Welcome to amorf’s documentation!

amorf is a multi-output regression framework in Python. It helps you to get started with multi-output regression fast and allows you to increase your performance by using customized models that suit your needs.

Installation

Use the package manager pip to install amorf.

pip install amorf

Getting Started

import amorf.neuralNetRegression as nnr
from amorf.metrics import average_relative_root_mean_squared_error as arrmse

# for data generation
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split

X, y = make_regression(n_samples=10000, n_features=12, n_targets=3, noise=0.1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

regressor = nnr.NeuralNetRegressor(patience=5, training_limit=None) #initialize neural net regressor
regressor.fit(X_train, y_train) #fit regressor to training data
prediction = regressor.predict(X_test) #predict test data
print(arrmse(prediction, y_test)) #print error

Contents:

Indices and tables