1.describe()：查看每一列的描述性統計量

# 導包
import numpy as np
import pandas as pddf = pd.DataFrame(data=np.random.randint(0,10,size=(5,3)),index=list("ABCDE"),columns=["Python","NumPy","Pandas"])
dfdf.describe()

	Python	NumPy	Pandas
count	5.000000	5.000000	5.000000
mean	5.600000	2.800000	5.400000
std	2.073644	2.167948	2.408319
min	4.000000	0.000000	2.000000
25%	4.000000	1.000000	4.000000
50%	5.000000	4.000000	6.000000
75%	6.000000	4.000000	7.000000
max	9.000000	5.000000	8.000000

# 自定義百分數
df.describe([0.01,0.3,0.4,0.9,0.99])

	Python	NumPy	Pandas
count	5.000000	5.000000	5.000000
mean	5.600000	2.800000	5.400000
std	2.073644	2.167948	2.408319
min	4.000000	0.000000	2.000000
1%	4.000000	0.040000	2.080000
30%	4.200000	1.600000	4.400000
40%	4.600000	2.800000	5.200000
50%	5.000000	4.000000	6.000000
90%	7.800000	4.600000	7.600000
99%	8.880000	4.960000	7.960000
max	9.000000	5.000000	8.000000

# 行列轉置
df.describe([0.01,0.3,0.4,0.9,0.99]).T

	count	mean	std	min	1%	30%	40%	50%	90%	99%	max
Python	5.0	5.6	2.073644	4.0	4.00	4.2	4.6	5.0	7.8	8.88	9.0
NumPy	5.0	2.8	2.167948	0.0	0.04	1.6	2.8	4.0	4.6	4.96	5.0
Pandas	5.0	5.4	2.408319	2.0	2.08	4.4	5.2	6.0	7.6	7.96	8.0

2.df.std()：可以求得DataFrame對象每一列的標準差

df.std()

Python    2.073644
NumPy     2.167948
Pandas    2.408319
dtype: float64

3.df.drop()：刪除特定索引

df2 = df.copy()
df2

	Python	NumPy	Pandas
A	9	0	8
B	5	1	2
C	6	5	7
D	4	4	6
E	4	4	4

# 默認刪除行
df2.drop("A")

	Python	NumPy	Pandas
B	5	1	2
C	6	5	7
D	4	4	6
E	4	4	4

df2.drop(index="A")

	Python	NumPy	Pandas
B	5	1	2
C	6	5	7
D	4	4	6
E	4	4	4

# 刪除列
df2.drop("Python",axis=1)

	NumPy	Pandas
A	0	8
B	1	2
C	5	7
D	4	6
E	4	4

df2.drop(columns="Python")

	NumPy	Pandas
A	0	8
B	1	2
C	5	7
D	4	6
E	4	4

# 刪除多列或多行
df2.drop(columns=["NumPy","Python"])

	Pandas
A	8
B	2
C	7
D	6
E	4

df2.drop(index=["A","B"])

	Python	NumPy	Pandas
C	6	5	7
D	4	4	6
E	4	4	4

# inplace修改原數據
df2.drop(index=["A","B"],inplace=True)
df2

	Python	NumPy	Pandas
C	6	5	7
D	4	4	6
E	4	4	4

4.unique()：唯一，去重(只能用于Series一維數組)

# DataFrame沒有unique屬性，Series調用unique
df["Python"].unique()

array([9, 5, 6, 4])

5.df.query：按條件查詢

# 找到Python列中等于6的所有行
df.query("Python == 6")

	Python	NumPy	Pandas
C	6	5	7

df.query("Python > 6")

	Python	NumPy	Pandas
A	9	0	8

df.query("Python < 6")

	Python	NumPy	Pandas
B	5	1	2
D	4	4	6
E	4	4	4

# and,&
df.query("Python > 4 and NumPy == 5")

	Python	NumPy	Pandas
C	6	5	7

df.query("Python > 4 & NumPy == 5")

	Python	NumPy	Pandas
C	6	5	7

# or,|
df.query("Python > 6 or NumPy == 8")

	Python	NumPy	Pandas
A	9	0	8

df.query("Python > 6 | NumPy == 8")

