tsne
数据不做预处理:
# coding: utf-8
import collections
import numpy as np
import os
import pickle
from sklearn.neighbors import NearestNeighbors
import numpy as np
from sklearn.manifold import TSNE
# .......
X = X+black_verify+white_verify+unknown_verify+bd_verify
print black_verify_labels+white_verify_labels+unknown_verify_labels+bd_verify_labels
y = y+black_verify_labels+white_verify_labels+unknown_verify_labels+bd_verify_labels
print("ALL data check:")
print("len of X:", len(X))
print("len of y:", len(y))
# print(unknown_verify)
X_embedded = TSNE(n_components=2).fit_transform(X)
with open("tsne_data_X.pkl", "wb") as f:
pickle.dump([X_embedded, y], f)
import pickle
from collections import Counter
import numpy as np
import matplotlib.pyplot as Plot
def main():
with open("tsne_data_X.pkl", "rb") as f:
[X_embedded, y] = pickle.load(f, encoding='iso-8859-1')
print(len(X_embedded))
print(len(y))
print(X_embedded[:3])
print(y[:3])
i = 0
for l in y:
if type(l) == type([]):
raise Exception(str([i,y]))
i+=1
print(Counter(y))
Y, labels = np.array(X_embedded), np.array(y)
titles = ("white","black","black_verify_labels","white_verify_labels","unknown_verify_labels","bd_verify_labels")
colors=['b', 'c', 'y', 'm', 'r', 'g', 'peru']
for i in range(0, 6):
idx_1 = [i1 for i1 in range(len(labels)) if labels[i1]==i]
flg1=Plot.scatter(Y[idx_1,0], Y[idx_1,1], 20,color=colors[i],label=titles[i]);
Plot.legend()
Plot.savefig('tsne.pdf')
Plot.show()
main()
数据做standard标准化处理
使用pca,不进行预处理:
使用standard scaler预处理,再做pca:
from sklearn import preprocessing
scaler = preprocessing.StandardScaler().fit(X)
#scaler = preprocessing.MinMaxScaler().fit(X)
X = scaler.transform(X)
print("standard X sample:", X[:3])
black_verify = scaler.transform(black_verify)
print(black_verify)
white_verify = scaler.transform(white_verify)
print(white_verify)
unknown_verify = scaler.transform(unknown_verify)
print(unknown_verify)
bd_verify = scaler.transform(bd_verify)
print(bd_verify)
#print black_verify_labels+white_verify_labels+unknown_verify_labels+bd_verify_labels
X = np.concatenate((X,black_verify,white_verify,unknown_verify,bd_verify))
#X = X+black_verify+white_verify+unknown_verify+bd_verify
y = y+black_verify_labels+white_verify_labels+unknown_verify_labels+bd_verify_labels
print("ALL data check:")
print("len of X:", len(X))
print("len of y:", len(y))
# print(unknown_verify)
X_embedded = PCA(n_components=2).fit_transform(X)
with open("pca_data_X_scaled.pkl", "wb") as f:
pickle.dump([X_embedded, y], f)
最后效果:
最后使用自编码器来来降维:
代码:
X = np.concatenate((X,black_verify,white_verify,unknown_verify,bd_verify))
y = y+black_verify_labels+white_verify_labels+unknown_verify_labels+bd_verify_labels
print("ALL data check:")
print("len of X:", len(X))
print("len of y:", len(y))
# print(unknown_verify)
ratio_of_train = 0.8
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=(1 - ratio_of_train))
# Building the encoder
encoder = tflearn.input_data(shape=[None, 75])
encoder = tflearn.fully_connected(encoder, 64)
encoder = tflearn.fully_connected(encoder, 2)
# Building the decoder
decoder = tflearn.fully_connected(encoder, 64)
decoder = tflearn.fully_connected(decoder, 75, activation='sigmoid')
# Regression, with mean square error
net = tflearn.regression(decoder, optimizer='adam', learning_rate=0.0001,
loss='mean_square', metric=None)
# Training the auto encoder
model = tflearn.DNN(net, tensorboard_verbose=0)
model.fit(X_train, X_train, n_epoch=200, validation_set=(X_test, X_test),
run_id="auto_encoder", batch_size=1024)
# Encoding X[0] for test
print("\nTest encoding of X[0]:")
# New model, re-using the same session, for weights sharing
encoding_model = tflearn.DNN(encoder, session=model.session)
print(encoding_model.predict([X[0]]))
X_embedded = encoding_model.predict(X) #TSNE(n_components=2).fit_transform(X)
with open("tflearn_auto_enc_data_X_scaled.pkl", "wb") as f:
pickle.dump([X_embedded, y], f)
如果是迭代次数不一样,则可能有一些差别,见下图,和上面的可能有些差别:
修改64为128: