nkululeko 0.89.2__py3-none-any.whl → 0.90.1__py3-none-any.whl

nkululeko/ensemble.py

@@ -15,28 +15,20 @@ Raises:
     ValueError: If an unknown ensemble method is provided.
     AssertionError: If the number of config files is less than 2 for majority voting.
 """
+
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
 
-from typing import List
 import configparser
 import time
 from argparse import ArgumentParser
 from pathlib import Path
+from typing import List
 
 import numpy as np
 import pandas as pd
-import matplotlib.pyplot as plt
-
-from sklearn.metrics import(
-    RocCurveDisplay,
-    balanced_accuracy_score, 
-    classification_report,
-    auc,
-    roc_auc_score,
-    roc_curve
-)
+from sklearn.metrics import balanced_accuracy_score, classification_report
 
 from nkululeko.constants import VERSION
 from nkululeko.experiment import Experiment
@@ -169,17 +161,19 @@ def performance_weighted_ensemble(ensemble_preds_ls, labels, weights):
 
     # asserts weiths in decimal 0-1
     assert all(0 <= w <= 1 for w in weights), "Weights must be between 0 and 1"
-    
+
     # assert lenght of weights matches number of models
-    assert len(weights) == len(ensemble_preds_ls), "Number of weights must match number of models"
-    
+    assert len(weights) == len(
+        ensemble_preds_ls
+    ), "Number of weights must match number of models"
+
     # Normalize weights
     total_weight = sum(weights)
     weights = [weight / total_weight for weight in weights]
-    
+
     for idx in ensemble_preds_ls[0].index:
         class_probabilities = {label: 0 for label in labels}
-        
+
         for df, weight in zip(ensemble_preds_ls, weights):
             row = df.loc[idx]
             for label in labels:
@@ -192,10 +186,12 @@ def performance_weighted_ensemble(ensemble_preds_ls, labels, weights):
     return final_predictions, final_confidences
 
 
-
-
 def ensemble_predictions(
-    config_files: List[str], method: str, threshold: float, weights: List[float], no_labels: bool
+    config_files: List[str],
+    method: str,
+    threshold: float,
+    weights: List[float],
+    no_labels: bool,
 ) -> pd.DataFrame:
     """
     Ensemble predictions from multiple experiments.
@@ -261,17 +257,20 @@ def ensemble_predictions(
             ensemble_preds_ls, labels, threshold
         )
     elif method == "uncertainty_weighted":
-        ensemble_preds["predicted"], ensemble_preds["uncertainty"] = (
-            uncertainty_weighted_ensemble(ensemble_preds_ls, labels)
-        )
+        (
+            ensemble_preds["predicted"],
+            ensemble_preds["uncertainty"],
+        ) = uncertainty_weighted_ensemble(ensemble_preds_ls, labels)
     elif method == "confidence_weighted":
-        ensemble_preds["predicted"], ensemble_preds["confidence"] = (
-            confidence_weighted_ensemble(ensemble_preds_ls, labels)
-        )
+        (
+            ensemble_preds["predicted"],
+            ensemble_preds["confidence"],
+        ) = confidence_weighted_ensemble(ensemble_preds_ls, labels)
     elif method == "performance_weighted":
-        ensemble_preds["predicted"], ensemble_preds["confidence"] = (
-            performance_weighted_ensemble(ensemble_preds_ls, labels, weights)
-        )
+        (
+            ensemble_preds["predicted"],
+            ensemble_preds["confidence"],
+        ) = performance_weighted_ensemble(ensemble_preds_ls, labels, weights)
     else:
         raise ValueError(f"Unknown ensemble method: {method}")
 

nkululeko/experiment.py

@@ -5,13 +5,13 @@ import pickle
 import random
 import time
 
+import audeer
+import audformat
 import numpy as np
 import pandas as pd
 from sklearn.preprocessing import LabelEncoder
 
-import audeer
-import audformat
-
+import nkululeko.glob_conf as glob_conf
 from nkululeko.data.dataset import Dataset
 from nkululeko.data.dataset_csv import Dataset_CSV
 from nkululeko.demo_predictor import Demo_predictor
@@ -19,7 +19,6 @@ from nkululeko.feat_extract.feats_analyser import FeatureAnalyser
 from nkululeko.feature_extractor import FeatureExtractor
 from nkululeko.file_checker import FileChecker
 from nkululeko.filter_data import DataFilter
-import nkululeko.glob_conf as glob_conf
 from nkululeko.plots import Plots
 from nkululeko.reporting.report import Report
 from nkululeko.runmanager import Runmanager
@@ -101,12 +100,15 @@ class Experiment:
             if data.got_speaker:
                 self.got_speaker = True
             self.datasets.update({d: data})
-        self.target = self.util.config_val("DATA", "target", "emotion")
+        self.target = self.util.config_val("DATA", "target", "none")
         glob_conf.set_target(self.target)
         # print target via debug
         self.util.debug(f"target: {self.target}")
         # print keys/column
         dbs = ",".join(list(self.datasets.keys()))
+        if self.target == "none":
+            self.util.debug(f"loaded databases {dbs}")
+            return
         labels = self.util.config_val("DATA", "labels", False)
         auto_labels = list(next(iter(self.datasets.values())).df[self.target].unique())
         if labels:
@@ -191,7 +193,8 @@ class Experiment:
             self.df_train, self.df_test = pd.DataFrame(), pd.DataFrame()
             for d in self.datasets.values():
                 d.split()
-                d.prepare_labels()
+                if self.target != "none":
+                    d.prepare_labels()
                 if d.df_train.shape[0] == 0:
                     self.util.debug(f"warn: {d.name} train empty")
                 self.df_train = pd.concat([self.df_train, d.df_train])
@@ -207,6 +210,8 @@ class Experiment:
             self.df_test.to_csv(storage_test)
             self.df_train.to_csv(storage_train)
 
+        if self.target == "none":
+            return
         self.util.copy_flags(self, self.df_test)
         self.util.copy_flags(self, self.df_train)
         # Try data checks
@@ -738,7 +743,6 @@ class Experiment:
         if model.is_ann():
             print("converting to onnx from torch")
         else:
-
             print("converting to onnx from sklearn")
         # save the rest
         f = open(filename, "wb")