Distribution plots (histplot, kdeplot) in Data Analysis Python - Mini Project: Build & Apply

Distribution plots (histplot, kdeplot)

📖 Scenario: You work as a data analyst for a small bakery. You have collected data on the number of cookies sold each day for a week. You want to understand how the sales are distributed to help plan baking quantities.

🎯 Goal: Build a simple Python program that creates a list of daily cookie sales, sets a threshold for high sales, uses distribution plots (histogram and KDE) to visualize the sales data, and prints the sales data.

📋 What You'll Learn

Create a list of daily cookie sales with exact values

Create a threshold variable for high sales

Use seaborn to plot a histogram and KDE plot of the sales data

Print the sales data list

💡 Why This Matters

🌍 Real World

Distribution plots help businesses understand how their data points, like daily sales, are spread out. This helps in planning and decision making.

💼 Career

Data analysts and scientists use distribution plots to explore data patterns and communicate insights clearly to teams and managers.

1

Create the daily sales data list

Create a list called daily_sales with these exact values: 12, 15, 14, 10, 18, 20, 16 representing cookies sold each day.

Data Analysis Python

# Create the daily_sales list with the exact values
# Your code here

Hint

Use square brackets to create a list and separate numbers with commas.

2

Set a threshold for high sales

Create a variable called high_sales_threshold and set it to 15 to mark days with high cookie sales.

Data Analysis Python

daily_sales = [12, 15, 14, 10, 18, 20, 16]
# Create high_sales_threshold variable and set it to 15
# Your code here

Hint

Just assign the number 15 to the variable named high_sales_threshold.

3

Plot the distribution of daily sales

Import seaborn as sns and matplotlib.pyplot as plt. Use sns.histplot to plot a histogram of daily_sales with kde=True to add a smooth curve. Then call plt.show() to display the plot.

Data Analysis Python

daily_sales = [12, 15, 14, 10, 18, 20, 16]
high_sales_threshold = 15
# Import seaborn as sns and matplotlib.pyplot as plt
# Plot histogram with KDE of daily_sales
# Show the plot
# Your code here

Hint

Use sns.histplot with kde=True to add the smooth curve on the histogram.

4

Print the daily sales data

Write a print statement to display the daily_sales list.

Data Analysis Python

import seaborn as sns
import matplotlib.pyplot as plt

daily_sales = [12, 15, 14, 10, 18, 20, 16]
high_sales_threshold = 15

sns.histplot(daily_sales, kde=True)
plt.show()
# Print the daily_sales list
# Your code here

Hint

Use print(daily_sales) to show the list.

Practice

1. What does the histplot function primarily display in a distribution plot?

easy

A. Bars showing the frequency of data values in bins

B. A smooth curve estimating the data density

C. Scatter points representing individual data values

D. A line chart showing data over time

Solution

1. Step 1: Understand the purpose of histplot

   The histplot function creates a histogram, which groups data into bins and shows how many values fall into each bin using bars.

2. Step 2: Differentiate from kdeplot

   Unlike kdeplot which draws a smooth curve, histplot uses bars to represent frequency counts.

3. Final Answer:

   Bars showing the frequency of data values in bins -> Option A

4. Quick Check:

   histplot = bars frequency [OK]

Hint: Histplot uses bars for counts, kdeplot uses smooth curves [OK]

Common Mistakes:

• Confusing histplot with kdeplot
• Thinking histplot shows individual points
• Assuming histplot draws lines instead of bars

2. Which of the following is the correct way to import seaborn and plot a histogram of a list data using histplot?

easy

A. import seaborn as sb
sb.kdeplot(data)

B. import seaborn
seaborn.plot_hist(data)

C. from seaborn import histplot
kdeplot(data)

D. import seaborn as sns
sns.histplot(data)

Solution

1. Step 1: Check the standard import for seaborn

   The common alias for seaborn is sns, so import seaborn as sns is correct.

2. Step 2: Verify the function call for histogram

   The function to plot a histogram is histplot, so sns.histplot(data) is the correct syntax.

