def get_1dlbp_features(neighborhood):
tf = TrainFiles(inp_path, floor = neighborhood * 2 + 1)
inputs = tf.get_training_inputs()
start = timer()
hist = np.array([])
outs = np.array([])
i = 0
writeBatch = 2000
prep_out_path(out_path)
p = 1 << np.array(range(0, 2 * neighborhood), dtype='int32')
d_powers = cuda.to_device(p)
for inp in inputs:
data_file = path.join(inp_path, inp)
out_file = path.join(out_path, path.splitext(inp)[0] + ext)
arr = np.fromfile(data_file, dtype = 'uint8')
##GPU##
file_hist = extract_1dlbp_gpu(arr, neighborhood, d_powers)
##CPU##
#file_hist = extract_1dlbp_cpu(arr, neighborhood, p)
#file_hist = file_histogram(file_hist, neighborhood)
i += 1
hist = append_to_arr(hist, file_hist)
outs = append_to_arr(outs, out_file)
if i == writeBatch:
i = 0
first = True
print "Writing....."
for j in range(0, outs.shape[0]):
hist[j].tofile(outs[j])
hist = np.array([])
outs = np.array([])
print "==============Done==================="
print "Elapsed: ", timer() - start
print "Writing......."
for i in range(0, outs.shape[0]):
hist[i].tofile(outs[i])
print "==============Done==================="
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)
def do_train_with_freq():
tf_mix = TrainFiles(train_path = train_path_mix, labels_file = labels_file, test_size = 0.)
tf_freq = TrainFiles(train_path = train_path_freq, labels_file = labels_file, test_size = 0.)
X_m, Y_m, _, _ = tf_mix.prepare_inputs()
X_f, Y_f, _, _ = tf_freq.prepare_inputs()
X = np.c_[X_m, X_f]
Y = Y_f
X, Xt, Y, Yt = train_test_split(X, Y, test_size = 0.1)
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)
#sl.train_params = {'C': 100, 'gamma': 0.0001, 'probability' : True}
#print "Start SVM: ", time_now_str()
#sl_ll_trn, sl_ll_tst = sl.fit_and_validate()
#print "Finish Svm: ", time_now_str()
##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_pca, Y, X_pca_test, Yt)
fnn = train(trndata, tstdata, epochs = 1000, test_error = 0.025, momentum = 0.2, weight_decay = 0.0001)
def do_train_with_freq():
tf_mix = TrainFiles(train_path=train_path_mix,
labels_file=labels_file,
test_size=0.)
tf_freq = TrainFiles(train_path=train_path_freq,
labels_file=labels_file,
test_size=0.)
X_m, Y_m, _, _ = tf_mix.prepare_inputs()
X_f, Y_f, _, _ = tf_freq.prepare_inputs()
X = np.c_[X_m, X_f]
Y = Y_f
X, Xt, Y, Yt = train_test_split(X, Y, test_size=0.1)
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)
#sl.train_params = {'C': 100, 'gamma': 0.0001, 'probability' : True}
#print "Start SVM: ", time_now_str()
#sl_ll_trn, sl_ll_tst = sl.fit_and_validate()
#print "Finish Svm: ", time_now_str()
##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_pca, Y, X_pca_test, Yt)
fnn = train(trndata,
tstdata,
epochs=1000,
test_error=0.025,
momentum=0.2,
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 tr_utils import time_now_str
import sklearn.svm as svm
import numpy as np
from train_files import TrainFiles
from SupervisedLearning import SKSupervisedLearning
from sklearn.decomposition import PCA
out_labels = "/kaggle/malware/scratchpad/submission_fake.csv"
# instantiate file system interface
tf = TrainFiles('/kaggle/malware/scratchpad/train/1dlbp',
'/kaggle/malware/scratchpad/test/1dlbp',
"/kaggle/malware/trainLabels.csv")
# read in our data
X_train, Y_train, X_test, Y_test = tf.prepare_inputs()
sl = SKSupervisedLearning(svm.SVC, X_train, Y_train, X_test, Y_test)
sl.fit_standard_scaler()
def test_fit_svm():
# start fitting
sl.train_params = {'probability': True, 'C': 100, 'gamma': 0.1}
print "Starting: ", time_now_str()
# logloss is the score
tscore, valscore = sl.fit_and_validate()
print "Finished: ", time_now_str()
from tr_utils import time_now_str
import sklearn.svm as svm
import numpy as np
from train_files import TrainFiles
from SupervisedLearning import SKSupervisedLearning
from sklearn.decomposition import SparsePCA, PCA
from train_nn import train, createDataSets
