{"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":"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nfrom tqdm import tqdm\n\n\ndef merge1(submit_file, sub_sample_file):\n    \"\"\"merge two csv files.\"\"\"\n    # reading submission files\n    my_submission_df = pd.read_csv(submit_file)\n    sample_submission_df = pd.read_csv(sub_sample_file)\n    \n    imageId2Str = {row['ID']: row['PredictionString'] \n                   for idx, row in my_submission_df.iterrows()}\n    for img_id, pred_str in tqdm(imageId2Str.items(), total=len(imageId2Str)):\n        row_idx = sample_submission_df[sample_submission_df.ID == img_id].index.tolist()[0]\n        sample_submission_df.loc[row_idx, 'PredictionString'] = pred_str\n    return sample_submission_df\n        \n\nmy_submission_df = '../input/offline-csv/offinle_sub.csv'\nsample_submission_df = '../input/hpa-single-cell-image-classification/sample_submission.csv'\n\nsub = merge1(my_submission_df, sample_submission_df)\nprint(sub.head())\nsub.to_csv('submission.csv', index=False)","metadata":{},"execution_count":null,"outputs":[]}]}