{"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":"markdown","source":"## Simple Exploratory Data Analysis and Submission file","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd\nimport os","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load train.csv file with the image filenames and labels\ny_train = pd.read_csv('/kaggle/input/plant-pathology-2021-fgvc8/train.csv')\ny_train","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"file_path_test = '/kaggle/input/plant-pathology-2021-fgvc8/test_images'\ntest_filenames = os.listdir(file_path_test)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sumb_sample = pd.read_csv('../input/plant-pathology-2021-fgvc8/sample_submission.csv')\nsumb_sample","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"subm = [(item, 'frog_eye_leaf_spot complex') for item in test_filenames]\nsubm","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.DataFrame(subm, columns= ['image', 'labels'])\nsubmission.set_index('image', inplace = True)\nsubmission.to_csv('./submission.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submited = pd.read_csv('./submission.csv')\nsubmited","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# # Simple bar plot indicating 12 classes\n# fig, ax = plt.subplots(figsize= (15,5))\n# ax.barh(gb.index, gb)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# # The pie of labels\n# fig, ax = plt.subplots(figsize= (10,10))\n# ax.pie(gb, labels= gb.index , autopct='%1.1f%%')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"As you can see, there are 12 classes unevenly distribuited.","metadata":{}},{"cell_type":"markdown","source":"### In order to figure out if private images are similar, you can produce a one-single-class submission file and check the score","metadata":{}},{"cell_type":"code","source":"# # create list of tuples (filename, single label)\n# subm = [(item, 'complex') for item in y_train['image']]\n# subm[:10]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# # create submission file\n# submission = pd.DataFrame(subm, columns= ['image', 'labels'])\n# submission.set_index('image', inplace = True)\n# submission.to_csv('./submission.csv')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# # Check the file before submission\n# submited = pd.read_csv('./submission.csv')\n# submited\n# # All labels are the same","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## When you submit this file you can get 0.112\n#### Don't forget to disable internet on right panel > settings > Internet of your notebook","metadata":{}}]}