ddi-fw 0.0.178__py3-none-any.whl → 0.0.180__py3-none-any.whl

ddi_fw/datasets/core.py

@@ -225,9 +225,9 @@ class BaseDataset(BaseModel):
         
         # Dataframe to numpy array conversion
         self.X_train = np.array(self.X_train)
-        self.y_train = np.array(self.y_train)
+        self.y_train = np.array(self.y_train.tolist())
         self.X_test = np.array(self.X_test)
-        self.y_test = np.array(self.y_test)
+        self.y_test = np.array(self.y_test.tolist())
 
         if save_indexes:
             # train_pairs = [row['id1'].join(',').row['id2'] for index, row in X_train.iterrows()]

ddi_fw/ml/tensorflow_wrapper.py

@@ -136,8 +136,11 @@ class TFModelWrapper(ModelWrapper):
                 print(best_model_key)
                 self.best_model: Model = best_model
                 pred = self.predict()
-                pred = tf.keras.utils.to_categorical(np.argmax(pred,axis=1), num_classes=self.num_classes)
-                actual = tf.keras.utils.to_categorical(self.test_label, num_classes=self.num_classes)
+                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)
+                if not utils.is_binary_encoded(actual):
+                    actual = tf.keras.utils.to_categorical(actual, num_classes=self.num_classes)
 
                 logs, metrics = evaluate(
                     actual=actual, pred=pred, info=self.descriptor, print_detail=print_detail)
@@ -155,8 +158,11 @@ class TFModelWrapper(ModelWrapper):
             print(best_model_key)
             self.best_model = best_model
             pred = self.predict()
-            pred = tf.keras.utils.to_categorical(np.argmax(pred,axis=1), num_classes=self.num_classes)
-            actual = tf.keras.utils.to_categorical(self.test_label, num_classes=self.num_classes)
+            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)
+            if not utils.is_binary_encoded(actual):
+                actual = tf.keras.utils.to_categorical(actual, num_classes=self.num_classes)
 
             logs, metrics = evaluate(
                 actual=actual, pred=pred, info=self.descriptor)

ddi_fw/utils/__init__.py

@@ -3,4 +3,5 @@ from .zip_helper import ZipHelper
 from .py7zr_helper import Py7ZipHelper
 from .enums import UMLSCodeTypes, DrugBankTextDataTypes
 from .package_helper import get_import
-from .kaggle import create_kaggle_dataset
+from .kaggle import create_kaggle_dataset
+from .categorical_data_encoding_checker import is_one_hot_encoded, is_binary_encoded, is_binary_vector

ddi_fw/utils/categorical_data_encoding_checker.py

@@ -0,0 +1,32 @@
+import numpy as np
+
+
+def is_one_hot_encoded(arr):
+    # Check if the array is one-hot encoded
+    # Ensure the input is a numpy ndarray and is 2D
+    if not isinstance(arr, np.ndarray):
+        raise ValueError("Input must be a NumPy ndarray.")
+    if not np.all(np.isin(arr, [0, 1])):
+        return False
+    # Check if each row (or column) has exactly one "1"
+    return np.all(np.sum(arr, axis=1) == 1)  # For row-wise checking
+
+
+def is_binary_encoded(arr):
+    # Ensure the input is a numpy ndarray and is 2D
+    if not isinstance(arr, np.ndarray):
+        raise ValueError("Input must be a NumPy ndarray.")
+    if arr.ndim != 2:
+        raise ValueError("Input must be a 2D array.")
+
+    # Check if all elements are either 0 or 1
+    return np.all(np.isin(arr, [0, 1]))
+
+
+def is_binary_vector(arr):
+    # Ensure the input is a numpy ndarray and is 1D
+    if not isinstance(arr, np.ndarray):
+        raise ValueError("Input must be a NumPy ndarray.")
+    if arr.ndim != 1:
+        raise ValueError("Input must be a 1D array.")
+    return arr.ndim == 1 and np.all(np.isin(arr, [0, 1]))

