{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":52254,"databundleVersionId":6863140,"sourceType":"competition"},{"sourceId":6125,"sourceType":"modelInstanceVersion","modelInstanceId":4596},{"sourceId":6128,"sourceType":"modelInstanceVersion","modelInstanceId":4596}],"dockerImageVersionId":30646,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-02-12T18:44:43.139321Z","iopub.execute_input":"2024-02-12T18:44:43.139745Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"![download.png](attachment:a98c2ef5-16c8-49a8-85b1-274cd126e146.png)","metadata":{},"attachments":{"a98c2ef5-16c8-49a8-85b1-274cd126e146.png":{"image/png":"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"}}},{"cell_type":"code","source":"pip install plotly","metadata":{"execution":{"iopub.status.busy":"2024-02-12T19:08:37.722882Z","iopub.execute_input":"2024-02-12T19:08:37.724026Z","iopub.status.idle":"2024-02-12T19:08:55.01914Z","shell.execute_reply.started":"2024-02-12T19:08:37.723977Z","shell.execute_reply":"2024-02-12T19:08:55.017373Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pip install pydicom matplotlib","metadata":{"execution":{"iopub.status.busy":"2024-02-12T19:27:04.080679Z","iopub.execute_input":"2024-02-12T19:27:04.081084Z","iopub.status.idle":"2024-02-12T19:27:17.802756Z","shell.execute_reply.started":"2024-02-12T19:27:04.081053Z","shell.execute_reply":"2024-02-12T19:27:17.801303Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport pydicom\nimport seaborn as sns\nimport plotly.express as px\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.applications import VGG16\nfrom tensorflow.keras.layers import GlobalAveragePooling2D, Dense, Dropout\nfrom sklearn.model_selection import train_test_split\nfrom keras.preprocessing.image import ImageDataGenerator\nimport cv2\n\n# To ignore all warnings\nimport warnings\nwarnings.filterwarnings(\"ignore\")","metadata":{"execution":{"iopub.status.busy":"2024-02-26T12:51:58.96497Z","iopub.execute_input":"2024-02-26T12:51:58.96547Z","iopub.status.idle":"2024-02-26T12:52:19.998015Z","shell.execute_reply.started":"2024-02-26T12:51:58.965432Z","shell.execute_reply":"2024-02-26T12:52:19.996066Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load the train.csv file\ntrain_data = pd.read_csv('/kaggle/input/rsna-2023-abdominal-trauma-detection/train.csv')\ntrain_data\n","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:29:47.717226Z","iopub.execute_input":"2024-02-25T11:29:47.718101Z","iopub.status.idle":"2024-02-25T11:29:47.770735Z","shell.execute_reply.started":"2024-02-25T11:29:47.718056Z","shell.execute_reply":"2024-02-25T11:29:47.769391Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_series_meta = pd.read_csv('/kaggle/input/rsna-2023-abdominal-trauma-detection/train_series_meta.csv')\ntrain_series_meta\n","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:29:52.77914Z","iopub.execute_input":"2024-02-25T11:29:52.779796Z","iopub.status.idle":"2024-02-25T11:29:52.801305Z","shell.execute_reply.started":"2024-02-25T11:29:52.779758Z","shell.execute_reply":"2024-02-25T11:29:52.799824Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Check the column names in the DataFrame\nprint(train_data.columns)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:29:56.451776Z","iopub.execute_input":"2024-02-25T11:29:56.452233Z","iopub.status.idle":"2024-02-25T11:29:56.459062Z","shell.execute_reply.started":"2024-02-25T11:29:56.452196Z","shell.execute_reply":"2024-02-25T11:29:56.457822Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Display basic information about the dataset\nprint(train_data.info())","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:29:59.752515Z","iopub.execute_input":"2024-02-25T11:29:59.754156Z","iopub.status.idle":"2024-02-25T11:29:59.772543Z","shell.execute_reply.started":"2024-02-25T11:29:59.754086Z","shell.execute_reply":"2024-02-25T11:29:59.770779Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Display