半小時拿下Python數據處理之Pandas篇
import pandas as pd
Pandas數據結構
Series
Series
是一維的數據結構。
通過list構建Series
ser_obj =pd.Series(range(10,15))
print(type(ser_obj)) # <class 'pandas.core.series.Series'>
print(ser_obj)
<class 'pandas.core.series.Series'>
0 10
1 11
2 12
3 13
4 14
dtype: int32
獲取數據
print(type(ser_obj.values)) # <class 'numpy.ndarray'>
print(ser_obj.values) # [10 11 12 13 14]
<class 'numpy.ndarray'>
[10 11 12 13 14]
獲取索引
print(type(ser_obj.index)) # <class 'pandas.core.indexes.range.RangeIndex'>
print(ser_obj.index) # RangeIndex(start=0, stop=5, step=1)
<class 'pandas.core.indexes.range.RangeIndex'>
RangeIndex(start=0, stop=5, step=1)
注意索引對象不可變
# 索引對象不可變
ser_obj.index[0] = 2
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-53-ce46badf9dd7> in <module>()
----> 1 ser_obj.index[0] = 2
G:\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in __setitem__(self, key, value)
1668
1669 def __setitem__(self, key, value):
-> 1670 raise TypeError("Index does not support mutable operations")
1671
1672 def __getitem__(self, key):
TypeError: Index does not support mutable operations
預覽數據
print(ser_obj.head(3))
0 10
1 11
2 12
dtype: int32
通過索引獲取數據
print(ser_obj[0]) # 10
10
索引與數據的對應關係仍保持在數組運算的結果中
print(ser_obj > 12)
print(ser_obj[ser_obj > 12])
0 False
1 False
2 False
3 True
4 True
dtype: bool
3 13
4 14
dtype: int32
整合代碼
# 通過list構建Series
ser_obj =pd.Series(range(10,15))
print(type(ser_obj)) # <class 'pandas.core.series.Series'>
print(ser_obj)
# 獲取數據
print(type(ser_obj.values)) # <class 'numpy.ndarray'>
print(ser_obj.values) # [10 11 12 13 14]
# 獲取索引
print(type(ser_obj.index)) # <class 'pandas.core.indexes.range.RangeIndex'>
print(ser_obj.index) # RangeIndex(start=0, stop=5, step=1)
# 預覽數據
print(ser_obj.head(3))
#通過索引獲取數據
print(ser_obj[0]) # 10
# 索引與數據的對應關係仍保持在數組運算的結果中
print(ser_obj > 12)
print(ser_obj[ser_obj > 12])
<class 'pandas.core.series.Series'>
0 10
1 11
2 12
3 13
4 14
dtype: int32
<class 'numpy.ndarray'>
[10 11 12 13 14]
<class 'pandas.core.indexes.range.RangeIndex'>
RangeIndex(start=0, stop=5, step=1)
0 10
1 11
2 12
dtype: int32
10
0 False
1 False
2 False
3 True
4 True
dtype: bool
3 13
4 14
dtype: int32
通過dict構建Series(注意:字典的key自動作爲索引)
year_data = {2001: 17.8, 2002: 20.1, 2003: 16.5}
ser_obj2 = pd.Series(year_data)
print(type(ser_obj2)) # <class 'pandas.core.series.Series'>
print(ser_obj2)
<class 'pandas.core.series.Series'>
2001 17.8
2002 20.1
2003 16.5
dtype: float64
獲取數據
print(type(ser_obj2.values)) # <class 'numpy.ndarray'>
print(ser_obj2.values) # [ 17.8 20.1 16.5]
<class 'numpy.ndarray'>
[ 17.8 20.1 16.5]
獲取索引
print(type(ser_obj2.index)) # <class 'pandas.core.indexes.numeric.Int64Index'>
print(ser_obj2.index) # Int64Index([2001, 2002, 2003], dtype='int64')
