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
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
pca = PCA()
pca.plot_in_2d(X_test, y_pred, title="Adaboost", accuracy=accuracy)
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
pca = PCA()
pca.plot_in_2d(X_test,
y_pred,
title="Logistic Regression",
accuracy=accuracy)
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=0.33,
seed=1)
# MLP
clf = MultilayerPerceptron(n_hidden=12,
n_iterations=5000,
learning_rate=0.01,
early_stopping=True,
plot_errors=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
pca = PCA()
pca.plot_in_2d(X_test,
y_pred,
title="Multilayer Perceptron",
accuracy=accuracy,
legend_labels=np.unique(y))
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(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
pca = PCA()
pca.plot_in_2d(X_test,
y_pred,
title="XGBoost",
accuracy=accuracy,
legend_labels=data.target_names)
def main():
data = load_iris_dataset(dir_path + r"/../data/iris.csv")
X = data['X']
y = data['target']
# Change class labels from strings to numbers
# df = df.replace(to_replace="setosa", value="-1")
# df = df.replace(to_replace="virginica", value="1")
# df = df.replace(to_replace="versicolor", value="2")
# Only select data for two classes
#X = df.loc[df['species'] != "2"].drop("species", axis=1).as_matrix()
#y = df.loc[df['species'] != "2"]["species"].as_matrix()
X = X[y != 2]
y = y[y != 2]
y[y == 0] = -1
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
# Adaboost classification
clf = Adaboost(n_clf=8)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
# Reduce dimensions to 2d using pca and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
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=0.33,
seed=1)
# Optimization method for finding weights that minimizes loss
optimizer = RMSprop(learning_rate=0.01)
# Perceptron
clf = Perceptron(n_iterations=5000,
activation_function=ExpLU,
optimizer=optimizer,
early_stopping=True,
plot_errors=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
pca = PCA()
pca.plot_in_2d(X_test,
y_pred,
title="Perceptron",
accuracy=accuracy,
legend_labels=np.unique(y))
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=0.33,
seed=1)
# Perceptron
clf = Perceptron(n_iterations=4000, learning_rate=0.01, plot_errors=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
pca = PCA()
pca.plot_in_2d(X_test,
y_pred,
title="Perceptron",
accuracy=accuracy,
legend=True)
def main():
# Load the dataset
X, y = datasets.make_blobs()
# Cluster the data
clf = GaussianMixtureModel(k=3)
y_pred = clf.predict(X)
pca = PCA()
pca.plot_in_2d(X, y_pred)
pca.plot_in_2d(X, y)
def main():
# Load the dataset
X, y = datasets.make_blobs()
# Cluster the data
clf = GaussianMixtureModel(k=3)
y_pred = clf.predict(X)
pca = PCA()
pca.plot_in_2d(X, y_pred, title="GMM Clustering")
pca.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
pca = PCA()
pca.plot_in_2d(X, y_pred)
pca.plot_in_2d(X, y)
def main():
# Load the dataset
X, y = datasets.make_blobs()
# Cluster the data using K-Medoids
clf = PAM(k=3)
y_pred = clf.predict(X)
# Project the data onto the 2 primary principal components
pca = PCA()
pca.plot_in_2d(X, y_pred, title="PAM Clustering")
pca.plot_in_2d(X, y, title="Actual Clustering")
def main(): iris = load_iris() X = normalize(iris.data) y = iris.target X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33) clf = KNN(k=3) y_pred = clf.predict(X_test, X_train, y_train) print "Accuracy score:", accuracy_score(y_test, y_pred) # Reduce dimensions to 2d using pca and plot the results pca = PCA() pca.plot_in_2d(X_test, y_pred)
def main():
iris = load_iris()
X = normalize(iris.data)
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
clf = KNN(k=3)
y_pred = clf.predict(X_test, X_train, y_train)
print "Accuracy score:", accuracy_score(y_test, y_pred)
# Reduce dimensions to 2d using pca and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
def main():
print("-- Gradient Boosting Classification --")
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 = GradientBoostingClassifier(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)
pca = PCA()
pca.plot_in_2d(X_test,
y_pred,
title="Gradient Boosting",
accuracy=accuracy,
legend_labels=data.target_names)
print("-- Gradient Boosting Regression --")
X, y = datasets.make_regression(n_features=1,
n_samples=150,
bias=0,
noise=5)
X_train, X_test, y_train, y_test = train_test_split(standardize(X),
y,
test_size=0.5)
clf = GradientBoostingRegressor(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)
# Plot the results
plt.scatter(X_test[:, 0], y_test, color='black')
plt.scatter(X_test[:, 0], y_pred, color='green')
plt.title("Gradient Boosting Regression (%.2f MSE)" % mse)
plt.show()
def main(): iris = datasets.load_iris() X = normalize(iris.data) y = iris.target X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5) clf = NaiveBayes() clf.fit(X_train, y_train) y_pred = clf.predict(X_test) print "Accuracy score:", accuracy_score(y_test, y_pred) # Reduce dimension to two using PCA and plot the results pca = PCA() pca.plot_in_2d(X_test, y_pred)
def main():
iris = datasets.load_iris()
X = normalize(iris.data)
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)
clf = NaiveBayes()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print "Accuracy score:", accuracy_score(y_test, y_pred)
