{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":10338,"databundleVersionId":862042,"isSourceIdPinned":false,"sourceType":"competition"},{"sourceId":12478807,"sourceType":"datasetVersion","datasetId":7873569}],"dockerImageVersionId":31089,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"!pip install -q -U efficientnet tensorflow_addons==0.20.0 typeguard==2.13.3\n\nimport numpy as np\nimport pandas as pd\nimport os\nimport cv2\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nfrom sklearn.model_selection import train_test_split\nimport efficientnet.tfkeras as efn\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T10:59:27.391978Z","iopub.execute_input":"2025-07-15T10:59:27.392313Z","iopub.status.idle":"2025-07-15T10:59:31.432441Z","shell.execute_reply.started":"2025-07-15T10:59:27.392287Z","shell.execute_reply":"2025-07-15T10:59:31.431411Z"},"editable":false},"outputs":[],"execution_count":9},{"cell_type":"code","source":"data_dir = '/kaggle/input/rsna-pneumonia-detection-challenge/'\nlabels_df = pd.read_csv(os.path.join(data_dir, 'stage_2_train_labels.csv'))\nlabels_df = labels_df.drop_duplicates('patientId')\nlabels_df['Target'] = labels_df['Target'].astype(str)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T11:01:08.344066Z","iopub.execute_input":"2025-07-15T11:01:08.344514Z","iopub.status.idle":"2025-07-15T11:01:08.414422Z","shell.execute_reply.started":"2025-07-15T11:01:08.344480Z","shell.execute_reply":"2025-07-15T11:01:08.413331Z"},"editable":false},"outputs":[],"execution_count":10},{"cell_type":"code","source":"image_dir = os.path.join(data_dir, 'stage_2_train_images')\nlabels_df['path'] = labels_df['patientId'].apply(lambda x: os.path.join(image_dir, f\"{x}.dcm\"))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T11:01:11.284591Z","iopub.execute_input":"2025-07-15T11:01:11.284919Z","iopub.status.idle":"2025-07-15T11:01:11.325107Z","shell.execute_reply.started":"2025-07-15T11:01:11.284897Z","shell.execute_reply":"2025-07-15T11:01:11.324329Z"},"editable":false},"outputs":[],"execution_count":11},{"cell_type":"code","source":"import pydicom\n\ndef load_dicom_image(path, resize=(224, 224)):\n dcm = pydicom.dcmread(path)\n image = dcm.pixel_array\n image = cv2.resize(image, resize)\n image = np.stack((image,) * 3, axis=-1) # Convert to 3 channels\n image = image / 255.0\n return image","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T11:01:13.722427Z","iopub.execute_input":"2025-07-15T11:01:13.722772Z","iopub.status.idle":"2025-07-15T11:01:13.728759Z","shell.execute_reply.started":"2025-07-15T11:01:13.722748Z","shell.execute_reply":"2025-07-15T11:01:13.727717Z"},"editable":false},"outputs":[],"execution_count":12},{"cell_type":"code","source":"class PneumoniaDataset(tf.keras.utils.Sequence):\n def __init__(self, df, batch_size=16, shuffle=True, augment=False, **kwargs):\n super().__init__(**kwargs)\n self.df = df\n self.batch_size = batch_size\n self.shuffle = shuffle\n self.augment = augment\n self.on_epoch_end()\n\n \n def __len__(self):\n return int(np.floor(len(self.df) / self.batch_size))\n \n def on_epoch_end(self):\n self.indexes = np.arange(len(self.df))\n if self.shuffle:\n np.random.shuffle(self.indexes)\n \n def __getitem__(self, index):\n indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]\n df_batch = self.df.iloc[indexes]\n \n X = np.array([load_dicom_image(path) for path in df_batch['path']])\n y = df_batch['Target'].astype(int).values\n \n if self.augment:\n for i in range(len(X)):\n if np.random.rand() < 0.5:\n X[i] = tf.image.flip_left_right(X[i])\n \n return