import sys
from sklearn.cross_validation import cross_val_score
from util import load_validation_data
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import GradientBoostingClassifier, AdaBoostClassifier, ExtraTreesClassifier, RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import LogisticRegression, SGDClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import LinearSVC
if __name__ == "__main__":
# Get training data
Xt, Yt, Xunused = load_validation_data()
# Cross validation, 5-fold
cvf = 5
# Initialize classifiers
classifiers = {
"Naive Bayes" : GaussianNB(),
"Gradient Boost" : GradientBoostingClassifier(),
"Adaboost" : AdaBoostClassifier(DecisionTreeClassifier(max_depth=1)),
"Decision Tree" : DecisionTreeClassifier(),
"Extra Random Trees" : ExtraTreesClassifier(n_estimators=300),
"Logistic Regression" : LogisticRegression(),
"K-Nearest-Neighbors" : KNeighborsClassifier(),
"SGD" : SGDClassifier(),
"SVM" : LinearSVC(),
verbose=True,
weightdecay=0.01)
trainer.trainUntilConvergence()
#trainer.trainEpochs(5)
print "trained"
#trainer.trainEpochs(5)
# Return a functor that wraps calling predict
return NeuralNetworkClassifier(trainer)
if __name__ == "__main__":
# First obtain our training and testing data
# Training has 50K samples, Testing 100K
Xt, Yt, Xv = load_validation_data()
# Run Neural Network over training data
classifier = classify(Xt, Yt)
# Prepare validation data and predict
tstdata = ClassificationDataSet(Xv.shape[1], 1, nb_classes=2)
tstdata.setField('input', Xv)
tstdata._convertToOneOfMany() # one output neuron per class
predictions = classifier.predict(tstdata)
# Write prediction to file
write_test_prediction("out_nn.txt", np.array(majority))
# build neural net and train it
net = buildNetwork(trndata.indim, n_hidden, trndata.outdim, outclass=SoftmaxLayer)
trainer = BackpropTrainer(net, dataset=trndata, momentum=0.1, verbose=True, weightdecay=0.01)
trainer.trainUntilConvergence()
#trainer.trainEpochs(5)
print "trained"
#trainer.trainEpochs(5)
# Return a functor that wraps calling predict
return NeuralNetworkClassifier(trainer)
if __name__ == "__main__":
# First obtain our training and testing data
# Training has 50K samples, Testing 100K
Xt, Yt, Xv = load_validation_data()
# Run Neural Network over training data
classifier = classify(Xt, Yt)
# Prepare validation data and predict
tstdata = ClassificationDataSet(Xv.shape[1], 1, nb_classes=2)
tstdata.setField('input', Xv)
tstdata._convertToOneOfMany() # one output neuron per class
predictions = classifier.predict(tstdata)
# Write prediction to file
write_test_prediction("out_nn.txt", np.array(majority))
"""
gbc = GradientBoostingClassifier(verbose=1)
parameters = {'max_depth' : range(3,11),'n_estimators' : [400,500]}
classifier = GridSearchCV(gbc, parameters, scoring=metric)
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.
Xt, Xv, Yt, Yv = get_split_training_dataset()
Classifier = train(Xt, Yt)
print "Gradient Boost Classifier"
suite(Yv, Classifier.predict(Xv))
# smaller feature set
Xtimp, features = fclassify.get_important_data_features(Xt, Yt)
Xvimp = fclassify.compress_data_to_important_features(Xv, features)
ClassifierImp = train(Xtimp,Yt)
print "Gradient Boosts Classiifer, 25 important features"
suite(Yv, ClassifierImp.predict(Xvimp))
# save predictions on test data
X, Y, validation_data = load_validation_data()
predictions = Classifier.predict(validation_data)
filename = 'gradient_boost_predictions.txt'
write_test_prediction(filename, np.array(predictions))
predictions = classifier.predict(Xv)
print "Neural Net Test Accuracy:", acc(Yv, predictions), "%"
if __name__ == "__main__":
if len(sys.argv) < 2:
training = '../data/raw/phy_train.dat'
print "Usage: $ python neural_network.py /path/to/data/file/"
print "Using default data file:", training
else:
training = sys.argv[1]
impute_data = False
# load data from file, imputing data and/or removing some features if requested,
# then shuffle and split into test and validation
X, Y, test_data = load_validation_data()
if impute_data:
X = remove_features_missing_data(X)
test_data = remove_features_missing_data(test_data)
Xt, Xv, Yt, Yv = shuffle_split(X, Y)
# get the top features, running in parallel
children = []
for n_features in [20]:
'''for n_features in [23, 21, 19, 17]:
children.append(os.fork())
if children[-1]:
continue'''
X, features = get_important_data_features(X,
Y,
max_features=n_features)
print "Neural Net Train Accuracy:",acc(Yt, predictions),"%"
predictions = classifier.predict(Xv)
print "Neural Net Test Accuracy:",acc(Yv, predictions),"%"
if __name__ == "__main__":
if len(sys.argv) < 2:
training = '../data/raw/phy_train.dat'
print "Usage: $ python neural_network.py /path/to/data/file/"
print "Using default data file:", training
else:
training = sys.argv[1]
impute_data = False
# load data from file, imputing data and/or removing some features if requested,
# then shuffle and split into test and validation
X, Y, test_data = load_validation_data()
if impute_data:
X = remove_features_missing_data(X)
test_data = remove_features_missing_data(test_data)
Xt, Xv, Yt, Yv = shuffle_split(X,Y)
# get the top features, running in parallel
children = []
for n_features in [20]:
'''for n_features in [23, 21, 19, 17]:
children.append(os.fork())
if children[-1]:
continue'''
X, features = get_important_data_features(X, Y, max_features=n_features)
print X.shape
# Do it for test data too...
