{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceType":"competition","sourceId":24800,"datasetId":1042002,"databundleVersionId":1831594},{"sourceType":"datasetVersion","sourceId":11339939,"datasetId":7094420,"databundleVersionId":11766384},{"sourceType":"datasetVersion","sourceId":2057341,"datasetId":1232864,"databundleVersionId":2097467},{"sourceType":"datasetVersion","sourceId":8785422,"datasetId":5281464,"databundleVersionId":8941916},{"sourceType":"datasetVersion","sourceId":11215393,"datasetId":6799157,"databundleVersionId":11623300},{"sourceType":"datasetVersion","sourceId":1799839,"datasetId":1069682,"databundleVersionId":1837296},{"sourceType":"datasetVersion","sourceId":1799615,"datasetId":1069544,"databundleVersionId":1837072},{"sourceType":"modelInstanceVersion","sourceId":309588,"databundleVersionId":11623012,"modelInstanceId":262719}],"dockerImageVersionId":30919,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# 1. ***Libraries Installation & Importing*** ","metadata":{}},{"cell_type":"code","source":"!pip install ultralytics\n#!pip install torchxrayvision\n!pip install pydicom Pillow\n!pip install scikit-image\n!pip install tqdm --upgrade\n!pip install scikit-learn\n!pip install -q ensemble-boxes","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-05-06T22:58:05.318693Z","iopub.execute_input":"2025-05-06T22:58:05.318968Z","iopub.status.idle":"2025-05-06T22:58:36.219376Z","shell.execute_reply.started":"2025-05-06T22:58:05.318942Z","shell.execute_reply":"2025-05-06T22:58:36.217877Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ─────────────────────────────\n# ✅ Standard libraries\n# ─────────────────────────────\nimport os\nimport gc\nimport ast\nimport zipfile\nimport shutil\nimport random\nimport pprint\nimport warnings\nfrom glob import glob\nfrom collections import Counter\nfrom concurrent.futures import ThreadPoolExecutor\n\n# ─────────────────────────────\n# ✅ Data handling\n# ─────────────────────────────\nimport numpy as np\nimport pandas as pd\nimport yaml\nfrom tqdm.autonotebook import tqdm\n\n# ─────────────────────────────\n# ✅ Image handling & visualization\n# ─────────────────────────────\nimport cv2\nfrom PIL import Image\nimport matplotlib.pyplot as plt\nimport matplotlib.patches as patches\nimport seaborn as sns\nfrom IPython.display import display, FileLink\nimport pydicom\n\n# ─────────────────────────────\n# ✅ Scientific image processing\n# ─────────────────────────────\nimport skimage.io\nimport skimage.transform\nimport albumentations as A\n\n# ─────────────────────────────\n# ✅ Machine learning & utilities\n# ─────────────────────────────\nfrom sklearn.model_selection import StratifiedGroupKFold\nfrom sklearn.manifold import TSNE\n\n# ─────────────────────────────\n# ✅ Deep learning\n# ─────────────────────────────\nimport torch\nimport torch.nn.functional as F\nimport torchvision\nimport torchvision.transforms as T\nfrom torch.utils.data import DataLoader, Dataset\n#import torchxrayvision as xrv  \n\n# ─────────────────────────────\n# ✅ Object Detection (YOLO & WBF)\n# ─────────────────────────────\nfrom ultralytics import YOLO\nfrom ensemble_boxes import weighted_boxes_fusion","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-06T22:58:36.220547Z","iopub.execute_input":"2025-05-06T22:58:36.220923Z","iopub.status.idle":"2025-05-06T22:58:50.712107Z","shell.execute_reply.started":"2025-05-06T22:58:36.220892Z","shell.execute_reply":"2025-05-06T22:58:50.710876Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import skimage.io\nimport numpy as np\nimport torch\nimport torch.nn.functional as F\nimport torchvision.transforms\nimport torchxrayvision as xrv\n\n# ----- Manually set your configuration -----\nimg_path = \"/kaggle/input/private-dataset/thickened.jpg\"\nweights = \"densenet121-res224-all\"\nresize = True\ncuda = False\nfeats = False\n# ------------------------------------------\n\n# Load and normalize image\nimg = skimage.io.imread(img_path)\nimg = xrv.datasets.normalize(img, 255)\n\n# Convert to 2D grayscale if needed\nif len(img.shape) > 2:\n    img = img[:, :, 0]\nif len(img.shape) < 2:\n    raise ValueError(\"Image has less than 2 dimensions.\")\nimg = img[None, :, :]\n\n# Apply transformation\nif resize:\n    transform = torchvision.transforms.Compose([\n        xrv.datasets.XRayCenterCrop(),\n        xrv.datasets.XRayResizer(224)\n    ])\nelse:\n    transform = torchvision.transforms.Compose([\n        xrv.datasets.XRayCenterCrop()\n    ])\nimg = transform(img)\n\n# Load model\nmodel = xrv.models.get_model(weights)\n\n# Inference\noutput = {}\nwith torch.no_grad():\n    img_tensor = torch.from_numpy(img).unsqueeze(0)\n    if cuda:\n        img_tensor = img_tensor.cuda()\n        model = model.cuda()\n\n    if feats:\n        feats = model.features(img_tensor)\n        feats = F.relu(feats, inplace=True)\n        feats = F.adaptive_avg_pool2d(feats, (1, 1))\n        output[\"feats\"] = list(feats.cpu().numpy().reshape(-1))\n    else:\n        preds = model(img_tensor).cpu()\n        probs = preds[0].detach().numpy()\n        output[\"preds\"] = {\n            pathology: round(prob * 100, 2)\n            for pathology, prob in zip(xrv.datasets.default_pathologies, probs)\n        }\n\n# Display results\nif feats:\n    print(\"Feature vector extracted:\")\n    print(output[\"feats\"])\nelse:\n    print(f\"\\nClassification Predictions for {img_path} (in %):\")\n    for pathology, percent in output[\"preds\"].items():\n        print(f\"{pathology}: {percent}%\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 2. Data Preparation, Bounding Box Visualization, and Class Distribution","metadata":{}},{"cell_type":"code","source":"# ✅ Load dataset\nlabel_data_file = \"/kaggle/input/vinbigdata-1024-image-dataset/vinbigdata/train.csv\"\ntrain_df = pd.read_csv(label_data_file)\n\n# ✅ Add image_path column\ntrain_df['image_path'] = '/kaggle/input/vinbigdata-1024-image-dataset/vinbigdata/train/' + train_df.image_id + '.png'\n\n# ✅ Remove class 14 (No Finding) and class 2 (Calcification) completely\ntrain_df = train_df[~train_df.class_id.isin([14, 2])].reset_index(drop=True)\n\n# ✅ Print remaining images to confirm\nprint(f\"✅ Number of images remaining: {train_df['image_id'].nunique()}\")\n\n# ✅ Convert VinBigData bbox format to YOLO format\ntrain_df['x_mid'] = (train_df['x_min'] + train_df['x_max']) / (2 * train_df['width'])\ntrain_df['y_mid'] = (train_df['y_min'] + train_df['y_max']) / (2 * train_df['height'])\ntrain_df['w'] = (train_df['x_max'] - train_df['x_min']) / train_df['width']\ntrain_df['h'] = (train_df['y_max'] - train_df['y_min']) / train_df['height']\n\ntrain_df['source_dataset'] = 'vinbig'\n\ntrain_df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-06T22:58:50.717307Z","iopub.execute_input":"2025-05-06T22:58:50.71762Z","iopub.status.idle":"2025-05-06T22:58:51.062149Z","shell.execute_reply.started":"2025-05-06T22:58:50.717591Z","shell.execute_reply":"2025-05-06T22:58:51.061048Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ✅ Load the new NIH dataset\nnew_nih_file = \"/kaggle/input/nih-chest-xray-dataset-bbox-for-vinbigdata/nih.csv\"\nnew_nih_df = pd.read_csv(new_nih_file)\n\n# ✅ Add image path for new NIH dataset\nnew_nih_df['image_path'] = '/kaggle/input/nih-chest-xray-dataset-bbox-for-vinbigdata/nih/' + new_nih_df['image_id'] + '.png'\n\n# ✅ Remove rows with unmapped class names (NaN)\nnew_nih_df = new_nih_df.dropna(subset=['class_name'])\n\n# ✅ Define the class_name_to_id mapping\nclass_name_to_id = {\n    \"Aortic enlargement\": 0,\n    \"Cardiomegaly\": 2,  \n    \"Consolidation\": 3,\n    \"ILD\": 4,\n    \"Infiltration\": 5,\n    \"Lung Opacity\": 6,\n    \"Nodule/Mass\": 7,\n    \"Other lesion\": 8,\n    \"Pleural effusion\": 9,\n    \"Pleural thickening\": 10,\n    \"Pneumothorax\": 11,\n    \"Pulmonary fibrosis\": 12,\n    \"Atelectasis\": 1\n}\n\n# ✅ Assign class_id based on class_name\nnew_nih_df[\"class_id\"] = new_nih_df[\"class_name\"].map(class_name_to_id)\n\n# ✅ Calculate actual image width and height\nimage_widths = []\nimage_heights = []\n\nfor path in new_nih_df[\"image_path\"]:\n    image = cv2.imread(path)\n    if image is not None:\n        height, width = image.shape[:2]\n    else:\n        height, width = -1, -1  # Handle missing/corrupted image case\n    image_widths.append(width)\n    image_heights.append(height)\n\n# ✅ Store as 'width' and 'height' (actual image dimensions, not bbox)\nnew_nih_df[\"width\"] = image_widths\nnew_nih_df[\"height\"] = image_heights\n\n# ✅ Convert bbox to YOLO format (1-step calculation + normalization)\nnew_nih_df['x_mid'] = (new_nih_df['x_min'] + new_nih_df['x_max']) / (2 * new_nih_df['width'])\nnew_nih_df['y_mid'] = (new_nih_df['y_min'] + new_nih_df['y_max']) / (2 * new_nih_df['height'])\nnew_nih_df['w'] = (new_nih_df['x_max'] - new_nih_df['x_min']) / new_nih_df['width']\nnew_nih_df['h'] = (new_nih_df['y_max'] - new_nih_df['y_min']) / new_nih_df['height']\n\nnew_nih_df['source_dataset'] = 'nih_for_vin'\n\n# ✅ Select relevant columns (now width/height = image size)\nnew_nih_df = new_nih_df[[\n    'image_id', 'class_name', 'class_id', 'rad_id',\n    'x_mid', 'y_mid', 'w', 'h',\n    'x_min', 'y_min', 'x_max', 'y_max',\n    'width', 'height', 'image_path', 'source_dataset'\n]]\n\n# ✅ Filter for only the classes you want to add: Atelectasis, Pneumothorax, and Nodule/Mass\nrelevant_classes = [\"Atelectasis\", \"Pneumothorax\", \"Nodule/Mass\"]\nfiltered_nih_df = new_nih_df[new_nih_df[\"class_name\"].isin(relevant_classes)]\n\n# ✅ Merge the filtered DataFrame with the existing train_df\ntrain_df = pd.concat([train_df, filtered_nih_df], ignore_index=True)\n\n# ✅ Check for NaN class IDs after merging\nprint(f\"Number of NaN class IDs after merge: {train_df['class_id'].isna().sum()}\")  # Should be 0\n\n# ✅ Print final dataset details\nprint(f\"✅ Number of unique images after final merge: {train_df['image_id'].nunique()}\")\ntrain_df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-06T22:58:51.063312Z","iopub.execute_input":"2025-05-06T22:58:51.063902Z","iopub.status.idle":"2025-05-06T22:59:26.527099Z","shell.execute_reply.started":"2025-05-06T22:58:51.063868Z","shell.execute_reply":"2025-05-06T22:59:26.525908Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def visualize_bboxes(image_paths, bboxes_list, labels_list, image_sizes, num_images=5):\n    num_images = min(num_images, len(image_paths))  \n    fig, axes = plt.subplots(1, num_images, figsize=(50, 30))\n\n    if num_images == 1:\n        axes = [axes]\n\n    for idx in range(num_images):\n        image_path, bboxes, labels, (orig_width, orig_height) = (\n            image_paths[idx], bboxes_list[idx], labels_list[idx], image_sizes[idx])\n\n        image = cv2.imread(image_path)\n        if image is None:\n            print(f\"⚠️ Error: Could not read {image_path}\")\n            continue\n\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)  \n        height, width, _ = image.shape  \n\n        # ✅ Rescale bounding boxes\n        for i in range(len(bboxes)):\n            x_min, y_min, x_max, y_max = bboxes[i]\n            bboxes[i] = [\n                int((x_min / orig_width) * width),\n                int((y_min / orig_height) * height),\n                int((x_max / orig_width) * width),\n                int((y_max / orig_height) * height),\n            ]\n            cv2.rectangle(image, (bboxes[i][0], bboxes[i][1]), (bboxes[i][2], bboxes[i][3]), (0, 255, 0), 2)\n            cv2.putText(image, labels[i], (bboxes[i][0], bboxes[i][1] - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 2)\n\n        axes[idx].imshow(image)\n        axes[idx].axis(\"off\")\n\n    plt.show()\n    return bboxes_list  # Return updated bounding boxes","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-06T22:59:26.528725Z","iopub.execute_input":"2025-05-06T22:59:26.529338Z","iopub.status.idle":"2025-05-06T22:59:26.539142Z","shell.execute_reply.started":"2025-05-06T22:59:26.529303Z","shell.execute_reply":"2025-05-06T22:59:26.537669Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ✅ Select a random sample of unique images\nnum_samples = 5\nsampled_images = train_df[\"image_id\"].drop_duplicates().sample(n=min(num_samples, train_df[\"image_id\"].nunique())).tolist()\n\n# ✅ Prepare lists for visualization\nimage_paths, bboxes_list, labels_list, image_sizes = [], [], [], []\n\nfor image_id in sampled_images:\n    sample_df = train_df[train_df[\"image_id\"] == image_id]\n    image_path = sample_df[\"image_path\"].iloc[0]\n    print(f\"🔍 Visualizing image: {image_path}\")  # <-- ✅ Print the image path here\n    image_paths.append(image_path)\n    bboxes_list.append(sample_df[[\"x_min\", \"y_min\", \"x_max\", \"y_max\"]].values.tolist())\n    labels_list.append(sample_df[\"class_name\"].tolist())\n    image_sizes.append(sample_df[[\"width\", \"height\"]].iloc[0].tolist())\n\n# ✅ Visualize & Update Bounding Boxes\nbboxes_list_updated = visualize_bboxes(image_paths, bboxes_list, labels_list, image_sizes, num_images=num_samples)\n\n# ✅ Update train_df with new bounding boxes\nfor i, image_id in enumerate(sampled_images):\n    sample_df = train_df[train_df[\"image_id\"] == image_id].copy()\n    updated_bboxes = bboxes_list_updated[i]\n    \n    for j, bbox in enumerate(updated_bboxes):\n        train_df.loc[sample_df.index[j], ['x_min', 'y_min', 'x_max', 'y_max']] = bbox\n\nprint(\"✅ Bounding boxes updated in train_df!\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-06T22:59:26.541166Z","iopub.execute_input":"2025-05-06T22:59:26.541878Z","iopub.status.idle":"2025-05-06T22:59:28.954792Z","shell.execute_reply.started":"2025-05-06T22:59:26.541832Z","shell.execute_reply":"2025-05-06T22:59:28.953767Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ✅ Load NIH dataset\nnih_bbox_file = \"/kaggle/input/nih-chest-x-rays-bbox-version/BBox_List_2017.csv\"\nnih_df = pd.read_csv(nih_bbox_file)\n# ✅ Add image path\nnih_df['image_path'] = '/kaggle/input/nih-chest-x-rays-bbox-version/bbox_img/' + nih_df['Image Index']\n\n# ✅ Map class names\nnih_class_mapping = {\n    \"Infiltrate\": \"Infiltration\",\n    \"Atelectasis\": \"Atelectasis\",\n    \"Pneumonia\": \"Pneumonia\",\n    \"Cardiomegaly\": \"Cardiomegaly\",\n    \"Effusion\": \"Pleural effusion\",\n    \"Pneumothorax\": \"Pneumothorax\",\n    \"Mass\": \"Nodule/Mass\",\n    \"Nodule\": \"Nodule/Mass\"\n}\nnih_df['class_name'] = nih_df['Finding Label'].map(nih_class_mapping)\nnih_df = nih_df.dropna(subset=['class_name'])\n\n# ✅ Rename bbox columns\nnih_df = nih_df.rename(columns={\n    \"Image Index\": \"image_id\",\n    \"Bbox [x\": \"x_min\",\n    \"y\": \"y_min\",\n    \"w\": \"w\",\n    \"h]\": \"h\"\n})\n\n# ✅ Compute x_max, y_max\nnih_df['x_max'] = nih_df['x_min'] + nih_df['w']\nnih_df['y_max'] = nih_df['y_min'] + nih_df['h']\n\n# ✅ Assume fixed image size if actual dimensions are not available (e.g., 1024x1024)\nnih_df['width'] = 1024\nnih_df['height'] = 1024\n\n# ✅ Compute YOLO format in one step\nnih_df['x_mid'] = (nih_df['x_min'] + nih_df['x_max']) / (2 * nih_df['width'])\nnih_df['y_mid'] = (nih_df['y_min'] + nih_df['y_max']) / (2 * nih_df['height'])\nnih_df['w'] = (nih_df['x_max'] - nih_df['x_min']) / nih_df['width']\nnih_df['h'] = (nih_df['y_max'] - nih_df['y_min']) / nih_df['height']\n\nnih_df['source_dataset'] = 'nih'\n\n# ✅ Final column selection\nnih_df = nih_df[['image_id', 'class_name', 'x_mid', 'y_mid', 'w', 'h', 'x_min', 'y_min', 'x_max', 'y_max', 'width', 'height', 'image_path','source_dataset']]\n\n# ✅ Filter for only the classes you want to add: Atelectasis, Pneumothorax, and Nodule/Mass\nrelevant_classes = [\"Atelectasis\", \"Pneumothorax\", \"Nodule/Mass\"]\nfiltered_nih_df = nih_df[nih_df[\"class_name\"].isin(relevant_classes)]\n\n# ✅ Merge the filtered DataFrame with the existing train_df\ntrain_df = pd.concat([train_df, filtered_nih_df], ignore_index=True)\n\n# ✅ Assign class_id to the merged dataset\nclass_name_to_id = {\n    \"Aortic enlargement\": 0,\n    \"Cardiomegaly\": 2,  \n    \"Consolidation\": 3,\n    \"ILD\": 4,\n    \"Infiltration\": 5,\n    \"Lung Opacity\": 6,\n    \"Nodule/Mass\": 7,\n    \"Other lesion\": 8,\n    \"Pleural effusion\": 9,\n    \"Pleural thickening\": 10,\n    \"Pneumothorax\": 11,\n    \"Pulmonary fibrosis\": 12,\n    \"Atelectasis\": 1,\n    \"Pneumonia\": 13 \n}\ntrain_df[\"class_id\"] = train_df[\"class_name\"].map(class_name_to_id)\n\n# ✅ Check for NaN class IDs after merging\nprint(f\"Number of NaN class IDs: {train_df['class_id'].isna().sum()}\")  # Should be 0\n\n# ✅ Print final dataset details\nprint(f\"✅ Number of unique images after merging: {train_df['image_id'].nunique()}\")\ntrain_df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-06T23:02:13.706492Z","iopub.execute_input":"2025-05-06T23:02:13.706948Z","iopub.status.idle":"2025-05-06T23:02:13.777136Z","shell.execute_reply.started":"2025-05-06T23:02:13.706915Z","shell.execute_reply":"2025-05-06T23:02:13.776171Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport cv2\nimport pandas as pd\n\n# Define the directories where the images and their corresponding label files are stored\nimages_dir = \"/kaggle/input/chestxrayabnormalities/train/images\"  # Correct directory\nlabels_dir = \"/kaggle/input/chestxrayabnormalities/train/labels\"  # Correct directory\n\n# Class mapping (ID to class name) based on the ChestX-ray dataset\nclass_mapping = {\n    0: \"Aortic_enlargement\",\n    1: \"Atelectasis\",\n    2: \"Calcification\",\n    3: \"Cardiomegaly\",\n    4: \"Consolidation\",\n    5: \"ILD\",\n    6: \"Infiltration\",\n    7: \"Lung_Opacity\",\n    8: \"Nodule-Mass\",  # This is mapped to 'Nodule/Mass'\n    9: \"Other_lesion\",\n    10: \"Pleural_effusion\",\n    11: \"Pleural_thickening\",\n    12: \"Pneumothorax\",\n    13: \"Pulmonary_fibrosis\"\n}\n\n# Define the relevant classes you want to keep\nrelevant_classes = [\"Atelectasis\", \"Pneumothorax\", \"Nodule-Mass\"]\n\n# Create a list to hold the processed data\nprocessed_data = []\n\n# List all image files in the images directory\nimage_files = os.listdir(images_dir)\n\n# Loop through all the label files in the directory\nfor label_file in os.listdir(labels_dir):\n    if label_file.endswith('.txt'):\n        # Extract the image ID (without extension)\n        image_id = label_file.split('.')