{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \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 \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from fastai import *\nfrom fastai.vision import *","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"path = Path(\"/kaggle/input/aptos2019-blindness-detection\")\ntrain_path = path/'train_images'\ntest_path = path/'test_images'\nworking_path = Path(\"/kaggle/working\")\noutput_path = Path(\"/kaggle/output\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Path('/tmp/.cache/torch/checkpoints/').mkdir(exist_ok=True, parents=True)\nmodel_path = '/tmp/.cache/torch/checkpoints/resnet152-b121ed2d.pth'\n!cp ../input/resnet152/resnet152-b121ed2d.pth {model_path}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"kappa = KappaScore()\nkappa.weights = \"quadratic\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = (ImageList.from_csv(path, csv_name='train.csv', folder='train_images', suffix='.png')\n                .split_by_rand_pct(valid_pct=0.2, seed=42)\n                .label_from_df()\n                .transform(get_transforms(flip_vert=True, max_rotate=360.0, max_warp=0.1), size=224)\n                .databunch(bs=16, num_workers=os.cpu_count())\n                .normalize())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.show_batch(rows=3, figsize=(7,8))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = cnn_learner(data, models.resnet152, metrics=[error_rate, kappa])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.model_dir = '/kaggle/working'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fit_one_cycle(5, 1e-3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage-1-224')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.load('stage-1-224')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.unfreeze()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fit_one_cycle(5, max_lr=slice(1e-6, 1e-4))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage-2-224')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = (ImageList.from_csv(path, csv_name='train.csv', folder='train_images', suffix='.png')\n                .split_by_rand_pct(valid_pct=0.2, seed=42)\n                .label_from_df()\n                .transform(get_transforms(flip_vert=True, max_rotate=360.0, max_warp=0.1), size=448)\n                .databunch(bs=16, num_workers=os.cpu_count())\n                .normalize())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = cnn_learner(data, models.resnet152, metrics=[error_rate, kappa])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.model_dir = '/kaggle/working'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.load('stage-2-224')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fit_one_cycle(3, 1e-3)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage-1-448')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.unfreeze()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot(suggestion=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fit_one_cycle(3, max_lr=slice(4e-06, 4e-4))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage-2-448')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_df = pd.read_csv('../input/aptos2019-blindness-detection/sample_submission.csv')\nsample_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.data.add_test(ImageList.from_df(sample_df, path, folder='test_images', suffix='.png'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport os\nimport scipy as sp\nfrom functools import partial\nfrom sklearn import metrics\nfrom collections import Counter\nimport json","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class OptimizedRounder(object):\n    def __init__(self):\n        self.coef_ = 0\n\n    def _kappa_loss(self, coef, X, y):\n        X_p = np.copy(X)\n        for i, pred in enumerate(X_p):\n            if pred < coef[0]:\n                X_p[i] = 0\n            elif pred >= coef[0] and pred < coef[1]:\n                X_p[i] = 1\n            elif pred >= coef[1] and pred < coef[2]:\n                X_p[i] = 2\n            elif pred >= coef[2] and pred < coef[3]:\n                X_p[i] = 3\n            else:\n                X_p[i] = 4\n\n        ll = metrics.cohen_kappa_score(y, X_p, weights='quadratic')\n        return -ll\n\n    def fit(self, X, y):\n        loss_partial = partial(self._kappa_loss, X=X, y=y)\n        initial_coef = [0.5, 1.5, 2.5, 3.5]\n        self.coef_ = sp.optimize.minimize(loss_partial, initial_coef, method='nelder-mead')\n\n    def predict(self, X, coef):\n        X_p = np.copy(X)\n        for i, pred in enumerate(X_p):\n            if pred < coef[0]:\n                X_p[i] = 0\n            elif pred >= coef[0] and pred < coef[1]:\n                X_p[i] = 1\n            elif pred >= coef[1] and pred < coef[2]:\n                X_p[i] = 2\n            elif pred >= coef[2] and pred < coef[3]:\n                X_p[i] = 3\n            else:\n                X_p[i] = 4\n        return X_p\n\n    def coefficients(self):\n        return self.coef_['x']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"val_preds, targets = learn.get_preds(DatasetType.Valid)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"_ , val_index = val_preds.max(1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_preds, y = learn.get_preds(DatasetType.Test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"_ , test_index = test_preds.max(1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"optR = OptimizedRounder()\noptR.fit(val_index, targets)\ncoefficients = optR.coefficients()\nval_index = optR.predict(val_index, coefficients)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_index = optR.predict(test_index, coefficients)\nsample_df.diagnosis = test_index.astype(int)\nsample_df.to_csv('submission.csv',index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":1}