Scatter plots are a type of data visualization used to display values for typically two continuous variables(typically, but can be used to visualize categorical variables as well) for a set of data. The data are displayed as a collection of points, each having the value of one variable determining the position on the horizontal axis and the value of the other variable determining the position on the vertical axis. Scatter plots are used to observe relationships between variables.
Properties:
Axes: Represent the variables being compared. Typically, the independent variable or predictor is placed on the x-axis, and the dependent variable or response is placed on the y-axis.
Points: Each point on the scatter plot represents an individual data point. The position is determined by the values of the two variables.
Trend: The overall direction of the data points in the plot can suggest a relationship (e.g., positive, negative, or no correlation).
Clusters: Groupings or clusters of points may indicate that those data points have something in common.
Outliers: Points that lie significantly outside the general distribution of data may be highlighted as they could indicate anomalies or special cases.
# Load necessary librariesif (!require(ggplot2)) install.packages("ggplot2")library(ggplot2)# Generate sample dataset.seed(42) # For reproducibilityx <-rnorm(100, mean =50, sd =10) # Sample x-valuesy <- x *1.5+rnorm(100, sd =5) # Corresponding y-values with some added noise# Create a data frame from the vectorsdata <-data.frame(x, y)# Generate the scatter plotggplot(data, aes(x = x, y = y)) +geom_point(aes(color = x), size =3, alpha =0.6) +# Points with color gradient based on x-valuetheme_minimal() +# Clean themelabs(title ="Scatter Plot of X vs Y",x ="X Axis Label",y ="Y Axis Label") +scale_color_gradient(low ="blue", high ="red") +# Color gradient from blue to redtheme(plot.title =element_text(hjust =0.5)) # Center the plot title
# Load the ggplot2 packagelibrary(ggplot2)# Load the mtcars dataset (this step is actually unnecessary as mtcars is built-in)# Start with the base layer and add layers sequentiallyggplot(mtcars, aes(x = wt, y = mpg)) +# Combine the data and aesgeom_point() +# Add the data layerstat_smooth(method ="lm", aes(color ="Regression Line"), se =TRUE, linewidth =1) +# Add the statistical transformation layercoord_cartesian(xlim =c(1.5, 5.5), ylim =c(10, 35)) +# Add the coordinate system layerscale_x_continuous(breaks =seq(2, 5, by =1)) +# Add the scale layerscale_y_continuous(breaks =seq(10, 35, by =5)) +scale_color_manual(values ="red", labels ="Linear Model") +# Assign color to the regression linelabs(title ="Car Weight vs. Mileage", # Add labels and titlex ="Weight (1000 lbs)",y ="Miles per Gallon",color ="Line Type") +# Label for legendtheme_bw() +# Add the theme layertheme(plot.title =element_text(hjust =0.5), # Customize theme elementsaxis.title =element_text(face ="bold"))
Scatter plot - Layer by Layer
1. Creating data and aesthetics Layer.
library(ggplot2)ggplot(mtcars, aes(x = wt, y = mpg))
2. Adding Geometric layer(geom_point)
ggplot(mtcars, aes(x = wt, y = mpg)) +# Combine the data and aesgeom_point() # Add the data layer
3. Adding Statistical Layer - Regression Line
ggplot(mtcars, aes(x = wt, y = mpg)) +# Combine the data and aesgeom_point() +# Add the data layerstat_smooth(method ="lm", aes(color ="Regression Line"), se =TRUE, linewidth =1) # Add the statistical transformation layer
4. Adding the Co-ordinate Layer
ggplot(mtcars, aes(x = wt, y = mpg)) +# Combine the data and aesgeom_point() +# Add the data layerstat_smooth(method ="lm", aes(color ="Regression Line"), se =TRUE, linewidth =1) +# Add the statistical transformation layercoord_cartesian(xlim =c(1.5, 5.5), ylim =c(10, 35)) # Add the coordinate system layer
5. Adding the scale layer
ggplot(mtcars, aes(x = wt, y = mpg)) +# Combine the data and aesgeom_point() +# Add the data layerstat_smooth(method ="lm", aes(color ="Regression Line"), se =TRUE, linewidth =1) +# Add the statistical transformation layercoord_cartesian(xlim =c(1.5, 5.5), ylim =c(10, 35)) +# Add the coordinate system layerscale_x_continuous(breaks =seq(2, 5, by =1)) +# Add the scale layerscale_y_continuous(breaks =seq(10, 35, by =2))
6. Adding color to Regression Line
ggplot(mtcars, aes(x = wt, y = mpg)) +# Combine the data and aesgeom_point() +# Add the data layerstat_smooth(method ="lm", aes(color ="Regression Line"), se =TRUE, linewidth =1) +# Add the statistical transformation layercoord_cartesian(xlim =c(1, 6), ylim =c(5, 35)) +# Add the coordinate system layerscale_x_continuous(breaks =seq(1, 6, by =1)) +# Add the scale layerscale_y_continuous(breaks =seq(5, 35, by =2)) +scale_color_manual(values ="blue", labels ="Linear Model") # Assign color to the regression line
7. Adding labels and Title
ggplot(mtcars, aes(x = wt, y = mpg)) +# Combine the data and aesgeom_point() +# Add the data layerstat_smooth(method ="lm", aes(color ="Regression Line"), se =TRUE, linewidth =1) +# Add the statistical transformation layercoord_cartesian(xlim =c(1, 6), ylim =c(5, 35)) +# Add the coordinate system layerscale_x_continuous(breaks =seq(1, 6, by =1)) +# Add the scale layerscale_y_continuous(breaks =seq(5, 35, by =2)) +scale_color_manual(values ="blue", labels ="Linear Model") +# Assign color to the regression linelabs(title ="Car Weight vs. Mileage", # Add labels and titlex ="Weight (1000 lbs)",y ="Miles per Gallon",color ="Line Type") # Label for legend
8. Adding Themes
ggplot(mtcars, aes(x = wt, y = mpg)) +# Combine the data and aesgeom_point() +# Add the data layerstat_smooth(method ="lm", aes(color ="Regression Line"), se =TRUE, linewidth =1) +# Add the statistical transformation layercoord_cartesian(xlim =c(1, 6), ylim =c(5, 35)) +# Add the coordinate system layerscale_x_continuous(breaks =seq(1, 6, by =1)) +# Add the scale layerscale_y_continuous(breaks =seq(5, 35, by =2)) +scale_color_manual(values ="blue", labels ="Linear Model") +# Assign color to the regression linelabs(title ="Car Weight vs. Mileage", # Add labels and titlex ="Weight (1000 lbs)",y ="Miles per Gallon",color ="Line Type") +# Label for legendtheme_bw() +# Add the theme layertheme(plot.title =element_text(hjust =0.5), # Customize theme elementsaxis.title =element_text(face ="bold"))
