{"cells":[{"metadata":{},"cell_type":"markdown","source":"A copy of Giba's simple baseline (https://www.kaggle.com/titericz/simple-baseline), appending the information about the dimensions of the image","execution_count":null},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom sklearn.metrics import roc_auc_score\nimport matplotlib.pyplot as plt\n\nimport os\nimport imagesize","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/siim-isic-melanoma-classification/train.csv')\ntest  = pd.read_csv('../input/siim-isic-melanoma-classification/test.csv')\nsub   = pd.read_csv('../input/siim-isic-melanoma-classification/sample_submission.csv')\n\ntrain.shape, test.shape, sub.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['sex'] = train['sex'].fillna('na')\ntrain['age_approx'] = train['age_approx'].fillna(0)\ntrain['anatom_site_general_challenge'] = train['anatom_site_general_challenge'].fillna('na')\n\ntest['sex'] = test['sex'].fillna('na')\ntest['age_approx'] = test['age_approx'].fillna(0)\ntest['anatom_site_general_challenge'] = test['anatom_site_general_challenge'].fillna('na')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"im_shape_test = []\nim_shape_train = []\n\nfor i in range(train.shape[0]):\n    im_shape_train.append(imagesize.get('../input/siim-isic-melanoma-classification/jpeg/train/'+train['image_name'][i]+'.jpg'))\nfor i in range(test.shape[0]):\n    im_shape_test.append(imagesize.get('../input/siim-isic-melanoma-classification/jpeg/test/'+test['image_name'][i]+'.jpg'))\n    \n\ntrain['dim'] = im_shape_train\ntest['dim'] = im_shape_test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.groupby('dim')['target'].count().reset_index(name='N').sort_values('N', ascending=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"L = 15\nfeat = ['sex','age_approx','anatom_site_general_challenge', 'dim']\n\nM = train.target.mean()\nte = train.groupby(feat)['target'].agg(['mean','count']).reset_index()\nte['ll'] = ((te['mean']*te['count'])+(M*L))/(te['count']+L)\ndel te['mean'], te['count']\n\ntest = test.merge( te, on=feat, how='left' )\ntest['ll'] = test['ll'].fillna(M)\n\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.target = test.ll.values\nsub.head(10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.to_csv( 'submission.csv', index=False )","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}