<class 'pandas.core.indexes.numeric.Int64Index'>
Int64Index([2001, 2002, 2003], dtype='int64')
預覽數據(head()不加參數則顯示全部)
print(ser_obj2.head())
2001 17.8
2002 20.1
2003 16.5
dtype: float64
通過索引獲取數據
print(ser_obj2[2001]) # 17.8
17.8
整合代碼
# 通過dict構建Series(注意:字典的key自動作爲索引)
year_data = {2001: 17.8, 2002: 20.1, 2003: 16.5}
ser_obj2 = pd.Series(year_data)
print(type(ser_obj2)) # <class 'pandas.core.series.Series'>
print(ser_obj2)
# 獲取數據
print(type(ser_obj2.values)) # <class 'numpy.ndarray'>
print(ser_obj2.values) # [ 17.8 20.1 16.5]
# 獲取索引
print(type(ser_obj2.index)) # <class 'pandas.core.indexes.numeric.Int64Index'>
print(ser_obj2.index) # Int64Index([2001, 2002, 2003], dtype='int64')
# 預覽數據(head()不加參數則顯示全部)
print(ser_obj2.head())
#通過索引獲取數據
print(ser_obj2[2001]) # 17.8
<class 'pandas.core.series.Series'>
2001 17.8
2002 20.1
2003 16.5
dtype: float64
<class 'numpy.ndarray'>
[ 17.8 20.1 16.5]
<class 'pandas.core.indexes.numeric.Int64Index'>
Int64Index([2001, 2002, 2003], dtype='int64')
2001 17.8
2002 20.1
2003 16.5
dtype: float64
17.8
DataFrame
一個Dataframe
就是一張表格,Series
表示的是一維數組,Dataframe
則是一個二維數組,可以類比成一張excel
的spreadsheet
。也可以把 Dataframe
當做一組Series
的集合。
通過ndarray構建DataFrame
import numpy as np
# 通過ndarray構建DataFrame
array = np.random.randn(5,4)
print(array)
df_obj = pd.DataFrame(array)
print(df_obj.head())
[[ 0.7346628 -1.13733651 0.72853785 0.38743511]
[ 0.49549724 3.96998008 1.13567695 -0.21425912]
[ 0.22094222 0.7766603 0.46086182 0.33199643]
[-0.46279419 0.85898771 0.41993259 -0.61997791]
[-0.83296535 1.19450707 -1.45531366 -0.13990243]]
0 1 2 3
0 0.734663 -1.137337 0.728538 0.387435
1 0.495497 3.969980 1.135677 -0.214259
2 0.220942 0.776660 0.460862 0.331996
3 -0.462794 0.858988 0.419933 -0.619978
4 -0.832965 1.194507 -1.455314 -0.139902
通過dict構建DataFrame
dict_data = {'A': 1.,
'B': pd.Timestamp('20180316'),
'C': pd.Series(1, index=list(range(4)),dtype='float32'),
'D': np.array([3] * 4,dtype='int32'),
'E' : pd.Categorical(["Python","Java","C++","C#"])
}
print(dict_data)
df_obj2 = pd.DataFrame(dict_data)
print(df_obj2.head())
{'A': 1.0, 'B': Timestamp('2018-03-16 00:00:00'), 'C': 0 1.0
1 1.0
2 1.0
3 1.0
dtype: float32, 'D': array([3, 3, 3, 3]), 'E': [Python, Java, C++, C#]
Categories (4, object): [C#, C++, Java, Python]}
A B C D E
0 1.0 2018-03-16 1.0 3 Python
1 1.0 2018-03-16 1.0 3 Java
2 1.0 2018-03-16 1.0 3 C++
3 1.0 2018-03-16 1.0 3 C#
通過列索引獲取列數據
print(df_obj2['A'])
print(type(df_obj2['A']))
print(df_obj2.A)
0 1.0
1 1.0
2 1.0
3 1.0
Name: A, dtype: float64
<class 'pandas.core.series.Series'>
0 1.0
1 1.0
2 1.0
3 1.0
Name: A, dtype: float64
通過行索引(.loc)獲取行數據
print(df_obj2.loc[0])
print(type(df_obj2.loc[0]))
A 1
B 2018-03-16 00:00:00
C 1
D 3
E Python