X, y","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T11:01:16.562482Z","iopub.execute_input":"2025-07-15T11:01:16.562810Z","iopub.status.idle":"2025-07-15T11:01:16.571979Z","shell.execute_reply.started":"2025-07-15T11:01:16.562786Z","shell.execute_reply":"2025-07-15T11:01:16.570946Z"},"editable":false},"outputs":[],"execution_count":13},{"cell_type":"code","source":"train_df, val_df = train_test_split(labels_df, test_size=0.2, stratify=labels_df['Target'], random_state=42)\ntrain_gen = PneumoniaDataset(train_df, batch_size=16, augment=True)\nval_gen = PneumoniaDataset(val_df, batch_size=16, augment=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T11:01:19.244564Z","iopub.execute_input":"2025-07-15T11:01:19.244924Z","iopub.status.idle":"2025-07-15T11:01:19.288432Z","shell.execute_reply.started":"2025-07-15T11:01:19.244895Z","shell.execute_reply":"2025-07-15T11:01:19.287525Z"},"editable":false},"outputs":[],"execution_count":14},{"cell_type":"code","source":"from tensorflow.keras.applications import EfficientNetV2B3\n\ndef build_model():\n base_model = EfficientNetV2B3(weights='imagenet', include_top=False, input_shape=(224, 224, 3))\n base_model.trainable = False\n\n inputs = keras.Input(shape=(224, 224, 3))\n x = base_model(inputs, training=False)\n x = layers.GlobalAveragePooling2D()(x)\n x = layers.Dropout(0.3)(x)\n outputs = layers.Dense(1, activation='sigmoid')(x)\n\n model = keras.Model(inputs, outputs)\n model.compile(optimizer='adam',\n loss='binary_crossentropy',\n metrics=['accuracy'])\n return model\n\nmodel = build_model()\nmodel.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T11:01:22.547453Z","iopub.execute_input":"2025-07-15T11:01:22.548369Z","iopub.status.idle":"2025-07-15T11:01:24.681730Z","shell.execute_reply.started":"2025-07-15T11:01:22.548339Z","shell.execute_reply":"2025-07-15T11:01:24.680933Z"},"editable":false},"outputs":[{"output_type":"display_data","data":{"text/plain":"\u001b[1mModel: \"functional_1\"\u001b[0m\n","text/html":"
Model: \"functional_1\"\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n│ input_layer_3 (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m224\u001b[0m, \u001b[38;5;34m3\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ efficientnetv2-b3 (\u001b[38;5;33mFunctional\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m1536\u001b[0m) │ \u001b[38;5;34m12,930,622\u001b[0m │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ global_average_pooling2d_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1536\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m) │ │ │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1536\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m1,537\u001b[0m │\n└─────────────────────────────────┴────────────────────────┴───────────────┘\n","text/html":"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n│ input_layer_3 (InputLayer)      │ (None, 224, 224, 3)    │             0 │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ efficientnetv2-b3 (Functional)  │ (None, 7, 7, 1536)     │    12,930,622 │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ global_average_pooling2d_1      │ (None, 1536)           │             0 │\n│ (GlobalAveragePooling2D)        │                        │               │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dropout_1 (Dropout)             │ (None, 1536)           │             0 │\n├─────────────────────────────────┼────────────────────────┼───────────────┤\n│ dense_1 (Dense)                 │ (None, 1)              │         1,537 │\n└─────────────────────────────────┴────────────────────────┴───────────────┘\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m12,932,159\u001b[0m (49.33 MB)\n","text/html":"
 Total params: 12,932,159 (49.33 MB)\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m1,537\u001b[0m (6.00 KB)\n","text/html":"
