fix: weights handling for N=1, empty splits in DecisionTree, and exception types

- LinearRegression: fix np.squeeze causing 0-d array when N=1 (fixes #77)
- DecisionTree: handle empty child nodes to prevent ZeroDivisionError (fixes #58)
- Replace bare except with specific types (gp.py, trainer.py)
- Replace generic Exception with ValueError/RuntimeError (knn.py, general.py)

Author: mshzy

numpy_ml/linear_models/linear_regression.py

@@ -197,7 +197,7 @@ def fit(self, X, y, weights=None):
         N = X.shape[0]
 
         weights = np.ones(N) if weights is None else np.atleast_1d(weights)
-        weights = np.squeeze(weights) if weights.size > 1 else weights
+        weights = np.atleast_1d(np.squeeze(weights)) if weights.size > 1 else weights
         err_str = f"weights must have shape ({N},) but got {weights.shape}"
         assert weights.shape == (N,), err_str
 

numpy_ml/nonparametric/gp.py

@@ -5,7 +5,7 @@
 try:
     _SCIPY = True
     from scipy.stats import norm
-except:
+except ImportError:
     _SCIPY = False
     warnings.warn(
         "Could not import scipy.stats. Confidence scores "

numpy_ml/nonparametric/knn.py

@@ -56,7 +56,7 @@ def fit(self, X, y):
             Targets for the `N` rows in `X`.
         """
         if X.ndim != 2:
-            raise Exception("X must be two-dimensional")
+            raise ValueError("X must be two-dimensional")
         self._ball_tree.fit(X, y)
 
     def predict(self, X):

numpy_ml/preprocessing/general.py

@@ -238,7 +238,7 @@ def transform(self, X):
             The feature-wise standardized version of `X`.
         """
         if not self._is_fit:
-            raise Exception("Must call `fit` before using the `transform` method")
+            raise RuntimeError("Must call `fit` before using the `transform` method")
         return (X - self._mean) / self._std
 
     def inverse_transform(self, Z):

numpy_ml/trees/dt.py

@@ -120,7 +120,10 @@ def predict_class_probs(self, X):
         return np.array([self._traverse(x, self.root, prob=True) for x in X])
 
     def _grow(self, X, Y, cur_depth=0):
-        # if all labels are the same, return a leaf
+        # if all labels are the same, or node is empty, return a leaf
+        if len(Y) == 0:
+            prob = np.zeros(self.n_classes) if self.classifier else 0.0
+            return Leaf(prob)
         if len(set(Y)) == 1:
             if self.classifier:
                 prob = np.zeros(self.n_classes)