Name: 0, dtype: object
<class 'pandas.core.series.Series'>
增加列
df_obj2['F'] = df_obj2['D'] + 4
print(df_obj2.head())
A B C D E F
0 1.0 2018-03-16 1.0 3 Python 7
1 1.0 2018-03-16 1.0 3 Java 7
2 1.0 2018-03-16 1.0 3 C++ 7
3 1.0 2018-03-16 1.0 3 C# 7
刪除列
del(df_obj2['F'] )
print(df_obj2.head())
A B C D E
0 1.0 2018-03-16 1.0 3 Python
1 1.0 2018-03-16 1.0 3 Java
2 1.0 2018-03-16 1.0 3 C++
3 1.0 2018-03-16 1.0 3 C#
整合代碼
import numpy as np
# 通過ndarray構建DataFrame
array = np.random.randn(5,4)
print(array)
# 通過dict構建DataFrame
df_obj = pd.DataFrame(array)
print(df_obj.head())
dict_data = {'A': 1.,
'B': pd.Timestamp('20180316'),
'C': pd.Series(1, index=list(range(4)),dtype='float32'),
'D': np.array([3] * 4,dtype='int32'),
'E' : pd.Categorical(["Python","Java","C++","C#"])
}
print(dict_data)
df_obj2 = pd.DataFrame(dict_data)
print(df_obj2.head())
# 通過列索引獲取列數據
print(df_obj2['A'])
print(type(df_obj2['A']))
print(df_obj2.A)
# 通過行索引獲取行數據
print(df_obj2.loc[0])
print(type(df_obj2.loc[0]))
# 增加列
df_obj2['G'] = df_obj2['D'] + 4
print(df_obj2.head())
# 刪除列
del(df_obj2['G'] )
print(df_obj2.head())
[[ 0.23758715 -1.13751056 -0.0863061 -0.71309414]
[ 0.08129935 1.32099551 -0.27057527 0.49270974]
[ 0.96111551 1.08307556 1.5094844 0.96117055]
[-0.31003598 1.33959047 -0.42150857 -1.20605423]
[ 0.12655879 -1.01810288 -1.34025171 0.98758417]]
0 1 2 3
0 0.237587 -1.137511 -0.086306 -0.713094
1 0.081299 1.320996 -0.270575 0.492710
2 0.961116 1.083076 1.509484 0.961171
3 -0.310036 1.339590 -0.421509 -1.206054
4 0.126559 -1.018103 -1.340252 0.987584
{'A': 1.0, 'B': Timestamp('2018-03-16 00:00:00'), 'C': 0 1.0
1 1.0
2 1.0
3 1.0
dtype: float32, 'D': array([3, 3, 3, 3]), 'E': [Python, Java, C++, C#]
Categories (4, object): [C#, C++, Java, Python]}
A B C D E
0 1.0 2018-03-16 1.0 3 Python
1 1.0 2018-03-16 1.0 3 Java
2 1.0 2018-03-16 1.0 3 C++
3 1.0 2018-03-16 1.0 3 C#
0 1.0
1 1.0
2 1.0
3 1.0
Name: A, dtype: float64
<class 'pandas.core.series.Series'>
0 1.0
1 1.0
2 1.0
3 1.0
Name: A, dtype: float64
A 1
B 2018-03-16 00:00:00
C 1
D 3
E Python
Name: 0, dtype: object
<class 'pandas.core.series.Series'>
A B C D E G
0 1.0 2018-03-16 1.0 3 Python 7
1 1.0 2018-03-16 1.0 3 Java 7
2 1.0 2018-03-16 1.0 3 C++ 7
3 1.0 2018-03-16 1.0 3 C# 7
A B C D E
0 1.0 2018-03-16 1.0 3 Python
1 1.0 2018-03-16 1.0 3 Java
2 1.0 2018-03-16 1.0 3 C++
3 1.0 2018-03-16 1.0 3 C#
Pandas 數據操作
import pandas as pd
Series索引
ser_obj = pd.Series(range(5), index = ['a', 'b', 'c', 'd', 'e'])
ser_obj.head()
a 0
b 1
c 2
d 3
e 4
dtype: int32
行索引
# 行索引
ser_obj['a'] #等同描述ser_obj[0]
0
切片索引可以按照默認索引號,也可以按照實際索引值
# 切片索引(按索引號)
ser_obj[1:3] #python索引默認是左閉右開
b 1
c 2
dtype: int32
# 切片索引(按索引值)
ser_obj['b':'d']
b 1
c 2
d 3
dtype: int32
不連續索引,同樣可以按照默認索引號,也可以按照實際索引值
