Summary  
This chapter covers how to use seaborn’s regplot function to visualize the relationship between two variables by drawing a scatter plot and fitting a linear regression line (with optional confidence interval), with customization via parameters like fit_reg, marker, and color.

General domain of usage  
Exploratory data analysis

The `regplot` (regression plot) is used to plot data and a linear regression model fit.

It draws a scatter plot of two variables, `x` and `y`, and then fits a linear regression line (best prediction line) through them to visualize the correlation.



## Key Parameters

* **`fit_reg`**: this is the most important switch;
* `True` (default): draws the regression line and the confidence interval (the shaded area);
* `False`: draws only the scatter plot. This is useful when you want the styling of `regplot` but don't need the model;
* **`marker`**: changes the symbol of the data points (e.g., `'+'`, `'x'`, `'o'`);
* **`color`**: sets the color for both the points and the line.



## Example

Here is a regression plot showing the strong relationship between total bill and tip amount.

import seaborn as sns
import matplotlib.pyplot as plt

# Load dataset
df = sns.load_dataset('tips')

# Create a regression plot
sns.regplot(
    data=df,
    x='total_bill',
    y='tip',
    color='b',       # Blue color
    marker='x',      # Use 'x' as marker
    fit_reg=True     # Show the line
)

plt.show()

import unittest
import importlib
import sys
import pandas as pd
from unittest.mock import patch, MagicMock

# Helper function to dynamically generate test names and assertions
def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)

class TestUserCode(unittest.TestCase):

    def setUp(self):
        self.patcher_csv = patch('pandas.read_csv')
        self.mock_read_csv = self.patcher_csv.start()
        
        # Provide real data structure
        self.mock_df = pd.DataFrame({
            'total_bill': [16.99, 10.34, 21.01],
            'tip': [1.01, 1.66, 3.50]
        })
        self.mock_read_csv.return_value = self.mock_df

    def tearDown(self):
        self.patcher_csv.stop()

    # Test custom style configuration
    def test_style_configuration(self):
        with patch('seaborn.regplot'), patch('matplotlib.pyplot.show'):
            with patch('seaborn.set_style') as mock_style:
                if 'user_code' in sys.modules:
                    importlib.reload(sys.modules['user_code'])
                import user_code
            
            if not mock_style.called:
                 _dynamic_test(self, False, "", "Expected `sns.set_style()` to be called.")
                 return

            args, kwargs = mock_style.call_args
            style_name_correct = args[0] == 'darkgrid'
            
            # Check dictionary configuration
            rc_params = args[1] if len(args) > 1 else kwargs.get('rc', {})
            fig_face_correct = rc_params.get('figure.facecolor') == 'tan'
            ax_face_correct = rc_params.get('axes.facecolor') == 'cornsilk'

            _dynamic_test(
                self,
                style_name_correct and fig_face_correct and ax_face_correct,
                "The style is set to 'darkgrid' with 'tan' figure and 'cornsilk' axes.",
                "Expected `sns.set_style('darkgrid', {'figure.facecolor': 'tan', 'axes.facecolor': 'cornsilk'})`."
            )

    # Test regplot parameters
    def test_regplot_params(self):
        with patch('seaborn.regplot') as mock_reg:
            with patch('matplotlib.pyplot.show'):
                if 'user_code' in sys.modules:
                    importlib.reload(sys.modules['user_code'])
                import user_code
            
            if not mock_reg.called:
                _dynamic_test(self, False, "", "Expected `sns.regplot()` to be used.")
                return

            args, kwargs = mock_reg.call_args
            
            # Check data binding
            x_check = kwargs.get('x') == 'total_bill'
            y_check = kwargs.get('y') == 'tip'
            data_check = kwargs.get('data') is user_code.df

            # Check styling parameters
            marker_check = kwargs.get('marker') == '+'
            color_check = kwargs.get('color') == 'green'
            fit_reg_check = kwargs.get('fit_reg') is False

            _dynamic_test(
                self,
                all([x_check, y_check, data_check, marker_check, color_check, fit_reg_check]),
                "The `regplot` parameters (`marker`, `color`, `fit_reg`) are configured correctly.",
                f"Expected `marker='+'`, `color='green'`, `fit_reg=False`. Got: {kwargs}"
            )

    # Test show
    def test_show_used(self):
        with patch('seaborn.regplot'):
            with patch('matplotlib.pyplot.show') as mock_show:
                if 'user_code' in sys.modules:
                    importlib.reload(sys.modules['user_code'])
                import user_code

                _dynamic_test(
                    self,
                    mock_show.called,
                    "The `plt.show()` function is used.",
                    "Expected `plt.show()` to be used to display the plot."
                )

if __name__ == '__main__':
    unittest.main()

test_code.py

Explore the power of statistical data visualization designed to reveal patterns and relationships. Use Seaborn to create informative distribution plots, heatmaps, and categorical charts with minimal code. Learn to apply aesthetic themes and color palettes that make complex statistical data accessible and easy to interpret.

Visualizing Linear Regression

Key Parameters

Example

解答