Python GaussianMixture.predict方法代码示例

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
	def learn_subset(self, search_space):
	
		#Mask undesired features
		current_array = self.vectors[:,search_space]
	
		GM = GaussianMixture(n_components = 2, 
							covariance_type = "full", 
							tol = 0.001, 
							reg_covar = 1e-06, 
							max_iter = 1000, 
							n_init = 25, 
							init_params = "kmeans", 
							weights_init = None, 
							means_init = None, 
							precisions_init = None, 
							random_state = None, 
							warm_start = False, 
							verbose = 0, 
							verbose_interval = 10
							)
							
		GM.fit(current_array)

		labels = GM.predict(current_array)
		unique, counts = np.unique(labels, return_counts = True)
		count_dict = dict(zip(unique, counts))
		
		return count_dict, labels

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
 def gmm(nclusters, coords, n_init=50, n_iter=500):
     if USE_GAUSSIAN_MIXTURE:
         est = GaussianMixture(n_components=nclusters, n_init=n_init, max_iter=n_iter)
     else:
         est = GMM(n_components=nclusters, n_init=n_init, n_iter=n_iter)
     est.fit(coords)
     return Partition(est.predict(coords))

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
def gmm(k, X, run_times=5):
    gm = GMM(k, n_init=run_times, init_params='kmeans')
    #gm = GMM(k)
    gm.fit(X)
    zh = gm.predict(X)
    mu = gm.means_
    cov = gm.covariances_
    return zh, mu, cov

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
def gmm(k, X, run_times=10, init='kmeans'):
    """GMM from sklearn library. init = {'kmeans', 'random'}, run_times
    is the number of times the algorithm is gonna run with different
    initializations.
    
    """
    gm = GMM(k, n_init=run_times, init_params=init)
    gm.fit(X)
    zh = gm.predict(X)
    return zh

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
		# Make data array to be put through the GMM - 5 components: 3 PCs, scaled energy, amplitude
		this_cluster = np.where(predictions == int(clusters[0]))[0]
		n_pc = 3
		data = np.zeros((len(this_cluster), n_pc + 2))	
		data[:,2:] = pca_slices[this_cluster,:n_pc]
		data[:,0] = energy[this_cluster]/np.max(energy[this_cluster])
		data[:,1] = np.abs(amplitudes[this_cluster])/np.max(np.abs(amplitudes[this_cluster]))

		# Cluster the data
		g = GaussianMixture(n_components = n_clusters, covariance_type = 'full', tol = thresh, max_iter = n_iter, n_init = n_restarts)
		g.fit(data)
	
		# Show the cluster plots if the solution converged
		if g.converged_:
			split_predictions = g.predict(data)
			x = np.arange(len(spike_waveforms[0])/10) + 1
			for cluster in range(n_clusters):
				split_points = np.where(split_predictions == cluster)[0]				
				# plt.figure(cluster)
				slices_dejittered = spike_waveforms[this_cluster, :]		# Waveforms and times from the chosen cluster
				times_dejittered = spike_times[this_cluster]
				times_dejittered = times_dejittered[split_points]		# Waveforms and times from the chosen split of the chosen cluster
				ISIs = np.ediff1d(np.sort(times_dejittered))/30.0
				violations1 = 100.0*float(np.sum(ISIs < 1.0)/split_points.shape[0])
				violations2 = 100.0*float(np.sum(ISIs < 2.0)/split_points.shape[0])
				fig, ax = blech_waveforms_datashader.waveforms_datashader(slices_dejittered[split_points, :], x)
				# plt.plot(x-15, slices_dejittered[split_points, :].T, linewidth = 0.01, color = 'red')
				ax.set_xlabel('Sample (30 samples per ms)')
				ax.set_ylabel('Voltage (microvolts)')
				ax.set_title("Split Cluster{:d}, 2ms ISI violations={:.1f} percent".format(cluster, violations2) + "\n" + "1ms ISI violations={:.1f}%, Number of waveforms={:d}".format(violations1, split_points.shape[0]))

