def main():
print("-- XGBoost --")
data = datasets.load_iris()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.4,
seed=2)
clf = XGBoost()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_in_2d(X_test,
y_pred,
title="XGBoost",
accuracy=accuracy,
legend_labels=data.target_names)
def main():
# Load dataset
data = datasets.load_iris()
X = normalize(data.data[data.target != 0])
y = data.target[data.target != 0]
y[y == 1] = 0
y[y == 2] = 1
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.33,
seed=1)
clf = LogisticRegression(gradient_descent=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
# Reduce dimension to two using PCA and plot the results
Plot().plot_in_2d(X_test,
y_pred,
title="Logistic Regression",
accuracy=accuracy)
def main():
data = datasets.load_digits()
X = data.data
y = data.target
digit1 = 1
digit2 = 8
idx = np.append(np.where(y == digit1)[0], np.where(y == digit2)[0])
y = data.target[idx]
# Change labels to {-1, 1}
y[y == digit1] = -1
y[y == digit2] = 1
X = data.data[idx]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)
# Adaboost classification with 5 weak classifiers
clf = Adaboost(n_clf=5)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print ("Accuracy:", accuracy)
# Reduce dimensions to 2d using pca and plot the results
Plot().plot_in_2d(X_test, y_pred, title="Adaboost", accuracy=accuracy)
def main():
data = datasets.load_digits()
X = normalize(data.data)
y = data.target
# One-hot encoding of nominal y-values
y = to_categorical(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, seed=1)
# Perceptron
clf = Perceptron(n_iterations=5000,
learning_rate=0.001,
loss=CrossEntropy,
activation_function=Sigmoid)
clf.fit(X_train, y_train)
y_pred = np.argmax(clf.predict(X_test), axis=1)
y_test = np.argmax(y_test, axis=1)
accuracy = accuracy_score(y_test, y_pred)
print ("Accuracy:", accuracy)
# Reduce dimension to two using PCA and plot the results
Plot().plot_in_2d(X_test, y_pred, title="Perceptron", accuracy=accuracy, legend_labels=np.unique(y))
def main():
optimizer = Adam()
#-----
# MLP
#-----
data = datasets.load_digits()
X = data.data
y = data.target
# Convert to one-hot encoding
y = to_categorical(y.astype("int"))
n_samples, n_features = X.shape
n_hidden = 512
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, seed=1)
clf = NeuralNetwork(optimizer=optimizer,
loss=CrossEntropy,
validation_data=(X_test, y_test))
clf.add(Dense(n_hidden, input_shape=(n_features,)))
clf.add(Activation('leaky_relu'))
clf.add(Dense(n_hidden))
clf.add(Activation('leaky_relu'))
clf.add(Dropout(0.25))
clf.add(Dense(n_hidden))
clf.add(Activation('leaky_relu'))
clf.add(Dropout(0.25))
clf.add(Dense(n_hidden))
clf.add(Activation('leaky_relu'))
clf.add(Dropout(0.25))
clf.add(Dense(10))
clf.add(Activation('softmax'))
print ()
clf.summary(name="MLP")
train_err, val_err = clf.fit(X_train, y_train, n_epochs=50, batch_size=256)
# Training and validation error plot
n = len(train_err)
training, = plt.plot(range(n), train_err, label="Training Error")
validation, = plt.plot(range(n), val_err, label="Validation Error")
plt.legend(handles=[training, validation])
plt.title("Error Plot")
plt.ylabel('Error')
plt.xlabel('Iterations')
plt.show()
_, accuracy = clf.test_on_batch(X_test, y_test)
print ("Accuracy:", accuracy)
# Reduce dimension to 2D using PCA and plot the results
y_pred = np.argmax(clf.predict(X_test), axis=1)
Plot().plot_in_2d(X_test, y_pred, title="Multilayer Perceptron", accuracy=accuracy, legend_labels=range(10))
def main():
X, y = datasets.make_classification(n_samples=1000, n_features=10, n_classes=4, n_clusters_per_class=1, n_informative=2)
data = datasets.load_iris()
X = normalize(data.data)
y = data.target
y = to_categorical(y.astype("int"))
# Model builder
def model_builder(n_inputs, n_outputs):
model = NeuralNetwork(optimizer=Adam(), loss=CrossEntropy)
model.add(Dense(16, input_shape=(n_inputs,)))
model.add(Activation('relu'))
model.add(Dense(n_outputs))
model.add(Activation('softmax'))
return model
# Print the model summary of a individual in the population
print ("")
