{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":14774,"databundleVersionId":875431,"sourceType":"competition"}],"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","trusted":true,"execution":{"iopub.status.busy":"2025-04-16T15:31:54.725734Z","iopub.execute_input":"2025-04-16T15:31:54.726166Z","iopub.status.idle":"2025-04-16T15:31:57.368410Z","shell.execute_reply.started":"2025-04-16T15:31:54.726131Z","shell.execute_reply":"2025-04-16T15:31:57.367381Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Importing Libaries ","metadata":{}},{"cell_type":"code","source":"import os\nimport warnings \nimport cv2 as cv\nimport numpy as np \nimport pandas as pd\nimport seaborn as sns \nimport matplotlib.pyplot as plt\nfrom tensorflow import keras\nfrom tensorflow.keras import Sequential\nfrom tensorflow.keras.losses import SparseCategoricalCrossentropy\nfrom tensorflow.keras.callbacks import EarlyStopping\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.metrics import confusion_matrix,ConfusionMatrixDisplay\nwarnings.filterwarnings(\"ignore\")\nsns.set_style(style=\"darkgrid\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T15:31:57.369770Z","iopub.execute_input":"2025-04-16T15:31:57.370047Z","iopub.status.idle":"2025-04-16T15:31:57.378070Z","shell.execute_reply.started":"2025-04-16T15:31:57.370024Z","shell.execute_reply":"2025-04-16T15:31:57.376587Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Read data","metadata":{}},{"cell_type":"code","source":"df = pd.read_csv(\"/kaggle/input/aptos2019-blindness-detection/train.csv\")\nprint(df.shape)\ndf.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T15:31:57.379219Z","iopub.execute_input":"2025-04-16T15:31:57.379594Z","iopub.status.idle":"2025-04-16T15:31:57.414626Z","shell.execute_reply.started":"2025-04-16T15:31:57.379564Z","shell.execute_reply":"2025-04-16T15:31:57.413024Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Visualize Distribution ","metadata":{}},{"cell_type":"code","source":"data = df.replace({\"diagnosis\":{0:\"No DR\",1:\"Mild\",2:\"Moderate\",3:\"Severe\",4:\"Proliferative DR\"}})\ndiagnosis_count = data.diagnosis.value_counts()\nsns.countplot(data=data,x=\"diagnosis\",order=diagnosis_count.index)\nplt.xlabel(\"Diagnosis\",weight=\"bold\",size=15)\nplt.ylabel(\"Freq\",weight=\"bold\",size=15)\nfor i,v in enumerate(diagnosis_count.values,0):\n    text = f\"{v*100/len(data):0.2f}%\"\n    plt.text(s=text,x=i,y=v+10,ha=\"center\",weight=\"bold\")\nplt.show()\ndel data","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T15:31:57.417278Z","iopub.execute_input":"2025-04-16T15:31:57.417616Z","iopub.status.idle":"2025-04-16T15:31:57.696122Z","shell.execute_reply.started":"2025-04-16T15:31:57.417594Z","shell.execute_reply":"2025-04-16T15:31:57.692425Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Read Image & preprocessing","metadata":{}},{"cell_type":"code","source":"import os\nimport cv2 as cv\nimport numpy as np\nimport pandas as pd\nfrom concurrent.futures import ThreadPoolExecutor\n\n# Load the CSV file containing image IDs and their corresponding diagnoses\ndf = pd.read_csv('/kaggle/input/aptos2019-blindness-detection/train.csv')\n\n# Define the base path to the training images\nbase_path = '/kaggle/input/aptos2019-blindness-detection/train_images'\n\n# Helper function to process each image\ndef process_image(row):\n    image_id = row['id_code']\n    target = row['diagnosis']\n    path = os.path.join(base_path, f\"{image_id}.png\")\n    img = cv.imread(path, 1)\n    if img is None:\n        return []  # Skip if image is not found\n    img = cv.resize(img, (224, 224), interpolation=cv.INTER_AREA)\n    img = img / 255.0  # Normalize pixel values\n    results = [(img, target)]\n    if target in (3, 4):\n        flipped = cv.flip(img, 1)\n        results.append((flipped, target))\n    return results\n\n# Prepare the list of image processing tasks\nrows = df.to_dict('records')\n\n# Process