python类scatter()的实例源码

def plot(embeddings, labels):
  assert embeddings.shape[0] >= len(labels), 'More labels than embeddings'
  pylab.figure(figsize=(15,15))  # in inches
  for i, label in enumerate(labels):
    x, y = embeddings[i,:]
    pylab.scatter(x, y)
    pylab.annotate(label, xy=(x, y), xytext=(5, 2), textcoords='offset points',
                   ha='right', va='bottom')
  pylab.show()

def run_mnist():
    np.random.seed(42)

    # import dataset
    f = gzip.open('./tmp/data/mnist.pkl.gz', 'rb')
    (x_train, t_train), (x_valid, t_valid), (x_test, t_test) = cPickle.load(f)
    f.close()

    Y = x_train[:100, :]
    labels = t_train[:100]

    Y[Y < 0.5] = -1
    Y[Y > 0.5] = 1

    # inference
    print "inference ..."
    M = 30
    D = 2
    # lvm = vfe.SGPLVM(Y, D, M, lik='Gaussian')
    lvm = vfe.SGPLVM(Y, D, M, lik='Probit')
    # lvm.train(alpha=0.5, no_epochs=10, n_per_mb=100, lrate=0.1, fixed_params=['sn'])
    lvm.optimise(method='L-BFGS-B')
    plt.figure()
    mx, vx = lvm.get_posterior_x()
    zu = lvm.sgp_layer.zu
    plt.scatter(mx[:, 0], mx[:, 1], c=labels)
    plt.plot(zu[:, 0], zu[:, 1], 'ko')

    nx = ny = 30
    x_values = np.linspace(-5, 5, nx)
    y_values = np.linspace(-5, 5, ny)
    sx = 28
    sy = 28
    canvas = np.empty((sx * ny, sy * nx))
    for i, yi in enumerate(x_values):
        for j, xi in enumerate(y_values):
            z_mu = np.array([[xi, yi]])
            x_mean, x_var = lvm.predict_f(z_mu)
            t = x_mean / np.sqrt(1 + x_var)
            Z = 0.5 * (1 + special.erf(t / np.sqrt(2)))
            canvas[(nx - i - 1) * sx:(nx - i) * sx, j *
                   sy:(j + 1) * sy] = Z.reshape(sx, sy)

    plt.figure(figsize=(8, 10))
    Xi, Yi = np.meshgrid(x_values, y_values)
    plt.imshow(canvas, origin="upper", cmap="gray")
    plt.tight_layout()

    plt.show()

def run_cluster():
    import GPy
    # create dataset
    print "creating dataset..."
    N = 50
    k1 = GPy.kern.RBF(5, variance=1, lengthscale=1. /
                      np.random.dirichlet(np.r_[10, 10, 10, 0.1, 0.1]), ARD=True)
    k2 = GPy.kern.RBF(5, variance=1, lengthscale=1. /
                      np.random.dirichlet(np.r_[10, 0.1, 10, 0.1, 10]), ARD=True)
    k3 = GPy.kern.RBF(5, variance=1, lengthscale=1. /
                      np.random.dirichlet(np.r_[0.1, 0.1, 10, 10, 10]), ARD=True)
    X = np.random.normal(0, 1, (N, 5))
    A = np.random.multivariate_normal(np.zeros(N), k1.K(X), 10).T
    B = np.random.multivariate_normal(np.zeros(N), k2.K(X), 10).T
    C = np.random.multivariate_normal(np.zeros(N), k3.K(X), 10).T

    Y = np.vstack((A, B, C))
    labels = np.hstack((np.zeros(A.shape[0]), np.ones(
        B.shape[0]), np.ones(C.shape[0]) * 2))

