Results:
Of the loyal, the model accurately predicts 99.7%.
Of the loyal, the model inaccurately predicts 0.3%.
Of the left,, the model accurately predicted 96.5%.
Of the left, the model inaccurately predicted 3.5%.
In total, the model is correct 98.9% of the times.
In total, the model is incorrect 1% of the times.
##
##
## Cell Contents
## |-------------------------|
## | N |
## | Chi-square contribution |
## | N / Row Total |
## | N / Col Total |
## | N / Table Total |
## |-------------------------|
##
##
## Total Observations in Table: 4459
##
##
## | val_rf$predicted_left
## val_rf$left | 0 | 1 | Row Total |
## -------------|-----------|-----------|-----------|
## 0 | 3390 | 9 | 3399 |
## | 231.507 | 768.774 | |
## | 0.997 | 0.003 | 0.762 |
## | 0.989 | 0.009 | |
## | 0.760 | 0.002 | |
## -------------|-----------|-----------|-----------|
## 1 | 37 | 1023 | 1060 |
## | 742.352 | 2465.155 | |
## | 0.035 | 0.965 | 0.238 |
## | 0.011 | 0.991 | |
## | 0.008 | 0.229 | |
## -------------|-----------|-----------|-----------|
## Column Total | 3427 | 1032 | 4459 |
## | 0.769 | 0.231 | |
## -------------|-----------|-----------|-----------|
##
##
Initial data preparations:
Explore Data:
There are 8 continuous variables and 2 categorical variables.
Satisfaction level: Most employees are highly satisfied.
Last Evaluation: Most employees are good performers with 75% of the data set being evaluated between 56 percent - 87 percent.
Number of Projects: Most employees do a reasonable number of projects.
Average Monthly Hours: Most employees spend, fairly, a higher amount of hours at work.
Time Spent in Company: Fewer employees stay beyond 4 years.
Summary of the variable ‘Work_accident’
- Work Accident: Most employees do not meet accidents at work.
## var frequency percentage cumulative_perc
## 1 0 12830 85.54 85.54
## 2 1 2169 14.46 100.00
- Promotion in Last 5years: Most employees have not received promotions in the last five years.
## var frequency percentage cumulative_perc
## 1 0 14680 97.87 97.87
## 2 1 319 2.13 100.00
Summary of the variable ‘left’
- Left: Most employees stay with the organization and do not leave.
## var frequency percentage cumulative_perc
## 1 0 11428 76.19 76.19
## 2 1 3571 23.81 100.00
- 0 denotes those who did NOT leave.
- 1 denotes those who left.
Summary of the variable ‘salary’
- Salary : 8.25 percent of the organization are top level with the highest pay, 42.9 percent of the employees are paid a medium salary and 48.7% of the employees are paid low salary.
## var frequency percentage cumulative_perc
## 1 low 7316 48.78 48.78
## 2 medium 6446 42.98 91.76
## 3 high 1237 8.25 100.00
Summary of the variable ‘sales’
- Sales: Represents the number of employees in each department. Department Sales has the highest number of employees at 27% and management the lowest which forms only 4.2 percent.
## var frequency percentage cumulative_perc
## 1 sales 4140 27.60 27.60
## 2 technical 2720 18.13 45.73
## 3 support 2229 14.86 60.59
## 4 IT 1227 8.18 68.77
## 5 product_mng 902 6.01 74.78
## 6 marketing 858 5.72 80.50
## 7 RandD 787 5.25 85.75
## 8 accounting 767 5.11 90.86
## 9 hr 739 4.93 95.79
## 10 management 630 4.20 100.00
Splitting Data into Training and Validation:
- To split data into training and test set: validation, variable ‘random’ (14999 observations with 10 variables) was mutated to create random samples:
- train_rf (10540 observations with 10 variables) and
- val_rf (4459 observations with 10 variables).
- The function runif() is employed to generate random deviates of the uniform distribution.
## satisfaction_level last_evaluation number_project average_montly_hours
## Min. :0.0900 Min. :0.3600 Min. :2.000 Min. : 96.0
## 1st Qu.:0.4400 1st Qu.:0.5600 1st Qu.:3.000 1st Qu.:156.0
## Median :0.6400 Median :0.7200 Median :4.000 Median :200.0
## Mean :0.6128 Mean :0.7161 Mean :3.803 Mean :201.1
## 3rd Qu.:0.8200 3rd Qu.:0.8700 3rd Qu.:5.000 3rd Qu.:245.0
## Max. :1.0000 Max. :1.0000 Max. :7.000 Max. :310.0
##
## time_spend_company Work_accident left promotion_last_5years
## Min. : 2.000 0:12830 0:11428 0:14680
## 1st Qu.: 3.000 1: 2169 1: 3571 1: 319
## Median : 3.000
## Mean : 3.498
## 3rd Qu.: 4.000
## Max. :10.000
##
## sales salary random
## sales :4140 high :1237 Min. :0.0000653
## technical :2720 low :7316 1st Qu.:0.2513756
## support :2229 medium:6446 Median :0.4936664
## IT :1227 Mean :0.4979971
## product_mng: 902 3rd Qu.:0.7470968
## marketing : 858 Max. :0.9999414
## (Other) :2923
Model:
- Those who left:
- Loyal = 11428
- Left = 3571
- Model predicted:
- 0 represents those who did NOT leave (Loyal) = 3427
- 1 represents those who left = 1032
## Length Class Mode
## call 5 -none- call
## type 1 -none- character
## predicted 10540 factor numeric
## err.rate 1500 -none- numeric
## confusion 6 -none- numeric
## votes 21080 matrix numeric
## oob.times 10540 -none- numeric
## classes 2 -none- character
## importance 36 -none- numeric
## importanceSD 27 -none- numeric
## localImportance 0 -none- NULL
## proximity 0 -none- NULL
## ntree 1 -none- numeric
## mtry 1 -none- numeric
## forest 14 -none- list
## y 10540 factor numeric
## test 0 -none- NULL
## inbag 0 -none- NULL
## terms 3 terms call
## 0 1
## 3427 1032