Doctorado-ML/bayesclass
1
0
Fork 0
mirror of https://github.com/Doctorado-ML/bayesclass.git synced 2025-08-17 16:45:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

remove trace messages for first try

Browse Source
This commit is contained in:
Ricardo Montañana Gómez
2023-02-12 11:25:40 +01:00
parent 42ac57eb79
commit a5244f1c7f
1 changed files with 15 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
bayesclass/clfs.py
View File

@@ -475,7 +475,6 @@ class KDBNew(KDB):
return self.estimator.fit(X, y, **kwargs) return self.estimator.fit(X, y, **kwargs)
def predict(self, X): def predict(self, X):
self.plot()
return self.estimator.predict(X) return self.estimator.predict(X)
@@ -492,14 +491,14 @@ class Proposal:
# Build the model # Build the model
super(self.class_type, self.estimator).fit(self.Xd, y, **kwargs) super(self.class_type, self.estimator).fit(self.Xd, y, **kwargs)
self.check_integrity("f", self.Xd) self.check_integrity("f", self.Xd)
# # Local discretization based on the model # Local discretization based on the model
# features = kwargs["features"] features = kwargs["features"]
# # assign indices to feature names # assign indices to feature names
# self.idx_features_ = dict(list(zip(features, range(len(features))))) self.idx_features_ = dict(list(zip(features, range(len(features)))))
# upgraded, self.Xd = self._local_discretization() upgraded, self.Xd = self._local_discretization()
# if upgraded: if upgraded:
# kwargs = self.update_kwargs(y, kwargs) kwargs = self.update_kwargs(y, kwargs)
# super(self.class_type, self.estimator).fit(self.Xd, y, **kwargs) super(self.class_type, self.estimator).fit(self.Xd, y, **kwargs)
def predict(self, X): def predict(self, X):
self.check_integrity("p", self.discretizer.transform(X)) self.check_integrity("p", self.discretizer.transform(X))
@@ -534,14 +533,14 @@ class Proposal:
"""Discretize each feature with its fathers and the class""" """Discretize each feature with its fathers and the class"""
res = self.Xd.copy() res = self.Xd.copy()
upgraded = False upgraded = False
print("-" * 80) # print("-" * 80)
for idx, feature in enumerate(self.estimator.feature_names_in_): for idx, feature in enumerate(self.estimator.feature_names_in_):
fathers = self.estimator.dag_.get_parents(feature) fathers = self.estimator.dag_.get_parents(feature)
if len(fathers) > 1: if len(fathers) > 1:
print( # print(
"Discretizing " + feature + " with " + str(fathers), # "Discretizing " + feature + " with " + str(fathers),
end=" ", # end=" ",
) # )
# First remove the class name as it will be added later # First remove the class name as it will be added later
fathers.remove(self.estimator.class_name_) fathers.remove(self.estimator.class_name_)
# Get the fathers indices # Get the fathers indices
@@ -550,12 +549,12 @@ class Proposal:
res[:, idx] = self.discretizer.join_fit( res[:, idx] = self.discretizer.join_fit(
target=idx, features=features, data=self.Xd target=idx, features=features, data=self.Xd
) )
print(self.discretizer.y_join[:5]) # print(self.discretizer.y_join[:5])
upgraded = True upgraded = True
return upgraded, res return upgraded, res
def check_integrity(self, source, X): def check_integrity(self, source, X):
print(f"Checking integrity of {source} data") # print(f"Checking integrity of {source} data")
for i in range(X.shape[1]): for i in range(X.shape[1]):
if not set(np.unique(X[:, i]).tolist()).issubset( if not set(np.unique(X[:, i]).tolist()).issubset(
set(self.state_names_[self.features_[i]]) set(self.state_names_[self.features_[i]])