Cập nhật mã nguồn và file Colab Cache

2026-07-16 19:32:43 +07:00
parent 25969cb0f5
commit a258db54cd
69 changed files with 3377 additions and 645 deletions
@@ -0,0 +1,75 @@
+import json
+import glob
+import re
+
+def patch_python_script(filepath):
+    try:
+        with open(filepath, 'r', encoding='utf-8') as f:
+            content = f.read()
+            
+        original_content = content
+        
+        # Replace imports
+        content = re.sub(r'from sklearn\.ensemble import RandomForestClassifier', 
+                         'from xgboost import XGBClassifier', content)
+        
+        # Replace the model instantiations (for 01.train_ODC.py)
+        rf_pattern = re.compile(r'model\s*=\s*RandomForestClassifier\([^)]+\)', re.DOTALL)
+        xgb_replacement = """model = XGBClassifier(
+                    n_estimators=200,
+                    max_depth=30,
+                    tree_method="hist",
+                    device="cuda",
+                    random_state=42,
+                    n_jobs=-1,
+                    verbosity=1
+                )"""
+        
+        content = rf_pattern.sub(xgb_replacement, content)
+        
+        if content != original_content:
+            with open(filepath, 'w', encoding='utf-8') as f:
+                f.write(content)
+            print(f"Patched {filepath}")
+    except Exception as e:
+        print(f"Error patching {filepath}: {e}")
+
+def patch_notebook(filepath):
+    try:
+        with open(filepath, 'r', encoding='utf-8') as f:
+            nb = json.load(f)
+            
+        changed = False
+        import_pattern = re.compile(r'from\s+sklearn\.ensemble\s+import\s+RandomForestClassifier')
+        inst_pattern = re.compile(r'RandomForestClassifier\([^)]*\)')
+        
+        for cell in nb.get('cells', []):
+            if cell.get('cell_type') == 'code':
+                source = cell.get('source', [])
+                for i in range(len(source)):
+                    if import_pattern.search(source[i]):
+                        source[i] = import_pattern.sub('from xgboost import XGBClassifier', source[i])
+                        changed = True
+                        
+                    if inst_pattern.search(source[i]):
+                        source[i] = inst_pattern.sub("XGBClassifier(tree_method='hist', device='cuda', random_state=42, n_jobs=-1)", source[i])
+                        changed = True
+                        
+                    if "'classifier__criterion': ['gini', 'entropy']" in source[i]:
+                        source[i] = source[i].replace("'classifier__criterion': ['gini', 'entropy']",
+                                                      "'classifier__learning_rate': [0.01, 0.1, 0.2]")
+                        changed = True
+                        
+        if changed:
+            with open(filepath, 'w', encoding='utf-8') as f:
+                json.dump(nb, f, indent=1)
+            print(f"Patched {filepath}")
+    except Exception as e:
+        print(f"Error patching {filepath}: {e}")
+
+if __name__ == "__main__":
+    patch_python_script("01.train_ODC.py")
+    patch_python_script("new_train.py")
+    
+    for nb in glob.glob("*.ipynb"):
+        patch_notebook(nb)