    # inference
    print "inference ..."
    M = 20
    D = 5
    lvm_aep = aep.SGPLVM(Y, D, M, lik='Gaussian')
    lvm_aep.optimise(method='L-BFGS-B', alpha=0.1, maxiter=2000)

    lvm = ep.SGPLVM(Y, D, M, lik='Gaussian')
    lvm.update_hypers(lvm_aep.get_hypers())
    # # a quick hack to initialise the factors
    # lvm.sgp_layer.t1 = np.tile(lvm_aep.sgp_layer.theta_2[np.newaxis, :, :] / lvm.N, [lvm.N, 1, 1])
    # lvm.sgp_layer.t2 = np.tile(lvm_aep.sgp_layer.theta_1[np.newaxis, :, :, :] / lvm.N, [lvm.N, 1, 1, 1])
    # lvm.sgp_layer.update_posterior()
    # lvm.tx1 = lvm_aep.factor_x1
    # lvm.tx2 = lvm_aep.factor_x2
    lvm.inference(alpha=0.1, no_epochs=10, parallel=True, decay=0.5)

    ls = np.exp(lvm.sgp_layer.ls)
    print ls
    inds = np.argsort(ls)
    plt.figure()
    mx, vx = lvm.get_posterior_x()
    plt.scatter(mx[:, inds[0]], mx[:, inds[1]], c=labels)
    zu = lvm.sgp_layer.zu
    plt.plot(zu[:, inds[0]], zu[:, inds[1]], 'ko')
    plt.show()

def run_mnist():
    np.random.seed(42)

    # import dataset
    f = gzip.open('./tmp/data/mnist.pkl.gz', 'rb')
    (x_train, t_train), (x_valid, t_valid), (x_test, t_test) = cPickle.load(f)
    f.close()

    Y = x_train[:100, :]
    labels = t_train[:100]

    Y[Y < 0.5] = -1
    Y[Y > 0.5] = 1

    # inference
    print "inference ..."
    M = 30
    D = 2
    # lvm = aep.SGPLVM(Y, D, M, lik='Gaussian')
    lvm = aep.SGPLVM(Y, D, M, lik='Probit')
    # lvm.train(alpha=0.5, no_epochs=10, n_per_mb=100, lrate=0.1, fixed_params=['sn'])
    lvm.optimise(method='L-BFGS-B', alpha=0.1)
    plt.figure()
    mx, vx = lvm.get_posterior_x()
    zu = lvm.sgp_layer.zu
    plt.scatter(mx[:, 0], mx[:, 1], c=labels)
    plt.plot(zu[:, 0], zu[:, 1], 'ko')

    nx = ny = 30
    x_values = np.linspace(-5, 5, nx)
    y_values = np.linspace(-5, 5, ny)
    sx = 28
    sy = 28
    canvas = np.empty((sx * ny, sy * nx))
    for i, yi in enumerate(x_values):
        for j, xi in enumerate(y_values):
            z_mu = np.array([[xi, yi]])
            x_mean, x_var = lvm.predict_f(z_mu)
            t = x_mean / np.sqrt(1 + x_var)
            Z = 0.5 * (1 + special.erf(t / np.sqrt(2)))
            canvas[(nx - i - 1) * sx:(nx - i) * sx, j *
                   sy:(j + 1) * sy] = Z.reshape(sx, sy)

    plt.figure(figsize=(8, 10))
    Xi, Yi = np.meshgrid(x_values, y_values)
    plt.imshow(canvas, origin="upper", cmap="gray")
    plt.tight_layout()

    plt.show()

def run_xor():
    from operator import xor

    from scipy import special
    # create dataset
    print "generating dataset..."

    n = 25
    Y = np.zeros((0, 3))
    for i in [0, 1]:
        for j in [0, 1]:
            a = i * np.ones((n, 1))
            b = j * np.ones((n, 1))
            c = xor(bool(i), bool(j)) * np.ones((n, 1))
            Y_ij = np.hstack((a, b, c))
            Y = np.vstack((Y, Y_ij))

    Y = 2 * Y - 1

    # inference
    print "inference ..."
    M = 10
    D = 2
    lvm = aep.SGPLVM(Y, D, M, lik='Probit')
    lvm.optimise(method='L-BFGS-B', alpha=0.1, maxiter=200)

    # predict given inputs
    mx, vx = lvm.get_posterior_x()
    lims = [-1.5, 1.5]
    x = np.linspace(*lims, num=101)
    y = np.linspace(*lims, num=101)
    X, Y = np.meshgrid(x, y)
    X_ravel = X.ravel()
    Y_ravel = Y.ravel()
    inputs = np.vstack((X_ravel, Y_ravel)).T
    my, vy = lvm.predict_f(inputs)
    t = my / np.sqrt(1 + vy)
    Z = 0.5 * (1 + special.erf(t / np.sqrt(2)))
    for d in range(3):
        plt.figure()
        plt.scatter(mx[:, 0], mx[:, 1])
        zu = lvm.sgp_layer.zu
        plt.plot(zu[:, 0], zu[:, 1], 'ko')
        plt.contour(X, Y, np.log(Z[:, d] + 1e-16).reshape(X.shape))
        plt.xlim(*lims)
        plt.ylim(*lims)

