Lernen Sie mnist unbeaufsichtigt mit Variations-Auto-Encoder und -Cluster und bewerten Sie die letzte Phase

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
#Importieren Sie die erforderlichen Bibliotheken
from keras.datasets import mnist
import numpy as np
import pandas as pd
import sklearn
#Zeigen Sie Plotergebnisse im Notizbuch an, wenn Sie das Jupyter-Notizbuch verwenden
import matplotlib.pyplot as plt
%matplotlib inline

from keras.layers import Lambda, Input, Dense
from keras.models import Model
from keras.losses import mse
from keras import backend as K
import gc

Using TensorFlow backend.

feature_dims = range(2, 12)

#Lesen Sie Daten mit der Keras-Funktion. Mische Daten und teile sie in Trainingsdaten und Trainingsdaten auf
(x_train, y_train), (x_test, y_test) = mnist.load_data()

#Konvertieren Sie 2D-Daten in numerische Werte
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
#Typkonvertierung
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
#Teilen Sie durch 255 als neue Variable
x_train /= 255
x_test /= 255

# one-Methode zur Hot-Codierung
from keras.utils.np_utils import to_categorical
#10 Klassen
num_classes = 10
y_train = y_train.astype('int32')
y_test = y_test.astype('int32')
labels = y_test
# one-hot encoding
y_train = to_categorical(y_train, num_classes)
y_test =  to_categorical(y_test, num_classes)

def fitting(feature_dim, x_train, y_train, x_test, y_test):
    original_dim = x_train.shape[1]

    input_shape = (original_dim, )
    latent_dim = feature_dim

    # Reparametrization Trick 
    def sampling(args):
        z_mean, z_logvar = args
        batch = K.shape(z_mean)[0]
        dim = K.int_shape(z_mean)[1]
        epsilon = K.random_normal(shape=(batch, dim), seed = 5) # ε
        return z_mean + K.exp(0.5 * z_logvar) * epsilon

    #VAE Modellbau
    inputs = Input(shape=input_shape)
    x1 = Dense(256, activation='relu')(inputs)  
    x2 = Dense(64, activation='relu')(x1) 
    z_mean = Dense(latent_dim)(x2)
    z_logvar = Dense(latent_dim)(x2)
    z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_logvar])
    encoder = Model(inputs, [z_mean, z_logvar, z], name='encoder')
    encoder.summary()

    latent_inputs = Input(shape=(latent_dim,))
    x3 = Dense(64, activation='relu')(latent_inputs)  
    x4 = Dense(256, activation='relu')(x3)  
    outputs = Dense(original_dim, activation='sigmoid')(x4)
    decoder = Model(latent_inputs, outputs, name='decoder')
    decoder.summary()

    z_output = encoder(inputs)[2]
    outputs = [decoder(z_output),z_output]
    vae = Model(inputs, outputs, name='variational_autoencoder')

    #Verlustfunktion
    # Kullback-Leibler Loss
    kl_loss = 1 + z_logvar - K.square(z_mean) - K.exp(z_logvar)
    kl_loss = K.sum(kl_loss, axis=-1)
    kl_loss *= -0.5
    # Reconstruction Loss
    reconstruction_loss = mse(inputs, outputs[0])
    reconstruction_loss *= original_dim

    vae_loss = K.mean(reconstruction_loss + kl_loss)
    vae.add_loss(vae_loss)
    vae.compile(optimizer='adam')
    vae.summary()
    history = vae.fit(x_train,
                    epochs=50,
                    batch_size=256,
                    validation_data=(x_test, None))
    result = vae.predict(x_test)

    K.clear_session() #← Das ist
    gc.collect()
    from IPython.display import clear_output
    clear_output()
    return (history, vae, result)

