Plot individual and voting regression predictions

A voting regressor is an ensemble meta-estimator that fits several base regressors, each on the whole dataset. Then it averages the individual predictions to form a final prediction. We will use three different regressors to predict the data: GradientBoostingRegressor, RandomForestRegressor, and LinearRegression). Then the above 3 regressors will be used for the VotingRegressor.

Finally, we will plot the predictions made by all models for comparison.

We will work with the diabetes dataset which consists of 10 features collected from a cohort of diabetes patients. The target is a quantitative measure of disease progression one year after baseline.

import matplotlib.pyplot as plt

from sklearn.datasets import load_diabetes
from sklearn.ensemble import (
from sklearn.linear_model import LinearRegression

Training classifiers

First, we will load the diabetes dataset and initiate a gradient boosting regressor, a random forest regressor and a linear regression. Next, we will use the 3 regressors to build the voting regressor:

X, y = load_diabetes(return_X_y=True)

# Train classifiers
reg1 = GradientBoostingRegressor(random_state=1)
reg2 = RandomForestRegressor(random_state=1)
reg3 = LinearRegression(), y), y), y)

ereg = VotingRegressor([("gb", reg1), ("rf", reg2), ("lr", reg3)]), y)
VotingRegressor(estimators=[('gb', GradientBoostingRegressor(random_state=1)),
                            ('rf', RandomForestRegressor(random_state=1)),
                            ('lr', LinearRegression())])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with

Making predictions

Now we will use each of the regressors to make the 20 first predictions.

xt = X[:20]

pred1 = reg1.predict(xt)
pred2 = reg2.predict(xt)
pred3 = reg3.predict(xt)
pred4 = ereg.predict(xt)

Plot the results

Finally, we will visualize the 20 predictions. The red stars show the average prediction made by VotingRegressor.

plt.plot(pred1, "gd", label="GradientBoostingRegressor")
plt.plot(pred2, "b^", label="RandomForestRegressor")
plt.plot(pred3, "ys", label="LinearRegression")
plt.plot(pred4, "r*", ms=10, label="VotingRegressor")

plt.tick_params(axis="x", which="both", bottom=False, top=False, labelbottom=False)
plt.xlabel("training samples")
plt.title("Regressor predictions and their average")
Regressor predictions and their average

Total running time of the script: (0 minutes 0.930 seconds)

Gallery generated by Sphinx-Gallery