[0]\n        \n        # Search for the image file in the images directory that matches the image_id (contains it as a substring)\n        matching_image_files = [img for img in image_files if image_id in img]\n        \n        if matching_image_files:\n            # If there is a match, take the first one (in case there are multiple matches)\n            image_path = os.path.join(images_dir, matching_image_files[0])\n        else:\n            print(f\"❌ No matching image found for {image_id}\")\n            continue\n        \n        # Read the image to get its dimensions (height and width)\n        image = cv2.imread(image_path)\n        if image is not None:\n            image_height, image_width = image.shape[:2]\n        else:\n            image_height, image_width = -1, -1  # Handle missing or corrupted image case\n        \n        # Read the corresponding label file\n        label_file_path = os.path.join(labels_dir, label_file)\n        with open(label_file_path, 'r') as f:\n            lines = f.readlines()\n        \n        # Process each line in the label file\n        for line in lines:\n            parts = line.strip().split()\n            class_id = int(parts[0])  # Original class ID\n\n            # Only process the class_ids that are in the relevant_classes set\n            if class_mapping.get(class_id) in relevant_classes:\n                class_name = class_mapping[class_id]\n                \n                # YOLO format is already in normalized form\n                x_mid = float(parts[1])\n                y_mid = float(parts[2])\n                bbox_width = float(parts[3])\n                bbox_height = float(parts[4])\n\n                # Append the data for this image and label (including class_id and class_name)\n                processed_data.append([image_id, class_name, class_id, x_mid, y_mid, bbox_width, bbox_height])\n\n# Convert the processed data into a DataFrame\nprocessed_df = pd.DataFrame(processed_data, columns=['image_id', 'class_name', 'class_id', 'x_mid', 'y_mid', 'w', 'h'])\n\n# Construct the image path correctly by mapping to the correct image file in the directory\nprocessed_df['image_path'] = processed_df['image_id'].apply(\n    lambda x: os.path.join(images_dir, next((img for img in image_files if x in img), None))\n)\n\n# Add the source dataset name (in this case, 'chestxrayabnormalities')\nprocessed_df['source_dataset'] = 'chestxrayabnormalities'\n\n# Standardize class names to match the format in train_df (e.g., 'Nodule-Mass' to 'Nodule/Mass')\nprocessed_df['class_name'] = processed_df['class_name'].replace(\"Nodule-Mass\", \"Nodule/Mass\")\n\n# Define the class_name to class_id mapping for the final step\nclass_name_to_id = {\n    \"Aortic_enlargement\": 0,\n    \"Atelectasis\": 1,\n    \"Calcification\": 2,\n    \"Cardiomegaly\": 3,\n    \"Consolidation\": 4,\n    \"ILD\": 5,\n    \"Infiltration\": 6,\n    \"Lung_Opacity\": 7,\n    \"Nodule/Mass\": 8,  # Ensure it matches with 'Nodule/Mass' for consistency\n    \"Other_lesion\": 9,\n    \"Pleural_effusion\": 10,\n    \"Pleural_thickening\": 11,\n    \"Pneumothorax\": 12,\n    \"Pulmonary_fibrosis\": 13\n}\n\n# Assign class_id based on class_name\nprocessed_df['class_id'] = processed_df['class_name'].map(class_name_to_id)\n\n# Check for any NaN values in class_id (should be 0 if no issue)\nprint(f\"✅ Number of NaN class IDs: {processed_df['class_id'].isna().sum()}\")  # Should be 0\n\n# Print the first few rows of the final DataFrame\nprint(f\"✅ Final dataset preview:\")\nprint(processed_df.head())\n\n# ✅ Now, merge with train_df (if exists) or create a new train_df\ntrain_df = pd.concat([train_df, processed_df], ignore_index=True)\n\n# ✅ Print final dataset details\nprint(f\"✅ Number of unique images after merging: {train_df['image_id'].nunique()}\")\ntrain_df.head()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ✅ Group by image_id and get unique classes per image\nunique_class_per_image = train_df.groupby(\"image_id\")[\"class_name\"].unique()\n\n# ✅ Count how many images each class appears in\nclass_counts = unique_class_per_image.explode().value_counts()\n\n# ✅ Map class_name to class_id\nclass_name_to_id = train_df.drop_duplicates(\"class_name\")[[\"class_name\", \"class_id\"]].set_index(\"class_name\")[\"class_id\"].to_dict()\n\n# ✅ Add class_id to the labels\nclass_labels_with_ids = [f\"{cls} (ID {class_name_to_id.get(cls, 'Unknown')})\" for cls in class_counts.index]\n\n# ✅ Sort class counts\nclass_counts = class_counts.sort_values(ascending=False)\nclass_labels_with_ids = [label for _, label in sorted(zip(class_counts.values, class_labels_with_ids), reverse=True)]\n\n# ✅ Create color palette\ncolors = sns.color_palette(\"tab20\", len(class_counts))\n\n# ✅ Plot the class distribution\nplt.figure(figsize=(14, 6))\nbars = plt.bar(class_labels_with_ids, class_counts.values, color=colors)\nplt.title('Class Distribution Across Images (Unique Occurrences)', fontsize=16)\nplt.xlabel('Class Name (with Class ID)', fontsize=12)\nplt.ylabel('Number of Images', fontsize=12)\nplt.xticks(rotation=45, ha='right')\n\n# ✅ Annotate counts on top of bars\nfor i, bar in enumerate(bars):\n    height = bar.get_height()\n    plt.text(bar.get_x() + bar.get_width() / 2, height + 1, str(height), ha='center', va='bottom', fontsize=10)\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ✅ Group by class_name and count total occurrences (across all bounding boxes)\nclass_counts = train_df['class_name'].value_counts()\n\n# ✅ Map class_name to class_id\nclass_name_to_id = train_df.drop_duplicates(\"class_name\")[[\"class_name\", \"class_id\"]].set_index(\"class_name\")[\"class_id\"].to_dict()\n\n# ✅ Add class_id to the labels\nclass_labels_with_ids = [f\"{cls} (ID {class_name_to_id.get(cls, 'Unknown')})\" for cls in class_counts.index]\n\n# ✅ Sort class counts\nclass_counts = class_counts.sort_values(ascending=False)\nclass_labels_with_ids = [label for _, label in sorted(zip(class_counts.values, class_labels_with_ids), reverse=True)]\n\n# ✅ Create color palette\ncolors = sns.color_palette(\"tab20\", len(class_counts))\n\n# ✅ Plot the class distribution\nplt.figure(figsize=(14, 6))\nbars = plt.bar(class_labels_with_ids, class_counts.values, color=colors)\nplt.title('Class Distribution Across All Bounding Boxes (Total Occurrences)', fontsize=16)\nplt.xlabel('Class Name (with Class ID)', fontsize=12)\nplt.ylabel('Total Occurrences (Bounding Boxes)', fontsize=12)\nplt.xticks(rotation=45, ha='right')\n\n# ✅ Annotate counts on top of bars\nfor i, bar in enumerate(bars):\n    height = bar.get_height()\n    plt.text(bar.get_x() + bar.get_width() / 2, height + 1, str(height), ha='center', va='bottom', fontsize=10)\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 3. Class Mapping","metadata":{}},{"cell_type":"code","source":"# ✅ Define the class mapping dictionary with old IDs (0 to 13) and their corresponding new groupings\nclass_mapping = {\n    0: \"Aortic Enlargement\",    # Aortic enlargement (ID 0)\n    1: \"Lung Collapse\",         # Atelectasis (ID 1)\n    2: \"Cardiomegaly\",          # Cardiomegaly (ID 2)\n    3: \"Opacities/Infiltration\",  # Consolidation (ID 3)\n    4: \"Opacities/Infiltration\",  # ILD (ID 4)\n    5: \"Opacities/Infiltration\",  # Infiltration (ID 5)\n    6: \"Opacities/Infiltration\",  # Lung Opacity (ID 6)\n    7: \"Nodule/Mass\",           # Nodule/Mass (ID 7)\n    8: \"Nodule/Mass\",           # Nodule/Mass (ID 8)\n    9: \"Pleural Conditions\",    # Pleural Effusion (ID 9)\n    10: \"Pleural Conditions\",   # Pleural Thickening (ID 10)\n    11: \"Lung Collapse\",        # Pneumothorax (ID 11)\n    12: \"Opacities/Infiltration\",  # Pulmonary fibrosis (ID 12)\n    13: \"Opacities/Infiltration\"   # Lung Opacity (ID 13)\n}\n\n# ✅ Apply the class mapping to create `mapped_class_name`\ntrain_df['mapped_class_name'] = train_df['class_id'].map(class_mapping)\n\n# ✅ Debugging: Check for unmapped class IDs\nunmapped_classes = train_df[train_df['mapped_class_name'].isna()]['class_id'].unique()\nif len(unmapped_classes) > 0:\n    print(f\"⚠️ Warning: Some class IDs are not mapped! Unmapped class IDs: {unmapped_classes}\")\n\n# ✅ Remove any NaN values before creating unique class names\ntrain_df = train_df.dropna(subset=['mapped_class_name'])\n\n# ✅ Get unique class names (ensuring correct count)\nclass_names = sorted(train_df['mapped_class_name'].unique())\n\n# ✅ Explicitly map class names to new indices\nnew_class_ids = {name: idx for idx, name in enumerate(class_names)}\n\n# ✅ Apply the new mapping to create a new class ID\ntrain_df['new_class_id'] = train_df['mapped_class_name'].map(new_class_ids)\n\n# ✅ Create the final new class mapping (new class IDs)\nnew_class_mapping = {idx: name for name, idx in new_class_ids.items()}\n\n# ✅ Verify the new class mapping\nprint(f\"✅ New class mapping (new class IDs): {new_class_mapping}\")\ntrain_df.head()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport cv2\n\n# ✅ Function to visualize images with bounding boxes and show image path\ndef visualize_bboxes(image_paths, bboxes_list, labels_list, image_sizes, num_images=5):\n    num_images = min(num_images, len(image_paths))  \n    fig, axes = plt.subplots(1, num_images, figsize=(50, 30))\n\n    if num_images == 1:\n        axes = [axes]\n\n    for idx in range(num_images):\n        image_path, bboxes, labels, (orig_width, orig_height) = (\n            image_paths[idx], bboxes_list[idx], labels_list[idx], image_sizes[idx])\n        \n        # ✅ Print image path to console/log\n        print(f\"\\n🖼 Visualizing image {idx + 1}/{num_images}: {image_path}\")\n        \n        image = cv2.imread(image_path)\n        if image is None:\n            print(f\"⚠️ Error: Could not read {image_path}\")\n            continue\n    \n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)  \n        height, width, _ = image.shape  \n    \n        # ✅ Rescale and draw bounding boxes\n        for i in range(len(bboxes)):\n            x_min, y_min, x_max, y_max = bboxes[i]\n            x_min = int((x_min / orig_width) * width)\n            y_min = int((y_min / orig_height) * height)\n            x_max = int((x_max / orig_width) * width)\n            y_max = int((y_max / orig_height) * height)\n            bboxes[i] = [x_min, y_min, x_max, y_max]\n            cv2.rectangle(image, (x_min, y_min), (x_max, y_max), (0, 255, 0), 2)\n            cv2.putText(image, labels[i], (x_min, y_min - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 2)\n    \n        axes[idx].imshow(image)\n        axes[idx].axis(\"off\")\n        axes[idx].set_title(image_path.split('/')[-1], fontsize=14, color='blue')  # Optional shorter title\n\n    plt.tight_layout()\n    plt.show()\n\n# ✅ Select a random sample of unique images for visualization\nnum_samples = 5\nsampled_images = train_df[\"image_id\"].drop_duplicates().sample(n=min(num_samples, train_df[\"image_id\"].nunique())).tolist()\n\n# ✅ Prepare lists for visualization\nimage_paths, bboxes_list, labels_list, image_sizes = [], [], [], []\n\nfor image_id in sampled_images:\n    sample_df = train_df[train_df[\"image_id\"] == image_id]\n    image_paths.append(sample_df[\"image_path\"].iloc[0])\n    bboxes_list.append(sample_df[[\"x_min\", \"y_min\", \"x_max\", \"y_max\"]].values.tolist())\n    labels_list.append(sample_df[\"mapped_class_name\"].tolist())  # Use mapped class names\n    image_sizes.append(sample_df[[\"width\", \"height\"]].iloc[0].tolist())\n\n# ✅ Visualize images with bounding boxes!