from util import get_split_training_dataset
from metrics import suite
from sklearn.naive_bayes import GaussianNB
def train(Xtrain, Ytrain):
""" Use entirety of provided X, Y to predict
Default Arguments
Xtrain -- Training data
Ytrain -- Training prediction
Named Arguments
C -- regularization parameter
Returns
classifier -- a tree fitted to Xtrain and Ytrain
"""
classifier = GaussianNB()
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 "Naive Bayes Classifier"
suite(Yv, Classifier.predict(Xv))
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.grid_search import GridSearchCV
def train(Xtrain, Ytrain, n=250, d=None):
""" Use entirety of provided X, Y to train random forest
Arguments
Xtrain -- Training data
Ytrain -- Training prediction
Returns
classifier
"""
classifier = ExtraTreesClassifier(n_estimators=n,
max_depth=d,
min_samples_split=1,
random_state=0,
max_features=36)
classifier.fit(Xtrain, Ytrain)
return classifier
if __name__ == "__main__":
# Let's take our training data and train a random forest
# on a subset.
Xt, Xv, Yt, Yv = get_split_training_dataset()
Classifier = train(Xt, Yt)
print "Extra Random Trees Ensemble Classifier"
suite(Yv, Classifier.predict(Xv))
C -- regularization parameter
Returns
classifier -- a tree fitted to Xtrain and Ytrain
"""
# Initialize classifier parameters for adaboost
# For adaboost, this means the number of estimators for now
ada = AdaBoostClassifier(DecisionTreeClassifier(max_depth=1))
parameters = {'n_estimators': [150]}
# Classify over grid of parameters
classifier = GridSearchCV(ada, parameters)
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 "Adaboost Classifier"
suite(Yv, Classifier.predict(Xv))
# smaller feature set
Xtimp, features = fclassify.get_important_data_features(Xt, Yt, max_features=25)
Xvimp = fclassify.compress_data_to_important_features(Xv, features)
ClassifierImp = train(Xtimp,Yt)
print "Adaboosts Classiifer, 25 important features"
suite(Yv, ClassifierImp.predict(Xvimp))
def suite():
return unittest.TestSuite([db.suite(),
metrics.suite(),
analysis.suite(),
])
classifier -- A random forest of n estimators, fitted to Xtrain and Ytrain
"""
if grid == True:
forest = RandomForestClassifier(max_depth=None, random_state=0, min_samples_split=1,max_features=38)
parameters = {
'n_estimators': [200,250,300],
}
# Classify over grid of parameters
classifier = GridSearchCV(forest, parameters)
else:
classifier = RandomForestClassifier(n_estimators=n)
classifier.fit(Xtrain, Ytrain)
return classifier
if __name__ == "__main__":
# Let's take our training data and train a random forest
# on a subset.
Xt, Xv, Yt, Yv = get_split_training_dataset()
print "Random Forest Classifier"
Classifier = train(Xt, Yt)
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 "Forest Classiifer, ~25 important features"
suite(Yv, ClassifierImp.predict(Xvimp))