3. Final Answer:

   import seaborn as sns sns.histplot(data) -> Option D

4. Quick Check:

   Standard import + histplot call = import seaborn as sns sns.histplot(data) [OK]

Hint: Use 'import seaborn as sns' and call sns.histplot(data) [OK]

Common Mistakes:

• Using wrong alias like sb
• Calling non-existent seaborn.plot_hist
• Importing histplot directly from seaborn

3. What will the following code output?

import seaborn as sns
import matplotlib.pyplot as plt
data = [1, 2, 2, 3, 3, 3, 4, 4, 4, 4]
sns.kdeplot(data)
plt.show()

medium

A. A smooth curve estimating the data density

B. A bar chart showing counts of each number

C. A scatter plot of the data points

D. An error because kdeplot needs a DataFrame

Solution

1. Step 1: Understand what sns.kdeplot does

   The kdeplot function draws a smooth curve estimating the probability density of the data.

2. Step 2: Check the input data type

   The input is a list of numbers, which is valid for kdeplot, so no error occurs.

3. Final Answer:

   A smooth curve estimating the data density -> Option A

4. Quick Check:

   kdeplot = smooth density curve [OK]

Hint: kdeplot draws smooth curves, not bars or points [OK]

Common Mistakes:

• Expecting bars instead of curve
• Thinking kdeplot requires DataFrame input
• Confusing kdeplot with scatter plot

4. The following code does not display a plot. What is the most likely cause?

import seaborn as sns
data = [1, 2, 3, 4, 5]
sns.histplot(data, kde=True)

medium

A. Data must be a DataFrame, not a list

B. The parameter 'kde' is not valid for histplot

C. Missing import of matplotlib.pyplot to show the plot

D. histplot cannot plot numeric data

Solution

1. Step 1: Check if plot display is handled

   The code calls sns.histplot but does not call plt.show() to display the plot.

2. Step 2: Identify missing import and display call

   Without importing matplotlib.pyplot and calling plt.show(), the plot won't appear, which may be mistaken as an error.

3. Final Answer:

   Missing import of matplotlib.pyplot to show the plot -> Option C

4. Quick Check:

   Need plt.show() to display plot [OK]

Hint: Always import matplotlib.pyplot and call plt.show() to display plots [OK]

Common Mistakes:

• Assuming 'kde' param is invalid for histplot
• Thinking list data causes error
• Believing histplot can't plot numeric data

5. You have two groups of data: group1 = [1,2,2,3,4] and group2 = [3,4,4,5,6]. You want to compare their distributions on the same plot using seaborn. Which code correctly overlays their KDE plots with different colors?

hard

A. import seaborn as sns
import matplotlib.pyplot as plt
data = group1 + group2
labels = ['group1', 'group2']
sns.kdeplot(data, hue=labels)
plt.show()

B. import seaborn as sns
import matplotlib.pyplot as plt
sns.kdeplot(group1, color='blue')
sns.kdeplot(group2, color='red')
plt.show()

C. import seaborn as sns
sns.histplot(group1, color='blue')
sns.histplot(group2, color='red')

D. import seaborn as sns
sns.kdeplot(group1)
sns.kdeplot(group2)
plt.show()

Solution

1. Step 1: Understand how to overlay KDE plots

   Calling sns.kdeplot twice with different data and colors overlays the KDE curves on the same plot.

2. Step 2: Check for plot display

   Importing matplotlib.pyplot and calling plt.show() ensures the plot appears.

3. Step 3: Evaluate other options

   import seaborn as sns
   import matplotlib.pyplot as plt
   data = group1 + group2
   labels = ['group1']*len(group1) + ['group2']*len(group2)
   sns.kdeplot(data, hue=labels)
   plt.show()

   uses hue incorrectly on a list without DataFrame;

   import seaborn as sns
   sns.histplot(group1, color='blue')
   sns.histplot(group2, color='red')

   uses histplot, not KDE;

   import seaborn as sns
   sns.kdeplot(group1)
   sns.kdeplot(group2)
   plt.show()

   misses import matplotlib.pyplot as plt.

4. Final Answer:

   import seaborn as sns import matplotlib.pyplot as plt sns.kdeplot(group1, color='blue') sns.kdeplot(group2, color='red') plt.show() -> Option B

5. Quick Check:

   Overlay KDE with sns.kdeplot twice + plt.show() [OK]

Hint: Call sns.kdeplot twice with colors, then plt.show() [OK]

Common Mistakes:

• Using hue on plain lists without DataFrame
• Forgetting plt.show() to display plot
• Mixing histplot with kdeplot for smooth curves