Python manifold.TSNE类代码示例

def display_closestwords_tsnescatterplot(model, word):
    arr = np.empty((0,300), dtype='f')
    word_labels = [word]

    # get close words
    close_words = model.similar_by_word(word)
    
    # add the vector for each of the closest words to the array
    arr = np.append(arr, np.array([model[word]]), axis=0)
    for wrd_score in close_words:
        wrd_vector = model[wrd_score[0]]
        word_labels.append(wrd_score[0])
        arr = np.append(arr, np.array([wrd_vector]), axis=0)
        
    # find tsne coords for 2 dimensions
    tsne = TSNE(n_components=2, random_state=0)
    np.set_printoptions(suppress=True)
    Y = tsne.fit_transform(arr)

    x_coords = Y[:, 0]
    y_coords = Y[:, 1]
    # display scatter plot
    plt.scatter(x_coords, y_coords)

    for label, x, y in zip(word_labels, x_coords, y_coords):
        plt.annotate(label, xy=(x, y), xytext=(0, 0), textcoords='offset points')
    plt.xlim(x_coords.min()+0.00005, x_coords.max()+0.00005)
    plt.ylim(y_coords.min()+0.00005, y_coords.max()+0.00005)
    plt.show()

def plot_data(data, has_label=True):
	import numpy as np
	import seaborn as sns
	from sklearn.manifold import TSNE
	from sklearn.decomposition import PCA

	if not has_label:
		data = data.copy()
		data['label'] = np.zeros([len(data),1])

	LIMIT = 4000
	if data.shape[0] > LIMIT:
		dt = data.sample(n=LIMIT, replace=False)
		X = dt.ix[:,:-1]
		labels = dt.ix[:,-1]
	else:
		X = data.ix[:,:-1]
		labels = data.ix[:,-1]

	tsne_model = TSNE(n_components=2, random_state=0)
	np.set_printoptions(suppress=True)
	points1 = tsne_model.fit_transform(X)
	df1 = pd.DataFrame(data=np.column_stack([points1,labels]), columns=["x","y","class"])
	sns.lmplot("x", "y", data=df1, hue='class', fit_reg=False, palette=sns.color_palette('colorblind'))
	sns.plt.title('TNSE')

	pca = PCA(n_components=2)
	pca.fit(X)
	points2 = pca.transform(X)
	df2 = pd.DataFrame(data=np.column_stack([points2,labels]), columns=["x","y","class"])
	sns.lmplot("x", "y", data=df2, hue='class', fit_reg=False, palette=sns.color_palette('colorblind'))
	sns.plt.title('PCA')

def make_tsne_plot(model, rel_wds, plot_lims, title):

    dim = 30
    X, keys = make_data_matrix(model)

    # first we actually do PCA to reduce the
    # dimensionality to make tSNE easier to calculate
    X_std = StandardScaler().fit_transform(X)
    sklearn_pca = PCA(n_components=2)
    X = sklearn_pca.fit_transform(X_std)[:,:dim]

    # do downsample
    k = 5000
    sample = []
    important_words = []
    r_wds = [word[0] for word in rel_wds]
    for i, key in enumerate(keys):
        if key in r_wds:
            sample.append(i)
    sample = np.concatenate((np.array(sample),
                np.random.choice(len(keys), k-10, replace = False),
             ))
    X = X[sample,:]
    keys = [keys[i] for i in sample]



    # Do tSNE
    tsne = TSNE(n_components=2, random_state=0, metric="cosine")
    X_transf = tsne.fit_transform(X)

    k_means = KMeans(n_clusters=8)
    labels = k_means.fit_predict(X_transf)

    scatter_plot(X_transf[:,0], X_transf[:,1],  rel_wds, labels, title, keys, plot_lims)

def t_sne_view(norm_table, subj_cond, cohorts, image_type):

    # t-SNE analysis: Use stochastic neighbor embedding to reduce dimensionality of
    # data set to two dimensions in a non-linear, distance dependent fashion

    # Perform PCA data reduction if dimensionality of feature space is large:
    if len(norm_table.columns) > 12:
        pca = PCA(n_components = 12)
        pca.fit(norm_table.as_matrix())
        
        raw_data = pca.transform(norm_table.as_matrix())
    else:
        raw_data = norm_table.as_matrix()
 
    # Transform data into a two-dimensional embedded space:
    tsne = TSNE(n_components = 2, perplexity = 40.0, early_exaggeration= 2.0, 
        learning_rate = 100.0, init = 'pca')

    tsne_data = tsne.fit_transform(raw_data)

    # Prepare for normalization and view:
    cols = ['t-SNE', 'Cluster Visualization']
    tsne_table = pd.DataFrame(tsne_data, index = norm_table.index, columns = cols)
           