#model = fitting(10, x_train, y_train, x_test, y_test)
models = [None] * len(feature_dims)
histories = [None] * len(feature_dims)
dec_imgs = [None] * len(feature_dims)
results = [None] * len(feature_dims)
for i in range(len(feature_dims)):
    (histories[i], models[i], dec_imgs[i]) = fitting(feature_dims[i], x_train, y_train, x_test, y_test)

for i in range(len(feature_dims)):
    print(feature_dims[i])
    result = dec_imgs[i]
    decoded_imgs = result[0]
    #Anzeige des Testbildes und des konvertierten Bildes
    n = 10
    plt.figure(figsize=(10, 2))
    for j in range(n):
        #Testbild anzeigen
        ax = plt.subplot(2, n, j+1)
        plt.imshow(x_test[i].reshape(28, 28))
        plt.gray()
        ax.get_xaxis().set_visible(False)
        ax.get_yaxis().set_visible(False)

        #Konvertiertes Bild anzeigen
        ax = plt.subplot(2, n, j+1+n)
        plt.imshow(decoded_imgs[i][0][j].reshape(28, 28))
        plt.gray()
        ax.get_xaxis().set_visible(False)
        ax.get_yaxis().set_visible(False)
    plt.show()
    results[i] = result[1]

for i in range(len(feature_dims)):
    results[i] = dec_imgs[i][1]

#model.save('model/mnist-10')
#model = keras.models.load_model('model/mnist-10')
#for i in range(len(feature_dims)):
#    models[i].pop() #Entfernen Sie die Softmax-Ebene in der letzten Phase und verwenden Sie die Feature-Ebene als letzte Phase.
#    models[i].summary()

#result = model.predict(x_test)
#results = [None] * len(feature_dims)
#for i in range(len(feature_dims)):
#    keras.backend.clear_session()
#    results[i] = models[i].predict(x_test)

def tsne(result):
    #t-Dimensionsreduzierung mit SNE
    from sklearn.manifold import TSNE
    tsne = TSNE(n_components=2, random_state = 0, perplexity = 30, n_iter = 1000)
    return tsne.fit_transform(result)

#tsne = tsne(result)
tsnes = [None] * len(feature_dims)
for i in range(len(feature_dims)):
    tsnes[i] = tsne(results[i])

#df = pd.DataFrame(tsne, columns = ['x', 'y'])
#df['label'] = labels

def km(n_clusters, result):
    # k-Cluster mittels
    from sklearn.cluster import KMeans
    return KMeans(n_clusters).fit_predict(result)

#km = km(10, result)
#df['km'] = km
kms = [None] * len(feature_dims)
for i in range(len(feature_dims)):
    kms[i] = km(10, results[i])

def DBSCAN(n_clusters, result):
    from sklearn.cluster import DBSCAN
    db = DBSCAN(eps=0.2, min_samples=n_clusters).fit(result)
    return db.labels_

#dbscan = DBSCAN(20, result)
#df['DBSCAN'] = dbscan

def hierarchy(result):
    from scipy.cluster.hierarchy import linkage, dendrogram
    result1 = linkage(result, 
                  metric = 'braycurtis', 
                  #metric = 'canberra', 
                  #metric = 'chebyshev', 
                  #metric = 'cityblock', 
                  #metric = 'correlation', 
                  #metric = 'cosine', 
                  #metric = 'euclidean', 
                  #metric = 'hamming', 
                  #metric = 'jaccard', 
                  #method= 'single')
                  method = 'average')
                  #method= 'complete')
                  #method='weighted')
    return result1

#hierarchy = hierarchy(result)
#display(hierarchy)

def label_to_colors(label):
    color_dict = dict([(color[0], color[1]['color']) for color in zip(np.unique(label), plt.rcParams['axes.prop_cycle'])])
    colors = np.empty(label.shape, np.object)
    for k, v in color_dict.items():
        colors[label==k] = v
    return colors

#def cluster_visualization(x, y, label, cluster, method, n_clusters):
def cluster_visualization(x, y, label, cluster):
    plt.figure(figsize = (30, 15))
    plt.subplot(1,2,1)
    plt.scatter(x, y, c=label_to_colors(label))
#    for i in range(10):
#        tmp_df = df[df['label'] == i]
#        plt.scatter(tmp_df['x'], tmp_df['y'], label=i)
#    plt.legend(loc='upper left', bbox_to_anchor=(1,1))
    plt.subplot(1,2,2)
    plt.scatter(x, y, c=label_to_colors(cluster))
#    for i in range(n_clusters):
#        tmp_df = df[df[method] == i]
#        plt.scatter(tmp_df['x'], tmp_df['y'], label=i)
#    plt.legend(loc='upper left', bbox_to_anchor=(1,1))

for i in range(len(feature_dims)):
    cluster_visualization(tsnes[i][:,0], tsnes[i][:,1], labels, kms[i])

