{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"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\n# for 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":"2022-10-26T19:07:29.971798Z","iopub.execute_input":"2022-10-26T19:07:29.972272Z","iopub.status.idle":"2022-10-26T19:07:30.000711Z","shell.execute_reply.started":"2022-10-26T19:07:29.972173Z","shell.execute_reply":"2022-10-26T19:07:29.999845Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n%matplotlib inline\nimport warnings\nwarnings.filterwarnings('ignore')\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.model_selection import train_test_split\nfrom tqdm import tqdm\nimport tensorflow as tf\nfrom tensorflow import keras\nfrom tensorflow.keras import layers\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense\nfrom tensorflow.keras.layers import GlobalMaxPooling2D\nimport openslide\nfrom openslide import OpenSlide","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df = pd.read_csv('../input/mayo-clinic-strip-ai/train.csv')\ntest_df  = pd.read_csv('../input/mayo-clinic-strip-ai/test.csv')","metadata":{"execution":{"iopub.status.busy":"2022-10-26T19:07:36.061882Z","iopub.execute_input":"2022-10-26T19:07:36.062516Z","iopub.status.idle":"2022-10-26T19:07:36.091158Z","shell.execute_reply.started":"2022-10-26T19:07:36.062479Z","shell.execute_reply":"2022-10-26T19:07:36.090301Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.head()","metadata":{"execution":{"iopub.status.busy":"2022-10-26T19:07:36.092391Z","iopub.execute_input":"2022-10-26T19:07:36.092742Z","iopub.status.idle":"2022-10-26T19:07:36.111002Z","shell.execute_reply.started":"2022-10-26T19:07:36.092703Z","shell.execute_reply":"2022-10-26T19:07:36.110006Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df[\"file_path\"] = train_df[\"image_id\"].apply(lambda x: \"../input/mayo-clinic-strip-ai/train/\" + x + \".tif\")\ntest_df[\"file_path\"]  = test_df[\"image_id\"].apply(lambda x: \"../input/mayo-clinic-strip-ai/test/\" + x + \".tif\")","metadata":{"execution":{"iopub.status.busy":"2022-10-26T19:07:36.113418Z","iopub.execute_input":"2022-10-26T19:07:36.113762Z","iopub.status.idle":"2022-10-26T19:07:36.124505Z","shell.execute_reply.started":"2022-10-26T19:07:36.113727Z","shell.execute_reply":"2022-10-26T19:07:36.123514Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df[\"target\"] = train_df[\"label\"].apply(lambda x : 1 if x==\"CE\" else 0)","metadata":{"execution":{"iopub.status.busy":"2022-10-26T19:07:36.125947Z","iopub.execute_input":"2022-10-26T19:07:36.126351Z","iopub.status.idle":"2022-10-26T19:07:36.134592Z","shell.execute_reply.started":"2022-10-26T19:07:36.126306Z","shell.execute_reply":"2022-10-26T19:07:36.133686Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.head()","metadata":{"execution":{"iopub.status.busy":"2022-10-26T19:07:36.136624Z","iopub.execute_input":"2022-10-26T19:07:36.136912Z","iopub.status.idle":"2022-10-26T19:07:36.15239Z","shell.execute_reply.started":"2022-10-26T19:07:36.136887Z","shell.execute_reply":"2022-10-26T19:07:36.151522Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndef preprocess(image_path):\n    slide=OpenSlide(image_path)\n    region= (1000,1000)    \n    size  = (5000, 5000)\n    image = slide.read_region(region, 0, size)\n    image = tf.image.resize(image, (512, 512))\n    image = np.array(image)    \n    return image\n\nx_train=[]\nfor i in tqdm(train_df['file_path']):\n    x1=preprocess(i)\n    x_train.append(x1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train=np.array(x_train)\ny_train=train_df['target']\n\nx_train,x_test,y_train,y_test=train_test_split(x_train,y_train,test_size=0.1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential()\ninput_shape = (512, 512, 4)\n\nmodel.add(Conv2D(filters=64, kernel_size = (3,3), strides =2, padding = 'valid', activation = 'relu', input_shape = input_shape))\nmodel.add(Conv2D(filters=64, kernel_size = (3,3), strides =2, padding = 'valid', activation = 'relu'))\nmodel.add(Conv2D(filters=64, kernel_size = (3,3), strides =2, padding = 'valid', activation = 'relu'))\nmodel.add(Conv2D(filters=64, kernel_size = (3,3), strides =2, padding = 'valid', activation = 'relu'))\nmodel.add(Conv2D(filters=128, kernel_size = (3,3), strides =2, padding = 'valid', activation = 'relu'))\nmodel.add(Conv2D(filters=128, kernel_size = (3,3), strides =2, padding = 'valid', activation = 'relu'))\nmodel.add(Conv2D(filters=256, kernel_size = (3,3), strides =2, padding = 'valid', activation = 'relu'))\nmodel.add(Conv2D(filters=256, kernel_size = (3,3), strides =2, padding = 'valid', activation = 'relu'))\n\nmodel.add(Dropout(0.13))\nmodel.add(Flatten())\nmodel.add(Dense(256, activation = 'relu'))\nmodel.add(Dropout(0.13))\nmodel.add(Dense(100, activation = 'relu'))\n\nmodel.add(Dense(50, activation = 'relu'))\nmodel.add(Dense(1 , activation=\"sigmoid\"))\n\nmodel.compile(\n    loss = tf.keras.losses.BinaryCrossentropy(),\n    \n    metrics=['accuracy'],\n    optimizer = tf.keras.optimizers.Adam(1e-3))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit(\n    x_train,\n    y_train,\n    epochs = 70,\n    batch_size=64,\n    validation_data = (x_test,y_test),\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test1=[]\nfor i in test_df['file_path']:\n    x1=preprocess(i)\n    test1.append(x1)\ntest1=np.array(test1)\ncnn_pred=model.predict(test1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.DataFrame(test_df[\"patient_id\"].copy())\nsub[\"CE\"] = cnn_pred\n# sub[\"CE\"] = sub[\"CE\"].apply(lambda x : 0 if x<0 else x)\n# sub[\"CE\"] = sub[\"CE\"].apply(lambda x : 1 if x>1 else x)\nsub[\"LAA\"] = 1- sub[\"CE\"]\n\nsub = sub.groupby(\"patient_id\").mean()\nsub = sub[[\"CE\", \"LAA\"]].round(6).reset_index()\nsub","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub.to_csv(\"submission.csv\", index = False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}