    # The output is no longer centered or normalized, so shift & scale it before display:
    tsne_avg = ppmi.data_stats(tsne_table, subj_cond, cohorts)
    tsne_norm_table = ppmi.normalize_table(tsne_table, tsne_avg)       
    
    # Send out to graphics rendering engine:

    if (image_type == 'Gauss'):
        return scg.scatter_gauss(tsne_norm_table[cols[0]], tsne_norm_table[cols[1]], subj_cond)
    elif (image_type == 'Scatter'):
        return scg.scatter_plain(tsne_norm_table[cols[0]], tsne_norm_table[cols[1]], subj_cond)

def perform_AE(X, dim=2, tsne=False):
    y = np.zeros(shape=X.shape[0], dtype=int)
    
    if tsne:
        hidden_layers = [X.shape[1], 500, 100, 32]
        encoder_weights, decoder_weights = pretrain(X, hidden_layers)
        X_32d = ae(X, encoder_weights, decoder_weights, hidden_layers)

        ae_tsne = TSNE(n_components=dim, learning_rate=800, verbose=1)
        X_2d = ae_tsne.fit_transform(X_32d)

        method = 'ae_tsne_scaled'
    ### END - if tsne

    else:
        hidden_layers = [X.shape[1], 500, 100, 20, dim]
        encoder_weights, decoder_weights = pretrain(X, hidden_layers)
        X_2d = ae(X, encoder_weights, decoder_weights, hidden_layers)
        
        method = 'ae_scaled'
    ### END - else

    print('***** ' + method + ' *****')
    cluster(X_2d, method)
    np.save("{0}_{1}_X_2d".format(species, method), X_2d)

def visualize_latent_rep(args, model, x_latent):
    print("pca_on=%r pca_comp=%d tsne_comp=%d tsne_perplexity=%f tsne_lr=%f" % (
        args.use_pca,
        args.pca_components,
        args.tsne_components,
        args.tsne_perplexity,
        args.tsne_lr
    ))

    if args.use_pca:
        pca = PCA(n_components = args.pca_components)
        x_latent = pca.fit_transform(x_latent)

    figure(figsize=(6, 6))
    scatter(x_latent[:, 0], x_latent[:, 1], marker='.')
    show()

    tsne = TSNE(n_components = args.tsne_components,
                perplexity = args.tsne_perplexity,
                learning_rate = args.tsne_lr,
                n_iter = args.tsne_iterations,
                verbose = 4)
    x_latent_proj = tsne.fit_transform(x_latent)
    del x_latent

    figure(figsize=(6, 6))
    scatter(x_latent_proj[:, 0], x_latent_proj[:, 1], marker='.')
    show()

def vizualize_clusters(X, y, py, hist=None):
    """ Using T-SNE to visualize the site clusters.
        Plot and save the scatter (and the histogramm).
    """
    model = TSNE(n_components=2, random_state=0)

    fig = model.fit_transform(X, y)
    fig1 = model.fit_transform(X, py)

    pyplot.figure(figsize=(16, 8))
    pyplot.subplot(121)

    classes = list(set(y))
    for c, color in zip(classes, plt.colors.cnames.iteritems()):
        indeces = [i for i, p in enumerate(y) if p == c]
        pyplot.scatter(fig[indeces, 0], fig[indeces, 1], marker="o", c=color[0])

    pyplot.subplot(122)

    clusters = list(set(py))
    for c, color in zip(clusters, plt.colors.cnames.iteritems()):
        indeces = [i for i, p in enumerate(py) if p == c]
        pyplot.scatter(fig1[indeces, 0], fig1[indeces, 1], marker="o", c=color[0])

    # pyplot.show()
    pyplot.savefig("clusters" + "_scatter.png")

    if hist is not None:
        pyplot.figure(figsize=(4, 4))
        pyplot.xticks(clusters)

        pyplot.bar(clusters, hist, align="center")
        # pyplot.show()
        pyplot.savefig("clusters" + "_hist.png")

def tsnePlot(plotname, modelName, word, dest):
    
    """Plots a tsne graph of words most similar to the word passed in the argument (as represented in the model previously calculated)"""
    
    model = word2vec.Word2Vec.load(modelName)
    words = [model.most_similar(word)[i][0] for i in range(0, len(model.most_similar(word)))]
    words.append(word)

