Upload 2 files

util.py

@@ -0,0 +1,85 @@
+import pandas as pd
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.model_selection import train_test_split
+import os
+from imblearn.over_sampling import SMOTE
+import warnings
+warnings.filterwarnings("ignore")
+
+
+def load_data(data_dir : str, 
+              excel_file : str,
+                mode : str = "train",
+                scale = bool,
+                smote = bool,
+                ):
+    
+    
+    print("--------------Load RawData--------------")
+    df = pd.read_csv(os.path.join(data_dir, excel_file))
+    
+    #Inclusion
+    print("--------------Inclusion--------------")
+    print('Total : ', len(df))
+
+    print("--------------fillNA--------------")
+    # data = data.dropna()
+    df.fillna(0.0,inplace=True)
+    print(df['REAL_STONE'].value_counts())
+
+    #Column rename
+    df.rename(columns={'ID': 'patient_id', 'REAL_STONE':'target'}, inplace=True)
+
+   # df_all = ['SEX', 'FIRST_SBP', 'FIRST_DBP', 'FIRST_HR', 'FIRST_RR', 'FIRST_BT',
+    #    'AGE', 'VISIBLE_STONE_CT', 'PANCREATITIS', 'DUCT_DILIATATION_10MM',
+    #    'DUCT_DILIATATION_8MM', 'Hb', 'PLT', 'WBC', 'ALP', 'ALT', 'AST', 'CRP',
+    #    'BILIRUBIN', 'HR_100', 'GGT', 'BUN', 'CREATININE', 'BT_38', 'target']
+
+    # backward (n=13)
+    columns = ['patient_id','SEX',  'AGE', 'DUCT_DILIATATION_10MM', 'DUCT_DILIATATION_8MM', 'Hb', 'PLT', 'WBC', 'ALP', 'ALT', 'AST',  'GGT', 'BUN', 'CREATININE', 'target']
+
+ 
+    data = df[columns]
+    
+    if scale:
+        print("--------------Scaling--------------")
+        columns_to_scale = ['SEX',  'AGE', 'DUCT_DILIATATION_10MM', 'DUCT_DILIATATION_8MM', 'Hb', 'PLT', 'WBC', 'ALP', 'ALT', 'AST',  'GGT', 'BUN', 'CREATININE']
+
+        columns_to_scale_existing = [col for col in columns_to_scale if col in data.columns]
+
+        if columns_to_scale_existing:
+            scaler = MinMaxScaler()
+            data[columns_to_scale_existing] = scaler.fit_transform(data[columns_to_scale_existing])
+        else:
+            print("No columns to scale.")
+            
+    if mode == 'train' or mode == 'test':
+        if smote:  # Apply SMOTE if the flag is set
+            print(data['target'].value_counts())
+            print("Applying SMOTE...")
+            smote = SMOTE(sampling_strategy='all', random_state=42)
+            X_data = data.drop(columns=['target'])
+            y_data = data['target']
+            X_data_res, y_data_res = smote.fit_resample(X_data, y_data)
+            data_resampled = pd.DataFrame(X_data_res, columns=X_data.columns)
+            data_resampled['target'] = y_data_res
+            data = data_resampled  # Update train_data with resampled data
+            print(data['target'].value_counts())
+            
+        train_data, test_data = train_test_split(data, test_size=0.3, stratify=data['target'], random_state=123)
+        valid_data, test_data = train_test_split(test_data, test_size=0.4, stratify=test_data['target'], random_state=123)
+        
+        if mode == 'train':
+            print("Train set shape:", train_data.shape)
+            print("Validation set shape:", valid_data.shape)
+            return train_data, valid_data
+
+        elif mode == 'test':
+            print("Test set shape:", test_data.shape)
+            return test_data
+    
+    else:
+        raise ValueError("Choose mode!")
+    
+    
+    

view.py

@@ -0,0 +1,56 @@
+# Gradio
+examples = [
+    [
+        [['1', '0', '0', '104', '24', '10.6', '171', '14.54', '236', '182', '12.33', '3.2', '72']],
+        "PT_NO = 10001862, VISIBLE_STONE_CT = True, REAL_STONE = True",
+    ],
+    [
+        [['0', '1','0','106','18','13.6', '388', '21.13', '196', '118', '1.87', '2.7', '58']],
+        "PT_NO = 10007376, VISIBLE_STONE_CT = True, REAL_STONE = True",
+    ],
+    [
+        [['1', '0','1','205','18','9.3', '103', '8.45', '440', '100', '4.21', '4.5', '63']],
+        "PT_NO = 10040285, VISIBLE_STONE_CT = False, REAL_STONE = True",
+    ],
+    [
+        [['0', '1','1','130','20','12.1', '192', '8.63', '47', '59', '0.02', '0.4', '57']],
+        "PT_NO = 10005545, VISIBLE_STONE_CT = False, REAL_STONE = False",
+    ],
+]
+
+tabular_header = ['DUCT_DILIATATION_8MM', 'DUCT_DILIATATION_10MM','PANCREATITIS','FIRST_SBP','FIRST_RR','Hb', 'PLT', 'WBC', 'ALP', 'AST', 'CRP', 'BILIRUBIN', 'AGE']
+
+description = """
+GPU 리소스 제약으로 인해, 온라인 데모에서는 NVIDIA RTX 3090 24GB를 사용하고 있습니다. \n
+
+**Note**: 현재 저희 모델은 **총담관결석증**의 분석 및 진단을 중심으로 최적화되어 있으며, 정확하고 신뢰할 수 있는 결과를 제공합니다. \n 
+모델은 다음과 같은 입력 데이터를 처리하며, 아래와 같이 각각 **이산형(discrete)** **연속형(continuous)** 데이터로 처리됩니다. \n
+
+- 이산형 변수:
+- DUCT_DILIATATION_8MM
+- DUCT_DILIATATION_10MM
+- PANCREATITIS
+
+- 연속형 변수:
+- FIRST_SBP (Systolic blood pressure)
+- FIRST_RR (Respiratory rate)
+- Hb (Hemoglobin)
+- PLT (Platelet)
+- WBC (White Blood Cell)
+- ALP (Alkaline Phosphatase)
+- ALT (Alanine Aminotransferase)
+- AST (Aspartate Aminotransferase)
+- CRP (C-Reactive Protein)
+- BILIRUBIN
+- AGE 
+
+**중요**: 입력 데이터의 컬럼이 변경(추가, 삭제)될 경우, 모델의 예측 결과가 달라질 수 있습니다. \n 
+따라서 입력 데이터의 구조를 변경하기 전에 모델의 재학습 또는 재검증이 필요합니다. \n
+"""
+
+title_markdown = ("""
+# 임상 데이터 기반 머신러닝을 이용한 총담관석 예측 모델  
+## Development of a Common Bile Duct Stone Prediction Model Using Machine Learning Based on Clinical Data
+[📖[Learn more about Common Bile Duct Stones (총담관결석증)](https://namu.wiki/w/%EC%B4%9D%EB%8B%B4%EA%B4%80%EA%B2%B0%EC%84%9D%EC%A6%9D)] 
+### Copyright © 2024 Dongguk University (DGU) and Dongguk University Medical Center (DUMC). All rights reserved.
+""")