Assignment004

This is a programming assignment.

Part A

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tibble)
library(xtable)
library(ggplot2)

Read the data
You download this file from https://www.kaggle.com/ludobenistant/hr-analytics
and use your own path
get rows and columns

## [1] 14999    10

explore the data structure

## 'data.frame':    14999 obs. of  10 variables:
##  $ satisfaction_level   : num  0.38 0.8 0.11 0.72 0.37 0.41 0.1 0.92 0.89 0.42 ...
##  $ last_evaluation      : num  0.53 0.86 0.88 0.87 0.52 0.5 0.77 0.85 1 0.53 ...
##  $ number_project       : int  2 5 7 5 2 2 6 5 5 2 ...
##  $ average_montly_hours : int  157 262 272 223 159 153 247 259 224 142 ...
##  $ time_spend_company   : int  3 6 4 5 3 3 4 5 5 3 ...
##  $ Work_accident        : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ left                 : int  1 1 1 1 1 1 1 1 1 1 ...
##  $ promotion_last_5years: int  0 0 0 0 0 0 0 0 0 0 ...
##  $ sales                : Factor w/ 10 levels "accounting","hr",..: 8 8 8 8 8 8 8 8 8 8 ...
##  $ salary               : Factor w/ 3 levels "high","low","medium": 2 3 3 2 2 2 2 2 2 2 ...

Correlate all the numeric fields

## % latex table generated in R 3.4.1 by xtable 1.8-2 package
## % Sun Oct 01 03:12:18 2017
## \begin{table}[ht]
## \centering
## \begin{tabular}{rrrrrrrrr}
##   \hline
##  & satisfaction\_level & last\_evaluation & number\_project & average\_montly\_hours & time\_spend\_company & Work\_accident & left & promotion\_last\_5years \\ 
##   \hline
## satisfaction\_level & 1.00 & 0.11 & -0.14 & -0.02 & -0.10 & 0.06 & -0.39 & 0.03 \\ 
##   last\_evaluation & 0.11 & 1.00 & 0.35 & 0.34 & 0.13 & -0.01 & 0.01 & -0.01 \\ 
##   number\_project & -0.14 & 0.35 & 1.00 & 0.42 & 0.20 & -0.00 & 0.02 & -0.01 \\ 
##   average\_montly\_hours & -0.02 & 0.34 & 0.42 & 1.00 & 0.13 & -0.01 & 0.07 & -0.00 \\ 
##   time\_spend\_company & -0.10 & 0.13 & 0.20 & 0.13 & 1.00 & 0.00 & 0.14 & 0.07 \\ 
##   Work\_accident & 0.06 & -0.01 & -0.00 & -0.01 & 0.00 & 1.00 & -0.15 & 0.04 \\ 
##   left & -0.39 & 0.01 & 0.02 & 0.07 & 0.14 & -0.15 & 1.00 & -0.06 \\ 
##   promotion\_last\_5years & 0.03 & -0.01 & -0.01 & -0.00 & 0.07 & 0.04 & -0.06 & 1.00 \\ 
##    \hline
## \end{tabular}
## \end{table}

Create a correlation heat map

library(reshape2)
melted_cormat <- melt(cor(subset(mydf, select = -c(sales, salary))))
head(melted_cormat)

##                   Var1               Var2       value
## 1   satisfaction_level satisfaction_level  1.00000000
## 2      last_evaluation satisfaction_level  0.10502121
## 3       number_project satisfaction_level -0.14296959
## 4 average_montly_hours satisfaction_level -0.02004811
## 5   time_spend_company satisfaction_level -0.10086607
## 6        Work_accident satisfaction_level  0.05869724

g <- ggplot(data = melted_cormat, aes(x=Var1, y=Var2, fill=value)) + 
  geom_raster()
g <- g + theme(axis.text.x = element_text(angle = 90, hjust = 1))
g

Develop a 3-way table

mydf$status <- ifelse(mydf$left == 1, "Left", "Stay")
table(mydf$status,  mydf$salary, mydf$sales)

## , ,  = accounting
## 
##       
##        high  low medium
##   Left    5   99    100
##   Stay   69  259    235
## 
## , ,  = hr
## 
##       
##        high  low medium
##   Left    6   92    117
##   Stay   39  243    242
## 
## , ,  = IT
## 
##       
##        high  low medium
##   Left    4  172     97
##   Stay   79  437    438
## 
## , ,  = management
## 
##       
##        high  low medium
##   Left    1   59     31
##   Stay  224  121    194
## 
## , ,  = marketing
## 
##       
##        high  low medium
##   Left    9  126     68
##   Stay   71  276    308
## 
## , ,  = product_mng
## 
##       
##        high  low medium
##   Left    6  105     87
##   Stay   62  346    296
## 
## , ,  = RandD
## 
##       
##        high  low medium
##   Left    4   55     62
##   Stay   47  309    310
## 
## , ,  = sales
## 
##       
##        high  low medium
##   Left   14  697    303
##   Stay  255 1402   1469
## 
## , ,  = support
## 
##       
##        high  low medium
##   Left    8  389    158
##   Stay  133  757    784
## 
## , ,  = technical
## 
##       
##        high  low medium
##   Left   25  378    294
##   Stay  176  994    853