the first few rows of the dataset\nprint(train_data.head())","metadata":{"execution":{"iopub.status.busy":"2024-02-17T18:26:22.710186Z","iopub.execute_input":"2024-02-17T18:26:22.710782Z","iopub.status.idle":"2024-02-17T18:26:22.720855Z","shell.execute_reply.started":"2024-02-17T18:26:22.710744Z","shell.execute_reply":"2024-02-17T18:26:22.71917Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Summary statistics of numerical columns\nprint(train_data.describe())","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:30:13.414921Z","iopub.execute_input":"2024-02-25T11:30:13.415382Z","iopub.status.idle":"2024-02-25T11:30:13.46711Z","shell.execute_reply.started":"2024-02-25T11:30:13.415349Z","shell.execute_reply":"2024-02-25T11:30:13.465787Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Count of unique values in each column\nprint(train_data.nunique())","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:30:15.977746Z","iopub.execute_input":"2024-02-25T11:30:15.978215Z","iopub.status.idle":"2024-02-25T11:30:15.990229Z","shell.execute_reply.started":"2024-02-25T11:30:15.978178Z","shell.execute_reply":"2024-02-25T11:30:15.98889Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(train_data.isna().sum())","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:30:18.429965Z","iopub.execute_input":"2024-02-25T11:30:18.431303Z","iopub.status.idle":"2024-02-25T11:30:18.440359Z","shell.execute_reply.started":"2024-02-25T11:30:18.431248Z","shell.execute_reply":"2024-02-25T11:30:18.438877Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**There is no missing values**","metadata":{}},{"cell_type":"code","source":"train_data.corr()","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:30:20.828267Z","iopub.execute_input":"2024-02-25T11:30:20.82872Z","iopub.status.idle":"2024-02-25T11:30:20.868045Z","shell.execute_reply.started":"2024-02-25T11:30:20.828687Z","shell.execute_reply":"2024-02-25T11:30:20.866373Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Corrected code for exploring aortic_hu distribution\nplt.figure(figsize=(8, 6))\nsns.histplot(data=train_data, x='any_injury', bins=20)  # Replace with the actual column name\nplt.title('Distribution of Aortic Hounsfield Units')\nplt.xlabel('Aortic Hounsfield Units')\nplt.ylabel('Count')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:30:46.926282Z","iopub.execute_input":"2024-02-25T11:30:46.926712Z","iopub.status.idle":"2024-02-25T11:30:47.248323Z","shell.execute_reply.started":"2024-02-25T11:30:46.926678Z","shell.execute_reply":"2024-02-25T11:30:47.246892Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Distribution of target labels\n# Assuming 'any_injury' is a binary variable (0 or 1)\nfig = px.pie(train_data, names='any_injury', hole=0.4, \n             title='Distribution of Any Injury', \n             labels={'any_injury': 'Any Injury'}, \n             color_discrete_sequence=['#1f77b4', '#ff7f0e'])\n\nfig.update_traces(textinfo='percent+label')\nfig.show()\n","metadata":{"execution":{"iopub.status.busy":"2024-04-08T20:11:23.280824Z","iopub.execute_input":"2024-04-08T20:11:23.281195Z","iopub.status.idle":"2024-04-08T20:11:23.777098Z","shell.execute_reply.started":"2024-04-08T20:11:23.281162Z","shell.execute_reply":"2024-04-08T20:11:23.775547Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"injury_columns = ['bowel_healthy', 'bowel_injury', 'extravasation_healthy', 'extravasation_injury',\n                  'kidney_healthy', 'kidney_low', 'kidney_high',\n                  'liver_healthy', 'liver_low', 'liver_high',\n                  'spleen_healthy', 'spleen_low', 'spleen_high']\n\n# Define custom colors (e.g., green and purple)\ncustom_colors = [\"#2ecc71\", \"#9b59b6\"]  # Green and Purple\n\nplt.figure(figsize=(12, 18))\nfor i, column in enumerate(injury_columns):\n    