    #nested list constaining 100 dimensional word vectors of each most-similar word
    
    word_vectors = [model[word] for word in words]
    word_vectors = np.array(word_vectors)

    tsne_model = TSNE(n_components=2, random_state=0)
    Y = tsne_model.fit_transform(word_vectors)
    sb.plt.plot(Y[:,0], Y[:,1], 'o') 

    for word, x, y in zip(words, Y[:,0], Y[:,1]):  
        sb.plt.annotate(word, (x, y), size=12)
        #sb.plt.pause(10)

    plotname = plotname + ".png"

    if not os.path.exists(dest):
        os.makedirs(dest)

    path = os.path.join(dest, plotname)

    sb.plt.savefig(path)

 def reduce_dimentionality(self):
     self.vectors = []
     for key in self.selected_words:
         self.vectors.append(self.model[key])
     tnse_model = TSNE(n_components=2, random_state=0)
     np.set_printoptions(suppress=True)
     self.reduced_vectors = tnse_model.fit_transform(self.vectors)

def plotTSNEDecisionBoundaries(): 
    
    tsne = TSNE()
    tsne_data = tsne.fit_transform(feature_set)
    x_min,x_max = tsne_data[:,0].min()-1, tsne_data[:,0].max() + 1
    y_min,y_max = tsne_data[:,1].min()-1, tsne_data[:,1].max() + 1
    step_size = 2.0
    
    xx,yy = np.meshgrid(np.arange(x_min,x_max,step_size),np.arange(y_min,y_max,step_size))
    
    for index,classifier in enumerate(classifiers):
        
        plt.subplot(2,3,index+1)
        plt.subplots_adjust(wspace=0.5,hspace=0.5)
        classifier.fit(tsne_data,class_labels)
        
        Z = classifier.predict(zip(xx.ravel(),yy.ravel()))
        Z = Z.reshape(xx.shape)
        
        plt.contourf(xx,yy,Z,cmap=plt.cm.Paired,alpha=0.7)
        plt.scatter(tsne_data[:,0],tsne_data[:,1],c=class_labels,cmap=plt.cm.rainbow,alpha=0.6)
        plt.xlabel("Feature 1")
        plt.ylabel("Feature 2")
        plt.xlim(x_min,x_max)
        plt.ylim(y_min,y_max)
        plt.xticks(())
        plt.yticks(())
        plt.title(classifier_names[index])
        
    plt.show()

def tsne_plot(model):
    #"Creates and TSNE model and plots it"
    labels = []
    tokens = []

    for word in model.wv.vocab:
        tokens.append(model[word])
        labels.append(word)

    tsne_model = TSNE(perplexity=40, n_components=2, init='pca', n_iter=2500, random_state=23)
    new_values = tsne_model.fit_transform(tokens)

    x = []
    y = []
    for value in new_values:
        x.append(value[0])
        y.append(value[1])

    plt.figure(figsize=(16, 16))
    for i in range(len(x)):
        plt.scatter(x[i], y[i])
        plt.annotate(labels[i],
                     xy=(x[i], y[i]),
                     xytext=(5, 2),
                     textcoords='offset points',
                     ha='right',
                     va='bottom')
    plt.show()

def visualization(result, word_dict):
	tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
	plot_only = 500

	low_dim_embs = tsne.fit_transform(result[0:500])
	labels = [ word_dict[i] for i in range(500) ]
	plot_with_labels(low_dim_embs, labels)

def plotly_js_viz(word_2_vec_model):
    tsne_model=TSNE(n_components=2,random_state=5)
    data=tsne_model.fit_transform(word_2_vec_model.syn0)
    xd=list(data[:,0])
    yd=list(data[:,1])
    names_our=word_2_vec_model.index2word
    plot([Scatter(x=xd,y=yd,mode="markers",text=names_our)])

def PlotTSNE (data, labels):										#Takes the data and the labels
	# Visualize the results on TSNE reduced data

	print "BUSY IN TSNE"

	model = TSNE(n_components=2, random_state=0)
	reduced_data = model.fit_transform(data)

	print "DATA REDUCED"

	# Plot the decision boundary. For that, we will assign a color to each
	x_min, x_max = reduced_data[:, 0].min(), reduced_data[:, 0].max()
	y_min, y_max = reduced_data[:, 1].min(), reduced_data[:, 1].max()
	
	plt.plot(reduced_data[:, 0], reduced_data[:, 1], 'k.', markersize=2)
	
	#Adds labels to the plot
	for label, x, y in zip(labels, reduced_data[:, 0], reduced_data[:, 1]):
	    plt.annotate(
	        label, 
	        xy = (x, y), xytext = (-20, 20),
	        textcoords = 'offset points', ha = 'right', va = 'bottom',
	        bbox = dict(boxstyle = 'round,pad=0.5', fc = 'green', alpha = 0.5),
	        arrowprops = dict(arrowstyle = '->', connectionstyle = 'arc3,rad=0'))

	plt.title('TSNE Plot')
	plt.xlim(x_min, x_max)
	plt.ylim(y_min, y_max)
	plt.xticks(())
	plt.yticks(())
	plt.show()

def labtest_TSNE(PID):
    data = [patients[pid]['tests'] for pid in PID]
    X = pp.scale(data)
    tsne = TSNE(n_components=2, perplexity=30.0, learning_rate=1000.0, n_iter=1000, n_iter_without_progress=30, min_grad_norm=1e-07, angle=0.5)
    pos = tsne.fit(X).embedding_
    
    return pos