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
    x1_min, x1_max = expand(x1_min, x1_max)
    x2_min, x2_max = expand(x2_min, x2_max)
    x1, x2 = np.mgrid[x1_min:x1_max:500j, x2_min:x2_max:500j]
    grid_test = np.stack((x1.flat, x2.flat), axis=1)

    plt.figure(figsize=(6, 6), facecolor='w')
    plt.suptitle('GMM/DPGMM比较', fontsize=15)

    ax = plt.subplot(211)
    gmm = GaussianMixture(n_components=n_components, covariance_type='full', random_state=0)
    gmm.fit(x)
    centers = gmm.means_
    covs = gmm.covariances_
    print('GMM均值 = \n', centers)
    print('GMM方差 = \n', covs)
    y_hat = gmm.predict(x)

    grid_hat = gmm.predict(grid_test)
    grid_hat = grid_hat.reshape(x1.shape)
    plt.pcolormesh(x1, x2, grid_hat, cmap=cm)
    plt.scatter(x[:, 0], x[:, 1], s=20, c=y, cmap=cm, marker='o', edgecolors='#202020')

    clrs = list('rgbmy')
    for i, (center, cov) in enumerate(zip(centers, covs)):
        value, vector = sp.linalg.eigh(cov)
        width, height = value[0], value[1]
        v = vector[0] / sp.linalg.norm(vector[0])
        angle = 180* np.arctan(v[1] / v[0]) / np.pi
        e = Ellipse(xy=center, width=width, height=height,
                    angle=angle, color=clrs[i], alpha=0.5, clip_box = ax.bbox)
        ax.add_artist(e)

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
    N2 = 300
    N = N1 + N2
    x1 = np.random.multivariate_normal(mean=(1, 2), cov=cov1, size=N1)
    m = np.array(((1, 1), (1, 3)))
    x1 = x1.dot(m)
    x2 = np.random.multivariate_normal(mean=(-1, 10), cov=cov1, size=N2)
    x = np.vstack((x1, x2))
    y = np.array([0]*N1 + [1]*N2)

    types = ('spherical', 'diag', 'tied', 'full')
    err = np.empty(len(types))
    bic = np.empty(len(types))
    for i, type in enumerate(types):
        gmm = GaussianMixture(n_components=2, covariance_type=type, random_state=0)
        gmm.fit(x)
        err[i] = 1 - accuracy_rate(gmm.predict(x), y)
        bic[i] = gmm.bic(x)
    print('错误率：', err.ravel())
    print('BIC：', bic.ravel())
    xpos = np.arange(4)
    plt.figure(facecolor='w')
    ax = plt.axes()
    b1 = ax.bar(xpos-0.3, err, width=0.3, color='#77E0A0', edgecolor='k')
    b2 = ax.twinx().bar(xpos, bic, width=0.3, color='#FF8080', edgecolor='k')
    plt.grid(b=True, ls=':', color='#606060')
    bic_min, bic_max = expand(bic.min(), bic.max())
    plt.ylim((bic_min, bic_max))
    plt.xticks(xpos, types)
    plt.legend([b1[0], b2[0]], ('错误率', 'BIC'))
    plt.title('不同方差类型的误差率和BIC', fontsize=15)
    plt.show()

