TensorFlow Decision Forests
import tensorflow_decision_forests as tfdf
import pandas as pd
# Load a dataset in a Pandas dataframe.
train_df = pd.read_csv("project/train.csv")
test_df = pd.read_csv("project/test.csv")
# Convert the dataset into a TensorFlow dataset.
train_ds = tfdf.keras.pd_dataframe_to_tf_dataset(train_df, label="my_label")
test_ds = tfdf.keras.pd_dataframe_to_tf_dataset(test_df, label="my_label")
# Train a Random Forest model.
model = tfdf.keras.RandomForestModel()
model.fit(train_ds)
# Summary of the model structure.
model.summary()
# Evaluate the model.
model.evaluate(test_ds)
# Export the model to a SavedModel.
model.save("project/model")
TensorFlow Decision Forests (TF-DF) is a collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models. The library is a collection of Keras models and supports classification, regression and ranking.
TF-DF is a wrapper around the Yggdrasil Decision Forest C++ libraries. Models trained with TF-DF are compatible with Yggdrasil Decision Forests' models, and vice versa.
Unfortunately TF-DF is not yet available for Mac (#16) or Windows (#3), we are working on it.
Keywords: Decision Forests, TensorFlow, Random Forest, Gradient Boosted Trees, CART, model interpretation.
Documentation & Resources
The following resources are available:
Community
Contributing
Contributions to TensorFlow Decision Forests and Yggdrasil Decision Forests are welcome. If you want to contribute, make sure to review the developer manual.