images in parallel using ThreadPoolExecutor\nX = []\ny = []\nwith ThreadPoolExecutor() as executor:\n    for result in executor.map(process_image, rows):\n        for img, label in result:\n            X.append(img)\n            y.append(label)\n\n# Convert lists to NumPy arrays\nX = np.array(X)\ny = np.array(y)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T15:31:57.698015Z","iopub.execute_input":"2025-04-16T15:31:57.702707Z","iopub.status.idle":"2025-04-16T15:35:04.869893Z","shell.execute_reply.started":"2025-04-16T15:31:57.702385Z","shell.execute_reply":"2025-04-16T15:35:04.868640Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"data = pd.Series(y)\ndata = data.replace({0:\"No DR\",1:\"Mild\",2:\"Moderate\",3:\"Severe\",4:\"Proliferative DR\"})\ndiagnosis_count = data.value_counts()\nsns.countplot(x=data,order=diagnosis_count.index)\nplt.xlabel(\"Diagnosis\",weight=\"bold\",size=15)\nplt.ylabel(\"Freq\",weight=\"bold\",size=15)\nfor i,v in enumerate(diagnosis_count.values,0):\n    text = f\"{v*100/len(data):0.2f}%\"\n    plt.text(s=text,x=i,y=v+10,ha=\"center\",weight=\"bold\")\nplt.show()\ndel data","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T15:35:51.731286Z","iopub.execute_input":"2025-04-16T15:35:51.731681Z","iopub.status.idle":"2025-04-16T15:35:51.950884Z","shell.execute_reply.started":"2025-04-16T15:35:51.731655Z","shell.execute_reply":"2025-04-16T15:35:51.949896Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.3,random_state=0,shuffle=True)\nx_test,x_val,y_test,y_val = train_test_split(x_test,y_test,test_size=0.5,random_state=0,shuffle=True)\ndel X,y","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T15:36:13.501151Z","iopub.execute_input":"2025-04-16T15:36:13.501505Z","iopub.status.idle":"2025-04-16T15:36:16.316473Z","shell.execute_reply.started":"2025-04-16T15:36:13.501482Z","shell.execute_reply":"2025-04-16T15:36:16.315488Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\n\n# Input Layer\nmodel.add(keras.layers.InputLayer(shape=(224,224,3)))\n\n\n# CNN Layer1   \nmodel.add(keras.layers.Conv2D(32,(3,3),padding=\"valid\",activation=\"relu\")) \nmodel.add(keras.layers.MaxPool2D((2,2),strides=2)) \n\n# CNN Layer2\nmodel.add(keras.layers.Conv2D(64,(3,3),padding=\"valid\",activation=\"relu\"))\nmodel.add(keras.layers.MaxPool2D((3,3),strides=3))\n\n# CNN Layer3\nmodel.add(keras.layers.Conv2D(128,(3,3),padding=\"valid\",activation=\"relu\"))\nmodel.add(keras.layers.MaxPool2D((3,3),strides=3))\n\n# CNN Layer4\nmodel.add(keras.layers.Conv2D(256,(3,3),padding=\"valid\",activation=\"relu\"))\nmodel.add(keras.layers.Dropout(0.5))\nmodel.add(keras.layers.MaxPool2D((3,3),strides=3))\n\n# Flatten Layer\nmodel.add(keras.layers.Flatten())\n\n# Fully Connected layer\nmodel.add(keras.layers.Dense(256,activation=\"relu\"))\nmodel.add(keras.layers.Dense(128,activation=\"relu\"))\nmodel.add(keras.layers.Dense(5,activation=\"softmax\"))\n\n# Compile\nmodel.compile(loss=SparseCategoricalCrossentropy(),metrics=[\"accuracy\"],optimizer=\"adam\")\n\n# Summary for model\nmodel.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T15:36:49.251258Z","iopub.execute_input":"2025-04-16T15:36:49.251578Z","iopub.status.idle":"2025-04-16T15:36:49.442833Z","shell.execute_reply.started":"2025-04-16T15:36:49.251555Z","shell.execute_reply":"2025-04-16T15:36:49.441969Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"es = EarlyStopping(monitor='val_accuracy',\n                   mode=\"max\",\n                   verbose=1,\n                   patience=6,\n                   restore_best_weights=True)\n\n\nhistory = model.fit(x_train,y_train,\n                    epochs=25,batch_size=190,\n                    validation_data=[x_val,y_val],\n                    