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():
# Load the dataset
data=load_iris_dataset(dir_path + r"/../data/iris.csv")
X=data['X']
y=data['target']
# Project the data onto the 2 primary principal components and plot the
# data
pca = PCA()
pca.plot_in_2d(X, y)
def main():
# Load the dataset
data=load_iris_dataset(dir_path + r"/../data/iris.csv")
X=data['X']
y=data['target']
X = normalize(X)
# Project the data onto the 2 primary components
multi_class_lda = MultiClassLDA()
multi_class_lda.plot_in_2d(X, y)
def main():
# Load the dataset
data = load_iris_dataset(dir_path + r"/../data/iris.csv")
X = data['X']
y = data['target']
# 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)
pca.plot_in_2d(X, y)
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=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 = 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 = 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 = 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 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():
# 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)