 Trainable params: 1,537 (6.00 KB)\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m12,930,622\u001b[0m (49.33 MB)\n","text/html":"
 Non-trainable params: 12,930,622 (49.33 MB)\n
\n"},"metadata":{}}],"execution_count":15},{"cell_type":"code","source":"history = model.fit(train_gen,\n validation_data=val_gen,\n epochs=10)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T11:02:27.000614Z","iopub.execute_input":"2025-07-15T11:02:27.001021Z","iopub.status.idle":"2025-07-15T14:54:49.589632Z","shell.execute_reply.started":"2025-07-15T11:02:27.000993Z","shell.execute_reply":"2025-07-15T14:54:49.588740Z"},"editable":false},"outputs":[{"name":"stdout","text":"Epoch 1/10\n\u001b[1m1334/1334\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1392s\u001b[0m 1s/step - accuracy: 0.7768 - loss: 0.5366 - val_accuracy: 0.7746 - val_loss: 0.5365\nEpoch 2/10\n\u001b[1m1334/1334\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1346s\u001b[0m 1s/step - accuracy: 0.7717 - loss: 0.5421 - val_accuracy: 0.7744 - val_loss: 0.5336\nEpoch 3/10\n\u001b[1m1334/1334\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1350s\u001b[0m 1s/step - accuracy: 0.7760 - loss: 0.5388 - val_accuracy: 0.7750 - val_loss: 0.5324\nEpoch 4/10\n\u001b[1m1334/1334\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1473s\u001b[0m 1s/step - accuracy: 0.7707 - loss: 0.5413 - val_accuracy: 0.7744 - val_loss: 0.5414\nEpoch 5/10\n\u001b[1m1334/1334\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1350s\u001b[0m 1s/step - accuracy: 0.7758 - loss: 0.5365 - val_accuracy: 0.7746 - val_loss: 0.5386\nEpoch 6/10\n\u001b[1m1334/1334\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1413s\u001b[0m 1s/step - accuracy: 0.7693 - loss: 0.5458 - val_accuracy: 0.7744 - val_loss: 0.5457\nEpoch 7/10\n\u001b[1m1334/1334\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1354s\u001b[0m 1s/step - accuracy: 0.7761 - loss: 0.5351 - val_accuracy: 0.7746 - val_loss: 0.5360\nEpoch 8/10\n\u001b[1m1334/1334\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1469s\u001b[0m 1s/step - accuracy: 0.7795 - loss: 0.5368 - val_accuracy: 0.7750 - val_loss: 0.5317\nEpoch 9/10\n\u001b[1m1334/1334\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1401s\u001b[0m 1s/step - accuracy: 0.7746 - loss: 0.5368 - val_accuracy: 0.7752 - val_loss: 0.5396\nEpoch 10/10\n\u001b[1m1334/1334\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1394s\u001b[0m 1s/step - accuracy: 0.7755 - loss: 0.5393 - val_accuracy: 0.7748 - val_loss: 0.5317\n","output_type":"stream"}],"execution_count":17},{"cell_type":"code","source":"# Save model\nmodel.save(\"pneumonia_model.h5\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T15:09:39.794937Z","iopub.execute_input":"2025-07-15T15:09:39.795264Z","iopub.status.idle":"2025-07-15T15:09:40.337402Z","shell.execute_reply.started":"2025-07-15T15:09:39.795242Z","shell.execute_reply":"2025-07-15T15:09:40.336329Z"},"editable":false},"outputs":[],"execution_count":22},{"cell_type":"code","source":"from tensorflow.keras.models import load_model\nmodel = load_model(\"pneumonia_model.h5\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T15:09:43.062208Z","iopub.execute_input":"2025-07-15T15:09:43.063301Z","iopub.status.idle":"2025-07-15T15:09:45.013015Z","shell.execute_reply.started":"2025-07-15T15:09:43.063271Z","shell.execute_reply":"2025-07-15T15:09:45.012032Z"},"editable":false},"outputs":[],"execution_count":23},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nfig, axs = plt.subplots(1, 2, figsize=(14, 5))\n\n# Accuracy plot\naxs[0].plot(history.history['accuracy'], label='Train Accuracy')\naxs[0].plot(history.history['val_accuracy'], label='Val Accuracy')\naxs[0].set_title('Accuracy over