def main():
iris = load_iris()
# we only take the first two features. We could avoid this ugly
# slicing by using a two-dim dataset
X = iris.data[:, :2]
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
model = KNeighborsClassifier(n_neighbors=5)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
accuracy = calculate_accuracy_score(y_test, y_pred)
print("Accuracy Score: {:.2%}".format(accuracy))
h = .05 # step size in the mesh
cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF'])
cmap_bold = ListedColormap(['#FF0000', '#00FF00', '#0000FF'])
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.pcolormesh(xx, yy, Z, cmap=cmap_light)
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold, edgecolor='k', s=20)
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt.savefig('./examples/example_KNeighborsClassifier.png')
def main():
iris = load_iris()
X = iris.data
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
model = XGBoost(n_estimators=300, learning_rate=0.001)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
accuracy = calculate_accuracy_score(y_test, y_pred)
print("Accuracy Score: {:.2%}".format(accuracy))
def main():
iris = load_iris()
X = iris.data
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
clf = GradientBoostingClassifier(n_estimators=200, learning_rate=.5)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
accuracy = calculate_accuracy_score(y_test, y_pred)
print("Accuracy Score: {:.2%}".format(accuracy))
def main():
iris = load_iris()
X = iris.data
y = iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)
model = RandomForestClassifier(n_estimators=200, max_depth=10)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
accuracy = calculate_accuracy_score(y_test, y_pred)
print("Accuracy Score: {:.2%}".format(accuracy))
def main():
iris = load_iris()
X = iris.data
y = iris.target
target_names = iris.target_names
lda = LinearDiscriminantAnalysis(n_components=2)
pca = PCA(n_components=2)
X_r = pca.fit(X).transform(X)
X_r2 = lda.fit(X, y).transform(X)
# plot
plt.figure(figsize=(15, 6))
# pca, left
plt.subplot(121)
colors = ['navy', 'turquoise', 'darkorange']
lw = 2
for color, i, target_name in zip(colors, [0, 1, 2], target_names):
plt.scatter(X_r[y == i, 0],
X_r[y == i, 1],
color=color,
alpha=.8,
lw=lw,
label=target_name)
plt.legend(loc='best', shadow=False, scatterpoints=1)
plt.title('PCA of IRIS dataset')
# lda, right
plt.subplot(122)
for color, i, target_name in zip(colors, [0, 1, 2], target_names):
plt.scatter(X_r2[y == i, 0],
X_r2[y == i, 1],
alpha=.8,
color=color,
label=target_name)
plt.legend(loc='best', shadow=False, scatterpoints=1)
plt.title('LDA of IRIS dataset')
plt.savefig('./examples/example_PCA_LDA.png')
def main():
# Example 1
X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
Y = np.array([1, 1, 1, 2, 2, 2])
model = GaussianNB()
model.fit(X, Y)
print(model.predict([[-0.8, -1]]))
# Example 2
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=0.4)
model = GaussianNB()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
accuracy = calculate_accuracy_score(y_test, y_pred)
print("Accuracy Score: {:.2%}".format(accuracy))
def main():
iris = load_iris()
X = iris["data"][:, 3:] # petal width
y = (iris["target"] == 2).astype(np.int) # 1 if Iris-Virginica, else 0
model = LogisticRegression(max_iter=1000,
learning_rate=0.001,
fit_intercept=True)
model.fit(X, y)
y_pred = model.predict(X)
accuracy = calculate_accuracy_score(y, y_pred)
print("Accuracy Score: {:.2%}".format(accuracy))
X_new = np.linspace(0, 3, 1000).reshape(-1, 1)
y_proba = model.predict_proba(X_new)
plt.plot(X_new, y_proba[:, 0], "m--", label="Not Iris-Virginica")
plt.plot(X_new, y_proba[:, 1], "c-", label="Iris-Virginica")
plt.plot(X[y == 0], y[y == 0], "m.")
plt.plot(X[y == 1], y[y == 1], "c.")
plt.legend()
plt.savefig("./examples/example_LogisticRegression.png")
def main():
# Example 1
X = np.array([[1, 2], [1, 4], [1, 0], [10, 2], [10, 4], [10, 0]])
kmeans = KMeans(n_clusters=2)
kmeans.fit(X)
print(kmeans.cluster_centers_)
print(kmeans.labels_)
print(kmeans.inertia_)
print(kmeans.predict([[0, 0], [12, 3]]))
# Example 2
iris = load_iris()
X = iris.data
y = iris.target
kmeans = KMeans(n_clusters=3)
kmeans.fit(X)
labels = kmeans.labels_
fig = plt.figure(figsize=(12, 5))
ax = fig.add_subplot(1, 2, 1, projection='3d', elev=48, azim=134)
for name, label in [('Setosa', 0), ('Versicolour', 1), ('Virginica', 2)]:
ax.text3D(X[y == label, 3].mean(),
X[y == label, 0].mean(),
X[y == label, 2].mean() + 2,
name,
horizontalalignment='center',
bbox=dict(alpha=.2, edgecolor='w', facecolor='w'))
ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=labels, edgecolor='k')
ax.w_xaxis.set_ticklabels([])
ax.w_yaxis.set_ticklabels([])
ax.w_zaxis.set_ticklabels([])
ax.set_xlabel('Petal width')
ax.set_ylabel('Sepal length')
ax.set_zlabel('Petal length')
ax.set_title('3 clusters')
ax.dist = 12
ax = fig.add_subplot(1, 2, 2, projection='3d', elev=48, azim=134)
for name, label in [('Setosa', 0), ('Versicolour', 1), ('Virginica', 2)]:
ax.text3D(X[y == label, 3].mean(),
X[y == label, 0].mean(),
X[y == label, 2].mean() + 2,
name,
horizontalalignment='center',
bbox=dict(alpha=.2, edgecolor='w', facecolor='w'))
y = np.choose(y, [1, 2, 0]).astype(np.float)
ax.scatter(X[:, 3], X[:, 0], X[:, 2], c=y, edgecolor='k')
ax.w_xaxis.set_ticklabels([])
ax.w_yaxis.set_ticklabels([])
ax.w_zaxis.set_ticklabels([])
ax.set_xlabel('Petal width')
ax.set_ylabel('Sepal length')
ax.set_zlabel('Petal length')
ax.set_title('Ground Truth')
ax.dist = 12
plt.savefig("./examples/example_KMeans.png")