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
    d = (b - a) * 0.05
    return a-d, b+d


if __name__ == '__main__':
    data = np.loadtxt('..\\HeightWeight.csv', dtype=np.float, delimiter=',', skiprows=1)
    print(data.shape)
    y, x = np.split(data, [1, ], axis=1)
    x, x_test, y, y_test = train_test_split(x, y, train_size=0.6, random_state=0)
    gmm = GaussianMixture(n_components=2, covariance_type='full', random_state=0)
    x_min = np.min(x, axis=0)
    x_max = np.max(x, axis=0)
    gmm.fit(x)
    print('均值 = \n', gmm.means_)
    print('方差 = \n', gmm.covariances_)
    y_hat = gmm.predict(x)
    y_test_hat = gmm.predict(x_test)
    change = (gmm.means_[0][0] > gmm.means_[1][0])
    if change:
        z = y_hat == 0
        y_hat[z] = 1
        y_hat[~z] = 0
        z = y_test_hat == 0
        y_test_hat[z] = 1
        y_test_hat[~z] = 0
    acc = np.mean(y_hat.ravel() == y.ravel())
    acc_test = np.mean(y_test_hat.ravel() == y_test.ravel())
    acc_str = '训练集准确率：%.2f%%' % (acc * 100)
    acc_test_str = '测试集准确率：%.2f%%' % (acc_test * 100)
    print(acc_str)
    print(acc_test_str)

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]

#.........这里部分代码省略.........
        reduced_data = Rtsne(norm_counts, num_dimensions, 
                             theta=tsne_theta, perplexity=tsne_perplexity)
    elif "PCA" in dimensionality:
        n_comps = num_dimensions
        solver = "auto"
        if pca_auto_components is not None:
            n_comps = pca_auto_components
            solver = "full"
        decomp_model = PCA(n_components=n_comps, svd_solver=solver, 
                           whiten=True, copy=True)
    elif "ICA" in dimensionality:
        decomp_model = FastICA(n_components=num_dimensions, 
                               algorithm='parallel', whiten=True,
                               fun='logcosh', w_init=None, random_state=None)
    elif "SPCA" in dimensionality:
        import multiprocessing
        decomp_model = SparsePCA(n_components=num_dimensions, alpha=1, 
                                 n_jobs=multiprocessing.cpu_count()-1)
    elif "FactorAnalysis" in dimensionality:
        decomp_model = FactorAnalysis(n_components=num_dimensions)
    else:
        sys.stderr.write("Error, incorrect dimensionality reduction method\n")
        sys.exit(1)
     
    if not "tSNE" in dimensionality:
        # Perform dimensionality reduction, outputs a bunch of 2D/3D coordinates
        reduced_data = decomp_model.fit_transform(norm_counts)
    
    print("Performing clustering...")
    # Do clustering of the dimensionality reduced coordinates
    if "KMeans" in clustering:
        labels = KMeans(init='k-means++',
                        n_clusters=num_clusters,
                        n_init=10).fit_predict(reduced_data)
    elif "Hierarchical" in clustering:
        labels = AgglomerativeClustering(n_clusters=num_clusters,
                                         affinity='euclidean',
                                         linkage='ward').fit_predict(reduced_data)
    elif "DBSCAN" in clustering:
        labels = DBSCAN(eps=dbscan_eps, min_samples=dbscan_min_size, 
                        metric='euclidean', n_jobs=-1).fit_predict(reduced_data)
    elif "Gaussian" in clustering:
        gm = GaussianMixture(n_components=num_clusters,
                             covariance_type='full').fit(reduced_data)
        labels = gm.predict(reduced_data)
    else:
        sys.stderr.write("Error, incorrect clustering method\n")
        sys.exit(1)
        
    # Check if there are -1 in the labels and that the number of labels is correct
    if -1 in labels or len(labels) != len(norm_counts.index):
        sys.stderr.write("Error, something went wrong in the clustering..\n")
        sys.exit(1)
        
    # We do not want zeroes in the labels
    if 0 in labels: labels = labels + 1

    # Write the spots and their classes to a file
    file_writers = [open(os.path.join(outdir,
                                      "{}_clusters.tsv".format(
                                      os.path.splitext(os.path.basename(name))[0])),"w")
                    for name in counts_table_files]
    # Write the coordinates and the label/class that they belong to
    spot_plot_data = defaultdict(lambda: [[],[],[],[]])
    for i, spot in enumerate(norm_counts.index):
        tokens = spot.split("x")

