X = pca.transform(X, n_components=5) # Reduce to 5 dimensions
# ..........................
# TRAIN / TEST SPLIT
# ..........................
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)
# Rescale label for Adaboost to {-1, 1}
rescaled_y_train = 2 * y_train - np.ones(np.shape(y_train))
rescaled_y_test = 2 * y_test - np.ones(np.shape(y_test))
# .......
# SETUP
# .......
adaboost = Adaboost(n_clf=8)
naive_bayes = NaiveBayes()
knn = KNN(k=4)
logistic_regression = LogisticRegression()
mlp = MultilayerPerceptron(n_hidden=20)
perceptron = Perceptron()
decision_tree = DecisionTree()
random_forest = RandomForest(n_estimators=150)
support_vector_machine = SupportVectorMachine(C=1, kernel=rbf_kernel)
# ........
# TRAIN
# ........
print "Training:"
print "\tAdaboost"
adaboost.fit(X_train, rescaled_y_train)
print "\tNaive Bayes"
naive_bayes.fit(X_train, y_train)
# no. of examples
m = iris.shape[0]
# no. of features
n = iris.shape[1] - 1
X = np.ones((m, n + 1))
y = np.array((m, 1))
X[:, 1] = iris['X0'].values
X[:, 2] = iris['X1'].values
X[:, 3] = iris['X2'].values
X[:, 4] = iris['X3'].values
#Labels
y = iris['Y'].values
#Mean normalization
for j in range(n):
X[:, j] = (X[:, j] - X[:, j].mean())
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=11)
model = KNN(k=5)
y_pred = model.predict(X_test, X_train, y_train)
print(y_pred)
print("Test Accuracy:", accuracy_score(y_pred, y_test) * 100, "%")
# ..........................
# TRAIN / TEST SPLIT
# ..........................
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)
# Rescale label for Adaboost to {-1, 1}
rescaled_y_train = 2*y_train - np.ones(np.shape(y_train))
rescaled_y_test = 2*y_test - np.ones(np.shape(y_test))
# .......
# SETUP
# .......
adaboost = Adaboost(n_clf = 8)
naive_bayes = NaiveBayes()
knn = KNN(k=4)
logistic_regression = LogisticRegression()
mlp = MultilayerPerceptron(n_hidden=20)
perceptron = Perceptron()
decision_tree = DecisionTree()
random_forest = RandomForest(n_estimators=150)
support_vector_machine = SupportVectorMachine(C=1, kernel=rbf_kernel)
# ........
# TRAIN
# ........
print "Training:"
print "\tAdaboost"
adaboost.fit(X_train, rescaled_y_train)
print "\tNaive Bayes"
naive_bayes.fit(X_train, y_train)
def experiment(x_train, x_test, y_train, y_test):
"""Perform experiment.
Args:
x_train (ndarray): training data.
x_test (ndarray): test data.
y_train (ndarray): training labels.
y_test (ndarray): test labels.
Returns:
None.
"""
# Array of training sizes to plot the learning curves over.
training_sizes = np.arange(20, int(len(x_train) * 0.9), 10)
# K-Nearest Neighbor
print('\n--------------------------')
knn = KNN(k=1, weights='uniform', p=2)
knn.experiment(x_train,
x_test,
y_train,
y_test,
cv=10,
y_lim=0.3,
n_neighbors_range=np.arange(1, 50, 2),
p_range=np.arange(1, 20),
weight_functions=['uniform', 'distance'],
train_sizes=training_sizes)
# Support Vector Machines
print('\n--------------------------')
svm = SVM(c=1., kernel='rbf', degree=3, gamma=0.001, random_state=42)
svm.experiment(x_train,
x_test,
y_train,
y_test,
cv=10,
y_lim=0.2,
C_range=[1, 5] + list(range(10, 100, 20)) +
list(range(100, 1000, 50)),
kernels=['linear', 'poly', 'rbf'],
gamma_range=np.logspace(-7, 0, 50),
poly_degrees=[2, 3, 4],
train_sizes=training_sizes)
# Decision Trees
print('\n--------------------------')
dt = DecisionTree(max_depth=1, min_samples_leaf=1, random_state=42)
dt.experiment(x_train,
x_test,
y_train,
y_test,
cv=10,
y_lim=0.1,
max_depth_range=list(range(1, 50)),
min_samples_leaf_range=list(range(1, 30)),
train_sizes=training_sizes)
# AdaBoost
print('\n--------------------------')
boosted_dt = AdaBoost(n_estimators=50,
learning_rate=1.,
max_depth=3,
random_state=42)
boosted_dt.experiment(x_train,
x_test,
y_train,
y_test,
cv=10,
y_lim=0.2,
max_depth_range=list(range(1, 30)),
n_estimators_range=[1, 3, 5, 8] +
list(range(10, 100, 5)) + list(range(100, 1000, 50)),
learning_rate_range=np.logspace(-6, 1, 50),
train_sizes=training_sizes)
# Neural Networks
print('\n--------------------------')
nn = NeuralNetwork(alpha=0.01,
layer1_nodes=50,
layer2_nodes=30,
learning_rate=0.001,
max_iter=100)
nn.experiment(x_train,
x_test,
y_train,
y_test,
cv=10,
y_lim=0.1,
alpha_range=np.logspace(-5, 1, 30),
learning_rate_range=np.logspace(-4, 0, 50),
train_sizes=training_sizes)