def do_train():
X, Y, Xt, Yt = TrainFiles.from_csv(csv_file)
sl = SKSupervisedLearning(SVC, X, Y, Xt, Yt)
sl.fit_standard_scaler()
#pca = PCA(250)
#pca.fit(np.r_[sl.X_train_scaled, sl.X_test_scaled])
#X_pca = pca.transform(sl.X_train_scaled)
#X_pca_test = pca.transform(sl.X_test_scaled)
##construct a dataset for RBM
#X_rbm = X[:, 257:]
#Xt_rbm = X[:, 257:]
#rng = np.random.RandomState(123)
#rbm = RBM(X_rbm, n_visible=X_rbm.shape[1], n_hidden=X_rbm.shape[1]/4, numpy_rng=rng)
#pretrain_lr = 0.1
#k = 2
#pretraining_epochs = 200
#for epoch in xrange(pretraining_epochs):
# rbm.contrastive_divergence(lr=pretrain_lr, k=k)
# cost = rbm.get_reconstruction_cross_entropy()
# print >> sys.stderr, 'Training epoch %d, cost is ' % epoch, cost
trndata, tstdata = createDataSets(X, Y, X_test, Yt)
fnn = train(trndata,
tstdata,
epochs=1000,
test_error=0.025,
momentum=0.15,
weight_decay=0.0001)
def do_train():
X, Y, Xt, Yt = TrainFiles.from_csv(csv_file)
sl = SKSupervisedLearning(SVC, X, Y, Xt, Yt)
sl.fit_standard_scaler()
#pca = PCA(250)
#pca.fit(np.r_[sl.X_train_scaled, sl.X_test_scaled])
#X_pca = pca.transform(sl.X_train_scaled)
#X_pca_test = pca.transform(sl.X_test_scaled)
##construct a dataset for RBM
#X_rbm = X[:, 257:]
#Xt_rbm = X[:, 257:]
#rng = np.random.RandomState(123)
#rbm = RBM(X_rbm, n_visible=X_rbm.shape[1], n_hidden=X_rbm.shape[1]/4, numpy_rng=rng)
#pretrain_lr = 0.1
#k = 2
#pretraining_epochs = 200
#for epoch in xrange(pretraining_epochs):
# rbm.contrastive_divergence(lr=pretrain_lr, k=k)
# cost = rbm.get_reconstruction_cross_entropy()
# print >> sys.stderr, 'Training epoch %d, cost is ' % epoch, cost
trndata, tstdata = createDataSets(X, Y, X_test, Yt)
fnn = train(trndata, tstdata, epochs = 1000, test_error = 0.025, momentum = 0.15, weight_decay = 0.0001)
from SupervisedLearning import SKSupervisedLearning
from train_files import TrainFiles
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.metrics import log_loss, confusion_matrix
from sklearn.calibration import CalibratedClassifierCV
from tr_utils import vote
import matplotlib.pylab as plt
from train_nn import createDataSets, train
train_path_mix = "/kaggle/malware/mix_lbp.csv"
labels_file = "/kaggle/malware/trainLabels.csv"
X, Y_train, Xt, Y_test = TrainFiles.from_csv(train_path_mix)
def plot_confusion(sl):
conf_mat = confusion_matrix(sl.Y_test, sl.clf.predict(
sl.X_test_scaled)).astype(dtype='float')
norm_conf_mat = conf_mat / conf_mat.sum(axis=1)[:, None]
fig = plt.figure()
plt.clf()
ax = fig.add_subplot(111)
ax.set_aspect(1)
res = ax.imshow(norm_conf_mat, cmap=plt.cm.jet, interpolation='nearest')
cb = fig.colorbar(res)
labs = np.unique(Y_test)
x = labs - 1
plt.xticks(x, labs)
from SupervisedLearning import SKSupervisedLearning
from train_files import TrainFiles
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.metrics import log_loss, confusion_matrix
from sklearn.calibration import CalibratedClassifierCV
from tr_utils import vote
import matplotlib.pylab as plt
from train_nn import createDataSets, train
train_path_mix = "/kaggle/malware/mix_lbp.csv"
labels_file = "/kaggle/malware/trainLabels.csv"
X, Y_train, Xt, Y_test = TrainFiles.from_csv(train_path_mix)
def plot_confusion(sl):
conf_mat = confusion_matrix(sl.Y_test, sl.clf.predict(sl.X_test_scaled)).astype(dtype='float')
norm_conf_mat = conf_mat / conf_mat.sum(axis = 1)[:, None]
fig = plt.figure()
plt.clf()
ax = fig.add_subplot(111)
ax.set_aspect(1)
res = ax.imshow(norm_conf_mat, cmap=plt.cm.jet,
interpolation='nearest')
cb = fig.colorbar(res)
labs = np.unique(Y_test)
x = labs - 1
plt.xticks(x, labs)
plt.yticks(x, labs)