\nvisualize_bboxes(image_paths, bboxes_list, labels_list, image_sizes, num_images=num_samples)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ✅ Function to update the bounding boxes in the DataFrame\ndef update_bboxes_in_df(sampled_images, bboxes_list_updated):\n    for i, image_id in enumerate(sampled_images):\n        sample_df = train_df[train_df[\"image_id\"] == image_id].copy()\n        updated_bboxes = bboxes_list_updated[i]\n        \n        for j, bbox in enumerate(updated_bboxes):\n            train_df.loc[sample_df.index[j], ['x_min', 'y_min', 'x_max', 'y_max']] = bbox\n\n    print(\"✅ Bounding boxes updated in train_df!\")\n\n# ✅ Assuming bboxes_list_updated has been returned from the visualization function\n# Call the update function after visualizing\nupdate_bboxes_in_df(sampled_images, bboxes_list_updated)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import seaborn as sns\nimport matplotlib.pyplot as plt\n\n# ✅ Group by image_id and mapped_class_name, counting unique classes per image\nunique_classes_per_image = train_df.groupby(\"image_id\")[\"mapped_class_name\"].nunique()\n\n# ✅ Count how many images have each unique class (counting each class once per image)\nclass_counts = train_df.groupby(\"mapped_class_name\")[\"image_id\"].nunique()\nclass_counts = class_counts.sort_values(ascending=False)\n\n# ✅ Create a color palette for the plot\ncolors = sns.color_palette(\"Set2\", len(class_counts))\n\n# ✅ Plot the class distribution showing how many images each class appeared in\nplt.figure(figsize=(12, 6))\nclass_counts.plot(kind='bar', color=colors)\n\n# ✅ Add class count labels on top of bars\nfor i, value in enumerate(class_counts.values):\n    plt.text(i, value + 1, str(value), ha='center', va='bottom', fontsize=10)\n\n# ✅ Set plot title and labels\nplt.title('Mapped Class Distribution Across Images (Unique Occurrences)', fontsize=16)\nplt.xlabel('Mapped Class Name', fontsize=12)\nplt.ylabel('Number of Images', fontsize=12)\nplt.xticks(rotation=45, ha='right')\n\n# ✅ Add new class ID labels next to the class name on the x-axis\n# Here, we get the new class ID directly from train_df's 'new_class_id'\nnew_class_labels = [f\"{name} (ID: {train_df[train_df['mapped_class_name'] == name]['new_class_id'].iloc[0]})\" \n                    for name in class_counts.index]\n\nplt.xticks(ticks=range(len(class_counts)), labels=new_class_labels, rotation=45, ha='right')\n\n# ✅ Adjust layout and show plot\nplt.tight_layout()\nplt.show()\n\n# ✅ Display the class distribution with new class IDs\nprint(f\"Mapped class distribution (counting each class once per image):\\n{class_counts}\")\n\n# ✅ Create the new class ID mapping and display it\nnew_class_id_mapping = {name: train_df[train_df['mapped_class_name'] == name]['new_class_id'].iloc[0] \n                        for name in class_counts.index}\nprint(f\"\\nNew Class IDs Mapping:\\n{new_class_id_mapping}\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import seaborn as sns\nimport matplotlib.pyplot as plt\n\n# ✅ Count how many times each class appears in each image (including duplicates for multiple bboxes)\nclass_occurrences = train_df.groupby([\"image_id\", \"mapped_class_name\"]).size().reset_index(name=\"count\")\n\n# ✅ Sum the counts of each class across all images\nclass_counts = class_occurrences.groupby(\"mapped_class_name\")[\"count\"].sum()\n\n# ✅ Sort by count (optional, for better visualization)\nclass_counts = class_counts.sort_values(ascending=False)\n\n# ✅ Create a color palette for the plot\ncolors = sns.color_palette(\"Set2\", len(class_counts))\n\n# ✅ Plot the class distribution with annotations\nplt.figure(figsize=(12, 6))\nbarplot = class_counts.plot(kind='bar', color=colors)\n\n# ✅ Add value annotations above each bar\nfor i, value in enumerate(class_counts.values):\n    plt.text(i, value + max(class_counts.values) * 0.01, str(value), ha='center', va='bottom', fontsize=10)\n\n# ✅ Set plot title and labels\nplt.title('Mapped Class Distribution Across All Images (Total Bounding Box Occurrences)', fontsize=16)\nplt.xlabel('Mapped Class Name', fontsize=12)\nplt.ylabel('Total Number of Bounding Boxes', fontsize=12)\nplt.xticks(rotation=45, ha='right')\n\n# ✅ Add new class ID labels next to the class name on the x-axis\n# We are using the `new_class_id` from `train_df` to get the correct IDs for the classes\nnew_class_labels = [f\"{name} (ID: {train_df[train_df['mapped_class_name'] == name]['new_class_id'].iloc[0]})\" for name in class_counts.index]\n\nplt.xticks(ticks=range(len(class_counts)), labels=new_class_labels, rotation=45, ha='right')\n\n# ✅ Grid lines for better readability\nplt.grid(axis='y', linestyle='--', alpha=0.5)\n\n# ✅ Adjust layout and show plot\nplt.tight_layout()\nplt.show()\n\n# ✅ Print the full distribution as a summary\nprint(\"\\n📊 Mapped class distribution (counting total bounding box occurrences across images):\")\nprint(class_counts)\n\n# ✅ Print the new class ID mapping\nnew_class_id_mapping = {name: train_df[train_df['mapped_class_name'] == name]['new_class_id'].iloc[0] for name in class_counts.index}\nprint(f\"\\nNew Class IDs Mapping:\\n{new_class_id_mapping}\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"WBF","metadata":{}},{"cell_type":"code","source":"# ✅ Apply WBF Function\ndef apply_wbf(train_df, iou_thr=0.1, skip_box_thr=0.0001, min_box_size=0.001):\n    output = []\n\n    for image_id, group in tqdm(train_df.groupby(\"image_id\"), desc=\"Applying WBF\"):\n        w, h = group['width'].iloc[0], group['height'].iloc[0]\n\n        boxes_list = []\n        scores_list = []\n        labels_list = []\n\n        boxes_single = []\n        labels_single = []\n\n        count_dict = Counter(group['new_class_id'].tolist())\n        class_ids = group['new_class_id'].unique().tolist()\n\n        for cid in class_ids:\n            class_group = group[group.new_class_id == cid]\n\n            if count_dict[cid] == 1:\n                row = class_group.iloc[0]\n                # Use YOLO-normalized box and convert to (x_min, y_min, x_max, y_max)\n                x_mid, y_mid, box_w, box_h = row['x_mid'], row['y_mid'], row['w'], row['h']\n                x_min = x_mid - box_w / 2\n                y_min = y_mid - box_h / 2\n                x_max = x_mid + box_w / 2\n                y_max = y_mid + box_h / 2\n\n                box = [x_min, y_min, x_max, y_max]\n                boxes_single.append(box)\n                labels_single.append(cid)\n            else:\n                # Same as above, use YOLO-normalized coords\n                x_mid = class_group['x_mid'].to_numpy()\n                y_mid = class_group['y_mid'].to_numpy()\n                box_w = class_group['w'].to_numpy()\n                box_h = class_group['h'].to_numpy()\n\n                x_min = x_mid - box_w / 2\n                y_min = y_mid - box_h / 2\n                x_max = x_mid + box_w / 2\n                y_max = y_mid + box_h / 2\n\n                bboxes = np.stack([x_min, y_min, x_max, y_max], axis=1)\n                bboxes = np.clip(bboxes, 0, 1)  # Ensure in [0,1]\n\n                boxes_list.append(bboxes.tolist())\n                scores_list.append([1.0] * len(class_group))\n                labels_list.append([cid] * len(class_group))\n\n        # Apply WBF\n        if boxes_list:\n            fused_boxes, _, fused_labels = weighted_boxes_fusion(\n                boxes_list, scores_list, labels_list,\n                weights=None, iou_thr=iou_thr, skip_box_thr=skip_box_thr\n            )\n        else:\n            fused_boxes, fused_labels = np.empty((0, 4)), np.empty((0,))\n\n        # Combine with singles\n        if len(boxes_single) > 0:\n            all_boxes = np.vstack([fused_boxes, boxes_single])\n            all_labels = np.hstack([fused_labels, labels_single])\n        else:\n            all_boxes = fused_boxes\n            all_labels = fused_labels\n\n        # Convert back to YOLO format and append\n        for box, label in zip(all_boxes, all_labels):\n            x_min, y_min, x_max, y_max = box\n            box_w = x_max - x_min\n            box_h = y_max - y_min\n            x_center = (x_min + x_max) / 2\n            y_center = (y_min + y_max) / 2\n\n            # Filter out tiny boxes\n            