def main():
# Enter path to higgs dataset
dataset_reader = DatasetReader("/scratch/cpillsb1/cs66/data/")
X, y, X_final, y_final, dataset = dataset_reader.load_cancer()
# uncomment for higgs
# X, y, X_final, y_final, dataset = dataset_reader.load_higgs()
skf = StratifiedKFold(y, n_folds=4, shuffle=True, random_state=42)
ii = 0
for train, test in skf:
x_train = X[train]
x_test = X[test]
y_train = y[train]
y_test = y[test]
nums = [5, 10, 30, 50]
layer = Layer(ExtraTreeClassifier, {"max_depth": 1}, x_train, y_train,
nums[ii])
predictions = layer.predictAll(x_train)
lr = Layer(LogisticRegression, {
"n_jobs": -1,
"max_iter": 1000
}, predictions, y_train, 1)
network = Network([layer, lr])
evaluate_test(network, X_final, y_final, nums[ii], dataset)
ii += 1
def main():
dataset_reader = DatasetReader("/scratch/cpillsb1/cs66/data/")
X, y, X_final, y_final, dataset = dataset_reader.load_cancer()
# uncomment for higgs
# X, y, X_final, y_final, dataset = dataset_reader.load_higgs()
skf = StratifiedKFold(y, n_folds=4, shuffle=True, random_state=42)
dtree_params = [1, 5, 30, 50]
ii = 0
best_acc = 0
for train, test in skf:
x_train = X[train]
x_test = X[test]
y_train = y[train]
y_test = y[test]
clf = DecisionTreeClassifier(max_depth=dtree_params[ii],
max_features=1.0,
random_state=42)
clf.fit(x_train, y_train)
predictions = clf.predict(x_test)
acc = 0.0
for i, prediction in enumerate(predictions):
if prediction == y_test[i]:
acc += 1
acc /= len(predictions)
if acc > best_acc:
best_classifier = clf
best_depth = dtree_params[ii]
best_acc = acc
ii += 1
evaluate_test(best_classifier, X_final, y_final, best_depth, dataset)