apol jsr90 commited on
Commit
052d41d
1 Parent(s): 5604a08

Update app.py (#2)

Browse files

- Update app.py (4ae7e589686badb7210f306ac995b79b4913f6db)


Co-authored-by: JESUS SANCHEZ <jsr90@users.noreply.huggingface.co>

Files changed (1) hide show
  1. app.py +24 -4
app.py CHANGED
@@ -57,12 +57,32 @@ def humands(Sex,Age,Married,Monthlyincome,TotalWorkingYears,DistanceFromHome,Ove
57
  "JobRole_Healthcare Representative" : [0],
58
  "EducationField_Human Resources" : [0],
59
  "JobRole_Manager" : [0],
60
- "JobRole_Research Director" : [0],
61
-
62
-
63
-
64
  }
65
  )
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
  pred = model.predict(df)[0]
68
 
 
57
  "JobRole_Healthcare Representative" : [0],
58
  "EducationField_Human Resources" : [0],
59
  "JobRole_Manager" : [0],
60
+ "JobRole_Research Director" : [0],
 
 
 
61
  }
62
  )
63
+
64
+ columnas = ['Age', 'DailyRate', 'DistanceFromHome', 'Education',
65
+ 'EnvironmentSatisfaction', 'HourlyRate', 'JobInvolvement', 'JobLevel',
66
+ 'JobSatisfaction', 'MonthlyIncome', 'MonthlyRate', 'NumCompaniesWorked',
67
+ 'PercentSalaryHike', 'PerformanceRating', 'RelationshipSatisfaction',
68
+ 'StockOptionLevel', 'TotalWorkingYears', 'TrainingTimesLastYear',
69
+ 'WorkLifeBalance', 'YearsAtCompany', 'YearsInCurrentRole',
70
+ 'YearsSinceLastPromotion', 'YearsWithCurrManager',
71
+ 'BusinessTravel_Non-Travel', 'BusinessTravel_Travel_Frequently',
72
+ 'BusinessTravel_Travel_Rarely', 'Department_Human Resources',
73
+ 'Department_Research & Development', 'Department_Sales',
74
+ 'EducationField_Human Resources', 'EducationField_Life Sciences',
75
+ 'EducationField_Marketing', 'EducationField_Medical',
76
+ 'EducationField_Other', 'EducationField_Technical Degree',
77
+ 'Gender_Female', 'Gender_Male', 'JobRole_Healthcare Representative',
78
+ 'JobRole_Human Resources', 'JobRole_Laboratory Technician',
79
+ 'JobRole_Manager', 'JobRole_Manufacturing Director',
80
+ 'JobRole_Research Director', 'JobRole_Research Scientist',
81
+ 'JobRole_Sales Executive', 'JobRole_Sales Representative',
82
+ 'MaritalStatus_Divorced', 'MaritalStatus_Married',
83
+ 'MaritalStatus_Single', 'OverTime_No', 'OverTime_Yes']
84
+
85
+ df = df.reindex(columns=columnas)
86
 
87
  pred = model.predict(df)[0]
88