【Python-Pandas】Pandas常用指令

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/made_in_china_too/article/details/82079313

# Series 对象可以理解为一维数组
s = pd.Series([4, 2, 5, 0, 6, 3])
s

0    4
1    2
2    5
3    0
4    6
5    3
dtype: int64

# DataFrame 是二维数组对象
df = pd.DataFrame(np.random.randn(6,4), columns=list('ABCD'))
df

A   B   C   D
0   0.968762    1.501239    -0.284952   -0.456468
1   1.413471    -0.309746   0.407559    1.536548
2   -0.399065   -0.040439   1.339359    -0.318217
3   -0.152205   -0.121888   0.841658    -1.493958
4   0.248414    -0.676985   1.326487    -0.455541
5   0.906221    -2.158694   -0.201354   -0.024769

df.iloc[0]

A    0.968762
B    1.501239
C   -0.284952
D   -0.456468
Name: 0, dtype: float64

df.A

0    0.968762
1    1.413471
2   -0.399065
3   -0.152205
4    0.248414
5    0.906221
Name: A, dtype: float64

print("Row data type: {}".format(type(df.iloc[0])))
print("Column data type: {}".format(type(df.A)))

Row data type: <class 'pandas.core.series.Series'>
Column data type: <class 'pandas.core.series.Series'>

df.shape

(6, 4)

df.head(3)

A   B   C   D
0   0.968762    1.501239    -0.284952   -0.456468
1   1.413471    -0.309746   0.407559    1.536548
2   -0.399065   -0.040439   1.339359    -0.318217

df.tail(2)

A   B   C   D
4   0.248414    -0.676985   1.326487    -0.455541
5   0.906221    -2.158694   -0.201354   -0.024769

df.columns

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

df.index

RangeIndex(start=0, stop=6, step=1)

df.describe()

A   B   C   D
count   6.000000    6.000000    6.000000    6.000000
mean    0.497600    -0.301086   0.571459    -0.202068
std 0.709385    1.178177    0.719762    0.986474
min -0.399065   -2.158694   -0.284952   -1.493958
25% -0.052050   -0.585176   -0.049126   -0.456236
50% 0.577317    -0.215817   0.624608    -0.386879
75% 0.953127    -0.060802   1.205280    -0.098131
max 1.413471    1.501239    1.339359    1.536548

df.sort_index(axis=1, ascending=False)

D   C   B   A
0   -0.456468   -0.284952   1.501239    0.968762
1   1.536548    0.407559    -0.309746   1.413471
2   -0.318217   1.339359    -0.040439   -0.399065
3   -1.493958   0.841658    -0.121888   -0.152205
4   -0.455541   1.326487    -0.676985   0.248414
5   -0.024769   -0.201354   -2.158694   0.906221

df.sort_values(by='B')

A   B   C   D
5   0.906221    -2.158694   -0.201354   -0.024769
4   0.248414    -0.676985   1.326487    -0.455541
1   1.413471    -0.309746   0.407559    1.536548
3   -0.152205   -0.121888   0.841658    -1.493958
2   -0.399065   -0.040439   1.339359    -0.318217
0   0.968762    1.501239    -0.284952   -0.456468

df[3:5]

A   B   C   D
3   -0.152205   -0.121888   0.841658    -1.493958
4   0.248414    -0.676985   1.326487    -0.455541

df[['A', 'B', 'D']]

A   B   D
0   0.968762    1.501239    -0.456468
1   1.413471    -0.309746   1.536548
2   -0.399065   -0.040439   -0.318217
3   -0.152205   -0.121888   -1.493958
4   0.248414    -0.676985   -0.455541
5   0.906221    -2.158694   -0.024769

df.loc[3, 'A']

-0.15220488957687467

df.iloc[3, 0]

-0.15220488957687467

df.iloc[2:5, 0:2]

A   B
2   -0.399065   -0.040439
3   -0.152205   -0.121888
4   0.248414    -0.676985

df[df.C > 0]

A   B   C   D
1   1.413471    -0.309746   0.407559    1.536548
2   -0.399065   -0.040439   1.339359    -0.318217
3   -0.152205   -0.121888   0.841658    -1.493958
4   0.248414    -0.676985   1.326487    -0.455541

df["TAG"] = ["cat", "dog", "cat", "cat", "cat", "dog"]
df

A   B   C   D   TAG
0   0.968762    1.501239    -0.284952   -0.456468   cat
1   1.413471    -0.309746   0.407559    1.536548    dog
2   -0.399065   -0.040439   1.339359    -0.318217   cat
3   -0.152205   -0.121888   0.841658    -1.493958   cat
4   0.248414    -0.676985   1.326487    -0.455541   cat
5   0.906221    -2.158694   -0.201354   -0.024769   dog

df.groupby('TAG').sum()

A   B   C   D
TAG             
cat 0.665906    0.661926    3.222551    -2.724184
dog 2.319691    -2.468440   0.206205    1.511778