# 不連續索引表達一(按索引號)
ser_obj[[0, 2, 4]]
a 0
c 2
e 4
dtype: int32
# 不連續索引表達二(按索引值)
ser_obj[['a', 'e']]
a 0
e 4
dtype: int32
布爾索引
# 布爾索引
ser_bool = ser_obj > 2
print(ser_bool)
print()
print(ser_obj[ser_bool])
print()
print(ser_obj[ser_obj > 2])
a False
b False
c False
d True
e True
dtype: bool
d 3
e 4
dtype: int32
d 3
e 4
dtype: int32
DataFrame索引
import numpy as np
df_obj = pd.DataFrame(np.random.randn(5,4), columns = ['a', 'b', 'c', 'd'])
df_obj.head()
a | b | c | d | |
---|---|---|---|---|
0 | 0.983790 | 1.063804 | 0.854634 | -1.269025 |
1 | 0.161653 | -0.904602 | -1.840041 | 0.138183 |
2 | -1.256608 | -1.740634 | -1.653686 | -0.412524 |
3 | 0.165782 | 1.116089 | 0.065008 | -1.693706 |
4 | 1.313987 | 0.734437 | -0.625647 | -1.738446 |
列索引
# 列索引
print(type(df_obj['a'])) # 返回Series類型
df_obj['a'] # 返回對應列值
<class 'pandas.core.series.Series'>
0 0.983790
1 0.161653
2 -1.256608
3 0.165782
4 1.313987
Name: a, dtype: float64
行索引
# 行索引
print(type(df_obj.loc[0])) # 返回Series類型
df_obj.loc[0] # 返回對應行值
<class 'pandas.core.series.Series'>
a 0.983790
b 1.063804
c 0.854634
d -1.269025
Name: 0, dtype: float64
不連續索引
#不連續列索引
df_obj[['a','c']] #不連續列索引
a | c | |
---|---|---|
0 | 0.983790 | 0.854634 |
1 | 0.161653 | -1.840041 |
2 | -1.256608 | -1.653686 |
3 | 0.165782 | 0.065008 |
4 | 1.313987 | -0.625647 |
#不連續行索引
df_obj.loc[[1, 3]] #不連續行索引
a | b | c | d | |
---|---|---|---|---|
1 | 0.161653 | -0.904602 | -1.840041 | 0.138183 |
3 | 0.165782 | 1.116089 | 0.065008 | -1.693706 |
混合索引
# 混合索引 loc
print(df_obj.loc[0:2, 'a']) # 連續行加列索引(這裏是從0-2)
print()
print(df_obj.loc[[0,2,4], 'a']) # 不連續行加列索引
0 -1.018941
1 0.089275
2 -2.210780
Name: a, dtype: float64
0 -1.018941
2 -2.210780
4 1.435787
Name: a, dtype: float64
運算與對齊
Series
對齊操作
s1 = pd.Series(range(10, 13), index = range(3))
s2 = pd.Series(range(20, 25), index = range(5))
print('s1: ' )
print(s1)
print('')
print('s2: ')
print(s2)
s1:
0 10
1 11
2 12
dtype: int32
s2:
0 20
1 21
2 22
3 23
4 24
dtype: int32
# Series 對齊運算
print(s1 + s2) # 沒有對應上的部分會顯示NaN
print()
print(s1.add(s2, fill_value = -1)) # 沒有對應上的部分會填充-1,然後運算
print()
s3 = s1 + s2
s3_filled = s3.fillna(-1)
print(s3_filled) ## 先運算,然後NaN填充爲-1
0 30.0
1 32.0
2 34.0
3 NaN
4 NaN
dtype: float64
0 30.0
1 32.0
2 34.0
3 22.0
4 23.0
dtype: float64
0 30.0
1 32.0
2 34.0
3 -1.0
4 -1.0
dtype: float64
DataFrame
對齊操作
import numpy as np
df1 = pd.DataFrame(np.ones((2,2)), columns = ['a', 'b'])
df2 = pd.DataFrame(np.ones((3,3)), columns = ['a', 'b', 'c'])
print('df1: ')
print(df1)
print('')
print('df2: ')
print(df2)
df1:
a b
0 1.0 1.0
1 1.0 1.0
df2:
a b c
0 1.0 1.0 1.0
1 1.0 1.0 1.0
2 1.0 1.0 1.0
# DataFrame對齊操作
df1 + df2 # 沒有對應上的部分會顯示NaN
a | b | c | |
---|---|---|---|
0 | 2.0 | 2.0 | NaN |
