class Preprocessor(BaseEstimator):
def __init__(self):
# Pour avoir la 2D
self.transformer = PCA(n_components=2)
def fit(self, X, y=None):
if X.ndim > 1: self.num_feat = X.shape[1]
if y.ndim > 1: self.num_labels = y.shape[1]
X_preprocess = self.preprocess.fit_transform(X)
X_scaled = preprocessing.scale(X)
self.mod.fit(X_preprocess, y)
self.is_trained = True
self.transformer = IsolationForest(random_state=0).fit(X_scaled)
return self.transformer.fit(X, y)
def predict(self, X):
num_test_samples = X.shape[0]
if X.ndim > 1: num_feat = X.shape[1]
y = np.zeros([num_test_samples, self.num_labels])
X_preprocess = self.preprocess.transform(X)
y = self.mod.predict(X_preprocess)
return y
def save(self, path="./"):
pass
def load(self, path="./"):
pass
def fit_transform(self, X, y=None):
return self.transformer.fit_transform(X)
def transform(self, X, y=None):
return self.transformer.transform(X)