plt.subplot(5, 3, i + 1)\n    sns.countplot(data=train_data, x=column, palette=custom_colors)\n    plt.title(f'Distribution of {column}')\n    plt.xlabel(column)\n    plt.ylabel('Count')\n\nplt.tight_layout()\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:30:57.812882Z","iopub.execute_input":"2024-02-25T11:30:57.814101Z","iopub.status.idle":"2024-02-25T11:31:00.451497Z","shell.execute_reply.started":"2024-02-25T11:30:57.81405Z","shell.execute_reply":"2024-02-25T11:31:00.450002Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef visualize_dicom(dicom_files):\n    # Create subplots based on the number of DICOM files\n    num_files = len(dicom_files)\n    fig, axs = plt.subplots(1, num_files, figsize=(5 * num_files, 5))\n\n    for i, dicom_file in enumerate(dicom_files):\n        # Load a DICOM file\n        dicom_data = pydicom.dcmread(dicom_file)\n\n        # Display the CT scan image in a subplot\n        axs[i].imshow(dicom_data.pixel_array, cmap=plt.cm.bone)\n        axs[i].set_title(f'CT Scan {i+1}')\n        axs[i].axis('off')\n\n    plt.show()\n\n# Specify the paths to your DICOM files\ndicom_files = [\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/31614/72.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/55.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/7.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/36.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/31614/115.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/31614/98.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/31614/61.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/144.dcm\"\n]\n\n# Call the function to visualize the DICOM files\nvisualize_dicom(dicom_files)\n\ndicom_files2 = [\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/138.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/95.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/11.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/9.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/18.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/141.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/120.dcm\",\n    \"/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/26501/22032/12.dcm\"\n]\n# Call the function to visualize the DICOM files\nvisualize_dicom(dicom_files2)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T11:31:07.914975Z","iopub.execute_input":"2024-02-25T11:31:07.915412Z","iopub.status.idle":"2024-02-25T11:31:10.89083Z","shell.execute_reply.started":"2024-02-25T11:31:07.915381Z","shell.execute_reply":"2024-02-25T11:31:10.889366Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **2.Data Preprocessing**","metadata":{}},{"cell_type":"markdown","source":"# **3.Model Building**","metadata":{}},{"cell_type":"code","source":"train_path = '/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/10004/21057/*.dcm'\ntest_path = '/kaggle/input/rsna-2023-abdominal-trauma-detection/test_images/48843/62825/*.dcm'\n# Import necessary libraries\nimport glob                   # For file path matching\nimport numpy as np            # For numerical operations\nimport pandas as pd           # For data manipulation\nimport matplotlib.pyplot as plt  # For data visualization\nimport os                     # For interacting with the operating system\nimport pydicom as dicom       # For working with DICOM files (medical imaging)\nimport random                 # For random number generation\nrandom.seed(42)              # Set a random seed for reproducibility\n\nimport torch                  # For PyTorch-based deep learning\nimport torch.nn as nn         # For defining neural network modules\nimport torch.optim as optim   # For defining optimization algorithms\n\nimport tensorflow as tf       # For TensorFlow-based deep learning\nfrom tensorflow.keras import layers, models  # For defining Keras models and layers\nnum_train_examples = len(train_path)\nprint(num_train_examples)\npixel_arries = []\npixel_number = []\n\nfor _ in range(min(6, num_train_examples)):\n    randomly_selected_image = random.choice(os.listdir('/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/10004/21057'))\n    pixel_arries.append(dicom.dcmread('/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/10004/21057/' + randomly_selected_image).pixel_array)\n    pixel_number.append(randomly_selected_image)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T19:20:09.360127Z","iopub.execute_input":"2024-02-25T19:20:09.360549Z","iopub.status.idle":"2024-02-25T19:20:09.438773Z","shell.execute_reply.started":"2024-02-25T19:20:09.360514Z","shell.execute_reply":"2024-02-25T19:20:09.43745Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# randomly show some figures for checking\nplt.figure(figsize=(10, 8))\nfor x in range(min(6, num_train_examples)):\n    plt.subplot(2, 3, x + 1)\n    plt.imshow(pixel_arries[x], cmap='bone')\n    plt.title(pixel_number[x])\nplt.show()\ndf_train = pd.read_csv('/kaggle/input/rsna-2023-abdominal-trauma-detection/train.csv')\ndf_train.head().style.set_properties(**{'background-color': 'black',\n                                                'color': 'lawngreen',\n                                                'border': '1.5px  white'})","metadata":{"execution":{"iopub.status.busy":"2024-02-25T19:20:13.209992Z","iopub.execute_input":"2024-02-25T19:20:13.211529Z","iopub.status.idle":"2024-02-25T19:20:14.562101Z","shell.execute_reply.started":"2024-02-25T19:20:13.211465Z","shell.execute_reply":"2024-02-25T19:20:14.560655Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Convert patient_id column from DataFrame to a numpy array and cast it to string data type\nid = df_train.patient_id.to_numpy().astype(str)\n\n# Initialize empty lists for storing image data (X) and corresponding labels (y)\nX, y = [], []\n\n# Loop over the first 3 patient IDs\nfor x, p_id in enumerate(id[:3]):\n    # Define the directory path for the current patient's images\n    dir = '/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/' + p_id + '/'\n    \n    # Extract the features (labels) for the current patient using their index\n    features = df_train.iloc[x].to_numpy()[1:]\n    \n    # Loop through each file in the patient's directory\n    for file in glob.glob(dir + '*'):\n        # Loop through each image file in the current directory\n        for image_path in glob.glob(file + '/*'):\n            # Read the DICOM image and extract the pixel array\n            X.append(dicom.dcmread(image_path).pixel_array)\n            \n            # Append the features (labels) for this image to the y list\n            y.append(features)","metadata":{"execution":{"iopub.status.busy":"2024-02-25T19:20:21.324942Z","iopub.execute_input":"2024-02-25T19:20:21.325757Z","iopub.status.idle":"2024-02-25T19:21:08.098804Z","shell.execute_reply.started":"2024-02-25T19:20:21.325716Z","shell.execute_reply":"2024-02-25T19:21:08.097577Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(X), len(y)\nX = np.array(X)\ny = np.array(y)\n\nX.shape, y.shape\nplt.figure(figsize=(10, 8))\nplt.imshow(X[1], cmap='bone')\nplt.show()\n","metadata":{"execution":{"iopub.status.busy":"2024-02-25T21:53:45.269232Z","iopub.execute_input":"2024-02-25T21:53:45.269788Z","iopub.status.idle":"2024-02-25T21:53:47.995507Z","shell.execute_reply.started":"2024-02-25T21:53:45.269741Z","shell.execute_reply":"2024-02-25T21:53:47.994053Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define the input layer\ninputs = tf.keras.Input(shape=(X.shape[1], X.shape[2], 1))\n\n# First set of convolutional layers\nx = tf.keras.layers.Conv2D(2, (3, 3), activation='relu')(inputs)\nx = tf.keras.layers.Conv2D(2, (3, 3), activation='relu')(x)\nx = tf.keras.layers.BatchNormalization()(x)\nx = tf.keras.layers.MaxPool2D(2)(x)\n\n# Second