为Gensim模型绘制3D图

以下功能使用t-SNE代替PCA进行尺寸缩减，但是将生成二维，三维或二维和三维图（使用子图）。此外，它将为您着色主题，因此更容易区分它们。%matplotlib notebook从anaconda添加到Jupyter笔记本环境的开始，将允许旋转3d图和缩放2d图（不要同时使用来同时创建两个版本%matplotlib notebook）。

该函数非常长，大多数代码用于绘图格式设置，但会产生专业的输出。

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
from matplotlib.lines import Line2D
import seaborn as sns

from gensim.models import LdaModel
from gensim import corpora
from sklearn.manifold import TSNE
# %matplotlib notebook # if in Jupyter for rotating and zooming

def LDA_tSNE_topics_vis(dimension='both',
                        corpus=None, 
                        num_topics=10,
                        remove_3d_outliers=False,
                        save_png=False):
    """
    Returns the outputs of an LDA model plotted using t-SNE (t-distributed Stochastic Neighbor Embedding)

    Note: t-SNE reduces the dimensionality of a space such that similar points will be closer and dissimilar points farther

    Parameters
    ----------
        dimension : str (default=both)
            The dimension that t-SNE should reduce the data to for visualization
            Options: 2d, 3d, and both (a plot with two subplots)

        corpus : list, list of lists
            The tokenized and cleaned text corpus over which analysis should be done

        num_topics : int (default=10)
            The number of categories for LDA based approaches

        remove_3d_outliers : bool (default=False)
            Whether to remove outliers from a 3d plot

        save_png : bool (default=False)
            Whether to save the figure as a png

    Returns
    -------
        A t-SNE lower dimensional representation of an LDA model's topics and their constituent members
    """
    dirichlet_dict = corpora.Dictionary(corpus)
    bow_corpus = [dirichlet_dict.doc2bow(text) for text in corpus]

    dirichlet_model = LdaModel(corpus=bow_corpus,
                               id2word=dirichlet_dict,
                               num_topics=num_topics,
                               update_every=1,
                               chunksize=len(bow_corpus),
                               passes=10,
                               alpha='auto',
                               random_state=42) # set for testing

    df_topic_coherences = pd.DataFrame(columns = ['topic_{}'.format(i) for i in range(num_topics)])

    for i in range(len(bow_corpus)):
        df_topic_coherences.loc[i] = [0] * num_topics
        
        output = dirichlet_model.__getitem__(bow=bow_corpus[i], eps=0)
    
        for j in range(len(output)):
            topic_num = output[j][0]
            coherence = output[j][1]
            df_topic_coherences.iloc[i, topic_num] = coherence

    for i in range(num_topics):
        df_topic_coherences.iloc[:, i] = df_topic_coherences.iloc[:, i].astype('float64', copy=False)

    df_topic_coherences['main_topic'] = df_topic_coherences.iloc[:, :num_topics].idxmax(axis=1)

    if num_topics > 10:
        # cubehelix better for more than 10 colors
        colors = sns.color_palette("cubehelix", num_topics)
    else:
        # The default sns color palette
        colors = sns.color_palette('deep', num_topics)

    tsne_2 = None
    tsne_3 = None
    if dimension == 'both':
        tsne_2 = TSNE(n_components=2, perplexity=40, n_iter=300)
        tsne_3 = TSNE(n_components=3, perplexity=40, n_iter=300)
    elif dimension == '2d':
        tsne_2 = TSNE(n_components=2, perplexity=40, n_iter=300)
    elif dimension == '3d':
        tsne_3 = TSNE(n_components=3, perplexity=40, n_iter=300)
    else:
        ValueError("An invalid value has been passed to the 'dimension' argument - choose from 2d, 3d, or both.")

    if tsne_2 is not None:
        tsne_results_2 = tsne_2.fit_transform(df_topic_coherences.iloc[:, :num_topics])
        
        df_tsne_2 = pd.DataFrame()
        df_tsne_2['tsne-2d-d1'] = tsne_results_2[:,0]
        df_tsne_2['tsne-2d-d2'] = tsne_results_2[:,1]
        df_tsne_2['main_topic'] = df_topic_coherences.iloc[:, num_topics]
        df_tsne_2['color'] = [colors[int(t.split('_')[1])] for t in df_tsne_2['main_topic']]

        df_tsne_2['topic_num'] = [int(i.split('_')[1]) for i in df_tsne_2['main_topic']]
        df_tsne_2 = df_tsne_2.sort_values(['topic_num'], ascending = True).drop('topic_num', axis=1)
    
    if tsne_3 is not None:
        colors = [c for c in sns.color_palette()]

        tsne_results_3 = tsne_3.fit_transform(df_topic_coherences.iloc[:, :num_topics])
        
        df_tsne_3 = pd.DataFrame()
        df_tsne_3['tsne-3d-d1'] = tsne_results_3[:,0]
        df_tsne_3['tsne-3d-d2'] = tsne_results_3[:,1]
        df_tsne_3['tsne-3d-d3'] = tsne_results_3[:,2]
        df_tsne_3['main_topic'] = df_topic_coherences.iloc[:, num_topics]
        df_tsne_3['color'] = [colors[int(t.split('_')[1])] for t in df_tsne_3['main_topic']]

