rene
/
ma_cisco_malware
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

replace pca reduction by sklearn's truncated svd

This commit is contained in:
René Knaebel 2017-07-29 19:41:14 +02:00
parent 2593131e9e
commit 8cd1023165
1 changed files with 4 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
visualize.py
View File

@ -3,7 +3,7 @@ import os
import matplotlib.pyplot as plt
import numpy as np
from keras.utils import plot_model
from sklearn.decomposition import PCA
from sklearn.decomposition import TruncatedSVD
from sklearn.metrics import (
auc, classification_report, confusion_matrix, fbeta_score, precision_recall_curve,
roc_auc_score, roc_curve
@ -146,13 +146,11 @@ def plot_training_curve(logs, key, path, dpi=600):
def plot_embedding(domain_embedding, labels, path, dpi=600):
pca = PCA(n_components=2)
domain_reduced = pca.fit_transform(domain_embedding)
print(pca.explained_variance_ratio_)
svd = TruncatedSVD(n_components=2)
domain_reduced = svd.fit_transform(domain_embedding)
print(svd.explained_variance_ratio_)
# use if draw subset of predictions
# idx = np.random.choice(np.arange(len(domain_reduced)), 10000)
plt.scatter(domain_reduced[:, 0],
domain_reduced[:, 1],
c=(labels * (1, 2)).sum(1).astype(int),