class RC30(ClassifierMixin, BaseEstimator):
def __init__(self,
n_estimators=30,
max_depth=3,
min_samples_split=2,
min_samples_leaf=1,
ctype="isotonic"):
self.n_estimators = n_estimators
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.ctype = ctype
def fit(self, X, y):
X, y = check_X_y(X, y)
self.model = RandomForestClassifier(n_estimators=self.n_estimators,
max_depth=self.max_depth,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf)
if self.ctype == "logistic":
self.calibrator = LogisticRegression(C=1e20, solver="lbfgs")
elif self.ctype == "isotonic":
self.calibrator = IsotonicRegression(y_min=0, y_max=1,
out_of_bounds="clip")
X0, X1, y0, y1 = train_test_split(X, y, test_size=0.3)
self.model.fit(X0, y0)
if self.ctype == "logistic":
y_est = self.model.predict_proba(X1)[:,[1]]
self.calibrator.fit(y_est, y1)
elif self.ctype == "isotonic":
y_est = self.model.predict_proba(X1)[:,1]
self.calibrator.fit(y_est, y1)
self.is_fitted_ = True
return self
def predict_proba(self, X):
X = check_array(X)
check_is_fitted(self, 'is_fitted_')
if self.ctype == "logistic":
return self.calibrator.predict_proba(
self.model.predict_proba(X)[:,[1]])
elif self.ctype == "isotonic":
n, m = X.shape
y = np.zeros((n,2))
y[:,1] = self.calibrator.predict(
self.model.predict_proba(X)[:,1])
y[:,0] = 1 - y[:,1]
return y
class CaliForest(ClassifierMixin, BaseEstimator):
def __init__(self,
n_estimators=300,
criterion="gini",
max_depth=5,
min_samples_split=2,
min_samples_leaf=1,
ctype="isotonic",
alpha0=100,
beta0=25):
self.n_estimators = n_estimators
self.criterion = criterion
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.ctype = ctype
self.alpha0 = alpha0
self.beta0 = beta0
def fit(self, X, y):
X, y = check_X_y(X, y, accept_sparse=False)
self.estimators = []
self.calibrator = None
for i in range(self.n_estimators):
self.estimators.append(
Tree(criterion=self.criterion,
max_depth=self.max_depth,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
max_features="auto"))
if self.ctype == "logistic":
self.calibrator = LR(penalty="none", solver="saga", max_iter=5000)
elif self.ctype == "isotonic":
self.calibrator = Iso(y_min=0, y_max=1, out_of_bounds="clip")
n, m = X.shape
Y_oob = np.full((n, self.n_estimators), np.nan)
n_oob = np.zeros(n)
IB = np.zeros((n, self.n_estimators), dtype=int)
OOB = np.full((n, self.n_estimators), True)
for eid in range(self.n_estimators):
IB[:, eid] = np.random.choice(n, n)
OOB[IB[:, eid], eid] = False
for eid, est in enumerate(self.estimators):
ib_idx = IB[:, eid]
oob_idx = OOB[:, eid]
est.fit(X[ib_idx, :], y[ib_idx])
Y_oob[oob_idx, eid] = est.predict_proba(X[oob_idx, :])[:, 1]
n_oob[oob_idx] += 1
oob_idx = n_oob > 1
Y_oob_ = Y_oob[oob_idx, :]
n_oob_ = n_oob[oob_idx]
z_hat = np.nanmean(Y_oob_, axis=1)
z_true = y[oob_idx]
beta = self.beta0 + np.nanvar(Y_oob_, axis=1) * n_oob_ / 2
alpha = self.alpha0 + n_oob_ / 2
z_weight = alpha / beta
if self.ctype == "logistic":
self.calibrator.fit(z_hat[:, np.newaxis], z_true, z_weight)
elif self.ctype == "isotonic":
self.calibrator.fit(z_hat, z_true, z_weight)
self.is_fitted_ = True
return self
def predict_proba(self, X):
X = check_array(X)
check_is_fitted(self, 'is_fitted_')
n, m = X.shape
n_est = len(self.estimators)
z = np.zeros(n)
y_mat = np.zeros((n, 2))
for eid, est in enumerate(self.estimators):
z += est.predict_proba(X)[:, 1]
z /= n_est
if self.ctype == "logistic":
y_mat[:, 1] = self.calibrator.predict_proba(z[:, np.newaxis])[:, 1]
elif self.ctype == "isotonic":
y_mat[:, 1] = self.calibrator.predict(z)
y_mat[:, 0] = 1 - y_mat[:, 1]
return y_mat
def predict(self, X):
proba = self.predict_proba(X)
return np.argmax(proba, axis=1)
