ddi-fw 0.0.212__py3-none-any.whl → 0.0.214__py3-none-any.whl

ddi_fw/ml/ml_helper.py

@@ -156,7 +156,7 @@ class MultiModalRunner:
             (self.y_test_label.shape[0], self.y_test_label.shape[1]))
         for item in combination:
             prediction = prediction + single_results[item]
-        prediction = np.argmax(prediction, axis=1)
+        prediction = utils.to_one_hot_encode(prediction)
         logs, metrics = evaluate(
             actual=self.y_test_label, pred=prediction, info=combination_descriptor)
         if self.use_mlflow:

ddi_fw/ml/tensorflow_wrapper.py

@@ -183,11 +183,11 @@ class TFModelWrapper(ModelWrapper):
                 actual = self.test_label
                 # if not utils.is_binary_encoded(pred):
                 #     pred = tf.keras.utils.to_categorical(np.argmax(pred,axis=1), num_classes=self.num_classes)
-                pred= convert_to_categorical(pred, self.num_classes)
-                actual= convert_to_categorical(actual, self.num_classes)
+                pred_as_cat= convert_to_categorical(pred, self.num_classes)
+                actual_as_cat= convert_to_categorical(actual, self.num_classes)
 
                 logs, metrics = evaluate(
-                    actual=actual, pred=pred, info=self.descriptor, print_detail=print_detail)
+                    actual=actual_as_cat, pred=pred_as_cat, info=self.descriptor, print_detail=print_detail)
                 metrics.format_float()
                 mlflow.log_metrics(logs)
                 mlflow.log_param('best_cv', best_model_key)

ddi_fw/utils/__init__.py

@@ -4,5 +4,5 @@ from .py7zr_helper import Py7ZipHelper
 from .enums import UMLSCodeTypes, DrugBankTextDataTypes
 from .package_helper import get_import
 from .kaggle import create_kaggle_dataset
-from .categorical_data_encoding_checker import is_one_hot_encoded, is_binary_encoded, is_binary_vector,is_label_encoded
+from .categorical_data_encoding_checker import to_one_hot_encode,is_one_hot_encoded, is_binary_encoded, is_binary_vector,is_label_encoded
 from .numpy_utils import adjust_array_dims

ddi_fw/utils/categorical_data_encoding_checker.py

@@ -1,5 +1,51 @@
 import numpy as np
 
+def to_one_hot_encode(arr):
+    """
+    Convert a multi-dimensional array (1D, 2D, or 3D) into a one-hot encoded array.
+    
+    Parameters:
+    arr (numpy.ndarray): An array where each element or row (or slice) contains class indices or class probabilities.
+    
+    Returns:
+    numpy.ndarray: One-hot encoded array.
+    """
+    # Check if the input is a numpy array
+    if not isinstance(arr, np.ndarray):
+        raise ValueError("Input must be a numpy array")
+
+    # Get the shape of the input
+    shape = arr.shape
+    
+    # If the array is 1D, treat it as a list of class indices
+    if arr.ndim == 1:
+        num_classes = np.max(arr) + 1
+        one_hot = np.zeros((shape[0], num_classes))
+        one_hot[np.arange(shape[0]), arr] = 1
+
+    # If the array is 2D, treat each row as a list of class indices
+    elif arr.ndim == 2:
+        num_classes = shape[1]
+        one_hot = np.zeros((shape[0], num_classes))
+        # Handle one-hot encoding for each row (max index for each row)
+        max_indices = np.argmax(arr, axis=1)
+        one_hot[np.arange(shape[0]), max_indices] = 1
+
+    # If the array is 3D or higher, iterate over the first axis and apply one-hot encoding for each slice
+    elif arr.ndim >= 3:
+        num_classes = shape[-1]
+        # Initialize the output array for one-hot encoding with the same shape as input, but the last dimension is num_classes
+        one_hot = np.zeros_like(arr, dtype=int)
+        
+        # Iterate through the first axis (the batch dimension)
+        for i in range(shape[0]):
+            # Get the max indices along the second dimension for each slice
+            max_indices = np.argmax(arr[i], axis=1)
+            # Set the corresponding one-hot vectors in the slice
+            one_hot[i, np.arange(shape[1]), max_indices] = 1
+
+    return one_hot
+
 
 def is_one_hot_encoded(arr):
     # Check if the array is one-hot encoded

{ddi_fw-0.0.212.dist-info → ddi_fw-0.0.214.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.212
+Version: 0.0.214
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.212.dist-info → ddi_fw-0.0.214.dist-info}/RECORD

