#!/usr/bin/python2
# This is an optimized version of gradient boost.
import sys
import gradient_boost
import feature_selection_trees as fclassify
from util import write_test_prediction, load_validation_data
from metrics import acc
import numpy as np
if __name__ == "__main__":
# First obtain our training and testing data
Xt, Yt, Xv = load_validation_data()
# Train a gradietn boost classifier on it.
gboost = gradient_boost.train(Xt, Yt)
Yhat = gboost.predict(Xv)
# Final accuracy
write_test_prediction("gboost_optimal_2.txt", Yhat)
import numpy as np
cross_validate = True
if __name__ == "__main__":
# First obtain our training and testing data
Xt, Yt, Xv = load_validation_data()
if cross_validate:
# for cross-validation
Xt1, Xt2, Yt1, Yt2 = shuffle_split(Xt, Yt)
classifiers = [
adaboost.train(Xt1, Yt1),
extra_randomized_trees.train(Xt1, Yt1),
gradient_boost.train(Xt1, Yt1),
random_forest.train(Xt1, Yt1),
logistic_regression.train(Xt1, Yt1),
]
# Train another classifier on the ensembles output training predictions
# for each sample in the training data
training_predictions = np.mat(
[[c.predict(sample)[0] for c in classifiers] for sample in Xt1])
meta_classifier = logistic_regression.train(training_predictions, Yt1)
# Check results on training data
print "Accuracy for individual classifiers:", [
acc(Yt2, c.predict(Xt2)) for c in classifiers
]
import numpy as np
cross_validate = True
if __name__ == "__main__":
# First obtain our training and testing data
Xt, Yt, Xv = load_validation_data()
if cross_validate:
# for cross-validation
Xt1, Xt2, Yt1, Yt2 = shuffle_split(Xt, Yt)
classifiers = [
adaboost.train(Xt1, Yt1),
extra_randomized_trees.train(Xt1, Yt1),
gradient_boost.train(Xt1, Yt1),
random_forest.train(Xt1, Yt1),
logistic_regression.train(Xt1, Yt1),
]
# Train another classifier on the ensembles output training predictions
# for each sample in the training data
training_predictions = np.mat([[c.predict(sample)[0] for c in classifiers] for sample in Xt1])
meta_classifier = logistic_regression.train(training_predictions, Yt1)
# Check results on training data
print "Accuracy for individual classifiers:", [acc(Yt2, c.predict(Xt2)) for c in classifiers]
predictions = np.mat([c.predict(Xt2) for c in classifiers]).transpose()
print "Accuracy for ensemble classifier:", acc(Yt2, meta_classifier.predict(predictions))