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
t = PrettyTable(['Method', 'Accuracy'])

km = KMeans(k, n_init=5)
km.fit(Y)
zh_kmeans = km.labels_
x1_kmeans = X[np.where(zh_kmeans==0)][:, np.newaxis]
x2_kmeans = X[np.where(zh_kmeans==1)][:, np.newaxis]
x1_mu_kmeans, x2_mu_kmeans = km.cluster_centers_
x1_mu_kmeans, x2_mu_kmeans = x1_mu_kmeans[0], x2_mu_kmeans[0]
x1_var_kmeans, x2_var_kmeans = np.var(x1_kmeans), np.var(x2_kmeans)
acc_kmeans = metric.accuracy(z, zh_kmeans)
t.add_row(['k-means', acc_kmeans])

gm = GMM(k, n_init=5, init_params="kmeans")
gm.fit(Y)
zh_gmm = gm.predict(Y)
#x1_gmm = X[np.where(zh_gmm==0)][:, np.newaxis]
#x2_gmm = X[np.where(zh_gmm==1)][:, np.newaxis]
x1_mu_gmm, x2_mu_gmm = gm.means_
x1_mu_gmm, x2_mu_gmm = x1_mu_gmm[0], x2_mu_gmm[0]
x1_var_gmm, x2_var_gmm = gm.covariances_
x1_var_gmm, x2_var_gmm = x1_var_gmm[0][0], x2_var_gmm[0][0]
acc_gmm = metric.accuracy(z, zh_gmm)
t.add_row(['gmm', acc_gmm])

G = eclust.kernel_matrix(Y, lambda x, y: np.linalg.norm(x-y))
zh_kgroups = wrapper.kernel_kgroups(k, Y, G)
x1_kgroups = X[np.where(zh_kgroups==0)][:, np.newaxis]
x2_kgroups = X[np.where(zh_kgroups==1)][:, np.newaxis]
acc_kgroups = metric.accuracy(z, zh_kgroups)
t.add_row(['kernel k-groups', acc_kgroups])

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
    
    start = timer()
    zh = kernel_kmeans(k, G, Z0, W)
    end = timer()
    Zh = ztoZ(zh)
    t.add_row(["kernel k-means (k-means++)", metric.accuracy(z, zh), 
                  objective(Zh, G, W), end-start])
    
    start = timer()
    zh = kernel_kmeans(k, G, Z1, W)
    end = timer()
    Zh = ztoZ(zh)
    t.add_row(["kernel k-means (spectral)", metric.accuracy(z, zh), 
                  objective(Zh, G, W), end-start])
    
    start = timer()
    gmm = GMM(k)
    gmm.fit(X)
    zh = gmm.predict(X)
    end = timer()
    t.add_row(["GMM", metric.accuracy(z, zh), "-", end-start])
    
    start = timer()
    km = KMeans(k)
    zh = km.fit_predict(X)
    end = timer()
    t.add_row(["k-means", metric.accuracy(z, zh), "-", end-start])

    print t

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
    N2 = 300
    N = N1 + N2
    x1 = np.random.multivariate_normal(mean=(3, 2), cov=cov1, size=N1)
    m = np.array(((1, 1), (1, 3)))
    x1 = x1.dot(m)
    x2 = np.random.multivariate_normal(mean=(-1, 10), cov=cov1, size=N2)
    x = np.vstack((x1, x2))
    y = np.array([0]*N1 + [1]*N2)

    gmm = GaussianMixture(n_components=2, covariance_type='full', random_state=0)
    gmm.fit(x)
    centers = gmm.means_
    covs = gmm.covariances_
    print('GMM均值 = \n', centers)
    print('GMM方差 = \n', covs)
    y_hat = gmm.predict(x)

