nkululeko 0.94.3__py3-none-any.whl → 0.95.0__py3-none-any.whl

nkululeko/glob_conf.py

@@ -1,5 +1,14 @@
 # glob_conf.py
 
+# Initialize global variables
+config = None
+label_encoder = None
+util = None
+module = None
+report = None
+labels = None
+target = None
+
 
 def init_config(config_obj):
     global config

nkululeko/modelrunner.py

@@ -279,9 +279,18 @@ class Modelrunner:
             self.util.debug(
                 f"balanced with: {balancing}, new size: {X_res.shape[0]} (was {orig_size})"
             )
-            le = glob_conf.label_encoder
-            res = y_res.value_counts()
-            resd = {}
-            for i, e in enumerate(le.inverse_transform(res.index.values)):
-                resd[e] = res.values[i]
-            self.util.debug(f"{resd})")
+            # Check if label encoder is available before using it
+            if (
+                hasattr(glob_conf, "label_encoder")
+                and glob_conf.label_encoder is not None
+            ):
+                le = glob_conf.label_encoder
+                res = y_res.value_counts()
+                resd = {}
+                for i, e in enumerate(le.inverse_transform(res.index.values)):
+                    resd[e] = res.values[i]
+                self.util.debug(f"class distribution after balancing: {resd}")
+            else:
+                self.util.debug(
+                    "Label encoder not available, skipping class distribution report"
+                )

nkululeko/models/model.py

@@ -3,15 +3,11 @@ import ast
 import pickle
 import random
 
-from joblib import parallel_backend
 import numpy as np
 import pandas as pd
-from sklearn.model_selection import GridSearchCV
-from sklearn.model_selection import LeaveOneGroupOut
-from sklearn.model_selection import StratifiedKFold
 import sklearn.utils
-
-import audeer
+from joblib import parallel_backend
+from sklearn.model_selection import GridSearchCV, LeaveOneGroupOut, StratifiedKFold
 
 import nkululeko.glob_conf as glob_conf
 from nkululeko.reporting.reporter import Reporter
@@ -305,15 +301,8 @@ class Model:
     def get_type(self):
         return "generic"
 
-    def predict_sample(self, features: np.ndarray) -> dict | float:
-        """Predict a single sample using the trained model.
-
-        Args:
-            features (np.ndarray): The feature vector of the sample to predict.
-
-        Returns:
-            dict: A dictionary containing the predicted class probabilities or value.
-        """
+    def predict_sample(self, features):
+        """Predict one sample"""
         prediction = {}
         if self.util.exp_is_classification():
             # get the class probabilities
@@ -347,30 +336,3 @@ class Model:
         self.set_id(run, epoch)
         with open(path, "rb") as handle:
             self.clf = pickle.load(handle)
-
-    # next function exports the model to onnx
-    def export_onnx(self, onnx_path, input_shape=None):
-        """Export the trained sklearn model to ONNX format.
-
-        Args:
-            onnx_path (str): Path to save the ONNX model.
-            input_shape (tuple, optional): Shape of the input features. If None, inferred from feats_train.
-        """
-        import skl2onnx
-        from skl2onnx import convert_sklearn
-        from skl2onnx.common.data_types import FloatTensorType
-
-        if not hasattr(self, "clf"):
-            self.util.error("No trained model found to export.")
-            return
-
-        if input_shape is None:
-            n_features = self.feats_train.shape[1]
-            initial_type = [("input", FloatTensorType([None, n_features]))]
-        else:
-            initial_type = [("input", FloatTensorType(input_shape))]
-
-        onnx_model = convert_sklearn(self.clf, initial_types=initial_type)
-        with open(audeer.path(onnx_path), "wb") as f:
-            f.write(onnx_model.SerializeToString())
-        self.util.debug(f"Model exported to ONNX at {onnx_path}")