regression

The Turi Create regression toolkit contains models for regression problems. Currently, we support linear regression and boosted trees. In addition to these models, we provide a smart interface that selects the right model based on the data. If you are unsure about which model to use, simply use create() function.

Training data must contain a column for the ‘target’ variable and one or more columns representing feature variables.

# Set up the data
>>> import turicreate as tc
>>> data =  tc.SFrame('https://static.turi.com/datasets/regression/houses.csv')

# Select the best model based on your data.
>>> model = tc.regression.create(data, target='price',
...                                  features=['bath', 'bedroom', 'size'])

# Make predictions and evaluate results.
>>> predictions = model.predict(data)
>>> results = model.evaluate(data)

creating a regression model

regression.create

Automatically create a suitable regression model based on the provided training data.

random forest

random_forest_regression.create	Create a RandomForestRegression to predict a scalar target variable using one or more features.
random_forest_regression.RandomForestRegression	Encapsulates random forest models for regression tasks.

decision tree

decision_tree_regression.create	Create a DecisionTreeRegression to predict a scalar target variable using one or more features.
decision_tree_regression.DecisionTreeRegression	The prediction is based on a collection of base learners, regression trees.

boosted trees

boosted_trees_regression.create	Create a BoostedTreesRegression to predict a scalar target variable using one or more features.
boosted_trees_regression.BoostedTreesRegression	Encapsulates gradient boosted trees for regression tasks.

linear regression

linear_regression.create	Create a LinearRegression to predict a scalar target variable as a linear function of one or more features.
linear_regression.LinearRegression	Linear regression is an approach for modeling a scalar target \(y\) as a linear function of one or more explanatory variables denoted \(X\).