callbacks=[es])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T15:37:43.182890Z","iopub.execute_input":"2025-04-16T15:37:43.183246Z","iopub.status.idle":"2025-04-16T16:27:42.793168Z","shell.execute_reply.started":"2025-04-16T15:37:43.183216Z","shell.execute_reply":"2025-04-16T16:27:42.791604Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"plt.figure(figsize=(13,5))\nplt.subplot(1,2,1)\nplt.title(\"Accuracy\")\nplt.plot(history.history[\"val_accuracy\"],label=\"val accuracy\")\nplt.plot(history.history[\"accuracy\"],label=\"accuracy\")\nplt.legend()\nplt.subplot(1,2,2)\nplt.title(\"Loss\")\nplt.plot(history.history[\"val_loss\"],label=\"val loss\")\nplt.plot(history.history[\"loss\"],label=\"loss\")\nplt.legend()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T16:29:49.830704Z","iopub.execute_input":"2025-04-16T16:29:49.831062Z","iopub.status.idle":"2025-04-16T16:29:50.378844Z","shell.execute_reply.started":"2025-04-16T16:29:49.831041Z","shell.execute_reply":"2025-04-16T16:29:50.377870Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_predicted = model.predict(x_test)\ny_predicted = np.argmax(y_predicted,axis=1)\ncm = confusion_matrix(y_test,y_predicted)\ncmd = ConfusionMatrixDisplay(confusion_matrix = cm, display_labels = [\"No DR\",\"Mild\",\"Moderate\",\"Severe\",\"Proliferative DR\"])\ncmd.plot(cmap=plt.cm.Blues, values_format='d',xticks_rotation=\"vertical\")\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T16:29:55.159880Z","iopub.execute_input":"2025-04-16T16:29:55.160228Z","iopub.status.idle":"2025-04-16T16:30:04.431755Z","shell.execute_reply.started":"2025-04-16T16:29:55.160184Z","shell.execute_reply":"2025-04-16T16:30:04.430773Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"acc = accuracy_score(y_test,y_predicted)\nprint(f\"Test score: {acc*100:.2f}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T16:30:38.839724Z","iopub.execute_input":"2025-04-16T16:30:38.840621Z","iopub.status.idle":"2025-04-16T16:30:38.846509Z","shell.execute_reply.started":"2025-04-16T16:30:38.840592Z","shell.execute_reply":"2025-04-16T16:30:38.845678Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"decode = {0:\"No DR\",1:\"Mild\",2:\"Moderate\",3:\"Severe\",4:\"Proliferative DR\"}\nplt.figure(figsize=(15,5))\nfor i,test in enumerate(np.random.randint(0,len(df)-1,8),1):\n    plt.subplot(2,4,i)\n    image = df.loc[test,\"id_code\"]\n    path = os.path.join(\"/kaggle/input/aptos2019-blindness-detection/train_images\",f\"{image}.png\")\n    img = cv.imread(path,1)\n    img = cv.resize(img,(224,224))\n    plt.imshow(cv.cvtColor(img,cv.COLOR_BGR2RGB))\n    img = img/255.0\n    img = np.expand_dims(img,axis=0)\n    res = model.predict(img)\n    res = f\"Prediction is {decode[np.argmax(res)]}\"\n    true = f\"Real is {decode[df.loc[test,'diagnosis']]}\"\n    plt.axis(\"off\")\n    plt.text(x=10,y=20,s=true,color=\"Blue\",weight=\"bold\",backgroundcolor=\"Gray\",size=8)\n    plt.text(x=10,y=215,s=res,color=\"Blue\",weight=\"bold\",backgroundcolor=\"Gray\",size=8)\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T16:30:53.195812Z","iopub.execute_input":"2025-04-16T16:30:53.196105Z","iopub.status.idle":"2025-04-16T16:30:56.326852Z","shell.execute_reply.started":"2025-04-16T16:30:53.196084Z","shell.execute_reply":"2025-04-16T16:30:56.325936Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model.save(\"dabieticprediction.keras\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T16:32:15.355031Z","iopub.execute_input":"2025-04-16T16:32:15.355436Z","iopub.status.idle":"2025-04-16T16:32:15.512530Z","shell.execute_reply.started":"2025-04-16T16:32:15.355409Z","shell.execute_reply":"2025-04-16T16:32:15.511367Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"del x_train,x_test,x_val,y_train,y_test,y_val,history,df","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-04-16T16:32:40.515394Z","iopub.execute_input":"2025-04-16T16:32:40.516470Z","iopub.status.idle":"2025-04-16T16:32:40.562355Z","shell.execute_reply.started":"2025-04-16T16:32:40.516398Z","shell.execute_reply":"2025-04-16T16:32:40.561300Z"}},"outputs":[],"execution_count":null}]}