南大《探索数据的奥秘》课件示例代码笔记05

In [1]: import pandas as pd
import numpy as np
my_data = pd.read_csv("C:\Python\Scripts\my_data\Titanic.csv")
my_data.head(15)
Out[1]: PassengerId Survived Pclass \
0 1 0 3
1 2 1 1
2 3 1 3
3 4 1 1
4 5 0 3
5 6 0 3
6 7 0 1
7 8 0 3
8 9 1 3
9 10 1 2
10 11 1 3
11 12 1 1
12 13 0 3
13 14 0 3
14 15 0 3
Name Sex Age SibSp \
0 Braund, Mr. Owen Harris male 22.0 1
1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1
2 Heikkinen, Miss. Laina female 26.0 0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1
14 Allen, Mr. William Henry male 35.0 0
5 Moran, Mr. James male NaN 0
6 McCarthy, Mr. Timothy J male 54.0 0
7 Palsson, Master. Gosta Leonard male 2.0 3
8 Johnson, Mrs. Oscar W (Elisabeth Vilhelmina Berg) female 27.0 0
9 Nasser, Mrs. Nicholas (Adele Achem) female 14.0 1
10 Sandstrom, Miss. Marguerite Rut female 4.0 1
11 Bonnell, Miss. Elizabeth female 58.0 0
12 Saundercock, Mr. William Henry male 20.0 0
13 Andersson, Mr. Anders Johan male 39.0 1
14 Vestrom, Miss. Hulda Amanda Adolfina female 14.0 0
Parch Ticket Fare Cabin Embarked
0 0 A/5 21171 7.2500 NaN S
1 0 PC 17599 71.2833 C85 C
2 0 STON/O2. 3101282 7.9250 NaN S
3 0 113803 53.1000 C123 S
4 0 373450 8.0500 NaN S
5 0 330877 8.4583 NaN Q
6 0 17463 51.8625 E46 S
7 1 349909 21.0750 NaN S
8 2 347742 11.1333 NaN S
9 0 237736 30.0708 NaN C
10 1 PP 9549 16.7000 G6 S
11 0 113783 26.5500 C103 S
12 0 A/5. 2151 8.0500 NaN S
13 5 347082 31.2750 NaN S
14 0 350406 7.8542 NaN S
In [27]: print(my_data[['PassengerId','Age','Cabin']].iloc[:6])
PassengerId Age Cabin
0 1 22.0 NaN
1 2 38.0 C85
2 3 26.0 NaN
3 4 35.0 C123
4 5 35.0 NaN
5 6 NaN NaN
In [28]: my_fil_data1=my_data.dropna(axis=0)
my_fil_data1.head(7)
Out[28]: PassengerId Survived Pclass \
1 2 1 1
3 4 1 1
6 7 0 1
10 11 1 3
11 12 1 1
21 22 1 2
23 24 1 1
Name Sex Age SibSp \
1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1
6 McCarthy, Mr. Timothy J male 54.0 0
10 Sandstrom, Miss. Marguerite Rut female 4.0 1
11 Bonnell, Miss. Elizabeth female 58.0 0
21 Beesley, Mr. Lawrence male 34.0 0
23 Sloper, Mr. William Thompson male 28.0 0
Parch Ticket Fare Cabin Embarked
1 0 PC 17599 71.2833 C85 C
3 0 113803 53.1000 C123 S
6 0 17463 51.8625 E46 S
10 1 PP 9549 16.7000 G6 S
11 0 113783 26.5500 C103 S
21 0 248698 13.0000 D56 S
23 0 113788 35.5000 A6 S
In [29]: my_fil_data2=my_data.dropna(axis=1)
my_fil_data2.head(7)
Out[29]: PassengerId Survived Pclass \
0 1 0 3
1 2 1 1
2 3 1 3
33 4 1 1
4 5 0 3
5 6 0 3
6 7 0 1
Name Sex SibSp Parch \
0 Braund, Mr. Owen Harris male 1 0
1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 1 0
2 Heikkinen, Miss. Laina female 0 0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 1 0
4 Allen, Mr. William Henry male 0 0
5 Moran, Mr. James male 0 0
6 McCarthy, Mr. Timothy J male 0 0
Ticket Fare
0 A/5 21171 7.2500
1 PC 17599 71.2833
2 STON/O2. 3101282 7.9250
3 113803 53.1000
4 373450 8.0500
5 330877 8.4583
6 17463 51.8625
In [30]: mean_Age=int(my_data[['Age']].mean()[0])
my_dict={'Age':mean_Age,'Cabin':'haha'}
my_fil_data3=my_data.fillna(my_dict)
