def main():
dataset_reader = DatasetReader("/scratch/cpillsb1/cs66/data/")
# uncomment for cancer
# X, y, X_final, y_final, dataset = dataset_reader.load_cancer()
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(RandomForestClassifier, {
"max_depth": 1,
"n_estimators": nums[ii]
}, x_train, y_train, 10)
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/")
# uncomment for cancer
# X, y, X_final, y_final, dataset = dataset_reader.load_cancer()
X, y, X_final, y_final, dataset = dataset_reader.load_higgs()
input_s = (30,)
batch_size = 25
classes = 2
num_nodes = [5,10,30,50]
skf = StratifiedKFold(y, n_folds=4, shuffle = True, random_state=42)
best_acc = 0
ii = 0
for train,test in skf:
x_train = X[train]
x_test = X[test]
y_train = y[train]
y_test = y[test]
y_train = to_categorical(y_train, classes)
y_test = to_categorical(y_test, classes)
neural_net = Sequential()
neural_net.add(Dense(num_nodes[ii], activation='sigmoid', input_shape = input_s, kernel_initializer="TruncatedNormal"))
neural_net.add(Dropout(.01))
neural_net.add(Dense(2, activation='softmax'))
neural_net.compile(optimizer="RMSProp", loss = 'binary_crossentropy', metrics = ['accuracy'])
neural_net.fit(x_train, y_train, batch_size = batch_size, epochs = 100, verbose = 0, validation_data = (x_test, y_test))
predictions = neural_net.predict(x_test)
predictions = [round(x[1]) for x in predictions]
y_test = [x[1] for x in y_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 = neural_net
best_num_nodes = num_nodes[ii]
best_acc = acc
ii += 1
evaluate_test(best_classifier, X_final, y_final, best_num_nodes, dataset)