{ddi_fw-0.0.178.dist-info → ddi_fw-0.0.180.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.178
+Version: 0.0.180
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.178.dist-info → ddi_fw-0.0.180.dist-info}/RECORD

@@ -1,5 +1,5 @@
 ddi_fw/datasets/__init__.py,sha256=_I3iDHARwzmg7_EL5XKtB_TgG1yAkLSOVTujLL9Wz9Q,280
-ddi_fw/datasets/core.py,sha256=6tbLMcunzfTE-BbE9GAEy_-h15N5EgK2oP5TfsHLjsk,10569
+ddi_fw/datasets/core.py,sha256=H2PHwlGkEH-qvVq-zIoyIDitfXc1uHdf8Ge1EA3qGss,10587
 ddi_fw/datasets/dataset_splitter.py,sha256=8H8uZTAf8N9LUZeSeHOMawtJFJhnDgUUqFcnl7dquBQ,1672
 ddi_fw/datasets/db_utils.py,sha256=OTsa3d-Iic7z3HmzSQK9UigedRbHDxYChJk0s4GfLnw,6191
 ddi_fw/datasets/setup_._py,sha256=khYVJuW5PlOY_i_A16F3UbSZ6s6o_ljw33Byw3C-A8E,1047
@@ -77,7 +77,7 @@ ddi_fw/ml/evaluation_helper.py,sha256=2-7CLSgGTqLEk4HkgCVIOt-GxfLAn6SBozJghAtHb5
 ddi_fw/ml/ml_helper.py,sha256=E6ef7f1UnQl6JBUdGDbbbI4FIS-904VGypT7tI0a598,8545
 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=AeEXGbsQW6BgVf-Mgxe9NbvwNqLOqqCTGyTNxfg4G_Y,10564
+ddi_fw/ml/tensorflow_wrapper.py,sha256=ihiruZwWeRLkgz8dsC0P40XaikpJSN-krVbo1LE5GUw,10858
 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
@@ -86,7 +86,8 @@ ddi_fw/pipeline/multi_modal_combination_strategy.py,sha256=JSyuP71b1I1yuk0s2ecCJ
 ddi_fw/pipeline/multi_pipeline.py,sha256=NfcH4Ze5U-JRiH3lrxEDWj-VPxYQYtp7tq6bLCImBzs,5550
 ddi_fw/pipeline/ner_pipeline.py,sha256=kNGtkg5rNX5MDywzvRxmvyk-DxXAjEbYzZkp8pNlAZo,6023
 ddi_fw/pipeline/pipeline.py,sha256=70lYsluAnTWDLTlf6rbecffw3Bl34L1_6ALfLUoSvtY,11324
-ddi_fw/utils/__init__.py,sha256=77563ikqAtdzjjgRlLp5OAsJBbpLA1Cao8iecGaVUXQ,354
+ddi_fw/utils/__init__.py,sha256=L64M3YCB56eSiB-rE2Zmn6DMNNwqHPWHq6Z_f4fi9VQ,458
+ddi_fw/utils/categorical_data_encoding_checker.py,sha256=DNbxjpyD8XTqILSHHQ0_VUd61PNBSupSAuXiq5nLTK8,1122
 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
@@ -97,7 +98,7 @@ 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=Z1A_DOBqDFPqLN4YB-3oYlOQWJK-X6Oes6UFjpzR47Q,4760
 ddi_fw/vectorization/idf_helper.py,sha256=_Gd1dtDSLaw8o-o0JugzSKMt9FpeXewTh4wGEaUd4VQ,2571
-ddi_fw-0.0.178.dist-info/METADATA,sha256=nSzlXlVfJLUgh8w5uhzzVoKJu-fLVUV7BrXH6GvGqhk,2542
-ddi_fw-0.0.178.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ddi_fw-0.0.178.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.178.dist-info/RECORD,,
+ddi_fw-0.0.180.dist-info/METADATA,sha256=6FZKb9M4aisFLRZL03LXbKA70RVMOp9YsnjY6U8OzWs,2542
+ddi_fw-0.0.180.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ddi_fw-0.0.180.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.180.dist-info/RECORD,,