if box_w > min_box_size and box_h > min_box_size:\n                output.append({\n                    \"image_id\": image_id,\n                    \"x_mid\": x_center,\n                    \"y_mid\": y_center,\n                    \"w\": box_w,\n                    \"h\": box_h,\n                    \"new_class_id\": int(label) if isinstance(label, (int, float)) else label\n                })\n\n    return pd.DataFrame(output)\n\n# ✅ Display summary BEFORE WBF\nprint(\"📊 Before WBF:\")\nprint(f\"🔹 Total images: {train_df['image_id'].nunique()}\")\nprint(f\"🔹 Total labels: {len(train_df)}\\n\")\n\n# ✅ Apply WBF once\ntrain_df_wbf = apply_wbf(train_df)\n\n# ✅ Merge additional image metadata\ntrain_df_wbf = train_df_wbf.merge(\n    train_df[['image_id', 'image_path', 'width', 'height', 'source_dataset']].drop_duplicates(),\n    on='image_id',\n    how='left'\n)\n\n# ✅ Display summary AFTER WBF\nprint(\"📊 After WBF:\")\nprint(f\"✅ Total images: {train_df_wbf['image_id'].nunique()}\")\nprint(f\"✅ Total labels: {len(train_df_wbf)}\")\n\nprint(\"\\n🔍 Sample of processed DataFrame:\")\nprint(train_df_wbf.head(5))\n\nprint(\"\\n📌 Columns in WBF output:\")\nprint(train_df_wbf.columns.tolist())","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport cv2\nimport matplotlib.pyplot as plt\nimport matplotlib.patches as patches\n\n# ✅ Visualization function\n# ✅ Compare visualization before vs after WBF\ndef visualize_before_after(image_id, df_before, df_after, class_names=None):\n    # Get the image path from df_before\n    img_path = df_before[df_before[\"image_id\"] == image_id].iloc[0][\"image_path\"]\n    \n    # Check if the image exists\n    if not os.path.exists(img_path):\n        print(f\"❌ Image not found at {img_path}\")\n        return\n    \n    # Read and process the image\n    img = cv2.imread(img_path)\n    if img is None:\n        print(f\"❌ Failed to load image at {img_path}\")\n        return\n    \n    # Convert the image to RGB format\n    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n    h, w = img.shape[:2]\n\n    # Set up the visualization with two subplots\n    fig, axs = plt.subplots(1, 2, figsize=(18, 8))\n    titles = [\"Before WBF\", \"After WBF\"]\n    dfs = [df_before, df_after]\n\n    # Loop through each subplot (before and after WBF)\n    for i, (ax, title, df) in enumerate(zip(axs, titles, dfs)):\n        bboxes = df[df[\"image_id\"] == image_id]\n\n        ax.imshow(img)\n        ax.set_title(f\"{title}\", fontsize=16)\n\n        # Loop through the bounding boxes and draw them on the image\n        for _, row in bboxes.iterrows():\n            x_mid = row[\"x_mid\"] * w\n            y_mid = row[\"y_mid\"] * h\n            box_w = row[\"w\"] * w\n            box_h = row[\"h\"] * h\n\n            x_min = x_mid - box_w / 2\n            y_min = y_mid - box_h / 2\n\n            # Draw rectangle for bounding box\n            rect = patches.Rectangle(\n                (x_min, y_min),\n                box_w,\n                box_h,\n                linewidth=2,\n                edgecolor='lime',\n                facecolor='none'\n            )\n            ax.add_patch(rect)\n\n            # Get class ID and label\n            class_id = int(row[\"new_class_id\"])\n            label = class_names[class_id] if class_names else str(class_id)\n            ax.text(\n                x_min, y_min - 5, label,\n                color='white',\n                fontsize=12,\n                bbox=dict(facecolor='green', alpha=0.6, edgecolor='none', pad=1)\n            )\n\n        ax.axis('off')\n\n    plt.tight_layout()\n    plt.show()\n\n# ✅ Define the class names based on your class_mapping\nclass_names = [\n    \"Aortic Enlargement\",    # ID 0\n    \"Cardiomegaly\",     # ID 1 \n    \"Lung Collapse\", #ID 2\n    \"Nodule/Mass\",   # ID 3 \n    \"Opacities/Infiltration\", # ID 4 \n    \"Pleural Conditions\"     # ID 5 \n]\n\n# ✅ Pick 5 random image_ids\nsample_ids = random.sample(list(train_df[\"image_id\"].unique()), 5)\n\n# ✅ Visualize each image before and after WBF\nfor img_id in sample_ids:\n    visualize_before_after(img_id, train_df, train_df_wbf, class_names)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Map class IDs to class names\nclass_id_to_name = {\n    0: \"Aortic Enlargement\",    # ID 0\n    1: \"Cardiomegaly\",          # ID 1\n    2: \"Lung Collapse\",         # ID 2\n    3: \"Nodule/Mass\",           # ID 3\n    4: \"Opacities/Infiltration\",# ID 4\n    5: \"Pleural Conditions\"     # ID 5\n}\n\n# ✅ Unique Class Distribution (Images Count) After WBF using class names\nunique_class_distribution = train_df_wbf.groupby('new_class_id')['image_id'].nunique().sort_index()\n\n# Map class IDs to class names\nunique_class_distribution = unique_class_distribution.rename(index=class_id_to_name)\n\n# Plot the distribution\nplt.figure(figsize=(12, 6))\nbars = unique_class_distribution.plot(kind='bar', color='lightgreen')\nplt.title('Unique Class Distribution (Images Count) After WBF', fontsize=16)\nplt.xlabel('Class Name', fontsize=12)\nplt.ylabel('Number of Unique Images', fontsize=12)\nplt.xticks(rotation=45)\n\n# Annotate the count on top of each bar\nfor bar in bars.patches:\n    height = bar.get_height()\n    bars.text(\n        bar.get_x() + bar.get_width() / 2, height + 50,  # Positioning the text above the bar\n        f'{height:.0f}', ha='center', va='bottom', fontsize=10\n    )\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ✅ Total Class Distribution (Bounding Boxes Count) After WBF using class names\ntotal_class_distribution = train_df_wbf['new_class_id'].value_counts().sort_index()\n\n# Map class IDs to class names\ntotal_class_distribution = total_class_distribution.rename(index=class_id_to_name)\n\n# Plot the distribution\nplt.figure(figsize=(12, 6))\nbars = total_class_distribution.plot(kind='bar', color='skyblue')\nplt.title('Total Class Distribution (Bounding Boxes Count) After WBF', fontsize=16)\nplt.xlabel('Class Name', fontsize=12)\nplt.ylabel('Number of Bounding Boxes', fontsize=12)\nplt.xticks(rotation=45)\n\n# Annotate the count on top of each bar\nfor bar in bars.patches:\n    height = bar.get_height()\n    bars.text(\n        bar.get_x() + bar.get_width() / 2, height + 50,  # Positioning the text above the bar\n        f'{height:.0f}', ha='center', va='bottom', fontsize=10\n    )\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 3. ***Data Split ***","metadata":{}},{"cell_type":"code","source":"# ----------------------------------------------\n# 📦 Import necessary libraries\n# ----------------------------------------------\nimport os\nimport cv2\nimport random\nimport numpy as np\nimport pandas as pd\nimport shutil\nimport matplotlib.pyplot as plt\nimport albumentations as A\nfrom albumentations.pytorch import ToTensorV2\nfrom tqdm import tqdm\nfrom glob import glob\nfrom pathlib import Path\nfrom sklearn.model_selection import StratifiedGroupKFold\n\n# ----------------------------------------------\n# 📦 Split original data BEFORE augmentation\n# ----------------------------------------------\n\n# Assuming your original dataframe is `train_df_wbf`\nbalanced_df_multi = train_df_wbf.groupby('image_id')['new_class_id'].agg(lambda x: list(set(x))).reset_index()\ntrain_df_wbf = train_df_wbf.merge(balanced_df_multi, on='image_id', suffixes=(\"\", \"_multi\"))\ntrain_df_wbf = train_df_wbf.loc[:, ~train_df_wbf.columns.duplicated()]\ntrain_df_wbf['multi_class_str'] = train_df_wbf['new_class_id_multi'].apply(lambda x: str(sorted(x)))\n\nsgkf = StratifiedGroupKFold(n_splits=4, shuffle=True, random_state=42)\n\nfor train_idx, val_idx in sgkf.split(train_df_wbf, train_df_wbf['multi_class_str'], groups=train_df_wbf['image_id']):\n    train_df_split = train_df_wbf.iloc[train_idx].reset_index(drop=True)\n    val_df_split = train_df_wbf.iloc[val_idx].reset_index(drop=True)\n    break\n\n# Drop extra columns not needed after split\ntrain_df_split.drop(columns=['new_class_id_multi', 'multi_class_str'], inplace=True)\nval_df_split.drop(columns=['new_class_id_multi', 'multi_class_str'], inplace=True)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Function to check bounding box validity for both formats\ndef check_bboxes_validity(df):\n    valid_bbox_count = 0\n    invalid_bbox_count = 0\n\n    valid_yolo_count = 0\n    invalid_yolo_count = 0\n\n    # Loop through the DataFrame to validate the bounding boxes\n    for _, row in df.iterrows():\n        # Checking for corner format (x_min, y_min, x_max, y_max)\n        x_center, y_center = row['x_mid'], row['y_mid']\n        box_width, box_height = row['w'], row['h']\n        \n        # Convert YOLO format to corner format (x_min, y_min, x_max, y_max)\n        x_min = x_center - box_width / 2\n        y_min = y_center - box_height / 2\n        x_max = x_center + box_width / 2\n        y_max = y_center + box_height / 2\n\n        # Check validity for corner format\n        if x_max > x_min and y_max > y_min:\n            valid_bbox_count += 1\n        else:\n            invalid_bbox_count += 1\n\n        # Check validity for YOLO format (width and height must be positive)\n        if box_width > 0 and box_height > 0:\n            valid_yolo_count += 1\n        else:\n            invalid_yolo_count += 1\n\n    print(f\"Valid bounding boxes (corner format): {valid_bbox_count}\")\n    print(f\"Invalid bounding boxes (corner format): {invalid_bbox_count}\")\n    \n    print(f\"Valid YOLO bounding boxes: {valid_yolo_count}\")\n    print(f\"Invalid YOLO bounding boxes: {invalid_yolo_count}\")\n\n# ----------------------------------------------\n# 📦 Check the bounding boxes before augmentation\n# ----------------------------------------------\nprint(\"Checking bounding box validity...