# Reduce dimension to two using PCA and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
def main():
data = load_iris_dataset(dir_path + r"/../data/iris.csv")
X = data['X']
y = data['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
clf = RandomForest(n_estimators=50, debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
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)
clf = RandomForest(n_estimators=50, debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
def main():
data=load_iris_dataset(dir_path + r"/../data/iris.csv")
X=data['X']
y=data['target']
X = normalize(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
clf = KNN(k=3)
y_pred = clf.predict(X_test, X_train, y_train)
print "Accuracy score:", accuracy_score(y_test, y_pred)
# Reduce dimensions to 2d using pca and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
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) clf = RandomForest(n_estimators=50, debug=True) clf.fit(X_train, y_train) y_pred = clf.predict(X_test) print "Accuracy:", accuracy_score(y_test, y_pred) pca = PCA() pca.plot_in_2d(X_test, y_pred)
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)
# MLP
clf = MultilayerPerceptron(n_hidden=10)
clf.fit(X_train, y_train, n_iterations=4000, learning_rate=0.01)
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
# Reduce dimension to two using PCA and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
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)
# Perceptron
clf = Perceptron()
clf.fit(X_train, y_train, plot_errors=True)
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
# Reduce dimension to two using PCA and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
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=3)
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
pca = PCA()
pca.plot_in_2d(X_test, y_pred, title="K Nearest Neighbors", accuracy=accuracy, legend_labels=data.target_names)
def plotIn3D(self, X, y=None, k=1, labels=[]):
X_transformed = PCA().transform(X, n_components=3)
x1 = X_transformed[:, 0]
x2 = X_transformed[:, 1]
x3 = X_transformed[:, 2]
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.scatter(x1, x2, x3, c=y)
# Plot a star for each centroid
for i in range(k):
ax.scatter(np.mean(X_transformed[y == i, 0]),
np.mean(X_transformed[y == i, 1]),
np.mean(X_transformed[y == i, 2]),
s=400,
marker='*',
c='w',
cmap=chosenCmap)
plt.title(labels[0])
plt.xlabel(labels[1])
plt.ylabel(labels[2])
# plt.legend(handles = graphLegend)
# Do I add the
plt.show()
def main():
data = load_iris_dataset(dir_path + r"/../data/iris.csv")
X = data['X']
y = data['target']
X = normalize(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
# Perceptron
clf = Perceptron()
clf.fit(X_train, y_train, plot_errors=True)
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
# Reduce dimension to two using PCA and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
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) clf = DecisionTree() clf.fit(X_train, y_train) # clf.print_tree() y_pred = clf.predict(X_test) print "Accuracy:", accuracy_score(y_test, y_pred) pca = PCA() pca.plot_in_2d(X_test, y_pred)
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)
print "Accuracy:", accuracy_score(y_test, y_pred)
# Reduce dimension to two using PCA and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
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)
clf = DecisionTree()
clf.fit(X_train, y_train)
# clf.print_tree()
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
def main():
data = load_iris_dataset(dir_path + r"/../data/iris.csv")
X = data['X']
y = data['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
clf = DecisionTree()
clf.fit(X_train, y_train)
# clf.print_tree()
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
def main():
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 = RandomForest(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print("Accuracy:", accuracy_score(y_test, y_pred))
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
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=0.5)
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
pca = PCA()
pca.plot_in_2d(X_test, y_pred, title="Naive Bayes", accuracy=accuracy, legend_labels=data.target_names)
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
pca = PCA()
pca.plot_in_2d(X_test, y_pred, title="Support Vector Machine", accuracy=accuracy)
def main():
data = datasets.load_iris()
X = 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)
clf = LogisticRegression()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
# Reduce dimension to two using PCA and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
def main():
print ("-- Gradient Boosting Classification --")
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 = GradientBoostingClassifier(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print ("Accuracy:", accuracy)
pca = PCA()
pca.plot_in_2d(X_test, y_pred,
title="Gradient Boosting",
accuracy=accuracy,
legend_labels=data.target_names)
print ("-- Gradient Boosting Regression --")
X, y = datasets.make_regression(n_features=1, n_samples=150, bias=0, noise=5)
X_train, X_test, y_train, y_test = train_test_split(standardize(X), y, test_size=0.5)
clf = GradientBoostingRegressor(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