Employees who leave by department

ggplot(mydf[ which(mydf$status=='Left'),], 
       aes(x = sales, fill = status)) + geom_bar() + guides(fill=FALSE) + 
  theme(axis.text.x = element_text(angle = 90, hjust = 1))

- Complete this for employees who stay in the company by department

ggplot(mydf[ which(mydf$status=='Stay'),], 
       aes(x = sales, fill = status)) + 
  geom_bar() +
  labs(x = "DEPARTMENT", y = "STAY") + 
  guides(fill=FALSE) + 
  theme(axis.text.x = element_text(angle = 0, hjust = 0.5))

Part B

Complete this for employees who leave the company by salary level

mydf$salary <- factor(mydf$salary, levels = c("low", "medium", "high"))

ggplot(mydf[ which(mydf$status=='Left'),], 
       aes(x = salary, fill = status)) + 
  geom_bar() + 
  labs(x = "SALARY", y = "LEFT") + 
  guides(fill=FALSE) + 
  theme(axis.text.x = element_text(angle = 0, hjust = 0.5))

Complete this for employees who stay in the company by salary level

ggplot(mydf[ which(mydf$status=='Stay'),], 
       aes(x = salary, fill = status)) + 
  geom_bar() + 
  labs(x = "SALARY", y = "STAY") + 
  guides(fill=FALSE) + 
  theme(axis.text.x = element_text(angle = 0, hjust = 0.5))

Make a chart for number of employees who leave the company by time spent in the company

mydf$time_spend_company <- as.factor(mydf$time_spend_company)

ggplot(mydf[ which(mydf$status=='Left'),], 
       aes(x = time_spend_company, fill = status)) + 
  geom_bar() + 
  labs(x = "Time Spent in the company", y = "LEFT") + 
  guides(fill=FALSE) + 
  theme(axis.text.x = element_text(angle = 0, hjust = 0.3))

faceted by salary level AND department

ggplot(mydf[ which(mydf$status=='Left'),], 
       aes(x = time_spend_company, fill = status)) + 
  geom_bar() + 
  labs(x = "Time Spent in the company", y = "LEFT") + 
  guides(fill=FALSE) + 
  theme(axis.text.x = element_text(angle = 0, hjust = 0.3)) +
  facet_grid(salary~sales)

Make a chart for number of employees who who stay in the company by time spent in the company
faceted by salary level AND department

ggplot(mydf[ which(mydf$status=='Stay'),], 
       aes(x = time_spend_company, fill = status)) + 
  geom_bar() + 
  labs(x = "Time Spent in the company", y = "STAY") + 
  guides(fill=FALSE) + 
  theme(axis.text.x = element_text(angle = 0, hjust = 0.3)) +
  facet_grid(salary~sales)

Part C

Draw a bar plot of how many years did employees stay in the company before leaving
Year stayed in the company is the x axis

mydf$time_spend_company <- as.factor(mydf$time_spend_company)

ggplot(mydf[ which(mydf$status=='Left'),], 
       aes(x = time_spend_company, fill = status)) + 
  geom_bar() + 
  labs(x = "Year stayed in the company", y = "LEFT") + 
  guides(fill=FALSE) + 
  theme(axis.text.x = element_text(angle = 0, hjust = 0.3))

Draw a bar plot of how many years did employees stay in the company before leaving
by department
Year stayed in the company is the x axis

ggplot(mydf[ which(mydf$status=='Left'),], 
       aes(x = time_spend_company, fill = status)) + 
  geom_bar() + 
  labs(x = "Year stayed in the company", y = "LEFT") + 
  guides(fill=FALSE) + 
  theme(axis.text.x = element_text(angle = 0, hjust = 0.3)) +
  facet_grid(. ~ sales)

Draw a bar plot of how many years did employees stay in the company before leaving
by salary level
Year stayed in the company is the x axis

ggplot(mydf[ which(mydf$status=='Left'),], 
       aes(x = time_spend_company, fill = status)) + 
  geom_bar() + 
  labs(x = "Year stayed in the company", y = "LEFT") + 
  guides(fill=FALSE) + 
  theme(axis.text.x = element_text(angle = 0, hjust = 0.3)) +
  facet_grid(. ~ salary)

Write-up

The first thing to do the analysis work is to define the problem, and since we focus on staff’s status (left or stay), people who left the office is the group we need to concentrate on.
The graph which shows people left separated by salary level indicates that people with higher salary level tend to stay in the company, most office-leavings happen among people with low salary. Sales department have the largest number of people leaving office, but the proportion of office leaving is quite normal as it has the largest number of staff. Relatively, accounting and hr departments are 2 departments have the highest office-leaving rate.
When it comes to year spent in the company before leaving, it seems most people tend to leave office after 3-year working in the company. Rare people will choose to leave office after 2 years, and people tend to stay for a stable job when they spent more than 6 years in the company. Staff with 3-5 years of working experience in the company are the group of people who have a high office-leaving rate.

Assignment004

Shuwen Wang

September 30, 2017

Part A

Part B

Part C

Write-up