Using Scatter Plots

Hello, and welcome to this lesson on creating a scatter plot to visualize the relationship between the carat and price of diamonds using the popular diamonds dataset in Seaborn. Scatter plots are a fundamental part of exploratory data analysis (EDA) because they allow us to identify potential correlations and patterns between two continuous variables. By the end of this lesson, you will understand how to create and customize scatter plots for better data insights.

A scatter plot is a type of data visualization that displays values for two variables in a two-dimensional space. Each point on the scatter plot represents an observation, making it an excellent tool for visualizing relationships and identifying trends, clusters, or outliers in the data.

In our case, we will use a scatter plot to explore the relationship between the carat (size) of a diamond and its price. This will help us understand how these two variables are correlated and whether carat size significantly influences diamond pricing.

Once the dataset is loaded, we can proceed to create a scatter plot. We'll use the scatterplot function from the Seaborn library.

Here is the basic code to create a scatter plot:

import seaborn as sns
import matplotlib.pyplot as plt

# Load the diamonds dataset
diamonds = sns.load_dataset('diamonds')

# Filter out any entries with missing values
diamonds = diamonds.dropna()

# Basic Scatter plot of carat vs price
plt.figure(figsize=(10,6))
sns.scatterplot(x='carat', y='price', data=diamonds)
plt.title('Scatter Plot of Carat vs. Price')
plt.xlabel('Carat')
plt.ylabel('Price')
plt.show()

The output of the above code will be:

This plot visually indicates a positive correlation between the carat size of a diamond and its price, illustrating that, generally, larger diamonds tend to be more expensive.

To make the scatter plot more effective, we can enhance it by changing the size of the figure, adding transparency to the points, and customizing colors.

Let's update our plot for better visualization:

import seaborn as sns
import matplotlib.pyplot as plt

# Load the diamonds dataset
diamonds = sns.load_dataset('diamonds')

# Filter out any entries with missing values
diamonds = diamonds.dropna()

# Enhanced Scatter plot with added transparency
plt.figure(figsize=(10,6))
sns.scatterplot(x='carat', y='price', data=diamonds, alpha=0.6)
plt.title('Scatter Plot of Carat vs. Price')
plt.xlabel('Carat')
plt.ylabel('Price')
plt.show()

The output of the above code will be:

In this enhanced version:

• alpha=0.6 adds transparency to the points, making overlapping data points easier to see, which provides a clearer visualization of the concentration and distribution of data points.