        df_tsne_3['topic_num'] = [int(i.split('_')[1]) for i in df_tsne_3['main_topic']]
        df_tsne_3 = df_tsne_3.sort_values(['topic_num'], ascending = True).drop('topic_num', axis=1)

        if remove_3d_outliers:
            # Remove those rows with values that are more than three standard deviations from the column mean
            for col in ['tsne-3d-d1', 'tsne-3d-d2', 'tsne-3d-d3']:
                df_tsne_3 = df_tsne_3[np.abs(df_tsne_3[col] - df_tsne_3[col].mean()) <= (3 * df_tsne_3[col].std())]

    if tsne_2 is not None and tsne_3 is not None:
        fig, (ax1, ax2) = plt.subplots(nrows=1, ncols=2, # pylint: disable=unused-variable
                                       figsize=(20,10))
        ax1.axis('off')

    else:
        fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(20,10))

    if tsne_2 is not None and tsne_3 is not None:
        # Plot tsne_2, with tsne_3 being added later
        ax1 = sns.scatterplot(data=df_tsne_2, x="tsne-2d-d1", y="tsne-2d-d2",
                              hue=df_topic_coherences.iloc[:, num_topics], alpha=0.3)
        
        light_grey_tup = (242/256, 242/256, 242/256)
        ax1.set_facecolor(light_grey_tup)
        ax1.axes.set_title('t-SNE 2-Dimensional Representation', fontsize=25)
        ax1.set_xlabel('tsne-d1', fontsize=20)
        ax1.set_ylabel('tsne-d2', fontsize=20)

        handles, labels = ax1.get_legend_handles_labels()
        legend_order = list(np.argsort([i.split('_')[1] for i in labels]))
        ax1.legend([handles[i] for i in legend_order], [labels[i] for i in legend_order], 
                   facecolor=light_grey_tup)

    elif tsne_2 is not None:
        # Plot just tsne_2
        ax = sns.scatterplot(data=df_tsne_2, x="tsne-2d-d1", y="tsne-2d-d2",
                             hue=df_topic_coherences.iloc[:, num_topics], alpha=0.3)

        ax.set_facecolor(light_grey_tup)
        ax.axes.set_title('t-SNE 2-Dimensional Representation', fontsize=25)
        ax.set_xlabel('tsne-d1', fontsize=20)
        ax.set_ylabel('tsne-d2', fontsize=20)

        handles, labels = ax.get_legend_handles_labels()
        legend_order = list(np.argsort([i.split('_')[1] for i in labels]))
        ax.legend([handles[i] for i in legend_order], [labels[i] for i in legend_order], 
                  facecolor=light_grey_tup)

    if tsne_2 is not None and tsne_3 is not None:
        # tsne_2 has been plotted, so add tsne_3
        ax2 = fig.add_subplot(121, projection='3d')
        ax2.scatter(xs=df_tsne_3['tsne-3d-d1'], 
                    ys=df_tsne_3['tsne-3d-d2'], 
                    zs=df_tsne_3['tsne-3d-d3'],  
                    c=df_tsne_3['color'],
                    alpha=0.3)

        ax2.set_facecolor('white')
        ax2.axes.set_title('t-SNE 3-Dimensional Representation', fontsize=25)
        ax2.set_xlabel('tsne-d1', fontsize=20)
        ax2.set_ylabel('tsne-d2', fontsize=20)
        ax2.set_zlabel('tsne-d3', fontsize=20)

        with plt.rc_context({"lines.markeredgewidth" : 0}):
            # Add handles via blank lines and order their colors to match tsne_2
            proxy_handles = [Line2D([0], [0], linestyle="none", marker='o', markersize=8,
                                    markerfacecolor=colors[i]) for i in legend_order]
            ax2.legend(proxy_handles, ['topic_{}'.format(i) for i in range(num_topics)], 
                       loc='upper left', facecolor=(light_grey_tup))

    elif tsne_3 is not None:
        # Plot just tsne_3
        ax.axis('off')
        ax.set_facecolor('white')
        ax = fig.add_subplot(111, projection='3d')
        ax.scatter(xs=df_tsne_3['tsne-3d-d1'], 
                   ys=df_tsne_3['tsne-3d-d2'], 
                   zs=df_tsne_3['tsne-3d-d3'],  
                   c=df_tsne_3['color'],
                   alpha=0.3)

        ax.set_facecolor('white')
        ax.axes.set_title('t-SNE 3-Dimensional Representation', fontsize=25)
        ax.set_xlabel('tsne-d1', fontsize=20)
        ax.set_ylabel('tsne-d2', fontsize=20)
        ax.set_zlabel('tsne-d3', fontsize=20)

        with plt.rc_context({"lines.markeredgewidth" : 0}):
            # Add handles via blank lines
            proxy_handles = [Line2D([0], [0], linestyle="none", marker='o', markersize=8,
                                    markerfacecolor=colors[i]) for i in range(len(colors))]
            ax.legend(proxy_handles, ['topic_{}'.format(i) for i in range(num_topics)], 
                      loc='upper left', facecolor=light_grey_tup)

    if save_png:
        plt.savefig('LDA_tSNE_{}.png'.format(time.strftime("%Y%m%d-%H%M%S")), bbox_inches='tight', dpi=500)

    plt.show()

子图上10个主题gensim LDA模型的2d和3d（除去异常值）表示的示例图如下：