	Python	NumPy	Pandas
A	9	0	8

# in（成員運算符）
df.query("Python in [5,6,9]")

	Python	NumPy	Pandas
A	9	0	8
B	5	1	2
C	6	5	7

# 使用變量@符號
n = 6
df.query("Python == @n")

	Python	NumPy	Pandas
C	6	5	7

m = [5,6,9]
df.query("Python in @m")

	Python	NumPy	Pandas
A	9	0	8
B	5	1	2
C	6	5	7

6.df.sort_values()：根據值排序

# sort_values：默認按照列名排序，默認升序（常用）
df.sort_values("Python")

	Python	NumPy	Pandas
D	4	4	6
E	4	4	4
B	5	1	2
C	6	5	7
A	9	0	8

# ascending：是否升序，默認是True
df.sort_values("Python",ascending=False)

	Python	NumPy	Pandas
A	9	0	8
C	6	5	7
B	5	1	2
D	4	4	6
E	4	4	4

# 根據行索引名排序，會把列進行排序（不常用）
df.sort_values("B",axis=1)

	NumPy	Pandas	Python
A	0	8	9
B	1	2	5
C	5	7	6
D	4	6	4
E	4	4	4

7.df.sort_index()：根據索引排序

# 按照索引名排序，默認是對行索引進行排序，默認是升序
df.sort_index(ascending=False)

	Python	NumPy	Pandas
E	4	4	4
D	4	4	6
C	6	5	7
B	5	1	2
A	9	0	8

# 按照列索引排序
df.sort_index(ascending=False,axis=1)

	Python	Pandas	NumPy
A	9	8	0
B	5	2	1
C	6	7	5
D	4	6	4
E	4	4	4

8.df.info()：查看數據信息

# info：常用
df.info()

<class 'pandas.core.frame.DataFrame'>
Index: 5 entries, A to E
Data columns (total 3 columns):#   Column  Non-Null Count  Dtype
---  ------  --------------  -----0   Python  5 non-null      int321   NumPy   5 non-null      int322   Pandas  5 non-null      int32
dtypes: int32(3)
memory usage: 272.0+ bytes

9.練習

• 新建一個形狀為10000*3的標準正態分布的DataFrame(np.random.randn)，去除掉所有滿足以下情況的行：其中任一元素絕對值大約3陪標準差

df = pd.DataFrame(np.random.randn(10000,3))
df

	0	1	2
0	0.786386	-0.204965	-0.152465
1	0.400526	1.447733	0.310461
2	-0.363709	-0.989258	-1.093327
3	-2.856978	2.336645	1.474821
4	-0.847757	1.141278	-0.230877
...	...	...	...
9995	0.331052	0.263059	0.469468
9996	1.172189	-1.380337	0.648793
9997	-0.544049	-0.509627	-0.224698
9998	-0.034967	-0.085575	-0.687314
9999	0.007202	-0.069250	-0.803754

10000 rows × 3 columns

# 過濾掉 大于3陪標準差的行
# 標準差 df.std()，絕對值 df.abs()
# cond：找到每一個元素是否大于3陪標準差
cond = df.abs() > df.std()*3
cond

	0	1	2
0	False	False	False
1	False	False	False
2	False	False	False
3	False	False	False
4	False	False	False
...	...	...	...
9995	False	False	False
9996	False	False	False
9997	False	False	False
9998	False	False	False
9999	False	False	False

10000 rows × 3 columns

# 找到存在大于3陪標準差的行
cond2 = cond.any(axis=1)
cond2

0       False
1       False
2       False
3       False
4       False...  
9995    False
9996    False
9997    False
9998    False
9999    False
Length: 10000, dtype: bool

# bool值索引，過濾異常值（大于3陪標準差）
df.loc[~cond2]

	0	1	2
0	0.786386	-0.204965	-0.152465
1	0.400526	1.447733	0.310461
2	-0.363709	-0.989258	-1.093327
3	-2.856978	2.336645	1.474821
4	-0.847757	1.141278	-0.230877
...	...	...	...
9995	0.331052	0.263059	0.469468
9996	1.172189	-1.380337	0.648793
9997	-0.544049	-0.509627	-0.224698
9998	-0.034967	-0.085575	-0.687314
9999	0.007202	-0.069250	-0.803754

9904 rows × 3 columns