print ("Mean Squared Error:", mse)
# Plot the results
plt.scatter(X_test[:, 0], y_test, color='black')
plt.scatter(X_test[:, 0], y_pred, color='green')
plt.title("Gradient Boosting Regression (%.2f MSE)" % mse)
plt.show()
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,
seed=2)
clf = ClassificationTree()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print("Accuracy:", accuracy_score(y_test, y_pred))
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
print("-- Regression Tree --")
X, y = datasets.make_regression(n_features=1,
n_samples=100,
bias=0,
noise=5)
X_train, X_test, y_train, y_test = train_test_split(standardize(X),
y,
test_size=0.3)
clf = RegressionTree()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print("Mean Squared Error:", mean_squared_error(y_test, y_pred))
# Plot the results
plt.scatter(X_test[:, 0], y_test, color='black')
plt.scatter(X_test[:, 0], y_pred, color='green')
plt.show()
def plotIn2D(self, X, y=None, labels=[]):
X_transformed = PCA().transform(X, n_components=2)
x1 = X_transformed[:, 0]
x2 = X_transformed[:, 1]
plt.scatter(x1, x2, c=y)
plt.title(labels[0])
plt.xlabel(labels[1])
plt.ylabel(labels[2])
plt.legend(handles=graphLegend)
plt.show()
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=3)
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
pca = PCA()
pca.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 = data.data
y = data.target
pca = PCA()
X = pca.transform(X, n_components=5) # Reduce to 5 dimensions
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.4,
seed=1)
clf = RandomForest(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print("Accuracy:", accuracy_score(y_test, y_pred))
pca.plot_in_2d(X_test, y_pred)
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)
print "Accuracy:", accuracy_score(y_test, y_pred)
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
def main():
# Load the dataset
data = load_iris_dataset(dir_path + r"/../data/iris.csv")
X = data['X']
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)
print "Accuracy:", accuracy_score(y_test, y_pred)
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
def main():
data = load_iris_dataset(dir_path + r"/../data/iris.csv")
X = data['X']
y = data['target']
X = normalize(X)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
# MLP
clf = MultilayerPerceptron(n_hidden=10)
clf.fit(X_train,
y_train,
n_iterations=4000,
learning_rate=0.01,
plot_errors=True)
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
# Reduce dimension to two using PCA and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
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
pca = PCA()
pca.plot_in_2d(X_test, y_pred, title="Logistic Regression", accuracy=accuracy)
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=0.33, seed=1)
# Perceptron
clf = Perceptron(n_iterations=5000,
learning_rate=0.01,
early_stopping=True,
plot_errors=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
pca = PCA()
pca.plot_in_2d(X_test, y_pred, title="Perceptron", accuracy=accuracy, legend_labels=np.unique(y))
def main():
df = pd.read_csv(dir_path + "/../data/iris.csv")
# Change class labels from strings to numbers
df = df.replace(to_replace="setosa", value="-1")
df = df.replace(to_replace="virginica", value="1")
df = df.replace(to_replace="versicolor", value="2")
# Only select data for two classes
X = df.loc[df['species'] != "2"].drop("species", axis=1).as_matrix()
y = df.loc[df['species'] != "2"]["species"].as_matrix()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
# Adaboost classification
clf = Adaboost(n_clf = 8)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
# Reduce dimensions to 2d using pca and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
def main():
# Load dataset
data = load_iris_dataset(dir_path + r"/../data/iris.csv")
X = data['X']
y = data['target']
X = normalize(X[y != 0])
y = y[y != 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)
clf = LogisticRegression()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print "Accuracy:", accuracy_score(y_test, y_pred)
# Reduce dimension to two using PCA and plot the results
pca = PCA()
pca.plot_in_2d(X_test, y_pred)
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)
pca = PCA()
pca.plot_in_2d(X_test, y_pred, title="LDA", accuracy=accuracy)
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(debug=True)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print ("Accuracy:", accuracy)
pca = PCA()
pca.plot_in_2d(X_test, y_pred,
title="XGBoost",
accuracy=accuracy,
legend_labels=data.target_names)
def main():
data = datasets.load_iris()
X = data.data
y = data.target
X = X[y != 2]
y = y[y != 2]
y[y == 0] = -1
y[y == 1] = 1
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)
# Adaboost classification
clf = Adaboost(n_clf=10)
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
pca = PCA()
pca.plot_in_2d(X_test, y_pred, title="Adaboost", accuracy=accuracy)
# ...........
data = datasets.load_digits()
digit1 = 1
digit2 = 8
idx = np.append(np.where(data.target == digit1)[0], np.where(data.target == digit2)[0])
y = data.target[idx]
# Change labels to {0, 1}
y[y == digit1] = 0
y[y == digit2] = 1
X = data.data[idx]
X = normalize(X)
# ..........................
# DIMENSIONALITY REDUCTION
# ..........................
pca = PCA()
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)