model_builder(n_inputs=X.shape[1], n_outputs=y.shape[1]).summary()
population_size = 100
n_generations = 10
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, seed=1)
inertia_weight = 0.8
cognitive_weight = 0.8
social_weight = 0.8
print ("Population Size: %d" % population_size)
print ("Generations: %d" % n_generations)
print ("")
print ("Inertia Weight: %.2f" % inertia_weight)
print ("Cognitive Weight: %.2f" % cognitive_weight)
print ("Social Weight: %.2f" % social_weight)
print ("")
model = ParticleSwarmOptimizedNN(population_size=population_size,
inertia_weight=inertia_weight,
cognitive_weight=cognitive_weight,
social_weight=social_weight,
max_velocity=5,
model_builder=model_builder)
model = model.evolve(X_train, y_train, n_generations=n_generations)
loss, accuracy = model.test_on_batch(X_test, y_test)
print ("Accuracy: %.1f%%" % float(100*accuracy))
# Reduce dimension to 2D using PCA and plot the results
y_pred = np.argmax(model.predict(X_test), axis=1)
Plot().plot_in_2d(X_test, y_pred, title="Particle Swarm Optimized Neural Network", accuracy=accuracy, legend_labels=range(y.shape[1]))
def main():
X, y = datasets.make_classification(n_samples=1000,
n_features=10,
n_classes=4,
n_clusters_per_class=1,
n_informative=2)
data = datasets.load_digits()
X = normalize(data.data)
y = data.target
y = to_categorical(y.astype("int"))
# Model builder
def model_builder(n_inputs, n_outputs):
model = NeuralNetwork(optimizer=Adam(), loss=CrossEntropy)
model.add(Dense(16, input_shape=(n_inputs, )))
model.add(Activation('relu'))
model.add(Dense(n_outputs))
model.add(Activation('softmax'))
return model
# Print the model summary of a individual in the population
print("")
model_builder(n_inputs=X.shape[1], n_outputs=y.shape[1]).summary()
population_size = 100
n_generations = 3000
mutation_rate = 0.01
print("Population Size: %d" % population_size)
print("Generations: %d" % n_generations)
print("Mutation Rate: %.2f" % mutation_rate)
print("")
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.4,
seed=1)
model = Neuroevolution(population_size=population_size,
mutation_rate=mutation_rate,
model_builder=model_builder)
model = model.evolve(X_train, y_train, n_generations=n_generations)
loss, accuracy = model.test_on_batch(X_test, y_test)
# Reduce dimension to 2D using PCA and plot the results
y_pred = np.argmax(model.predict(X_test), axis=1)
Plot().plot_in_2d(X_test,
y_pred,
title="Evolutionary Evolved Neural Network",
accuracy=accuracy,
legend_labels=range(y.shape[1]))
def main():
# Load the dataset
X, y = datasets.make_blobs()
# Cluster the data
clf = GaussianMixtureModel(k=3)
y_pred = clf.predict(X)
p = Plot()
p.plot_in_2d(X, y_pred, title="GMM Clustering")
p.plot_in_2d(X, y, title="Actual Clustering")
def main():
# Load the dataset
X, y = datasets.make_moons(n_samples=300, noise=0.08, shuffle=False)
# Cluster the data using DBSCAN
clf = DBSCAN(eps=0.17, min_samples=5)
y_pred = clf.predict(X)
# Project the data onto the 2 primary principal components
p = Plot()
p.plot_in_2d(X, y_pred, title="DBSCAN")
p.plot_in_2d(X, y, title="Actual Clustering")
def main():
# Load the dataset
X, y = datasets.make_blobs()
# Cluster the data using K-Means
clf = KMeans(k=3)
y_pred = clf.predict(X)
# Project the data onto the 2 primary principal components
p = Plot()
p.plot_in_2d(X, y_pred, title="K-Means Clustering")
p.plot_in_2d(X, y, title="Actual Clustering")
def main():
data = datasets.load_iris()
X = normalize(data.data[data.target != 0])
y = data.target[data.target != 0]
y[y == 1] = -1
y[y == 2] = 1
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
clf = SupportVectorMachine(kernel=polynomial_kernel, power=4, coef=1)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print ("Accuracy:", accuracy)
# Reduce dimension to two using PCA and plot the results
Plot().plot_in_2d(X_test, y_pred, title="Support Vector Machine", accuracy=accuracy)
def main():
data = datasets.load_iris()
X = normalize(data.data)
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
clf = KNN(k=5)