1 | 2.0 | 2.0 | NaN |
2 | NaN | NaN | NaN |
df1.add(df2, fill_value = 0) # 加法操作,沒有對應上的補零
a | b | c | |
---|---|---|---|
0 | 2.0 | 2.0 | 1.0 |
1 | 2.0 | 2.0 | 1.0 |
2 | 1.0 | 1.0 | 1.0 |
df1 - df2 # 沒有對應上的部分會顯示NaN
a | b | c | |
---|---|---|---|
0 | 0.0 | 0.0 | NaN |
1 | 0.0 | 0.0 | NaN |
2 | NaN | NaN | NaN |
df1.sub(df2, fill_value = 2) # 加法操作,沒有對應上的補2(先補充後運算)
a | b | c | |
---|---|---|---|
0 | 0.0 | 0.0 | 1.0 |
1 | 0.0 | 0.0 | 1.0 |
2 | 1.0 | 1.0 | 1.0 |
df3 = df1 + df2
df3.fillna(100, inplace = True) # 先運行加法操作,沒有對應上的補2(先運算,後補充)
df3
a | b | c | |
---|---|---|---|
0 | 2.0 | 2.0 | 100.0 |
1 | 2.0 | 2.0 | 100.0 |
2 | 100.0 | 100.0 | 100.0 |
函數應用
可以與NumPy
中的ufunc
函數結合操作
# Numpy ufunc 函數
df = pd.DataFrame(np.random.randn(5,4) - 1)
df
0 | 1 | 2 | 3 | |
---|---|---|---|---|
0 | -0.938212 | -2.487779 | -1.805374 | -1.130723 |
1 | -0.533441 | 0.196536 | -1.094895 | -1.819312 |
2 | -3.233318 | 0.255510 | -1.560183 | -2.404621 |
3 | -1.956924 | -2.947539 | -1.640760 | -0.757321 |
4 | 0.198618 | 0.344484 | -0.893815 | -0.498036 |
np.abs(df) #取絕對值(還有其他諸多NumPy中的函數可以操作)
0 | 1 | 2 | 3 | |
---|---|---|---|---|
0 | 0.938212 | 2.487779 | 1.805374 | 1.130723 |
1 | 0.533441 | 0.196536 | 1.094895 | 1.819312 |
2 | 3.233318 | 0.255510 | 1.560183 | 2.404621 |
3 | 1.956924 | 2.947539 | 1.640760 | 0.757321 |
4 | 0.198618 | 0.344484 | 0.893815 | 0.498036 |
使用apply應用行或列數據
# 使用apply應用行或列數據
# f = lambda x : x.max() # lambda存在意義就是對簡單函數的簡潔表示
def f(x):
return x.max()
df.apply(f) # 默認按行比較(得到每列的最大值)
0 0.198618
1 0.344484
2 -0.893815
3 -0.498036
dtype: float64
df.apply(lambda x : x.max(), axis=1) # 按列比較(得到每行的最大值)
0 -0.938212
1 0.196536
2 0.255510
3 -0.757321
4 0.344484
dtype: float64
df.apply(lambda x : x.max(), axis=0) # # 按行比較(得到每列的最大值)
0 0.198618
1 0.344484
2 -0.893815
3 -0.498036
dtype: float64
使用applymap應用到每個數據
# 使用applymap應用到每個數據
f2 = lambda x : '%.2f' % x #每個數據顯示只保留兩位小數
df.applymap(f2)
0 | 1 | 2 | 3 | |
---|---|---|---|---|
0 | -0.94 | -2.49 | -1.81 | -1.13 |
1 | -0.53 | 0.20 | -1.09 | -1.82 |
2 | -3.23 | 0.26 | -1.56 | -2.40 |
3 | -1.96 | -2.95 | -1.64 | -0.76 |
4 | 0.20 | 0.34 | -0.89 | -0.50 |
排序
Series
索引排序 & 值排序
#索引亂序生成
s4 = pd.Series([10,13,12,25,14], index = [2,1,5,3,4])
s4
2 10
1 13
5 12
3 25
4 14
dtype: int64
# 索引排序
s4.sort_index(ascending=False) # 索引倒序排列
5 12
4 14
3 25
2 10
1 13
dtype: int64
# 值排序
s4.sort_values()
2 10
5 12
1 13
4 14
3 25
dtype: int64
DataFrame
索引排序 & 值排序
df4 = pd.DataFrame(np.random.randn(3, 4),
index=[1,3,2],
columns=[1,4,2,3])
df4
1 | 4 | 2 | 3 | |
---|---|---|---|---|
1 | 0.948112 | 0.076323 | 0.089607 | 0.091737 |
3 | -1.254556 | 1.483504 | 0.468995 | 0.286249 |
2 | -0.806738 | -0.842388 | -1.127489 | -0.020803 |
#按索引排序
df4.sort_index(ascending=False)# 對橫軸按倒序排列