# https://qiita.com/mamika311/items/75c24f6892f85593f7e7
from sklearn.metrics.cluster import adjusted_rand_score
for i in range(len(feature_dims)):
    print("dim:" + str(feature_dims[i]) + " RMI: " + str(adjusted_rand_score(labels, kms[i])))

dim:2 RMI: 0.36620498031529986
dim:3 RMI: 0.41914836520424376
dim:4 RMI: 0.49394921137719777
dim:5 RMI: 0.5245649990462847
dim:6 RMI: 0.47705674510916446
dim:7 RMI: 0.41013993209378174
dim:8 RMI: 0.3698302406743967
dim:9 RMI: 0.32840225806718926
dim:10 RMI: 0.4466812382927318
dim:11 RMI: 0.4090677997413063

# https://scikit-learn.org/stable/modules/generated/sklearn.metrics.normalized_mutual_info_score.html
# https://qiita.com/kotap15/items/38289edfe822005e1e44
from sklearn.metrics import normalized_mutual_info_score
#display(normalized_mutual_info_score(labels, df['km']))
for i in range(len(feature_dims)):
    print("dim:" + str(feature_dims[i]) + " NMI: " + str(normalized_mutual_info_score(labels, kms[i])))

dim:2 NMI: 0.5199419992579754
dim:3 NMI: 0.56100353575167
dim:4 NMI: 0.605060303081276
dim:5 NMI: 0.6020900415664949
dim:6 NMI: 0.5631744057166579
dim:7 NMI: 0.5014462787979749
dim:8 NMI: 0.46110014862882315
dim:9 NMI: 0.42836636346088663
dim:10 NMI: 0.5187118150024308
dim:11 NMI: 0.48519256224162205

def shilhouette(clusters, x_test):
    from sklearn.metrics import silhouette_samples
    from matplotlib import cm
    plt.figure(figsize = (10, 10))
    cluster_labels=np.unique(clusters)
    n_clusters=cluster_labels.shape[0]
    silhouette_vals=silhouette_samples(x_test,clusters,metric='euclidean')
    y_ax_lower,y_ax_upper=0,0
    yticks=[]
    for i,c in enumerate(cluster_labels):
        c_silhouette_vals=silhouette_vals[clusters==c]
        print(len(c_silhouette_vals))
        c_silhouette_vals.sort()
        y_ax_upper +=len(c_silhouette_vals)
        color=cm.jet(float(i)/n_clusters)
        plt.barh(range(y_ax_lower,y_ax_upper),
                c_silhouette_vals,
                height=1.0,
                edgecolor='none',
                color=color
                )
        yticks.append((y_ax_lower+y_ax_upper)/2.)
        y_ax_lower += len(c_silhouette_vals)

    #Wenn der Silhouette-Koeffizient 1 ist, können Sie gut gruppieren.
    #Wenn die Breite der Silhouette im Durchschnitt in Bezug auf die Anzahl der Cluster gleich ist, bedeutet dies, dass die gesamten Daten gleichmäßig aufgeteilt werden können.
    #Diese Teilungsbreite=Eine mögliche Einstellmethode besteht darin, k so zu optimieren, dass die Breiten der Silhouette-Balken gleich sind und sich der Silhouette-Koeffizient 1 nähert..

    #Zeichnen Sie eine Linie an der Durchschnittsposition
    silhouette_avg=np.mean(silhouette_vals)
    plt.axvline(silhouette_avg,color="red",linestyle="--")
    plt.ylabel("Cluster")
    plt.xlabel("Silhouette coefficient")

for i in range(len(feature_dims)):
    shilhouette(kms[i], x_test)

[PYTHON] Lernen Sie mnist unbeaufsichtigt mit Variations-Auto-Encoder und -Cluster und werten Sie latente Variablen aus

Lernen Sie mnist unbeaufsichtigt mit Variations-Auto-Encoder und -Cluster und bewerten Sie die letzte Phase