{"cells":[{"metadata":{"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 * \nfrom fastai import * \nimport pandas as pd \nimport numpy as np","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = Path('../input/cassava-leaf-disease-classification/train_images')\ntest_data = Path('../input/cassava-leaf-disease-classification/test_images')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Getting the labels \n\ndf = pd.read_csv('../input/cassava-leaf-disease-classification/train.csv')\ndf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Getting the filenames \n\nfns_train = get_image_files(train_data)\nfns_test = get_image_files(test_data)\n\nlen(fns_train) , len(fns_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fns_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Transforms \n\nitem_tfms = RandomResizedCrop(460, min_scale=0.75),\nbatch_tfms = [*aug_transforms(size=224, max_warp=0. , max_zoom= 0.8 ), Normalize.from_stats(*imagenet_stats)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Building a DataBlock \n\n\ncassava = DataBlock(blocks=(ImageBlock, CategoryBlock),\n                   get_x=ColReader(0, pref=train_data),\n                   splitter=RandomSplitter(),\n                   get_y=ColReader(1),\n                   item_tfms = item_tfms,\n                   batch_tfms = batch_tfms ) ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cassava.summary(df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Putting into a dataloader \n\ntrain_dls = cassava.dataloaders(df , bs = 32)\ntrain_dls.show_batch(figsize = (15 , 9))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n# Creating a learner \n\n# learn = cnn_learner(train_dls , alexnet  , metrics = [error_rate , accuracy] , pretrained = False )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn_inf = load_learner('../input/vgg-19/export_2.pkl', cpu = False)\nlearn_inf","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Creating a test dataloader \n\ntest_dl = train_dls.test_dl(fns_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Getting predictions with inference \ntest_pred = learn_inf.get_preds(dl = test_dl)\ntest_pred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Getting in the Sample Submission File \nsample_sub = pd.read_csv('../input/cassava-leaf-disease-classification/sample_submission.csv')\nsample_sub","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Getting our predictions inside a dataframe\n\ntest_pred_max = test_pred[0].argmax(dim=1)\npred_labels = [train_dls.vocab[o] for o in test_pred_max]\nsub = pd.DataFrame({'Image_Id':test_dl.items,'label':pred_labels})\nsub","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub['Image_Id'] = sub['Image_Id'].astype(str).str.replace('../input/cassava-leaf-disease-classification/test_images/' , '')\nsub","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.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":4}