def is_anomaly(adl_dataset, adl_data_test):
# At train time lsanomaly calculates parameters rho and sigma
lsanomaly = LSAnomaly(sigma=3, rho=0.1)
res = np.reshape((adl_dataset), (-1, 1))
lsanomaly.fit(res)
res_test = np.reshape((adl_data_test), (-1, 1))
predit_res = lsanomaly.predict(res_test)
return predit_res, lsanomaly.predict_proba(
res_test) # predicted result and probability of the result
def testing_func(a):
sigma, rho = a
print "Training with rho: %s, sigma: %s" % (rho, sigma)
clf = LSAnomaly(rho=rho, sigma=sigma)
clf.fit(X_train)
y_pred = clf.predict(X_test)
y_pred = np.asarray(y_pred)
anomalies = np.where(y_pred == 'anomaly')[0]
print anomalies
return [sigma, rho, len(anomalies),
len(anomalies)/float(X_test.shape[0])]
def test_example_doc(doc_arrays, check_ndarray):
test_pt = np.array([[0]])
x_train, predict_prob = doc_arrays
anomaly_model = LSAnomaly(sigma=3, rho=0.1, seed=42)
anomaly_model.fit(x_train)
expected = [0.0]
p = anomaly_model.predict(test_pt)
assert p == expected
expected = np.array([[0.7231233, 0.2768767]])
p = anomaly_model.predict_proba(test_pt)
logger.debug("p = {}".format(p))
check_ndarray(expected, p)
def testing_func(a):
sigma, rho = a
print "Training with rho: %s, sigma: %s" % (rho, sigma)
clf = LSAnomaly(rho=rho, sigma=sigma)
clf.fit(X_train)
y_pred = clf.predict(X_test)
y_pred = np.asarray(y_pred)
anomalies = np.where(y_pred == 'anomaly')[0]
print anomalies
return [
sigma, rho,
len(anomalies),
len(anomalies) / float(X_test.shape[0])
]
from multiprocessing import Pool
from itertools import product
pool = Pool(processes=8)
results = pool.map(testing_func, product(sigmas, rhos))
pool.close()
pool.join()
else:
results = []
for rho in rhos:
for sigma in sigmas:
print "Now fitting: rho - %s; sigma - %s" % (rho, sigma)
clf = LSAnomaly(rho=rho, sigma=sigma, verbose=False)
clf.fit(X_train)
y_pred = clf.predict(X_test)
anomalies = np.where(y_pred == 'anomaly')[0]
print np.unique(anomalies)
results.append([nu, gamma, len(anomalies),
len(anomalies)/float(X_test.shape[0])])
test_df = DataFrame(results, columns=["Sigma", "Rho", "Anomalies",
"Percent"])
test_df.to_csv("lsq_anomaly_testing_fifth_betterparams.csv")
if learn:
all_anom = []
# Repeat the process many times
from multiprocessing import Pool
from itertools import product
pool = Pool(processes=8)
results = pool.map(testing_func, product(sigmas, rhos))
pool.close()
pool.join()
else:
results = []
for rho in rhos:
for sigma in sigmas:
print "Now fitting: rho - %s; sigma - %s" % (rho, sigma)
clf = LSAnomaly(rho=rho, sigma=sigma, verbose=False)
clf.fit(X_train)
y_pred = clf.predict(X_test)
anomalies = np.where(y_pred == 'anomaly')[0]
print np.unique(anomalies)
results.append([
nu, gamma,
len(anomalies),
len(anomalies) / float(X_test.shape[0])
])
test_df = DataFrame(results,
columns=["Sigma", "Rho", "Anomalies", "Percent"])
test_df.to_csv("lsq_anomaly_testing_fifth_betterparams.csv")
if learn:
