library(readr)
library(ggplot2)
hr <- read_csv('https://raw.githubusercontent.com/aiplanethub/Datasets/refs/heads/master/HR_comma_sep.csv')
## Rows: 14999 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Department, salary
## dbl (8): satisfaction_level, last_evaluation, number_project, average_montly...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

#1 Average Monthly Hours vs Satisfavton Levels

cor.test(hr$average_montly_hours, hr$satisfaction_level)
## 
##  Pearson's product-moment correlation
## 
## data:  hr$average_montly_hours and hr$satisfaction_level
## t = -2.4556, df = 14997, p-value = 0.01408
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  -0.036040356 -0.004045605
## sample estimates:
##         cor 
## -0.02004811

-The p-value is small, but not small enough for the correlation between average monthly hours and satisifaction levels to be significant (<0.001)

-There is no correlation interpretation because it is not a significant relationship

-Satisfaction level is not affected by the number of average monthly hours worked

ggplot(hr, aes(x = average_montly_hours, y = satisfaction_level)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = "orange") +
  labs(title = "Satisfaction level is not affected by the number of average monthly hours worked",
       x = "Average Monthly Hours",
       y = "Satisfaction Level")
## `geom_smooth()` using formula = 'y ~ x'

2 - Last Evaluation vs Satisfaction Level

cor.test(hr$last_evaluation, hr$satisfaction_level)
## 
##  Pearson's product-moment correlation
## 
## data:  hr$last_evaluation and hr$satisfaction_level
## t = 12.933, df = 14997, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.08916727 0.12082195
## sample estimates:
##       cor 
## 0.1050212

- pvalue is very small (< 0.001), therefore the correlation between Last Evaluation and Satisfaction Level is significant

-The correlation is positive and very weak (0.1)

- Better last evaluation scores increase employee satisfaction levels

ggplot(hr, aes(x = last_evaluation, y = satisfaction_level)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = 'orange') +
  labs(title = "Better last evaluation scores increase employee satisfaction levels",
       x = "Last Evaluation",
       y = "Satisfaction Level")
## `geom_smooth()` using formula = 'y ~ x'

3: Number of Projects vs Average Monthly Hours

cor.test(hr$number_project, hr$average_montly_hours)
## 
##  Pearson's product-moment correlation
## 
## data:  hr$number_project and hr$average_montly_hours
## t = 56.219, df = 14997, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.4039037 0.4303411
## sample estimates:
##       cor 
## 0.4172106

- The p-value is very small (< 0.001), therefore the correlation between number of projects and average monthly hours worked is significant

- The correlation is positive and moderately strong (0.4)

- More projects typically mean employees work longer average monthly hours

ggplot(hr, aes(x = number_project, y = average_montly_hours)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = "orange") +
  labs(title = "More projects typically mean employees work longer average monthly hours",
       x = "Number of Projects",
       y = "Average Monthly Hours")
## `geom_smooth()` using formula = 'y ~ x'

- 4: Number of Projects vs Time Spent at Company

cor.test(hr$number_project, hr$time_spend_company)
## 
##  Pearson's product-moment correlation
## 
## data:  hr$number_project and hr$time_spend_company
## t = 24.579, df = 14997, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
##  0.1813532 0.2121217
## sample estimates:
##       cor 
## 0.1967859

- The p-value is very small (< 0.001), therefore the correlation between number of projects and average monthly hours worked is significant

- The correlation is positive and weak (0.2)

- Employees with fewer projects tend to stay at company slightly longer

ggplot(hr, aes(x = number_project, y = time_spend_company)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE, color = "orange") +
  labs(title = "Employees with fewer projects tend to stay at company slightly longer",
       x = "Number of Projects",
       y = "Time Spend at Company")
## `geom_smooth()` using formula = 'y ~ x'