1 | 4 | 2 | 3 | |
---|---|---|---|---|
3 | -1.254556 | 1.483504 | 0.468995 | 0.286249 |
2 | -0.806738 | -0.842388 | -1.127489 | -0.020803 |
1 | 0.948112 | 0.076323 | 0.089607 | 0.091737 |
#按索引排序
df4.sort_index(axis=1) #列軸按序排列
1 | 2 | 3 | 4 | |
---|---|---|---|---|
1 | 0.948112 | 0.089607 | 0.091737 | 0.076323 |
3 | -1.254556 | 0.468995 | 0.286249 | 1.483504 |
2 | -0.806738 | -1.127489 | -0.020803 | -0.842388 |
#按列排序
df4.sort_values(by=1) # by參數的作用是針對某一(些)列進行排序(不能對行使用 by 參數)
1 | 4 | 2 | 3 | |
---|---|---|---|---|
3 | -1.254556 | 1.483504 | 0.468995 | 0.286249 |
2 | -0.806738 | -0.842388 | -1.127489 | -0.020803 |
1 | 0.948112 | 0.076323 | 0.089607 | 0.091737 |
處理缺失數據
生成數據
df_data = pd.DataFrame([np.random.randn(3), [1., np.nan, np.nan],
[4., np.nan, np.nan], [1., np.nan, 2.]])
df_data.head()
0 | 1 | 2 | |
---|---|---|---|
0 | 1.089477 | -0.486706 | -0.322284 |
1 | 1.000000 | NaN | NaN |
2 | 4.000000 | NaN | NaN |
3 | 1.000000 | NaN | 2.000000 |
二值化(NaN爲False,非NaN爲True)
# isnull
df_data.isnull()
0 | 1 | 2 | |
---|---|---|---|
0 | False | False | False |
1 | False | True | True |
2 | False | True | True |
3 | False | True | False |
丟掉有NaN的行或列
# dropna
print(df_data.dropna()) #默認丟掉有NaN的行
print()
print(df_data.dropna(axis=1)) #丟掉有NaN的列
0 1 2
0 1.089477 -0.486706 -0.322284
0
0 1.089477
1 1.000000
2 4.000000
3 1.000000
填充NaN值
# fillna
df_data.fillna(-100.) # NaN值填充爲-100
0 | 1 | 2 | |
---|---|---|---|
0 | 1.089477 | -0.486706 | -0.322284 |
1 | 1.000000 | -100.000000 | -100.000000 |
2 | 4.000000 | -100.000000 | -100.000000 |
3 | 1.000000 | -100.000000 | 2.000000 |
數據統計計算和描述
常用的統計計算
df_obj = pd.DataFrame(np.random.randn(5,4), columns = ['a', 'b', 'c', 'd'])
df_obj
a | b | c | d | |
---|---|---|---|---|
0 | 0.145119 | -2.398595 | 0.640806 | 0.696701 |
1 | -0.877139 | -0.261616 | -2.211734 | 0.140729 |
2 | -0.644545 | 0.523667 | -1.460002 | -0.341459 |
3 | 1.369260 | 1.039981 | 0.164075 | 0.380755 |
4 | 0.089507 | -0.371051 | 1.348191 | -0.828315 |
df_obj.sum()
a 0.082203
b -1.467614
c -1.518663
d 0.048410
dtype: float64
df_obj.max()
a 1.369260
b 1.039981
c 1.348191
d 0.696701
dtype: float64
df_obj.min(axis=1)
0 -2.398595
1 -2.211734
2 -1.460002
3 0.164075
4 -0.828315
dtype: float64
統計描述
df_obj.describe()
a | b | c | d | |
---|---|---|---|---|
count | 5.000000 | 5.000000 | 5.000000 | 5.000000 |
mean | 0.016441 | -0.293523 | -0.303733 | 0.009682 |
std | 0.878550 | 1.311906 | 1.484695 | 0.602578 |
min | -0.877139 | -2.398595 | -2.211734 | -0.828315 |
25% | -0.644545 | -0.371051 | -1.460002 | -0.341459 |
50% | 0.089507 | -0.261616 | 0.164075 | 0.140729 |
75% | 0.145119 | 0.523667 | 0.640806 | 0.380755 |
max | 1.369260 | 1.039981 | 1.348191 | 0.696701 |