@@ -74,10 +74,10 @@ ddi_fw/langchain/sentence_splitter.py,sha256=h_bYElx4Ud1mwDNJfL7mUwvgadwKX3GKlSz
 ddi_fw/langchain/storage.py,sha256=OizKyWm74Js7T6Q9kez-ulUoBGzIMFo4R46h4kjUyIM,11200
 ddi_fw/ml/__init__.py,sha256=tIxiW0g6q1VsmDYVXR_ovvHQR3SCir8g2bKxx_CrS7s,221
 ddi_fw/ml/evaluation_helper.py,sha256=2-7CLSgGTqLEk4HkgCVIOt-GxfLAn6SBozJghAtHb5M,11581
-ddi_fw/ml/ml_helper.py,sha256=m6_yoZwkKgYh0RRlXExfBaE63H_UgeFOXW9Dzy1kVig,7710
+ddi_fw/ml/ml_helper.py,sha256=6BO1ikCHmlYK9TPDN7Atov0BuTtoyLg06NoSGl3RYGA,7716
 ddi_fw/ml/model_wrapper.py,sha256=kabPXuo7S8tGkp9a00V04n4rXDmv7dD8wYGMjotISRc,1050
 ddi_fw/ml/pytorch_wrapper.py,sha256=pe6UsjP2XeTgLxDnIUiodoyhJTGCxV27wD4Cjxysu2Q,8553
-ddi_fw/ml/tensorflow_wrapper.py,sha256=lNJvg3odqMKmILecOMdcOCAOrwzWZDzxB0DWGcYWsPg,12952
+ddi_fw/ml/tensorflow_wrapper.py,sha256=Vw6M2rHDHV90jzfCr0XWpUqYVl4vmZeKsS7FUb3VkH4,12980
 ddi_fw/ner/__init__.py,sha256=JwhGXrepomxPSsGsg2b_xPRC72AjvxOIn2CW5Mvscn0,26
 ddi_fw/ner/mmlrestclient.py,sha256=NZta7m2Qm6I_qtVguMZhqtAUjVBmmXn0-TMnsNp0jpg,6859
 ddi_fw/ner/ner.py,sha256=FHyyX53Xwpdw8Hec261dyN88yD7Z9LmJua2mIrQLguI,17967
@@ -86,8 +86,8 @@ ddi_fw/pipeline/multi_modal_combination_strategy.py,sha256=JSyuP71b1I1yuk0s2ecCJ
 ddi_fw/pipeline/multi_pipeline.py,sha256=SZFJ9QSPD_3mcG9NHZOtMqKyNvyWrodsdsLryMyDdUw,8686
 ddi_fw/pipeline/ner_pipeline.py,sha256=Bp6BA6nozfWFaMHH6jKlzesnCGO6qiMkzdGy_ed6nh0,5947
 ddi_fw/pipeline/pipeline.py,sha256=YhUBVLC29ZD2tmVd0e8X1FVBLhSKECZL2OP57oEW6HE,9171
-ddi_fw/utils/__init__.py,sha256=HC32XkYQTYH_9vt0eX6tqQngEFG-R70hGrYkT-BcHCk,519
-ddi_fw/utils/categorical_data_encoding_checker.py,sha256=gzb_vUDBrCMUhBxY1fBYTe8hmK72p0_uw3DTga8cqP8,1580
+ddi_fw/utils/__init__.py,sha256=WNxkQXk-694roG50D355TGLXstfdWVb_tUyr-PM-8rg,537
+ddi_fw/utils/categorical_data_encoding_checker.py,sha256=T1X70Rh4atucAuqyUZmz-iFULllY9dY0NRyV9-jTjJ0,3438
 ddi_fw/utils/enums.py,sha256=19eJ3fX5eRK_xPvkYcukmug144jXPH4X9zQqtsFBj5A,671
 ddi_fw/utils/json_helper.py,sha256=BVU6wmJgdXPxyqLPu3Ck_9Es5RrP1PDanKvE-OSj1D4,571
 ddi_fw/utils/kaggle.py,sha256=wKRJ18KpQ6P-CubpZklEgsDtyFpR9RUL1_HyyF6ttEE,2425
@@ -99,7 +99,7 @@ ddi_fw/utils/zip_helper.py,sha256=YRZA4tKZVBJwGQM0_WK6L-y5MoqkKoC-nXuuHK6CU9I,55
 ddi_fw/vectorization/__init__.py,sha256=LcJOpLVoLvHPDw9phGFlUQGeNcST_zKV-Oi1Pm5h_nE,110
 ddi_fw/vectorization/feature_vector_generation.py,sha256=EBf-XAiwQwr68az91erEYNegfeqssBR29kVgrliIyac,4765
 ddi_fw/vectorization/idf_helper.py,sha256=_Gd1dtDSLaw8o-o0JugzSKMt9FpeXewTh4wGEaUd4VQ,2571
-ddi_fw-0.0.212.dist-info/METADATA,sha256=omvMdFVFWtYigvW-ErpD_9fJ_KeumU_E3Q04mPkC8Ko,2631
-ddi_fw-0.0.212.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ddi_fw-0.0.212.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.212.dist-info/RECORD,,
+ddi_fw-0.0.214.dist-info/METADATA,sha256=IEDJdH40Nw4B0aJXnUwuxeNRdXMX5rw1RBsX93Zbj1A,2631
+ddi_fw-0.0.214.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ddi_fw-0.0.214.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.214.dist-info/RECORD,,