""" Use entirety of provided X, Y to predict
Default Arguments
Xtrain -- Training data
Ytrain -- Training prediction
Named Arguments
--
Returns
classifier -- a tree fitted to Xtrain and Ytrain
"""
classifier = KNeighborsClassifier(125)
classifier.fit(Xtrain, Ytrain)
return classifier
if __name__ == "__main__":
# Let's take our training data and train a decision tree
# on a subset. Scikit-learn provides a good module for cross-
# validation.
if len(sys.argv) < 2:
print "Usage: $ python decision-tree.py /path/to/data/file/"
else:
training = sys.argv[1]
X,Y,n,f = load_data(training)
Xt, Xv, Yt, Yv = shuffle_split(X,Y)
Classifier = train(Xt, Yt)
print "KNN Accuracy"
suite(Yv, Classifier.predict(Xv))
import logistic_regression
from util import write_test_prediction, load_validation_data, shuffle_split
from metrics import acc
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)
def classify(Xtrain, Ytrain):
""" Use entirety of provided X, Y to predict
Arguments
Xtrain -- Training data
Ytrain -- Training prediction
Returns
ready_tree -- a tree fitted to Xtrain and Ytrain
"""
ready_tree = tree.DecisionTreeClassifier()
ready_tree.fit(Xtrain, Ytrain)
return ready_tree
if __name__ == "__main__":
# Let's take our training data and train a decision tree
# on a subset. Scikit-learn provides a good module for cross-
# validation.
if len(sys.argv) < 2:
print "Usage: $ python decision-tree.py /path/to/data/file/"
else:
training = sys.argv[1]
X, Y, n, f = load_data(training)
Xt, Xv, Yt, Yv = shuffle_split(X, Y)
tree = classify(Xt, Yt)
print "Decision Tree Accuracy:", acc(Yv, tree.predict(Xv)), "%"
import logistic_regression
from util import write_test_prediction, load_validation_data, shuffle_split
from metrics import acc
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)