y_pred = clf.predict(X_test, X_train, y_train)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
# Reduce dimensions to 2d using pca and plot the results
Plot().plot_in_2d(X_test,
y_pred,
title="K Nearest Neighbors",
accuracy=accuracy,
legend_labels=data.target_names)
def main():
data = datasets.load_digits()
X = normalize(data.data)
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
clf = NaiveBayes()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
# Reduce dimension to two using PCA and plot the results
Plot().plot_in_2d(X_test,
y_pred,
title="Naive Bayes",
accuracy=accuracy,
legend_labels=data.target_names)
def main():
# Load the dataset
data = datasets.load_iris()
X = data.data
y = data.target
# Three -> two classes
X = X[y != 2]
y = y[y != 2]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
# Fit and predict using LDA
lda = LDA()
lda.fit(X_train, y_train)
y_pred = lda.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_in_2d(X_test, y_pred, title="LDA", accuracy=accuracy)
def main():
data = datasets.load_digits()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.4,
seed=2)
clf = RandomForest(n_estimators=100)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_in_2d(X_test,
y_pred,
title="Random Forest",
accuracy=accuracy,
legend_labels=data.target_names)
def main():
print("-- Classification Tree --")
data = datasets.load_iris()
X = data.data
y = data.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
clf = ClassificationTree()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
Plot().plot_in_2d(X_test,
y_pred,
title="Decision Tree",
accuracy=accuracy,
legend_labels=data.target_names)
def main():
data = datasets.load_digits()
X = normalize(data.data)
y = data.target
# Convert the nominal y values to binary
y = to_categorical(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, seed=1)
# MLP
clf = MultilayerPerceptron(n_hidden=16,
n_iterations=1000,
learning_rate=0.01)
clf.fit(X_train, y_train)
y_pred = np.argmax(clf.predict(X_test), axis=1)
y_test = np.argmax(y_test, axis=1)
accuracy = accuracy_score(y_test, y_pred)
print ("Accuracy:", accuracy)
# Reduce dimension to two using PCA and plot the results
Plot().plot_in_2d(X_test, y_pred, title="Multilayer Perceptron", accuracy=accuracy, legend_labels=np.unique(y))
def main():
#----------
# Conv Net
#----------
optimizer = Adam()
data = datasets.load_digits()
X = data.data
y = data.target
# Convert to one-hot encoding
y = to_categorical(y.astype("int"))
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.4,
seed=1)
# Reshape X to (n_samples, channels, height, width)
X_train = X_train.reshape((-1, 1, 8, 8))
X_test = X_test.reshape((-1, 1, 8, 8))
clf = NeuralNetwork(optimizer=optimizer,
loss=CrossEntropy,
validation_data=(X_test, y_test))
clf.add(
Conv2D(n_filters=16,
filter_shape=(3, 3),
stride=1,
input_shape=(1, 8, 8),
padding='same'))
clf.add(Activation('relu'))
clf.add(Dropout(0.25))
clf.add(BatchNormalization())
clf.add(Conv2D(n_filters=32, filter_shape=(3, 3), stride=1,
padding='same'))
clf.add(Activation('relu'))
clf.add(Dropout(0.25))
clf.add(BatchNormalization())
clf.add(Flatten())
clf.add(Dense(256))
clf.add(Activation('relu'))
clf.add(Dropout(0.4))
clf.add(BatchNormalization())
clf.add(Dense(10))
clf.add(Activation('softmax'))
print()
clf.summary(name="ConvNet")
train_err, val_err = clf.fit(X_train, y_train, n_epochs=50, batch_size=256)
# Training and validation error plot
n = len(train_err)
training, = plt.plot(range(n), train_err, label="Training Error")
validation, = plt.plot(range(n), val_err, label="Validation Error")
plt.legend(handles=[training, validation])
plt.title("Error Plot")
plt.ylabel('Error')
plt.xlabel('Iterations')
plt.show()
_, accuracy = clf.test_on_batch(X_test, y_test)
print("Accuracy:", accuracy)
y_pred = np.argmax(clf.predict(X_test), axis=1)
X_test = X_test.reshape(-1, 8 * 8)
# Reduce dimension to 2D using PCA and plot the results
Plot().plot_in_2d(X_test,
y_pred,
title="Convolutional Neural Network",
accuracy=accuracy,
legend_labels=range(10))