set of convolutional layers\nx = tf.keras.layers.Conv2D(4, (3, 3), activation='relu')(x)\nx = tf.keras.layers.Conv2D(4, (3, 3), activation='relu')(x)\nx = tf.keras.layers.BatchNormalization()(x)\nx = tf.keras.layers.MaxPool2D(2)(x)\n\n# Third set of convolutional layers\nx = tf.keras.layers.Conv2D(8, (3, 3), activation='relu')(x)\nx = tf.keras.layers.Conv2D(8, (3, 3), activation='relu')(x)\nx = tf.keras.layers.BatchNormalization()(x)\nx = tf.keras.layers.MaxPool2D(2)(x)\n\n# Fourth set of convolutional layers\nx = tf.keras.layers.Conv2D(8, (3, 3), activation='relu')(x)\nx = tf.keras.layers.Conv2D(8, (3, 3), activation='relu')(x)\nx = tf.keras.layers.BatchNormalization()(x)\nx = tf.keras.layers.MaxPool2D(2)(x)\n\n# Fifth set of convolutional layers\nx = tf.keras.layers.Conv2D(8, (3, 3), activation='relu')(x)\nx = tf.keras.layers.Conv2D(8, (3, 3), activation='relu')(x)\nx = tf.keras.layers.BatchNormalization()(x)\nx = tf.keras.layers.MaxPool2D(2)(x)\n\n# Flatten the output\nx = tf.keras.layers.Flatten()(x)\n\n# Fully connected layer\nx = tf.keras.layers.Dense(64, activation='relu')(x)\n\n# Output layer\noutputs = tf.keras.layers.Dense(y.shape[1], activation='sigmoid')(x)\n\n# Create the model\nmodel = tf.keras.Model(inputs=inputs, outputs=outputs)\n\n# Compile the model\nopt = tf.keras.optimizers.Adam(learning_rate=0.0008, beta_1=0.9, beta_2=0.999, epsilon=1e-07, amsgrad=False)\nmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\n\n# Print model summary\nmodel.summary()\n\n# Train the model\nhistory = model.fit(X, y, epochs=10, batch_size=512, validation_split=0.3, verbose=1, shuffle=True)\n\n# Save the trained model\n\nprint(\"Trained model saved successfully.\")\n","metadata":{"execution":{"iopub.status.busy":"2024-02-25T21:53:54.76069Z","iopub.execute_input":"2024-02-25T21:53:54.761203Z","iopub.status.idle":"2024-02-25T22:32:44.951037Z","shell.execute_reply.started":"2024-02-25T21:53:54.761136Z","shell.execute_reply":"2024-02-25T22:32:44.949506Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.models import load_model\n\n# Save the trained model in the native Keras format\nmodel.save('Abdominal_trauma_model1.keras')\n\n# Load the model\nloaded_model = load_model('Abdominal_trauma_model1.keras')\n","metadata":{"execution":{"iopub.status.busy":"2024-02-25T22:37:25.925522Z","iopub.execute_input":"2024-02-25T22:37:25.926104Z","iopub.status.idle":"2024-02-25T22:37:26.892678Z","shell.execute_reply.started":"2024-02-25T22:37:25.926062Z","shell.execute_reply":"2024-02-25T22:37:26.891534Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"'''\nimport tensorflow as tf\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras.layers import Input, Conv2D, BatchNormalization, MaxPooling2D, Flatten, Dense\nfrom sklearn.model_selection import train_test_split\n\n# Assuming X and y are your training data\n# len(X), len(y)\nX = np.array(X)\ny = np.array(y)\n\n# Display the shape of the data\nX.shape, y.shape\n\n# Display one of the images\nplt.figure(figsize=(10, 8))\nplt.imshow(X[1], cmap='bone')\nplt.show()\n\n# Define the input layer\ninputs = Input(shape=(X.shape[1], X.shape[2], 1))\n\n# Model architecture\nx = Conv2D(32, (3, 3), activation='relu')(inputs)\nx = BatchNormalization()(x)\nx = MaxPooling2D((2, 2))(x)\n\nx = Conv2D(64, (3, 3), activation='relu')(x)\nx = BatchNormalization()(x)\nx = MaxPooling2D((2, 2))(x)\n\nx = Conv2D(128, (3, 3), activation='relu')(x)\nx = BatchNormalization()(x)\nx = MaxPooling2D((2, 2))(x)\n\nx = Flatten()(x)\nx = Dense(256, activation='relu')(x)\nx = BatchNormalization()(x)\nx = Dense(128, activation='relu')(x)\nx = BatchNormalization()(x)\n\n# Output layer\noutputs = Dense(y.shape[1], activation='sigmoid')(x)\n\n# Create the model\nmodel = tf.keras.Model(inputs=inputs, outputs=outputs)\n\n# Compile the model with different optimizer and loss function\nopt = tf.keras.optimizers.Adam(learning_rate=0.001)\nmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\n# Print model summary\nmodel.summary()\n\n# Train the model with different parameters\nhistory = model.fit(X, y, epochs=15, batch_size=64, validation_split=0.2, verbose=1, shuffle=True)1\n'''","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"final_accuracy = history.history['accuracy'][-1]\nformatted_accuracy = f\"{final_accuracy * 100}\"\nprint(f\"Final Training Accuracy: {formatted_accuracy}\")","metadata":{"execution":{"iopub.status.busy":"2024-02-26T20:04:20.412798Z","iopub.execute_input":"2024-02-26T20:04:20.414051Z","iopub.status.idle":"2024-02-26T20:04:20.677707Z","shell.execute_reply.started":"2024-02-26T20:04:20.413999Z","shell.execute_reply":"2024-02-26T20:04:20.676331Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred_list = []\npred_df = np.stack(pred_list)\npred_df = pd.DataFrame(pred_df)\ncol_names = [\"liver_healthy\", \"liver_low\", \"liver_high\", \"spleen_healthy\", \"spleen_low\", \"spleen_high\", \"kidney_healthy\", \"kidney_low\", \"kidney_high\", \"extravasation_healthy\", \"extravasation_injury\", \"bowel_healthy\", \"bowel_injury\"]\npred_df.columns = col_names\npred_df[\"series_id\"] = series_list[:len(pred_df)]\npred_df[\"patient_id\"] = pred_df.series_id.apply(lambda x: x.split(\"/\")[-2]).astype(int)\npred_df[\"series_id\"] = pred_df.series_id.apply(lambda x: x.split(\"/\")[-1]).astype(int)","metadata":{"execution":{"iopub.status.busy":"2024-02-26T12:53:30.28701Z","iopub.execute_input":"2024-02-26T12:53:30.287524Z","iopub.status.idle":"2024-02-26T12:53:30.350008Z","shell.execute_reply.started":"2024-02-26T12:53:30.287491Z","shell.execute_reply":"2024-02-26T12:53:30.348286Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred_df = pred_df.groupby(\"patient_id\").mean().reset_index()\ndel pred_df[\"series_id\"]\npred_df[col_names] = pred_df[col_names] ** 0.5","metadata":{"execution":{"iopub.status.busy":"2024-02-26T12:52:20.589161Z","iopub.status.idle":"2024-02-26T12:52:20.589652Z","shell.execute_reply.started":"2024-02-26T12:52:20.589424Z","shell.execute_reply":"2024-02-26T12:52:20.589446Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nimport shutil\nimport zipfile\nimport os\n\ndef archive_folder(folder_path, archive_name):\n    # Ensure the folder exists\n    if not os.path.exists(folder_path):\n        print(f\"Error: Folder '{folder_path}' does not exist.\")\n        return\n    \n    # Ensure the folder is not already archived\n    if os.path.exists(archive_name):\n        print(f\"Error: Archive '{archive_name}' already exists.\")\n        return\n    \n    try:\n        # Create a ZIP file for archiving\n        with zipfile.ZipFile(archive_name, 'w') as zipf:\n            # Walk through the directory and add files to the ZIP file\n            for foldername, subfolders, filenames in os.walk(folder_path):\n                for filename in filenames:\n                    file_path = os.path.join(foldername, filename)\n                    # Add the file to the ZIP file with the relative path\n                    zipf.write(file_path, os.path.relpath(file_path, folder_path))\n                    \n        print(f\"Folder '{folder_path}' successfully archived as '{archive_name}'.\")\n    except Exception as e:\n        print(f\"Error archiving folder: {e}\")\n\n# Example usage:\nfolder_path = '/kaggle/input/rsna-2023-abdominal-trauma-detection/train_images/10004'\narchive_name = 'archive.zip'\narchive_folder(folder_path, archive_name)\n","metadata":{"execution":{"iopub.status.busy":"2024-05-05T18:24:54.119968Z","iopub.execute_input":"2024-05-05T18:24:54.120375Z","iopub.status.idle":"2024-05-05T18:24:54.131194Z","shell.execute_reply.started":"2024-05-05T18:24:54.120346Z","shell.execute_reply":"2024-05-05T18:24:54.129914Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}