Epochs')\naxs[0].set_xlabel('Epochs')\naxs[0].set_ylabel('Accuracy')\naxs[0].legend()\n\n# Loss plot\naxs[1].plot(history.history['loss'], label='Train Loss')\naxs[1].plot(history.history['val_loss'], label='Val Loss')\naxs[1].set_title('Loss over Epochs')\naxs[1].set_xlabel('Epochs')\naxs[1].set_ylabel('Loss')\naxs[1].legend()\n\nplt.tight_layout()\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T15:22:54.707701Z","iopub.execute_input":"2025-07-15T15:22:54.708191Z","iopub.status.idle":"2025-07-15T15:22:55.149362Z","shell.execute_reply.started":"2025-07-15T15:22:54.708163Z","shell.execute_reply":"2025-07-15T15:22:55.148393Z"},"editable":false},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":30},{"cell_type":"code","source":"# Class Distribution\nlabels_df['Target'].value_counts().plot(kind='bar', color=['green', 'red'])\nplt.title(\"Data Distribution (0 = Normal, 1 = Pneumonia)\")\nplt.xlabel(\"Class\")\nplt.ylabel(\"Count\")\nplt.show()\nimport os\nimport numpy as np\nimport pandas as pd\nimport cv2\nimport pydicom\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow.keras.models import load_model\n\n# Load labels and paths\ndata_dir = '/kaggle/input/rsna-pneumonia-detection-challenge/'\nlabels_df = pd.read_csv(os.path.join(data_dir, 'stage_2_train_labels.csv'))\nlabels_df = labels_df.drop_duplicates('patientId')\nlabels_df['Target'] = labels_df['Target'].astype(int)\nimage_dir = os.path.join(data_dir, 'stage_2_train_images')\nlabels_df['path'] = labels_df['patientId'].apply(lambda x: os.path.join(image_dir, f\"{x}.dcm\"))\n\n# Function to load and preprocess DICOM images\ndef load_dicom_image(path, resize=(224, 224)):\n try:\n dcm = pydicom.dcmread(path)\n img = dcm.pixel_array\n img = cv2.resize(img, resize)\n img = np.stack((img,) * 3, axis=-1)\n img = img / 255.0\n return img\n except:\n return None\n\n# Load a small sample to avoid memory overload\nsample_df = labels_df.sample(n=1000, random_state=42)\nsample_df['image'] = sample_df['path'].apply(load_dicom_image)\nsample_df = sample_df.dropna(subset=['image'])\n\n# Prepare X and y\nX = np.stack(sample_df['image'].values)\ny = sample_df['Target'].values\n\n# Split and load model\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)\nmodel = load_model(\"pneumonia_model.h5\")\n\n# Predict and evaluate\ny_pred = model.predict(X_test)\ny_pred_labels = (y_pred > 0.5).astype(int)\n\n# Accuracy\nacc = accuracy_score(y_test, y_pred_labels)\nprint(\"✅ Overall Accuracy on Test Set:\", acc)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T15:23:52.418624Z","iopub.execute_input":"2025-07-15T15:23:52.420197Z","iopub.status.idle":"2025-07-15T15:24:26.593068Z","shell.execute_reply.started":"2025-07-15T15:23:52.420167Z","shell.execute_reply":"2025-07-15T15:24:26.592299Z"},"editable":false},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}},{"name":"stdout","text":"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m20s\u001b[0m 2s/step\n✅ Overall Accuracy on Test Set: 0.785\n","output_type":"stream"}],"execution_count":31},{"cell_type":"code","source":"from sklearn.metrics import (\n accuracy_score, f1_score, precision_score, recall_score,\n confusion_matrix, classification_report, ConfusionMatrixDisplay\n)\nimport matplotlib.pyplot as plt\n\n# Predict\ny_pred = model.predict(X_test)\ny_pred_labels = (y_pred > 0.5).astype(int)\n\n# Metrics\nacc = accuracy_score(y_test, y_pred_labels)\nf1 = f1_score(y_test, y_pred_labels)\nprecision = precision_score(y_test, y_pred_labels)\nrecall = recall_score(y_test, y_pred_labels)\n\n# Output metrics\nprint(f\"✅ Accuracy: {acc:.4f}\")\nprint(f\"🎯 F1 Score: {f1:.4f}\")\nprint(f\"📌 Precision: {precision:.4f}\")\nprint(f\"📈 Recall: {recall:.4f}\")\n\n# Classification