R Markdown
#Load the ChickWeight dataset
data(ChickWeight)
summary(ChickWeight)
## weight Time Chick Diet
## Min. : 35.0 Min. : 0.00 13 : 12 1:220
## 1st Qu.: 63.0 1st Qu.: 4.00 9 : 12 2:120
## Median :103.0 Median :10.00 20 : 12 3:120
## Mean :121.8 Mean :10.72 10 : 12 4:118
## 3rd Qu.:163.8 3rd Qu.:16.00 17 : 12
## Max. :373.0 Max. :21.00 19 : 12
## (Other):506
library(summarytools)
# Select 10 columns from the dataset
selected_column1 <- c("weight", "Time")
selected_column2 <- c("Chick", "Diet")
# Create a subset of the dataset with the selected columns
subset_data1 <- ChickWeight[, selected_column1]
subset_data2 <- ChickWeight[, selected_column2]
# Generate summaries for the selected columns
summary_data1 <- summary(subset_data1)
print(summary_data1)
## weight Time
## Min. : 35.0 Min. : 0.00
## 1st Qu.: 63.0 1st Qu.: 4.00
## Median :103.0 Median :10.00
## Mean :121.8 Mean :10.72
## 3rd Qu.:163.8 3rd Qu.:16.00
## Max. :373.0 Max. :21.00
summary_data2 <- summary(subset_data2)
print(summary_data2)
## Chick Diet
## 13 : 12 1:220
## 9 : 12 2:120
## 20 : 12 3:120
## 10 : 12 4:118
## 17 : 12
## 19 : 12
## (Other):506
# Calculate the average weight by Time and Diet
agg_data <- aggregate(weight ~ Time + Diet, data = ChickWeight, FUN = mean)
print(agg_data)
## Time Diet weight
## 1 0 1 41.40000
## 2 2 1 47.25000
## 3 4 1 56.47368
## 4 6 1 66.78947
## 5 8 1 79.68421
## 6 10 1 93.05263
## 7 12 1 108.52632
## 8 14 1 123.38889
## 9 16 1 144.64706
## 10 18 1 158.94118
## 11 20 1 170.41176
## 12 21 1 177.75000
## 13 0 2 40.70000
## 14 2 2 49.40000
## 15 4 2 59.80000
## 16 6 2 75.40000
## 17 8 2 91.70000
## 18 10 2 108.50000
## 19 12 2 131.30000
## 20 14 2 141.90000
## 21 16 2 164.70000
## 22 18 2 187.70000
## 23 20 2 205.60000
## 24 21 2 214.70000
## 25 0 3 40.80000
## 26 2 3 50.40000
## 27 4 3 62.20000
## 28 6 3 77.90000
## 29 8 3 98.40000
## 30 10 3 117.10000
## 31 12 3 144.40000
## 32 14 3 164.50000
## 33 16 3 197.40000
## 34 18 3 233.10000
## 35 20 3 258.90000
## 36 21 3 270.30000
## 37 0 4 41.00000
## 38 2 4 51.80000
## 39 4 4 64.50000
## 40 6 4 83.90000
## 41 8 4 105.60000
## 42 10 4 126.00000
## 43 12 4 151.40000
## 44 14 4 161.80000
## 45 16 4 182.00000
## 46 18 4 202.90000
## 47 20 4 233.88889
## 48 21 4 238.55556
#visualsummary
library(ggplot2)
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
#Histogram of Weight
ggplot(ChickWeight, aes(x = weight)) +
geom_histogram(fill = "lightblue", color = "black") +
labs(title = "Distribution of Chick Weight", x = "Weight") +
theme_minimal()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
#Weight Over Time using line plot
ggplot(ChickWeight, aes(x = Time, y = weight, color = Diet)) +
geom_line() +
labs(title = "weight over time by diet", x = "time in days", y = "weight") +
theme_minimal()
#Weight vs Diet - Boxplot
ggplot(ChickWeight, aes(x = as.factor(Diet), y = weight, fill = as.factor(Diet))) +
geom_boxplot() +
labs(title = "weight distribution vs diet", x = 'diet', y = "weight") +
theme_minimal()
#Scatterplot of Weight vs. Time
ggplot(ChickWeight, aes(x = Time, y = weight, color = Diet)) +
geom_point() +
labs(title = "“Scatterplot of Weight vs. Time by Diet”", x = "“Time (days)”", y = "“Weight”") +
theme_minimal()
