{"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\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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import os\nos.listdir('/kaggle/input/histopathologic-cancer-detection')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.listdir('/kaggle/input/histopathologic-cancer-detection/train')[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport seaborn as sns\nfrom fastai import *\nfrom fastai.vision import *","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels = pd.read_csv('/kaggle/input/histopathologic-cancer-detection/train_labels.csv')\nlabels.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x='label',data=labels)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"A positive label means that there is at least one pixel of tumor tissue in the center region (32 x 32px) of the image.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"path=Path('/kaggle/input/histopathologic-cancer-detection/')\ntfms = get_transforms(do_flip=True,flip_vert=True, max_warp=0, max_rotate=10, max_lighting=0.05)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"path","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = ImageDataBunch.from_csv(path, \n                             csv_labels='train_labels.csv', \n                             folder='train', \n                             suffix='.tif',\n                             num_workers=2,\n                             ds_tfms=tfms,\n                             bs=64,\n                             size=72,\n                             test=path/'test').normalize(imagenet_stats)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.classes","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.c","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.show_batch(rows=3,figsize=(8,10))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import warnings\nwarnings.filterwarnings('ignore')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from fastai import *\nfrom fastai.vision import *\nfrom fastai.callbacks.hooks import *","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn= create_cnn(data, models.resnet34, metrics=[accuracy],model_dir='/kaggle/working/')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()\nlearn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#wd = weight decay\nlearn.fit_one_cycle(6, max_lr=(1e-4, 1e-3, 1e-2), wd=(1e-4, 1e-4, 1e-1))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Unfreeze the layers- weights of all the fozen layers will be updated","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.unfreeze()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()\nlearn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fit_one_cycle(15, slice(1e-5,1e-4,1e-3))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage-1') ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"interp = ClassificationInterpretation.from_learner(learn)\ninterp.plot_confusion_matrix(figsize=(10,8))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Validation Accuracy**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"preds,y = learn.get_preds(DatasetType.Valid)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Accuracy**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy(preds,y)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Predictions on the Test Data**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"label,y=learn.get_preds(DatasetType.Test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv(f'{path}/sample_submission.csv').set_index('id')\nsub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.test_ds.items[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"names=np.vectorize(lambda img_name: str(img_name).split('/')[-1][:-4]) \n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"file_names= names(data.test_ds.items).astype(str)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label.numpy()[:,1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.loc[file_names,'label']=label.numpy()[:,1]\nsub.to_csv(f'submission_resnet34.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = []\nfor i in label:\n    predictions.append(i.argmax().item())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(predictions)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.show_results()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Visualize Predictions made by the resnet34 Model**","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"_,axs = plt.subplots(3,5,figsize=(11,8))\nfor i,ax in enumerate(axs.flatten()): \n  img = data.test_ds[i][0]\n  img.show(ax=ax,y=learn.predict(img)[0])","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":4}