my_fil_data3.head(7)
Out[30]: PassengerId Survived Pclass \
0 1 0 3
1 2 1 1
2 3 1 3
3 4 1 1
4 5 0 3
5 6 0 3
6 7 0 1
Name Sex Age SibSp \
40 Braund, Mr. Owen Harris male 22.0 1
1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1
2 Heikkinen, Miss. Laina female 26.0 0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1
4 Allen, Mr. William Henry male 35.0 0
5 Moran, Mr. James male 29.0 0
6 McCarthy, Mr. Timothy J male 54.0 0
Parch Ticket Fare Cabin Embarked
0 0 A/5 21171 7.2500 haha S
1 0 PC 17599 71.2833 C85 C
2 0 STON/O2. 3101282 7.9250 haha S
3 0 113803 53.1000 C123 S
4 0 373450 8.0500 haha S
5 0 330877 8.4583 haha Q
6 0 17463 51.8625 E46 S
In [31]: my_fil_data4=my_data.fillna(method='ffill')
my_fil_data4.head(7)
Out[31]: PassengerId Survived Pclass \
0 1 0 3
1 2 1 1
2 3 1 3
3 4 1 1
4 5 0 3
5 6 0 3
6 7 0 1
Name Sex Age SibSp \
0 Braund, Mr. Owen Harris male 22.0 1
1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1
2 Heikkinen, Miss. Laina female 26.0 0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1
4 Allen, Mr. William Henry male 35.0 0
5 Moran, Mr. James male 35.0 0
6 McCarthy, Mr. Timothy J male 54.0 0
Parch Ticket Fare Cabin Embarked
0 0 A/5 21171 7.2500 NaN S
1 0 PC 17599 71.2833 C85 C
2 0 STON/O2. 3101282 7.9250 C85 S
3 0 113803 53.1000 C123 S
4 0 373450 8.0500 C123 S
5 0 330877 8.4583 C123 Q
6 0 17463 51.8625 E46 S
In [32]: my_fil_data5=my_data.fillna(method='bfill')
my_fil_data5.head(7)
Out[32]: PassengerId Survived Pclass \
0 1 0 3
1 2 1 1
2 3 1 3
3 4 1 1
4 5 0 3
5 6 0 3
6 7 0 1
Name Sex Age SibSp \
0 Braund, Mr. Owen Harris male 22.0 1
1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1
2 Heikkinen, Miss. Laina female 26.0 0
3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1
4 Allen, Mr. William Henry male 35.0 0
5 Moran, Mr. James male 54.0 0
6 McCarthy, Mr. Timothy J male 54.0 0
Parch Ticket Fare Cabin Embarked
0 0 A/5 21171 7.2500 C85 S
1 0 PC 17599 71.2833 C85 C
2 0 STON/O2. 3101282 7.9250 C123 S
3 0 113803 53.1000 C123 S
4 0 373450 8.0500 E46 S
5 0 330877 8.4583 E46 Q
6 0 17463 51.8625 E46 S
In [1]: import pandas as pd
student_scores=pd.DataFrame({'姓名':['张三']*3+['李四']*3+['王五']*3,
'成绩':[10,10,10,8,8,8,5,5,5]})
student_scores
Out[1]: 姓名 成绩
0 张三 10
1 张三 10
2 张三 10
3 李四 8
4 李四 8
5 李四 8
6 王五 5
7 王五 5
8 王五 5
In [2]: student_scores.duplicated()
Out[2]: 0 False
1 True
2 True
3 False
4 True
5 True
6 False
7 True
8 True
dtype: bool
In [3]: my_fil_data5=student_scores.drop_duplicates()
my_fil_data5
Out[3]: 姓名 成绩
0 张三 10
3 李四 8
6 王五 5
7In [4]: import pandas as pd
import numpy as np
my_data = pd.read_csv("C:\Python\Scripts\my_data\iris.csv",header=None,
names=['sepal_length','sepal_width','petal_length',
'petal_width','target'])
print(my_data.corr(method='pearson'))
sepal_length sepal_width petal_length petal_width
sepal_length 1.000000 -0.109369 0.871754 0.817954
sepal_width -0.109369 1.000000 -0.420516 -0.356544
petal_length 0.871754 -0.420516 1.000000 0.962757
petal_width 0.817954 -0.356544 0.962757 1.000000