    colors = '#A0FFA0', '#E080A0',
    levels = 10
    cm = mpl.colors.ListedColormap(colors)
    x1_min, x1_max = x[:, 0].min(), x[:, 0].max()
    x2_min, x2_max = x[:, 1].min(), x[:, 1].max()
    x1_min, x1_max = expand(x1_min, x1_max)
    x2_min, x2_max = expand(x2_min, x2_max)
    x1, x2 = np.mgrid[x1_min:x1_max:500j, x2_min:x2_max:500j]
    grid_test = np.stack((x1.flat, x2.flat), axis=1)
    print(gmm.score_samples(grid_test))
    grid_hat = -gmm.score_samples(grid_test)
    grid_hat = grid_hat.reshape(x1.shape)
    plt.figure(figsize=(7, 6), facecolor='w')
    ax = plt.subplot(111)

# 需要导入模块: from sklearn.mixture import GaussianMixture [as 别名]
# 或者: from sklearn.mixture.GaussianMixture import predict [as 别名]
 def gmm_analysis(self, X_train, X_test, y_train, y_test, data_set_name, max_clusters, analysis_name='GMM'):
     scl = RobustScaler()
     X_train_scl = scl.fit_transform(X_train)
     X_test_scl = scl.transform(X_test)
     
     em_bic = []
     em_aic = []
     em_completeness_score = []
     em_homogeneity_score = []
     em_measure_score = []
     em_adjusted_rand_score = []
     em_adjusted_mutual_info_score = []
     
     cluster_range = np.arange(2, max_clusters+1, 1)
     for k in cluster_range:
         print('K Clusters: ', k)
         
         ##
         ## Expectation Maximization
         ##
         em = GaussianMixture(n_components=k, covariance_type='full')
         em.fit(X_train_scl)
         em_pred = em.predict(X_train_scl)
         
         em_bic.append(em.bic(X_train_scl))
         em_aic.append(em.aic(X_train_scl))        
     
         # metrics
         y_train_score = y_train.reshape(y_train.shape[0],)
         
         em_homogeneity_score.append(homogeneity_score(y_train_score, em_pred))
         em_completeness_score.append(completeness_score(y_train_score, em_pred))
         em_measure_score.append(v_measure_score(y_train_score, em_pred))
         em_adjusted_rand_score.append(adjusted_rand_score(y_train_score, em_pred))
         em_adjusted_mutual_info_score.append(adjusted_mutual_info_score(y_train_score, em_pred))
         
     
     ##
     ## Plots
     ##
     ph = plot_helper()
     
     ##
     ## BIC/AIC Plot
     ##
     title = 'Information Criterion Plot (' + analysis_name + ') for ' + data_set_name
     name = data_set_name.lower() + '_' + analysis_name.lower() + '_ic'
     filename = './' + self.out_dir + '/' + name + '.png'
     
     ph.plot_series(cluster_range,
                 [em_bic, em_aic],
                 [None, None],
                 ['bic', 'aic'],
                 cm.viridis(np.linspace(0, 1, 2)),
                 ['o', '*'],
                 title,
                 'Number of Clusters',
                 'Information Criterion',
                 filename)
     
     ##
     ## Score Plot
     ##
     title = 'Score Summary Plot (' + analysis_name + ') for ' + data_set_name
     name = data_set_name.lower() + '_' + analysis_name.lower() + '_score'
     filename = './' + self.out_dir + '/' + name + '.png'
                 
     ph.plot_series(cluster_range,
                 [em_homogeneity_score, em_completeness_score, em_measure_score, em_adjusted_rand_score, em_adjusted_mutual_info_score],
                 [None, None, None, None, None, None],
                 ['homogeneity', 'completeness', 'measure', 'adjusted_rand', 'adjusted_mutual_info'],
                 cm.viridis(np.linspace(0, 1, 5)),
                 ['o', '^', 'v', '>', '<', '1'],
                 title,
                 'Number of Clusters',
                 'Score',
                 filename)