R Markdown

Question: What are the long-term trends and patterns in the water level of Lake Huron from 1875 to 1972, and is there any evidence of significant changes in water levels over this period?

In this final project I will uterlize the skills i have learned over the past 3 weeks.

  1. I will do Data Exploration by reading data from a file and use the summary function to explore data from lake Huron dataset.

  2. I will use Data wrangling i will first create a subset of the original data, change the names of the columns and replace some data in one column.

  3. I will create 4 charts to display the data graphically

Conclusion: looking at the data on the charts, over the span of the 97 years water levels has fluctuate in a decreasing trend after hitting a maximum high in 1876. water levels were constantly below the median from the early 1900s to erly 1970s, hitting a all time low in 1964.

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(ggplot2) 
library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
 water_data <- read.csv('https://vincentarelbundock.github.io/Rdatasets/csv/datasets/LakeHuron.csv') 
summary(water_data) 
##        X              time          value      
##  Min.   : 1.00   Min.   :1875   Min.   :576.0  
##  1st Qu.:25.25   1st Qu.:1899   1st Qu.:578.1  
##  Median :49.50   Median :1924   Median :579.1  
##  Mean   :49.50   Mean   :1924   Mean   :579.0  
##  3rd Qu.:73.75   3rd Qu.:1948   3rd Qu.:579.9  
##  Max.   :98.00   Max.   :1972   Max.   :581.9
head(data )
##                                                                             
## 1 function (..., list = character(), package = NULL, lib.loc = NULL,        
## 2     verbose = getOption("verbose"), envir = .GlobalEnv, overwrite = TRUE) 
## 3 {                                                                         
## 4     fileExt <- function(x) {                                              
## 5         db <- grepl("\\\\.[^.]+\\\\.(gz|bz2|xz)$", x)                     
## 6         ans <- sub(".*\\\\.", "", x)
# Calculate the number of years water level was at its lowest and highest 
lowest_water_level <- min(water_data$value) 
highest_water_level <- max(water_data$value) 
  
years_lowest <- water_data[water_data$value == lowest_water_level, ]$time 
years_highest <- water_data[water_data$value == highest_water_level, ]$time 
  
num_years_lowest <- length(unique(years_lowest)) 
num_years_highest <- length(unique(years_highest)) 
  
# Print the results 
cat('Number of years water level was at its lowest:', num_years_lowest, "\n") 
## Number of years water level was at its lowest: 1
cat("Number of years water level was at its highest:", num_years_highest, "\n") 
## Number of years water level was at its highest: 1
# Plot scatter plot 
ggplot(water_data, aes(x = time, y = value)) + 
  geom_point() + 
  labs(title = "Water Level Scatter Plot", 
       x = "Year", 
       y = "Water Level") 

# Plot box plot 
ggplot(water_data, aes(x = factor(time), y = value )) + 
  geom_boxplot() + 
  labs(title = "Water Level Box Plot", 
       x = "Year", 
       y = "Water Level") 

# Plot histogram 
ggplot(water_data, aes(x = value)) + 
  geom_histogram(bins = 20, fill = "green", color = "blue") + 
  labs(title = "Water Level Histogram", 
       x = "Water Level", 
       y = "Frequency") 

# Create an interactive plot
plot <- plot_ly(water_data, x = ~time, y = ~value, type = 'scatter', mode = 'lines',
                line = list(color = 'blue')) %>%
        layout(title = "Water Level of Lake Huron (1875 - 1972)",
               xaxis = list(title = "Year"),
               yaxis = list(title = "Water Level"))

# Display the interactive plot
plot
water_level_subset <- water_data[ , c("time", "value")]                # creating a subset 
head(water_level_subset, n=5) 
##   time  value
## 1 1875 580.38
## 2 1876 581.86
## 3 1877 580.97
## 4 1878 580.80
## 5 1879 579.79
water_level_ch <- water_level_subset 
colnames(water_level_ch) <- c("Year", "Water_lvl")  
head(water_level_ch, n=5) 
##   Year Water_lvl
## 1 1875    580.38
## 2 1876    581.86
## 3 1877    580.97
## 4 1878    580.80
## 5 1879    579.79
## Replacing values in water level  column
my_modified_data <- water_level_ch %>% 
  mutate(Water_lvl = ifelse(Water_lvl >= 575.00 & Water_lvl <= 576.80, 575.96, Water_lvl)) 
  
summary(my_modified_data) 
##       Year        Water_lvl    
##  Min.   :1875   Min.   :576.0  
##  1st Qu.:1899   1st Qu.:578.1  
##  Median :1924   Median :579.1  
##  Mean   :1924   Mean   :579.0  
##  3rd Qu.:1948   3rd Qu.:579.9  
##  Max.   :1972   Max.   :581.9
lowest_water_level2 <- min(my_modified_data$Water_lvl) 
highest_water_level2 <- max(my_modified_data$Water_lvl) 
  
years_lowest2 <- my_modified_data[my_modified_data$Water_lvl == lowest_water_level2, ]$Year 
years_highest2 <- my_modified_data[my_modified_data$Water_lvl == highest_water_level2, ]$Year 
  
num_years_lowest2 <- length(unique(years_lowest2)) 
num_years_highest2 <- length(unique(years_highest2)) 
  
# Print the results 
cat('Number of years water level was at its lowest:', num_years_lowest2, "\n") 
## Number of years water level was at its lowest: 5
cat("Number of years water level was at its highest:", num_years_highest2, "\n") 
## Number of years water level was at its highest: 1
## ploting modified data on histogram
ggplot(my_modified_data, aes(x = Water_lvl)) + 
  geom_histogram(bins = 20, fill = "green", color = "blue") + 
  labs(title = "Water Level Histogram", 
       x = "Water Level", 
       y = "Frequency") 

## Reading file from my github

mygithubfile <- 'https://raw.githubusercontent.com/MRobinson112/final_assignment/main/LakeHuron.csv'
water_data <- read.csv(mygithubfile)
head(water_data )
##   X time  value
## 1 1 1875 580.38
## 2 2 1876 581.86
## 3 3 1877 580.97
## 4 4 1878 580.80
## 5 5 1879 579.79
## 6 6 1880 580.39

Including Plots

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.