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 runWorker():
# import DistML.DistML as worker
if not ps.isWorker():
return
from model.logistic_regression import LogisticRegression
# TODO split data for diff worker
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)
def main():
#load data
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=0.3,
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)
#Redurce dimense to two using Pca and plot the result
"""PCA降维，将结果画出"""
Plot.plot_in_2d(X_train,
y_pred,
title="LogisticRegression",
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=0.2)
clf = NaiveBayes()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("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_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 = SuperVectorMachine(kernel=ploynomial_kernal,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)
print(X_test.shape)
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()
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="Gradient Boosting",
accuracy=accuracy,
legend_labels=data.target_names)
def acc(self, y, p):
return accuracy_score(np.argmax(y, axis=1), np.argmax(p, axis=1))