{"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 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","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from fastai.vision.all import *","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Unzip image files\nfrom zipfile import ZipFile\nwith ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip', 'r') as archive:\n    archive.extractall('/kaggle/working/')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Set path to working folder\npath = Path('/kaggle/working/')\npath.ls()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Set the pets dataloader\npets = DataBlock(blocks = (ImageBlock, CategoryBlock),\n                 get_items=get_image_files, \n                 splitter=RandomSplitter(seed=42),\n                 get_y=using_attr(RegexLabeller(r'(.+)\\.\\d+.jpg$'), 'name'),\n                 item_tfms=Resize(460),\n                 batch_tfms=aug_transforms(size=224, min_scale=0.75))\ndls = pets.dataloaders(path/'train')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Train a very simple model\nlearn = cnn_learner(dls, resnet34, metrics=error_rate)\nlearn.fine_tune(2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Unzip image files for testing\n\nwith ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip', 'r') as archive:\n    archive.extractall('/kaggle/working/')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#data loader pointed to test dataset and get predictions\ntest_dl = dls.test_dl(get_image_files(path/'test'))\nallPreds = learn.get_preds(dl=test_dl)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Match filename to prediction probs\nallFiles = list((path/'test').ls())\nguesses = [[int(re.findall(r'.+/(\\d+).jpg$', str(allFiles[i]))[0]), float(allPreds[0][i][1])] for i in range(len(allFiles))]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#Generate submission file...download this file and \n#manually upload it here: https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition/submit\nsubmissionFile = pd.DataFrame(guesses,columns=['id','label']).sort_values('id')\nsubmissionFile.to_csv('submissionFile_01March.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":4}