Plotting a regression model

Generalized Linear Models in Python

Ita Cirovic Donev

Data Science Consultant

Import libraries

import seaborn as sns
import matplotlib.pyplot as plt

Crab model 'sat ~ width' is saved as model

Plot data points

# Adjust figure size
plt.subplots(figsize = (8, 5))

# Plot data points
sns.regplot('width', 'sat', 
            data = crab,
            fit_reg = False)

Scatterplot of width and number of satellites from the crab dataset.

Add jitter

sns.regplot('width', 'sat', 
            data = crab,
            fit_reg = False,
            y_jitter = 0.3)

Scatterplot with added jitter of width and number of satellites from the crab dataset.

Add linear fit

sns.regplot('width', 'sat', 
            data = crab,
            y_jitter = 0.3,
            fit_reg = True,
            line_kws = {'color':'green', 
                        'label':'LM fit'})

Linear fit with confidence intervals and the scatterplot of width and number of satellites from the crab dataset.

Add Poisson GLM estimated values

crab['fit_values'] = model.fittedvalues

sns.scatterplot('width','fit_values', 
                data = crab,
                color = 'red', 
                label = 'Poisson')

Linear and Poisson fit and the scatterplot of width and number of satellites from the crab dataset.

Predictions

Poisson model fit overlaid on the scatterplot of width and number of satellites

Predictions

new_data = pd.DataFrame({'width':[24, 28, 32]})
model.predict(new_data)

0    1.881981

Reading off predicted values of the values of width at 24cm given fitted Poisson regression model.

Predictions

new_data = pd.DataFrame({'width':[24, 28, 32]})
model.predict(new_data)

0    1.881981
1    3.627360

Reading off predicted values of the values of width at 28cm given fitted Poisson regression model.

Predictions

new_data = pd.DataFrame({'width':[24, 28, 32]})
model.predict(new_data)

0    1.881981
1    3.627360
2    6.991433

Reading off predicted values of the values of width at 32cm given fitted Poisson regression model.

Let's practice!

Generalized Linear Models in Python