    # Y_test = np.array([[1, -1, 1], [-1, 1, 1], [-1, -1, -1], [1, 1, -1]])
    # # impute missing data
    # for k in range(3):
    #   Y_test_k = Y_test
    #   missing_mask = np.ones_like(Y_test_k)
    #   missing_mask[:, k] = 0
    #   my_pred, vy_pred = lvm.impute_missing(
    #       Y_test_k, missing_mask,
    #       alpha=0.1, no_iters=100, add_noise=False)

    #   print k, my_pred, vy_pred, Y_test_k

    plt.show()

def plot_simple_demo_1():
    pylab.clf()
    fig = pylab.figure(num=None, figsize=(10, 4))
    pylab.subplot(121)

    title = "Original feature space"
    pylab.title(title)
    pylab.xlabel("$X_1$")
    pylab.ylabel("$X_2$")

    x1 = np.arange(0, 10, .2)
    x2 = x1 + np.random.normal(scale=1, size=len(x1))

    good = (x1 > 5) | (x2 > 5)
    bad = ~good

    x1g = x1[good]
    x2g = x2[good]
    pylab.scatter(x1g, x2g, edgecolor="blue", facecolor="blue")

    x1b = x1[bad]
    x2b = x2[bad]
    pylab.scatter(x1b, x2b, edgecolor="red", facecolor="white")

    pylab.grid(True)

    pylab.subplot(122)

    X = np.c_[(x1, x2)]

    pca = decomposition.PCA(n_components=1)
    Xtrans = pca.fit_transform(X)

    Xg = Xtrans[good]
    Xb = Xtrans[bad]

    pylab.scatter(
        Xg[:, 0], np.zeros(len(Xg)), edgecolor="blue", facecolor="blue")
    pylab.scatter(
        Xb[:, 0], np.zeros(len(Xb)), edgecolor="red", facecolor="white")
    title = "Transformed feature space"
    pylab.title(title)
    pylab.xlabel("$X'$")
    fig.axes[1].get_yaxis().set_visible(False)

    print(pca.explained_variance_ratio_)

    pylab.grid(True)

    pylab.autoscale(tight=True)
    filename = "pca_demo_1.png"
    pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")

def plot_simple_demo_2():
    pylab.clf()
    fig = pylab.figure(num=None, figsize=(10, 4))
    pylab.subplot(121)

    title = "Original feature space"
    pylab.title(title)
    pylab.xlabel("$X_1$")
    pylab.ylabel("$X_2$")

    x1 = np.arange(0, 10, .2)
    x2 = x1 + np.random.normal(scale=1, size=len(x1))

    good = x1 > x2
    bad = ~good

    x1g = x1[good]
    x2g = x2[good]
    pylab.scatter(x1g, x2g, edgecolor="blue", facecolor="blue")

    x1b = x1[bad]
    x2b = x2[bad]
    pylab.scatter(x1b, x2b, edgecolor="red", facecolor="white")

    pylab.grid(True)

    pylab.subplot(122)

    X = np.c_[(x1, x2)]

    pca = decomposition.PCA(n_components=1)
    Xtrans = pca.fit_transform(X)

    Xg = Xtrans[good]
    Xb = Xtrans[bad]

    pylab.scatter(
        Xg[:, 0], np.zeros(len(Xg)), edgecolor="blue", facecolor="blue")
    pylab.scatter(
        Xb[:, 0], np.zeros(len(Xb)), edgecolor="red", facecolor="white")
    title = "Transformed feature space"
    pylab.title(title)
    pylab.xlabel("$X'$")
    fig.axes[1].get_yaxis().set_visible(False)

    print(pca.explained_variance_ratio_)

    pylab.grid(True)

    pylab.autoscale(tight=True)
    filename = "pca_demo_2.png"
    pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")

def plot_simple_demo_lda():
    pylab.clf()
    fig = pylab.figure(num=None, figsize=(10, 4))
    pylab.subplot(121)

    title = "Original feature space"
    pylab.title(title)
    pylab.xlabel("$X_1$")
    pylab.ylabel("$X_2$")

    good = x1 > x2
    bad = ~good

    x1g = x1[good]
    x2g = x2[good]
    pylab.scatter(x1g, x2g, edgecolor="blue", facecolor="blue")

    x1b = x1[bad]
    x2b = x2[bad]
    pylab.scatter(x1b, x2b, edgecolor="red", facecolor="white")

    pylab.grid(True)

    pylab.subplot(122)