from sklearn.naive_bayes import MultinomialNB
from sklearn.lda import LDA
from sklearn.preprocessing import normalize
tf = TrainFiles('/kaggle/malware/scratchpad/text/train/instr_freq', '/kaggle/malware/scratchpad/text/test/instr_freq', "/kaggle/malware/trainLabels.csv")
tf1 = TrainFiles('/kaggle/malware/scratchpad/train/1dlbp', '/kaggle/malware/scratchpad/test/1dlbp', "/kaggle/malware/trainLabels.csv")
X_train, Y_train, X_test, Y_test = tf1.prepare_inputs()
n_components = 300
pca = PCA(n_components = n_components)
pca.fit(np.r_[X_train, X_test])
#n_components = np.where(np.cumsum(pca.explained_variance_ratio_) >= 0.99)[0][0]
#print n_components
#pca = PCA(n_components = n_components)
#pca.fit(np.r_[X_train, X_test])
X_train_pca = pca.transform(X_train)
X_test_pca = pca.transform(X_test)
def predict():
tf = TrainFiles('/kaggle/malware/train/mix_lbp', val_path = '/kaggle/malware/test/mix_lbp', labels_file = "/kaggle/malware/trainLabels.csv")
X_train, Y_train, X_test, Y_test = tf.prepare_inputs()
sl_svm = SKSupervisedLearning(SVC, X_train, Y_train, X_test, Y_test)
sl_svm.fit_standard_scaler()
sl_svm.train_params = {'C': 100, 'gamma': 0.01, 'probability': True}
print "Starting SVM: ", time_now_str()
_, ll_svm = sl_svm.fit_and_validate()
print "SVM score: {0:.4f}".format(ll_svm if not prediction else _)
print "Finished training SVM: ", time_now_str()
# neural net
print "Starting NN: ", time_now_str()
trndata = _createDataSet(sl_svm.X_train_scaled, Y_train, one_based = True)
tstdata = _createUnsupervisedDataSet(sl_svm.X_test_scaled)
fnn = predict_nn(trndata)
proba_nn = fnn.activateOnDataset(tstdata)
print "Finished training NN: ", time_now_str()
# no validation labels on actual prediction
if doTrees:
# random forest
sl_ccrf = SKSupervisedLearning(CalibratedClassifierCV, X_train, Y_train, X_test, Y_test)
sl_ccrf.train_params = \
{'base_estimator': RandomForestClassifier(**{'n_estimators' : 7500, 'max_depth' : 200}), 'cv': 10}
sl_ccrf.fit_standard_scaler()
print "Starting on RF: ", time_now_str()
ll_ccrf_trn, ll_ccrf_tst = sl_ccrf.fit_and_validate()
print "RF score: {0:.4f}".format(ll_ccrf_tst if not prediction else ll_ccrf_trn)
sl_ccrf.proba_test.tofile("/temp/sl_ccrf.prob")
sl_svm.proba_test.tofile("/temp/sl_svm.prob")
proba_nn.tofile("/temp/nn.prob")
print "Finished training RF: ", time_now_str()
if prediction:
proba = vote([sl_svm.proba_test, sl_ccrf.proba_test, proba_nn], [2./3., 1./6., 1./3.])
out_labels = "/kaggle/malware/submission33.csv"
task_labels = "/kaggle/malware/testLabels.csv"
labels = [path.splitext(t)[0] for t in tf.get_val_inputs()]
out = write_to_csv(task_labels, labels, proba, out_labels)
else:
# visualize the decision surface, projected down to the first
# two principal components of the dataset
pca = PCA(n_components=2).fit(sl_svm.X_train_scaled)
X = pca.transform(sl_svm.X_train_scaled)
x = np.arange(X[:, 0].min() - 1, X[:, 1].max() + 1, 1)
y = np.arange(X[:, 1].min() - 1, X[:, 1].max() + 1, 1)
xx, yy = np.meshgrid(x, y)
# title for the plots
titles = ['SVC with rbf kernel',
'Random Forest \n'
'n_components=7500',
'Decision Trees \n'
'n_components=7500']
#plt.tight_layout()
plt.figure(figsize=(12, 5))
# predict and plot
for i, clf in enumerate((sl_svm.clf, sl_rfc.clf, sl_trees.clf)):
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, m_max]x[y_min, y_max].
plt.subplot(1, 3, i + 1)
clf.fit(X, Y_train)
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)
plt.axis('off')
# Plot also the training points
plt.scatter(X[:, 0], X[:, 1], c=Y_train, cmap=plt.cm.Paired)
plt.title(titles[i])
plt.tight_layout()
plt.show()
i += 1
hist = append_to_arr(hist, file_hist)
outs = append_to_arr(outs, out_file)
if i == writeBatch:
i = 0
first = True
for j in range(0, outs.shape[0]):
hist[j].tofile(outs[j])
hist = np.array([])
outs = np.array([])
print "==============Done==================="
print "Elapsed: ", timer() - start
print "Writing......."