\")\ncheck_bboxes_validity(train_df)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def count_bboxes_formats(df):\n    # Convert YOLO to corner format\n    df = df.copy()\n    df['x_min'] = df['x_mid'] - df['w'] / 2\n    df['y_min'] = df['y_mid'] - df['h'] / 2\n    df['x_max'] = df['x_mid'] + df['w'] / 2\n    df['y_max'] = df['y_mid'] + df['h'] / 2\n\n    # Check YOLO validity: all components must be finite and w, h > 0\n    yolo_invalid = (\n        df[['x_mid', 'y_mid', 'w', 'h']].isna().any(axis=1) |\n        (df['w'] <= 0) | (df['h'] <= 0)\n    )\n\n    # Check Corner validity: x_max > x_min, y_max > y_min\n    corner_invalid = (\n        df[['x_min', 'y_min', 'x_max', 'y_max']].isna().any(axis=1) |\n        (df['x_max'] <= df['x_min']) | (df['y_max'] <= df['y_min'])\n    )\n\n    # Count\n    total = len(df)\n    valid_yolo = (~yolo_invalid).sum()\n    valid_corner = (~corner_invalid).sum()\n\n    print(f\"🔎 Total bounding boxes: {total}\")\n    print(f\"✅ Valid YOLO format: {valid_yolo} ({valid_yolo / total:.2%})\")\n    print(f\"❌ Invalid YOLO format: {total - valid_yolo} ({(total - valid_yolo) / total:.2%})\")\n    print(f\"✅ Valid Corner format: {valid_corner} ({valid_corner / total:.2%})\")\n    print(f\"❌ Invalid Corner format: {total - valid_corner} ({(total - valid_corner) / total:.2%})\")\n\n# ✅ Run the check\ncount_bboxes_formats(train_df)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"#  4. **Data Augmentation + Label Preparation**","metadata":{}},{"cell_type":"code","source":"import os\nimport cv2\nimport shutil\nimport pandas as pd\nfrom tqdm import tqdm\nfrom pathlib import Path\nfrom glob import glob\nimport albumentations as A\n\n# ----------------------------------------------\n# 📦 Function to define augmentations\n# ----------------------------------------------\ndef get_chest_xray_augmentations():\n    return A.Compose([\n        A.RandomBrightnessContrast(brightness_limit=0.1, contrast_limit=0.1, p=0.5),\n        A.RandomGamma(gamma_limit=(95, 105), p=0.5),\n        A.Rotate(limit=5, p=0.5),\n        A.ShiftScaleRotate(shift_limit=0.01, scale_limit=0.05, rotate_limit=3, p=0.5, border_mode=0),\n        A.CLAHE(clip_limit=2.0, tile_grid_size=(8, 8), p=0.3),\n        A.GaussNoise(var_limit=(5.0, 10.0), p=0.2),\n    ], bbox_params=A.BboxParams(format='pascal_voc', label_fields=['labels']))\n\n\n# ----------------------------------------------\n# 📦 Apply augmentation\n# ----------------------------------------------\ndef apply_augmentation(image, bboxes, labels):\n    transform = get_chest_xray_augmentations()\n    augmented = transform(image=image, bboxes=bboxes, labels=labels)\n    return augmented['image'], augmented['bboxes']\n\n# ----------------------------------------------\n# 📦 Identify low-frequency classes\n# ----------------------------------------------\ndef identify_low_freq_classes(df, moderate_threshold=0.165, strong_threshold=0.1):\n    class_counts = df['new_class_id'].value_counts(normalize=True)\n    strong_freq_classes = class_counts[class_counts < strong_threshold].index.tolist()\n    moderate_freq_classes = class_counts[(class_counts >= strong_threshold) & (class_counts < moderate_threshold)].index.tolist()\n\n    print(f\"Strong frequency classes (<{strong_threshold}): {strong_freq_classes}\")\n    print(f\"Moderate frequency classes (<{moderate_threshold}): {moderate_freq_classes}\")\n    return moderate_freq_classes, strong_freq_classes\n\n# ----------------------------------------------\n# 📦 Save one image\n# ----------------------------------------------\ndef save_image(save_path, image):\n    cv2.imwrite(save_path, image, [int(cv2.IMWRITE_JPEG_QUALITY), ])\n\n# ----------------------------------------------\n# 📦 Augment and balance training data (updated)\n# ----------------------------------------------\ndef augment_and_balance_data(train_df, save_augmented_dir='augmented_images', target_image_count=3000):\n    # ✅ Skip pre-augmented dataset\n    train_df = train_df[train_df['source_dataset'] != 'chestxrayabnormalities'].copy()\n    augmented_data = []\n    augmented_image_ids = set()\n\n    os.makedirs(save_augmented_dir, exist_ok=True)\n\n    class_counts = train_df['new_class_id'].value_counts()\n    print(f\"[INFO] Class distribution before augmentation:\")\n    print(class_counts)\n\n    temp_df = train_df.copy()\n\n    # Get the maximum number of images in any class\n    max_class_count = class_counts.max()\n    print(f\"[INFO] Targeting {target_image_count} images per class.\")\n\n    for class_id in tqdm(class_counts.index, desc=\"Augmenting Classes\"):\n        current_count = (temp_df['new_class_id'] == class_id).sum()\n        \n        if current_count >= target_image_count:\n            continue\n\n        # Calculate how many more images are needed for the current class to reach target count\n        augment_needed = target_image_count - current_count\n\n        # Get images of the current class\n        class_group = train_df[train_df['new_class_id'] == class_id]\n        \n        # Sample images (with replacement) until we have enough\n        sampled_group = class_group.sample(n=augment_needed, replace=True, random_state=42)\n\n        for idx, (image_id, group) in enumerate(sampled_group.groupby('image_id')):\n            image_path = group.iloc[0]['image_path']\n            image = cv2.imread(image_path)\n            \n            if image is None:\n                print(f\"[WARN] Failed to load image {image_path}. Skipping.\")\n                continue\n        \n            h_img, w_img = image.shape[:2]\n            bboxes, labels = [], []\n        \n            for _, row in group.iterrows():\n                # Convert from YOLO to Pascal VOC format\n                box_width, box_height = row['w'] * w_img, row['h'] * h_img\n                x_center, y_center = row['x_mid'] * w_img, row['y_mid'] * h_img\n                x_min = x_center - box_width / 2\n                y_min = y_center - box_height / 2\n                x_max = x_center + box_width / 2\n                y_max = y_center + box_height / 2\n        \n                # Ensure bounding box validity\n                if x_min >= x_max or y_min >= y_max or box_width <= 0 or box_height <= 0:\n                    continue\n        \n                bboxes.append((x_min, y_min, x_max, y_max))\n                labels.append(row['new_class_id'])\n        \n            if not bboxes:\n                continue\n        \n            try:\n                augmented_image, augmented_bboxes = apply_augmentation(image.copy(), bboxes, labels)\n            except Exception as e:\n                print(f\"[ERROR] Augmentation failed for {image_id}: {e}\")\n                continue\n        \n            h_aug, w_aug = augmented_image.shape[:2]\n            augmented_image_id = f\"{image_id}_aug_{len(augmented_image_ids)}\"\n        \n            if augmented_image_id not in augmented_image_ids:\n                augmented_image_ids.add(augmented_image_id)\n                save_path = os.path.join(save_augmented_dir, f\"{augmented_image_id}.jpg\")\n                save_image(save_path, augmented_image)\n        \n                for (x_min, y_min, x_max, y_max), class_id_aug in zip(augmented_bboxes, labels):\n                    x_min = max(0, min(x_min, w_aug))\n                    x_max = max(0, min(x_max, w_aug))\n                    y_min = max(0, min(y_min, h_aug))\n                    y_max = max(0, min(y_max, h_aug))\n        \n                    if x_max <= x_min or y_max <= y_min:\n                        continue\n        \n                    x_center = ((x_min + x_max) / 2) / w_aug\n                    y_center = ((y_min + y_max) / 2) / h_aug\n                    width = (x_max - x_min) / w_aug\n                    height = (y_max - y_min) / h_aug\n        \n                    augmented_data.append({\n                        'image_id': augmented_image_id,\n                        'image_path': save_path,\n                        'new_class_id': class_id_aug,\n                        'x_mid': x_center,\n                        'y_mid': y_center,\n                        'w': width,\n                        'h': height\n                    })\n\n\n    print(\"[✅] Augmented images saved!