Report\nprint(\"\\n📋 Classification Report:\\n\")\nprint(classification_report(y_test, y_pred_labels))\n\n# Confusion Matrix\ncm = confusion_matrix(y_test, y_pred_labels)\ndisp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=[\"Normal\", \"Pneumonia\"])\ndisp.plot(cmap=plt.cm.Blues)\nplt.title(\"🧠 Confusion Matrix\")\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-15T15:24:26.594459Z","iopub.execute_input":"2025-07-15T15:24:26.594682Z","iopub.status.idle":"2025-07-15T15:24:37.633906Z","shell.execute_reply.started":"2025-07-15T15:24:26.594665Z","shell.execute_reply":"2025-07-15T15:24:37.632938Z"},"editable":false},"outputs":[{"name":"stdout","text":"\u001b[1m7/7\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 1s/step\n✅ Accuracy: 0.7850\n🎯 F1 Score: 0.0000\n📌 Precision: 0.0000\n📈 Recall: 0.0000\n\n📋 Classification Report:\n\n precision recall f1-score support\n\n 0 0.79 1.00 0.88 157\n 1 0.00 0.00 0.00 43\n\n accuracy 0.79 200\n macro avg 0.39 0.50 0.44 200\nweighted avg 0.62 0.79 0.69 200\n\n","output_type":"stream"},{"name":"stderr","text":"/usr/local/lib/python3.11/dist-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.\n _warn_prf(average, modifier, msg_start, len(result))\n/usr/local/lib/python3.11/dist-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n _warn_prf(average, modifier, msg_start, len(result))\n/usr/local/lib/python3.11/dist-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n _warn_prf(average, modifier, msg_start, len(result))\n/usr/local/lib/python3.11/dist-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n _warn_prf(average, modifier, msg_start, len(result))\n/usr/local/lib/python3.11/dist-packages/IPython/core/pylabtools.py:151: UserWarning: Glyph 129504 (\\N{BRAIN}) missing from current font.\n fig.canvas.print_figure(bytes_io, **kw)\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":32},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.models import load_model\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom PIL import Image\nimport cv2\nimport os\nimport pydicom\n\n# ====== Paths (UPDATE these) ======\nmodel_path = '/kaggle/working/pneumonia_model.h5' # Replace with your model folder name\nimage_path = '/kaggle/input/rsna-pneumonia-detection-challenge/stage_2_train_images/006cec2e-6ce2-4549-bffa-eadfcd1e9970.dcm' # Replace with image file path\n\n# ====== Load Model ======\nmodel = load_model(model_path)\n\n# ====== Load and Preprocess ======\ndef load_image(img_path, target_size=(224, 224)):\n ext = os.path.splitext(img_path)[1].lower()\n\n if ext == '.dcm':\n # Read DICOM\n dicom = pydicom.dcmread(img_path)\n img = dicom.pixel_array\n\n # Normalize to 0-255 and convert to 3 channels\n img = cv2.normalize(img, None, 0, 255, cv2.NORM_MINMAX)\n img = cv2.cvtColor(np.uint8(img), cv2.COLOR_GRAY2RGB)\n else:\n # For jpg/png\n img = Image.open(img_path).convert('RGB')\n img = np.array(img)\n\n # Resize and scale\n img = cv2.resize(img, target_size)\n img = img / 255.0\n return img\n\n# ====== Predict and Show ======\ndef predict_and_show(img_path):\n img_array = load_image(img_path)\n input_array = np.expand_dims(img_array, axis=0)\n pred = model.predict(input_array)[0][0]\n\n label = \"PNEUMONIA\" if pred > 0.5 else \"NORMAL\"\n color = (255, 0, 0) if label == \"PNEUMONIA\" else (0, 255, 0)\n\n # Add label to image\n display_img = (img_array * 255).astype(np.uint8)\n display_img = cv2.putText(display_img.copy(), f\"Prediction: {label}\", (10, 30),\n cv2.FONT_HERSHEY_SIMPLEX, 1, color, 2)\n\n plt.imshow(display_img)\n plt.axis('off')\n plt.title(label)\n plt.show()\n\n# 🔍 Run prediction\npredict_and_show(image_path)\n","metadata":{"trusted":true,"editable":false},"outputs":[],"execution_count":null}]}