def fit(self, X):
np.random.seed(self.random_state)
self.n_sample = X.shape[0]
x_arr, y_arr = [], []
for i in np.arange(self.lower_bound, self.higher_bound):
sample_size = 2**i
sample = X[np.random.choice(self.n_sample,
sample_size,
replace=True)]
clf = IsolationForest(random_state=self.random_state,
max_samples=sample_size,
contamination='auto').fit(
sample, max_depth=100000000)
depths = np.mean(clf._compute_actual_depth_leaf(sample)[0], axis=0)
bins = np.arange(int(depths.min()), int(depths.max() + 2))
y, x = np.histogram(depths, bins=bins)
y, x = y + 1, x[:-1]
break_point = np.argmax(y)
x_arr.append([i])
y_arr.append(x[break_point])
self.reg = LinearRegression(fit_intercept=False).fit(x_arr, y_arr)
self.clf = IsolationForest(random_state=self.random_state,
max_samples=len(X),
contamination='auto').fit(
X, max_depth=self.max_depth)
return self
def __init__(self, n_estimators=100, max_samples=256):
self.model = IsolationForest(n_estimators, max_samples)
self.threshold = 0.6 ## Recommended threshold in IForest paper.
self.trainedStatus = False