\")\n\n    augmented_df = pd.DataFrame(augmented_data)\n    balanced_df = pd.concat([train_df, augmented_df], ignore_index=True)\n    balanced_df = balanced_df.sample(frac=1, random_state=42).reset_index(drop=True)\n\n    print(f\"[✅] Balancing complete. Class distribution:\")\n    print(balanced_df['new_class_id'].value_counts())\n\n    return balanced_df\n\n            for _, row in group.iterrows():\n                # Get YOLO format: x_mid, y_mid, w, h (normalized)\n                x_center, y_center = row['x_mid'] * w_img, row['y_mid'] * h_img  # Use x_mid, y_mid\n                box_width, box_height = row['w'] * w_img, row['h'] * h_img\n\n                # Skip invalid bounding boxes where width or height is zero\n                if box_width <= 0 or box_height <= 0:\n                    continue\n\n                # YOLO format: (x_center, y_center, w, h) in normalized values\n                bboxes.append((x_center / w_img, y_center / h_img, box_width / w_img, box_height / h_img))\n                labels.append(row['new_class_id'])\n\n# ----------------------------------------------\n# 📦 Prepare YOLO labels\n# ----------------------------------------------\ndef prepare_yolo_labels(df, image_dest_dir, label_dest_dir):\n    df = df.drop_duplicates(subset=['image_id', 'new_class_id', 'x_mid', 'y_mid', 'w', 'h'])\n    os.makedirs(image_dest_dir, exist_ok=True)\n    os.makedirs(label_dest_dir, exist_ok=True)\n\n    for image_id, group in tqdm(df.groupby('image_id'), desc=f\"Processing {image_dest_dir}\"):\n        image_path = group.iloc[0]['image_path']\n        image_name = os.path.basename(image_path)\n        label_file = Path(label_dest_dir) / f\"{Path(image_name).stem}.txt\"\n        image_target = Path(image_dest_dir) / image_name\n\n        if not image_target.exists():\n            shutil.copy(image_path, image_target)\n\n        group_sorted = group.sort_values(by='new_class_id')\n\n        with open(label_file, 'w') as f:\n            for _, row in group_sorted.iterrows():\n                f.write(f\"{row['new_class_id']} {row['x_mid']:.6f} {row['y_mid']:.6f} {row['w']:.6f} {row['h']:.6f}\\n\")\n\n# ----------------------------------------------\n# 📦 Deduplicate YOLO labels\n# ----------------------------------------------\ndef deduplicate_yolo_labels(label_dir):\n    label_paths = glob(os.path.join(label_dir, \"*.txt\"))\n    total_files = len(label_paths)\n    deduplicated_count = 0\n\n    for path in label_paths:\n        with open(path, 'r') as f:\n            lines = f.readlines()\n        original_count = len(lines)\n        deduped = list(set([line.strip() for line in lines]))\n\n        if len(deduped) < original_count:\n            deduplicated_count += 1\n            with open(path, 'w') as f:\n                f.write('\\n'.join(deduped) + '\\n')\n\n    print(f\"✅ Deduplicated {deduplicated_count}/{total_files} files in: {label_dir}\")\n\n# ----------------------------------------------\n# 📦 Now Full Process\n# ----------------------------------------------\n# Assuming train_df_split and val_df_split are defined\n\n# 2. 📈 Augment training set only\nbalanced_train_df = augment_and_balance_data(train_df_split)\n\n# 3. 📄 Prepare YOLO labels\nprepare_yolo_labels(balanced_train_df, 'data/images/train', 'data/labels/train')\nprepare_yolo_labels(val_df_split, 'data/images/val', 'data/labels/val')\n\n# 4. 🧹 Deduplicate labels\ndeduplicate_yolo_labels('data/labels/train')\ndeduplicate_yolo_labels('data/labels/val')\n\n# 5. 🧹 Clean up augmented images to save disk space\nshutil.rmtree('augmented_images')\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class_id_to_name = {\n    0: \"Aortic Enlargement\",\n    1: \"Cardiomegaly\",\n    2: \"Lung Collapse\",\n    3: \"Nodule/Mass\",\n    4: \"Opacities/Infiltration\",\n    5: \"Pleural Conditions\"\n}\n\n# Bounding box count per class\nbbox_counts = balanced_train_df['new_class_id'].value_counts().sort_index()\n\n# Image count per class\nimage_counts = balanced_train_df.groupby('new_class_id')['image_id'].nunique().sort_index()\n\n# Combine both into a DataFrame\nsummary_df = pd.DataFrame({\n    'class_id': bbox_counts.index,\n    'class_name': [class_id_to_name[i] for i in bbox_counts.index],\n    'bbox_count': bbox_counts.values,\n    'unique_image_count': image_counts.values\n})\n\nprint(summary_df)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport random\nfrom PIL import Image\nfrom pathlib import Path\n\n# Define the path to your augmented image directory\naugmented_image_dir = Path('data/images/train')\n\n# Get list of all .png image files\naugmented_image_files = sorted([f for f in augmented_image_dir.glob('*') if f.suffix.lower() in ['.png', '.jpg', '.jpeg']])\n\n# Limit to available number of files\nnum_samples = min(5, len(augmented_image_files))\nif num_samples == 0:\n    print(\"No images found.\")\nelse:\n    # Optional: for reproducibility\n    random.seed(42)\n    sample_images = random.sample(augmented_image_files, num_samples)\n\n    # Plot sampled images\n    fig, axes = plt.subplots(1, num_samples, figsize=(3 * num_samples, 6))\n\n    if num_samples == 1:\n        axes = [axes]\n\n    for ax, img_path in zip(axes, sample_images):\n        img = Image.open(img_path).convert(\"RGB\")\n        ax.imshow(img)\n        ax.axis('off')\n        ax.set_title(img_path.name)\n\n    plt.tight_layout()\n    plt.show()\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import cv2\nimport os\n\ndef check_channels(image_dir):\n    for f in os.listdir(image_dir):\n        if f.lower().endswith(('.jpg', '.png', '.jpeg')):\n            img = cv2.imread(os.path.join(image_dir, f))\n            if img is not None and img.shape[2] != 3:\n                print(f\"{f} is not RGB\")\n\ncheck_channels('/kaggle/working/data/images/train')\ncheck_channels('/kaggle/working/data/images/val')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 5. ***data.yaml file & YOLO12 Training***","metadata":{}},{"cell_type":"code","source":"import cv2\nimport os\n\ndef convert_grayscale_to_rgb_in_place(image_dir):\n    \"\"\"\n    Convert grayscale or single-channel images to 3-channel RGB for YOLO compatibility.\n    Overwrites the images in place.\n    \"\"\"\n    image_files = [f for f in os.listdir(image_dir) if f.lower().endswith(('.png', '.jpg', '.jpeg'))]\n    total = len(image_files)\n    converted = 0\n\n    print(f\"Processing {total} images in: {image_dir}\")\n\n    for idx, image_file in enumerate(image_files, 1):\n        image_path = os.path.join(image_dir, image_file)\n        img = cv2.imread(image_path)\n\n        if img is None:\n            print(f\"⚠️ Failed to read: {image_file}\")\n            continue\n\n        # Skip if image is already RGB (3 channels)\n        if len(img.shape) == 3 and img.shape[2] == 3:\n            continue\n\n        # Convert grayscale to RGB\n        img_rgb = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)\n        cv2.imwrite(image_path, img_rgb)\n        converted += 1\n\n        if idx % 100 == 0 or idx == total:\n            print(f\"[{idx}/{total}] processed, {converted} converted\", flush=True)\n\n    print(f\"✅ Done. {converted} images converted in: {image_dir}\\n\")\n\n\n# Directories\ntrain_dir = '/kaggle/working/data/images/train'\nval_dir = '/kaggle/working/data/images/val'\n\n# Convert grayscale images to 3-channel RGB\nconvert_grayscale_to_rgb_in_place(train_dir)\nconvert_grayscale_to_rgb_in_place(val_dir)\n\n# Class names for YOLO\nclass_names = [\n    'Aortic Enlargement',\n    'Cardiomegaly',\n    'Lung Collapse',\n    'Nodule/Mass',\n    'Opacities/Infiltration',\n    'Pleural Conditions'\n]\n\n# Correctly format the names\nnames_yaml = '\\n'.join([f\"  - {name}\" for name in class_names])\n\n# Create YOLO data.yaml dynamically\ndata_yaml = f\"\"\"train: {train_dir}\nval: {val_dir}\n\nnc: {len(class_names)}\nnames:\n{names_yaml}\n\"\"\"\n\n# Save data.yaml\nyaml_path = 'data.yaml'\ntry:\n    with open(yaml_path, 'w') as f:\n        f.write(data_yaml)\n    print(f\"✅ data.yaml file created at {yaml_path}\")\nexcept Exception as e:\n    print(f\"❌ Failed to create data.yaml: {e}\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport random\nimport cv2\nimport matplotlib.pyplot as plt\n\ndef visualize_augmentations_with_bboxes(df, strong_freq_classes, moderate_freq_classes, num_samples=5):\n    df = df[df['image_path'].apply(lambda x: os.path.isfile(x))]\n\n    if len(df) == 0:\n        print(\"❌ No valid images found in the provided DataFrame.\")\n        return\n\n    sampled_image_ids = df['image_id'].drop_duplicates().sample(n=min(num_samples, df['image_id'].nunique()))\n\n    for image_id in sampled_image_ids:\n        group = df[df['image_id'] == image_id]\n        image_path = group.iloc[0]['image_path']\n        image = cv2.imread(image_path)\n        if image is None:\n            print(f\"❌ Failed to load image: {image_path}\")\n            continue\n\n        img_height, img_width = image.shape[:2]\n        bboxes = []\n        labels = []\n\n        image_with_boxes = image.copy()\n\n        for _, row in group.iterrows():\n            x_mid = row['x_mid'] * img_width\n            y_mid = row['y_mid'] * img_height\n            w = row['w'] * img_width\n            h = row['h'] * img_height\n\n            x_min = int(x_mid - w / 2)\n            y_min = int(y_mid - h / 2)\n            x_max = int(x_mid + w / 2)\n            y_max = int(y_mid + h / 2)\n\n            bboxes.append((x_min, y_min, x_max, y_max))\n            labels.append(row['new_class_id'])\n            cv2.rectangle(image_with_boxes, (x_min, y_min), (x_max, y_max), (255, 0, 0), 2)\n\n        if not bboxes:\n            continue\n\n        augmented_image, augmented_bboxes = apply_augmentation(\n            image.copy(), labels[0], bboxes, labels, strong_freq_classes, moderate_freq_classes\n        )\n\n        augmented_with_boxes = augmented_image.copy()\n        for bbox in augmented_bboxes:\n            x_min_aug, y_min_aug, x_max_aug, y_max_aug = map(int, bbox)\n            cv2.rectangle(augmented_with_boxes, (x_min_aug, y_min_aug), (x_max_aug, y_max_aug), (0, 255, 0), 2)\n\n        image_rgb = cv2.cvtColor(image_with_boxes, cv2.COLOR_BGR2RGB)\n        augmented_rgb = cv2.cvtColor(augmented_with_boxes, cv2.COLOR_BGR2RGB)\n\n        plt.figure(figsize=(12, 6))\n        plt.suptitle(f\"Image ID: {image_id}\", fontsize=16)\n        plt.subplot(1, 2, 1)\n        plt.imshow(image_rgb)\n        plt.title(\"Original + BBoxes\")\n        plt.axis('off')\n\n        plt.subplot(1, 