    X = np.c_[(x1, x2)]

    lda_inst = lda.LDA(n_components=1)
    Xtrans = lda_inst.fit_transform(X, good)

    Xg = Xtrans[good]
    Xb = Xtrans[bad]

    pylab.scatter(
        Xg[:, 0], np.zeros(len(Xg)), edgecolor="blue", facecolor="blue")
    pylab.scatter(
        Xb[:, 0], np.zeros(len(Xb)), edgecolor="red", facecolor="white")
    title = "Transformed feature space"
    pylab.title(title)
    pylab.xlabel("$X'$")
    fig.axes[1].get_yaxis().set_visible(False)

    pylab.grid(True)

    pylab.autoscale(tight=True)
    filename = "lda_demo.png"
    pylab.savefig(os.path.join(CHART_DIR, filename), bbox_inches="tight")

def plotScatter(self, xList, yList, saveFigPath):
        '''
        ?????? xList ???? yList ????????????
        ?????? saveFigPath ????
        :param xList: ????
        :param yList: ????
        :param saveFigPath: ????????
        :return:
        '''
        # ????????????
        # ??????????? 2
        # ???????? 2 ?????
        if len(xList[0]) >= 2:
            x1List = map(lambda x: x[0], xList)
            x2List = map(lambda x: x[1], xList)
        else:
            # 1 ? 2 ???????? 2 ?
            x1List = x2List = map(lambda x: x[0], xList)
        # ????
        scatterFig= plt.figure(saveFigPath)
        # ?????????
        colorDict = {-1: 'm', 1: 'r', 2: 'b', 3: 'pink', 4: 'orange'}
        # ?????
        map(lambda idx: \
                plt.scatter(x1List[idx], \
                            x2List[idx], \
                            marker='o', \
                            color=colorDict[yList[idx]], \
                            label=yList[idx]), \
            xrange(len(x1List)))
        # ?????????
        # ySet = set(yList)
        # map(lambda y: \
        #         plt.legend(str(y), \
        #                    loc='best'), \
        #     ySet)

        # ??????????????
        plt.title(saveFigPath)
        plt.xlabel(r'$x^1$')
        plt.ylabel(r'$x^2$')
        plt.grid(True)
        plt.savefig(saveFigPath)
        plt.show()

def kmeans():

    T=20
    n_train = 500
    mix_weights = (0.2,0.5,0.3)

    #create a class object:
    km = kmeans_gaussian(n_train,mix_weights)

    # set k-values
    kvalues = range(2,6)
    colors = ['blue','green','red','black','yellow']

    #store the cluster assignments:
    k_backup = [3,5]
    cluster_assgn35 = []

    plt.figure()
    for i in range(len(kvalues)):
        km.set_k(kvalues[i])
        km.initialize_cluster_centers()
        km.train(T)

        plt.plot(range(1,T+1),km.objective,colors[i])

        #store cluster assignments for k=3,5
        if kvalues[i] in k_backup:
            cluster_assgn35.append(km.cluster_assgn[:,0])

    plt.xticks(range(1,T+1))
    plt.xlabel('Iterations')
    plt.ylabel('Objective')
    plt.title('Objective vs Iteration for K = [2,3,4,5]')
    plt.legend(['K = %d'%i for i in kvalues])
    # plt.savefig('hw4_1a_kmean_obj')
    # plt.show()

    #plot part b:
    for i in range(2):
        plt.figure()
        colors_arr = [colors[int(x)] for x in cluster_assgn35[i]]
        plt.scatter(km.data[:,0],km.data[:,1],c=colors_arr)
        plt.xlabel('Dimension 1')
        plt.ylabel('Dimension 2')
        plt.title('Scatter plot with cluster assignment for K=%d'%k_backup[i])
        plt.savefig('hw4_2_k%d.png'%k_backup[i])
        plt.show()

#############################
#### PART B - MATRIX FACT
#############################