python_对异常值进行处理_丢弃_转化

python_对异常值进行处理_丢弃_转化

# 方法一：  丢弃
​
# 加载库
import pandas as pd
​
# 创建数据集
houses = pd.DataFrame()
houses['Price'] = [534433, 392333, 293222, 4322032]
houses['Bathrooms'] = [2, 3.5, 2, 116]
houses['Square_Feet'] = [1500, 2500, 1500, 48000]
​
# 筛选数据
houses[houses['Bathrooms'] < 20]
Price	Bathrooms	Square_Feet
0	534433	2.0	1500
1	392333	3.5	2500
2	293222	2.0	1500
# 方法二：标记出来，进行转化
​
# 라이브러리를 임포트합니다.
import numpy as np
​
# 基于布尔条件创建特征
houses["Outlier"] = np.where(houses["Bathrooms"] < 20, 0, 1)
​
# 데이터를 확인합니다.
houses
Price	Bathrooms	Square_Feet	Outlier
0	534433	2.0	1500	0
1	392333	3.5	2500	0
2	293222	2.0	1500	0
3	4322032	116.0	48000	1
# 로그 특성  对异常值进行转化
houses["Log_Of_Square_Feet"] = [np.log(x) for x in houses["Square_Feet"]]
​
# 데이터를 확인합니다.
houses
Price	Bathrooms	Square_Feet	Outlier	Log_Of_Square_Feet
0	534433	2.0	1500	0	7.313220
1	392333	3.5	2500	0	7.824046
2	293222	2.0	1500	0	7.313220
3	4322032	116.0	48000	1	10.778956