2, 2)\n        plt.imshow(augmented_rgb)\n        plt.title(\"Augmented + BBoxes\")\n        plt.axis('off')\n\n        plt.show()\n\n# Only use TRAIN images that were augmented\nmoderate_freq_classes, strong_freq_classes = identify_low_freq_classes(balanced_train_df)\n\n# Visualize\nvisualize_augmentations_with_bboxes(balanced_train_df, strong_freq_classes, moderate_freq_classes, num_samples=5)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\n\nproblem_images = [\n    'augmented_images/39a043040baac31c12db628415939f3e_aug_0_591.jpg',\n    'augmented_images/00029259_027_aug_0_383.jpg'\n]\n\nfor path in problem_images:\n    if not os.path.exists(path):\n        print(f\"❌ File does not exist: {path}\")\n    else:\n        try:\n            img = cv2.imread(path)\n            if img is None:\n                print(f\"❌ File exists but could not be read: {path}\")\n            else:\n                print(f\"✅ File exists and is readable: {path}\")\n        except Exception as e:\n            print(f\"❗ Error reading {path}: {e}\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ✅ Check available GPUs\nnum_gpus = torch.cuda.device_count()\nprint(f\"Available GPUs: {num_gpus}\")\nfor i in range(num_gpus):\n    print(f\"GPU {i}: {torch.cuda.get_device_name(i)}\")\n\n# ✅ CUDA memory optimization\ntorch.cuda.empty_cache()\nos.environ[\"PYTORCH_CUDA_ALLOC_CONF\"] = \"expandable_segments:True\"\n\n# ✅ Load YOLOv12-M model (ensure yolo12m.pt is available)\nmodel = YOLO(\"yolo12m.pt\")  # Adjust the model path if necessary\n\n# ✅ Train the model with the grayscale images\ntrain_results = model.train(\n    data=\"/kaggle/working/data.yaml\",\n    epochs=170,\n    batch=16,        \n    imgsz=512,\n    device=\"auto\",\n    half=True,       # P100 is good with fp16\n    workers=4,       \n    project=\"yolov12-training\",\n    name=\"yolo12m-vinbigdata\",\n    cache=False,     \n    exist_ok=True,\n    save=True,\n    save_period=10,\n    patience=20,\n    amp=True,        # mixed precision = faster training\n)\n# ✅ Print the final results\nprint(\"✅ Training complete!\")\nprint(\"The training results have been saved in the 'yolov12-training' folder.\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ✅ Check training results\nprint(\"✅ Training results:\")\nprint(train_results)\n\n# ✅ Validate the model\nmetrics = model.val()\n\n# ✅ Print evaluation metrics\nprint(\"Evaluation metrics:\")\nprint(metrics)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!zip -r yolov12-training.zip /kaggle/working/yolov12-training/","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Provide a clickable download link\nFileLink(r'yolov12-training.zip')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ***6. Mode & 90th percentile***","metadata":{}},{"cell_type":"code","source":"!pip install ultralytics\nfrom ultralytics import YOLO","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_path = \"/kaggle/input/mymodel/pytorch/yolo12/1/best.pt\"\nmodel = YOLO(model_path)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport numpy as np\nimport glob\nfrom collections import defaultdict, Counter\n\n# Move model to GPU\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\nmodel.to(device)\n\n# Get all image file paths\nimage_dir = \"/kaggle/input/vinbigdata-1024-image-dataset/vinbigdata/test/\"\nimage_paths = sorted(glob.glob(image_dir + \"*.png\"))  # Adjust extension if needed\n\nbatch_size = 16  # Adjust based on GPU memory\nall_results = []\n\n# Run inference in batches\nfor i in range(0, len(image_paths), batch_size):\n    batch = image_paths[i : i + batch_size]  # Get batch of image paths\n    batch_results = model(batch, conf=0.1)  # Run inference\n    all_results.extend(batch_results)\n\n# Collect confidence scores by class\nconf_scores = defaultdict(list)\n\nfor result in all_results:\n    if result.boxes is not None:  # Ensure detections exist\n        for det in result.boxes.to(device):  # Keep tensors on GPU\n            cls = int(det.cls.item())  # Get class ID\n            conf = float(det.conf.item())  # Get confidence score\n            class_name = model.names[cls] if hasattr(model, \"names\") else str(cls)\n            conf_scores[class_name].append(conf)\n\n# Calculate the mode (most common confidence score) and 90th percentile for each class\nclass_conf_stats = {}\n\nfor cls, scores in conf_scores.items():\n    # Calculate the mode\n    mode_conf = Counter(scores).most_common(1)[0][0]\n    \n    # Calculate the 90th percentile\n    percentile_90 = np.percentile(scores, 90)\n    \n    class_conf_stats[cls] = {\n        \"mode\": mode_conf,\n        \"90th_percentile\": percentile_90\n    }\n\nprint(class_conf_stats)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# modes & 90th percentile for each class\nclass_conf_data = {\n    'Cardiac & Vascular': {'mode': 0.131, '90th_percentile': 0.705},\n    'Pleural Abnormalities': {'mode': 0.115, '90th_percentile': 0.389},\n    'Lung Collapse': {'mode': 0.111, '90th_percentile': 0.507},\n    'Fibrosis & ILD': {'mode': 0.337, '90th_percentile': 0.635},\n    'Nodule/Mass or Other Lesion': {'mode': 0.208, '90th_percentile': 0.524},\n    'Lung Opacity': {'mode': 0.195, '90th_percentile': 0.515}\n}\n\nadjusted_thresholds = {}\n\nfor cls, values in class_conf_data.items():\n    mode = values['mode']\n    perc90 = values['90th_percentile']\n\n    if mode < 0.2:\n        # Use the 75th percentile if mode is too low\n        new_threshold = np.percentile([mode, perc90], 75)\n    elif mode >= 0.3:\n        # Use the mode directly if reasonable\n        new_threshold = mode\n    else:\n        # Use a weighted average if 90th percentile is much higher\n        new_threshold = (0.7 * mode) + (0.3 * perc90)\n\n    adjusted_thresholds[cls] = round(new_threshold, 3)\n\nprint(adjusted_thresholds)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nfrom pathlib import Path\nimport torch\nfrom PIL import Image\nimport numpy as np\nimport cv2\nimport matplotlib.pyplot as plt\nfrom ultralytics import YOLO  \n\n# ✅ Force inline display in Kaggle\n%matplotlib inline  \n\n# Load YOLO model\nmodel_path = \"/kaggle/input/mymodel/pytorch/yolo12/1/best.pt\"\nmodel = YOLO(model_path)\n\n# Confidence thresholds\nadjusted_thresholds = {\n    'Cardiac & Vascular': 0.562,\n    'Pleural Abnormalities': 0.32,\n    'Lung Collapse': 0.408,\n    'Fibrosis & ILD': 0.337,\n    'Nodule/Mass or Other Lesion': 0.303,\n    'Lung Opacity': 0.435\n}\n\n# Unique colors per class\nclass_colors = {\n    'Cardiac & Vascular': (255, 0, 0),\n    'Pleural Abnormalities': (0, 255, 0),\n    'Lung Collapse': (0, 0, 255),\n    'Fibrosis & ILD': (255, 255, 0),\n    'Nodule/Mass or Other Lesion': (255, 165, 0),\n    'Lung Opacity': (128, 0, 128)\n}\n\n# Dataset path\ndataset_path = Path(\"/kaggle/input/testing/\")\n\n# Function to preprocess image\ndef preprocess_image(image_path):\n    img = Image.open(image_path).convert(\"RGB\")\n    return img\n\n# Process images\nfor image_path in dataset_path.glob(\"*.*\"):\n    if image_path.suffix.lower() in [\".png\", \".jpg\", \".jpeg\"]:\n        processed_img = preprocess_image(image_path)\n        img_array = np.array(processed_img)  \n        img_height, img_width = img_array.shape[:2]  \n\n        # Run inference\n        results = model(processed_img)[0]  \n\n        # Extract boxes, confidences, and classes\n        boxes = results.boxes.xyxy.cpu().numpy()\n        confidences = results.boxes.conf.cpu().numpy()\n        classes = results.boxes.cls.cpu().numpy().astype(int)\n\n        filtered_boxes, filtered_classes, filtered_confidences = [], [], []\n\n        for i in range(len(classes)):\n            class_idx = classes[i]\n            class_name = model.names[class_idx]\n            conf = confidences[i]\n\n            class_threshold = adjusted_thresholds.get(class_name, 0.1)\n            if conf >= class_threshold:\n                filtered_boxes.append(boxes[i])\n                filtered_classes.append(class_name)\n                filtered_confidences.append(conf)\n\n        # If valid detections exist\n        if filtered_boxes:\n            image = np.array(processed_img)  \n\n            for i in range(len(filtered_boxes)):\n                x1, y1, x2, y2 = map(int, filtered_boxes[i])\n\n                # Assign unique color\n                color = class_colors.get(filtered_classes[i], (255, 255, 255))  \n\n                # Dynamic font scaling\n                font_scale = max(0.5, min(img_width, img_height) / 600)  # Adjusted for image size\n                thickness = max(2, int(font_scale * 2))  # Bold text by increasing thickness\n\n                # Draw bounding box\n                cv2.rectangle(image, (x1, y1), (x2, y2), color, thickness)  \n\n                # Text label (No background)\n                label = f\"{filtered_classes[i]} ({filtered_confidences[i]:.2f})\"\n                \n                # Draw text\n                cv2.putText(image, label, (x1, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, font_scale, color, thickness)\n\n            # ✅ Convert BGR to RGB for proper display\n            image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n\n            # ✅ Ensure images appear properly\n            plt.figure(figsize=(8, 8))\n            plt.imshow(image_rgb)  # Show the image in RGB format\n            plt.axis(\"off\")\n            plt.title(f\"Detections for {image_path.name}\")\n            plt.show()\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}