<no title>

def plot_data(X):
    plt.plot(X[:, 0], X[:, 1], 'k.', markersize=2)

    
def plot_centroids(centroids, weights=None, circle_color='w', cross_color='k'):
    if weights is not None:
        centroids = centroids[weights > weights.max() / 10]
    plt.scatter(centroids[:, 0], centroids[:, 1],
                marker='o', s=35, linewidths=8,
                color=circle_color, zorder=10, alpha=0.9)
    plt.scatter(centroids[:, 0], centroids[:, 1],
                marker='x', s=2, linewidths=12,
                color=cross_color, zorder=11, alpha=1)

def plot_decision_boundaries(clusterer, X, resolution=1000, show_centroids=True,
                             show_xlabels=True, show_ylabels=True):
    mins = X.min(axis=0) - 0.1
    maxs = X.max(axis=0) + 0.1
    xx, yy = np.meshgrid(np.linspace(mins[0], maxs[0], resolution),
                         np.linspace(mins[1], maxs[1], resolution))
    Z = clusterer.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)

    plt.contourf(Z, extent=(mins[0], maxs[0], mins[1], maxs[1]),
                cmap="Pastel2")
    plt.contour(Z, extent=(mins[0], maxs[0], mins[1], maxs[1]),
                linewidths=1, colors='k')
    plot_data(X)
    if show_centroids:
        plot_centroids(clusterer.cluster_centers_)

    if show_xlabels:
        plt.xlabel("$x_1$", fontsize=14)
    else:
        plt.tick_params(labelbottom=False)
    if show_ylabels:
        plt.ylabel("$x_2$", fontsize=14, rotation=0)
    else:
        plt.tick_params(labelleft=False)

blob_centers = np.array(
    [[ 0.2,  2.3],
     [-1.5 ,  2.3],
     [-2.8,  1.8],
     [-2.8,  2.8],
     [-2.8,  1.3]])
blob_std = np.array([0.4, 0.3, 0.1, 0.1, 0.1])

X, y = make_blobs(n_samples=2000, centers=blob_centers,
                  cluster_std=blob_std, random_state=7)

plt.figure(figsize=(8, 4))
plt.scatter(X[:, 0], X[:, 1], s=1)
plt.xlabel("$x_1$", fontsize=14)
plt.ylabel("$x_2$", fontsize=14, rotation=0)
plt.show()

from sklearn.cluster import KMeans
kmeans = KMeans(n_clusters=5)
y_pred = kmeans.fit_predict(X)
y_pred

kmeans.cluster_centers_

kmeans.inertia_

c_x, c_y = kmeans.cluster_centers_.T
plt.figure(figsize=(8, 4))
plt.scatter(X[:, 0], X[:, 1], s=1)
plt.scatter(c_x, c_y, c='red')
plt.xlabel("$x_1$", fontsize=14)
plt.ylabel("$x_2$", fontsize=14, rotation=0)
plt.show()

kmeans_iter1 = KMeans(n_clusters=5, init="random", n_init=1, max_iter=1, random_state=42)
kmeans_iter2 = KMeans(n_clusters=5, init="random", n_init=1, max_iter=2, random_state=42)
kmeans_iter3 = KMeans(n_clusters=5, init="random", n_init=1, max_iter=3, random_state=42)
kmeans_iter1.fit(X)
kmeans_iter2.fit(X)
kmeans_iter3.fit(X)

plt.figure(figsize=(8, 4))
plt.scatter(X[:, 0], X[:, 1], s=1)

for m,c in zip([kmeans_iter1, kmeans_iter2, kmeans_iter3],['red','purple','green']) :
    c_x, c_y = m.cluster_centers_.T
    plt.scatter(c_x, c_y, c=c)
    
plt.xlabel("$x_1$", fontsize=14)
plt.ylabel("$x_2$", fontsize=14, rotation=0)
plt.show()

plot_decision_boundaries(kmeans_iter3, X)

kmeans8 = KMeans(n_clusters=8).fit(X)
plot_decision_boundaries(kmeans8, X)

kmeans_per_k = [KMeans(n_clusters=k, random_state=42).fit(X)
                for k in range(1, 10)]
inertias = [model.inertia_ for model in kmeans_per_k]

plt.figure(figsize=(8, 3.5))
plt.plot(range(1, 10), inertias, "bo-")
plt.xlabel("$k$", fontsize=14)
plt.ylabel("Inertia", fontsize=14)
plt.axis([1, 8.5, 0, 1300])
plt.title("Elbow plot")
plt.show()

Contents