for i in range(0, outs.shape[0]):
hist[i].tofile(outs[i])
print "==============Done==================="
neighborhood = 4
get_1dlbp_features(neighborhood)
tf = TrainFiles(out_path, labels_file='/kaggle/retina/trainLabels.csv', test_size = 0.0)
X, Y, _, _ = tf.prepare_inputs()
tf.dump_to_csv(path.join(root_path, '1dlbp.csv'), X, Y)
i += 1
hist = append_to_arr(hist, file_hist)
outs = append_to_arr(outs, out_file)
if i == writeBatch:
i = 0
first = True
for j in range(0, outs.shape[0]):
hist[j].tofile(outs[j])
hist = np.array([])
outs = np.array([])
print "==============Done==================="
print "Elapsed: ", timer() - start
print "Writing......."
for i in range(0, outs.shape[0]):
hist[i].tofile(outs[i])
print "==============Done==================="
neighborhood = 4
get_1dlbp_features(neighborhood)
tf = TrainFiles(out_path,
labels_file='/kaggle/retina/trainLabels.csv',
test_size=0.0)
X, Y, _, _ = tf.prepare_inputs()
tf.dump_to_csv(path.join(root_path, '1dlbp.csv'), X, Y)
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)
def predict():
tf = TrainFiles('/kaggle/malware/train/mix_lbp',
val_path='/kaggle/malware/test/mix_lbp',
labels_file="/kaggle/malware/trainLabels.csv")
X_train, Y_train, X_test, Y_test = tf.prepare_inputs()
sl_svm = SKSupervisedLearning(SVC, X_train, Y_train, X_test, Y_test)
sl_svm.fit_standard_scaler()
sl_svm.train_params = {'C': 100, 'gamma': 0.01, 'probability': True}
print "Starting SVM: ", time_now_str()
_, ll_svm = sl_svm.fit_and_validate()
print "SVM score: {0:.4f}".format(ll_svm if not prediction else _)
print "Finished training SVM: ", time_now_str()
# neural net
print "Starting NN: ", time_now_str()
trndata = _createDataSet(sl_svm.X_train_scaled, Y_train, one_based=True)
tstdata = _createUnsupervisedDataSet(sl_svm.X_test_scaled)
fnn = predict_nn(trndata)
proba_nn = fnn.activateOnDataset(tstdata)
print "Finished training NN: ", time_now_str()
# no validation labels on actual prediction
if doTrees:
# random forest
sl_ccrf = SKSupervisedLearning(CalibratedClassifierCV, X_train,
Y_train, X_test, Y_test)
sl_ccrf.train_params = \
{'base_estimator': RandomForestClassifier(**{'n_estimators' : 7500, 'max_depth' : 200}), 'cv': 10}
sl_ccrf.fit_standard_scaler()
print "Starting on RF: ", time_now_str()
ll_ccrf_trn, ll_ccrf_tst = sl_ccrf.fit_and_validate()
print "RF score: {0:.4f}".format(
ll_ccrf_tst if not prediction else ll_ccrf_trn)
sl_ccrf.proba_test.tofile("/temp/sl_ccrf.prob")
sl_svm.proba_test.tofile("/temp/sl_svm.prob")
proba_nn.tofile("/temp/nn.prob")
print "Finished training RF: ", time_now_str()
if prediction:
proba = vote([sl_svm.proba_test, sl_ccrf.proba_test, proba_nn],
[2. / 3., 1. / 6., 1. / 3.])
out_labels = "/kaggle/malware/submission33.csv"
task_labels = "/kaggle/malware/testLabels.csv"
labels = [path.splitext(t)[0] for t in tf.get_val_inputs()]
out = write_to_csv(task_labels, labels, proba, out_labels)
else:
# visualize the decision surface, projected down to the first
# two principal components of the dataset
pca = PCA(n_components=2).fit(sl_svm.X_train_scaled)
X = pca.transform(sl_svm.X_train_scaled)
x = np.arange(X[:, 0].min() - 1, X[:, 1].max() + 1, 1)
y = np.arange(X[:, 1].min() - 1, X[:, 1].max() + 1, 1)
xx, yy = np.meshgrid(x, y)
# title for the plots
titles = [
'SVC with rbf kernel', 'Random Forest \n'
'n_components=7500', 'Decision Trees \n'
'n_components=7500'
]
#plt.tight_layout()
plt.figure(figsize=(12, 5))
# predict and plot
for i, clf in enumerate((sl_svm.clf, sl_rfc.clf, sl_trees.clf)):
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, m_max]x[y_min, y_max].
plt.subplot(1, 3, i + 1)
clf.fit(X, Y_train)
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)
plt.axis('off')
# Plot also the training points
plt.scatter(X[:, 0], X[:, 1], c=Y_train, cmap=plt.cm.Paired)
plt.title(titles[i])
plt.tight_layout()
plt.show()
