转换分类变量

HR Analytics：用 Python 预测员工流失

Hrant Davtyan

Assistant Professor of Data Science American University of Armenia

分类变量类型

有序型：包含两个或以上类别，且可排序
- 例：salary
- 取值：low、medium、high
无序型：包含两个或以上类别，且无内在顺序
- 例：department
- 取值：sales、accounting、hr、technical、support、management、IT、product_mng、marketing、RandD

类别编码（salary）

# 将 "salary" 列转换为分类类型
data.salary = data.salary.astype('category')     
# 指定类别顺序
data.salary = data.salary.cat.reorder_categories(['low',
                                                  'medium',
                                                  'high'])
# 用整数编码类别
data.salary = data.salary.cat.codes

旧值	新值
low	0
medium	1
high	2

生成哑变量

# 生成哑变量并保存到新 DataFrame
departments = pd.get_dummies(data.department)

示例输出：

       IT  RandD  accounting  hr  management  marketing  product_mng  sales  support  technical
0       0      0           0   0           0          0            0      0        0          1

虚拟变量陷阱

departments.head()

       IT  RandD  accounting  hr  management  marketing  product_mng  sales  support  technical
0       0      0           0   0           0          0            0      0        0          1

departments = departments.drop("technical", axis = 1)
departments.head()

       IT  RandD  accounting  hr  management  marketing  product_mng  sales  support
0       0      0           0   0           0          0            0      0        0

开始练习！

HR Analytics：用 Python 预测员工流失