File size: 4,200 Bytes
cb0befc | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 | ---
license: apache-2.0
language:
- en
inference: true
---
# HR Attrition Model
This model predicts the survival function of employees based on various features using a Cox Proportional Hazards model. The model aims to estimate how long an employee is likely to stay at the company based on a variety of factors.
## Model Description
The HR Attrition Model leverages the Cox Proportional Hazards method to predict employee retention. Key features used in this model include demographic information, job details, and work-life balance metrics. The model is trained on the "HR_Attrition" dataset and is designed to help HR departments understand employee attrition risks.
## Features
The following features are used for predictions:
- Age
- DistanceFromHome
- Education
- NumCompaniesWorked
- PercentSalaryHike
- TotalWorkingYears
- TrainingTimesLastYear
- WorkLifeBalance
- YearsInCurrentRole
- YearsSinceLastPromotion
- YearsWithCurrManager
- BusinessTravel (Travel_Rarely, Travel_Frequently)
- Department (Research & Development, Sales)
- EducationField (Life Sciences, Medical, Marketing, Other, Technical Degree)
- Gender (Male)
- JobRole (Research Scientist, Sales Executive, Laboratory Technician, Manufacturing Director, Healthcare Representative, Manager, Sales Representative, Research Director)
- MaritalStatus (Married, Single)
- OverTime (Yes)
## Usage
To use this model, you need to load the model and pass the input features in the required format.
### Example
Here is an example of how to use the model to predict the survival function:
```python
import joblib
import pandas as pd
class HRAttritionModel:
def __init__(self, model_path):
self.model = joblib.load(model_path)
self.features = ['Age', 'DistanceFromHome', 'Education', 'NumCompaniesWorked', 'PercentSalaryHike',
'TotalWorkingYears', 'TrainingTimesLastYear', 'WorkLifeBalance', 'YearsInCurrentRole',
'YearsSinceLastPromotion', 'YearsWithCurrManager', 'BusinessTravel_Travel_Rarely',
'BusinessTravel_Travel_Frequently', 'Department_Research & Development', 'Department_Sales',
'EducationField_Life Sciences', 'EducationField_Medical', 'EducationField_Marketing',
'EducationField_Other', 'EducationField_Technical Degree', 'Gender_Male', 'JobRole_Research Scientist',
'JobRole_Sales Executive', 'JobRole_Laboratory Technician', 'JobRole_Manufacturing Director',
'JobRole_Healthcare Representative', 'JobRole_Manager', 'JobRole_Sales Representative',
'JobRole_Research Director', 'MaritalStatus_Married', 'MaritalStatus_Single', 'OverTime_Yes']
def predict_survival(self, input_data):
df = pd.DataFrame([input_data], columns=self.features)
survival_function = self.model.predict_survival_function(df)
return survival_function.T
# Load the model and make a prediction
model = HRAttritionModel('cox_model.pkl')
sample_input = {'Age': 41, 'DistanceFromHome': 1, 'Education': 2, 'NumCompaniesWorked': 1, 'PercentSalaryHike': 11,
'TotalWorkingYears': 8, 'TrainingTimesLastYear': 0, 'WorkLifeBalance': 1, 'YearsInCurrentRole': 4,
'YearsSinceLastPromotion': 0, 'YearsWithCurrManager': 5, 'BusinessTravel_Travel_Rarely': 1,
'BusinessTravel_Travel_Frequently': 0, 'Department_Research & Development': 0, 'Department_Sales': 1,
'EducationField_Life Sciences': 1, 'EducationField_Medical': 0, 'EducationField_Marketing': 0,
'EducationField_Other': 0, 'EducationField_Technical Degree': 0, 'Gender_Male': 1,
'JobRole_Research Scientist': 0, 'JobRole_Sales Executive': 0, 'JobRole_Laboratory Technician': 0,
'JobRole_Manufacturing Director': 0, 'JobRole_Healthcare Representative': 0, 'JobRole_Manager': 0,
'JobRole_Sales Representative': 0, 'JobRole_Research Director': 0, 'MaritalStatus_Married': 0,
'MaritalStatus_Single': 1, 'OverTime_Yes': 0}
prediction = model.predict_survival(sample_input)
print(prediction) |