Practical Data Analysis Cookbook

Predicting subscribers with random tree forests

Random forests belong to a family of ensemble models. The ensemble models work on a premise that two brains are better than one; they combine the predictions of many weaker models (decision trees) to come up with a prediction that reflects a mode among these weaker models. For more, check https://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm.

Getting ready

To execute this recipe, you will need pandas and scikit-learn. No other prerequisites are required.

How to do it…

As in previous examples, Scikit provides an easy way of building a random forest classifier (the classification_randomForest.py file):

import sklearn.ensemble as en @hlp.timeit def fitRandomForest(data): ''' Build a random forest ...