  False  False

            A  B  C  D
2013-01-01  0  1  2  3
2013-01-02  4  5  6  7

"""

1-3 设置数据值

date = pd.date_range('20100101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6, 4)), index=date, columns=['A', 'B', 'C', 'D'])
print(df)

# set values by position: iloc
df.iloc[2,2] = 111
print(df)
# set values by label: loc
df.loc['20100103', 'B'] = 999
print(df)
# 设置>大于某个数的值  改变全部值
# df[df.A>0] = 0
# print(df)
"""
            A  B  C  D
2010-01-01  0  1  2  3
2010-01-02  0  0  0  0
2010-01-03  0  0  0  0
2010-01-04  0  0  0  0
2010-01-05  0  0  0  0
2010-01-06  0  0  0  0
"""
# 改变一部分的值
# df.A[df.A>3] = 0
# print(df)
"""
            A    B    C   D
2010-01-01  0    1    2   3
2010-01-02  0    5    6   7
2010-01-03  0  999  111  11
2010-01-04  0   13   14  15
2010-01-05  0   17   18  19
2010-01-06  0   21   22  23
"""
# 增加值
df['F'] = np.nan
print(df)
"""
             A    B    C   D   F
2010-01-01   0    1    2   3 NaN
2010-01-02   4    5    6   7 NaN
2010-01-03   8  999  111  11 NaN
2010-01-04  12   13   14  15 NaN
2010-01-05  16   17   18  19 NaN
2010-01-06  20   21   22  23 NaN
"""
df['E'] = pd.Series([1,2,3,4,5,6], index=pd.date_range('20100101', periods=6))
print(df)
             A    B    C   D   F  E
2010-01-01   0    1    2   3 NaN  1
2010-01-02   4    5    6   7 NaN  2
2010-01-03   8  999  111  11 NaN  3
2010-01-04  12   13   14  15 NaN  4
2010-01-05  16   17   18  19 NaN  5
2010-01-06  20   21   22  23 NaN  6

1-4 处理丢失的数据

import numpy as np
import pandas as pd

# 原始数据
date = pd.date_range('20100101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6, 4)), index=date, columns=['A', 'B', 'C', 'D'])
print(df)
df.iloc[0, 1] = np.nan
df.iloc[1, 2] = np.nan
print(df)
# 处理数据-丢掉有nan的整行数据  any-只要行或列中年有nan就算，all-要全部都为nan才算
print(df.dropna(axis=0, how='any'))   # axis = 0， 竖直方向对行进行操作
print(df.dropna(axis=1, how='any'))   # axis = 1   水平方向对列进行操作
"""
             A     B     C   D
2010-01-03   8   9.0  10.0  11
2010-01-04  12  13.0  14.0  15
2010-01-05  16  17.0  18.0  19
2010-01-06  20  21.0  22.0  23
          A   D
2010-01-01   0   3
2010-01-02   4   7
2010-01-03   8  11
2010-01-04  12  15
2010-01-05  16  19
2010-01-06  20  23
"""
# 将nan的位置填入其他值，如0
print(df.fillna(value=0))
"""
             A     B     C   D
2010-01-01   0   0.0   2.0   3
2010-01-02   4   5.0   0.0   7
2010-01-03   8   9.0  10.0  11
2010-01-04  12  13.0  14.0  15
2010-01-05  16  17.0  18.0  19
2010-01-06  20  21.0  22.0  23
"""
# 打印True或者False的值
print(df.isnull())
"""
                A      B      C      D
2010-01-01  False   True  False  False
2010-01-02  False  False   True  False
2010-01-03  False  False  False  False
2010-01-04  False  False  False  False
2010-01-05  False  False  False  False
2010-01-06  False  False  False  False
"""
# 打印至少一个是丢失的数据的判断情况
print(np.any(df.isnull()))   # True

1-5 导入与导出数据

# 将csv文件读入，该文件可以再=在任意目录，将其读入就可以
data = pd.read_csv('C:/Users/liyuelong/Desktop/student.csv')
print(data)
# 转成其他模式，目录地址要相同。
data.to_pickle('C:/Users/liyuelong/Desktop/student.pickle')

标签：02,01,1.0,复习,df,pandas,print,2010
来源： https://blog.csdn.net/weixin_49499690/article/details/122464506

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。

ICode9

0-2 pandas 复习