{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":14774,"databundleVersionId":875431,"sourceType":"competition"},{"sourceId":2819730,"sourceType":"datasetVersion","datasetId":1723812}],"dockerImageVersionId":31239,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\nimport os\n\n# --- LOAD CSV FILES ---\n\n# Messidor\nmessidor_csv = pd.read_csv(\"/kaggle/input/messidor2preprocess/messidor_data.csv\")\nprint(\"Messidor CSV columns:\", messidor_csv.columns.tolist())\nprint(\"Messidor shape:\", messidor_csv.shape)\n\n# APTOS\naptos_csv = pd.read_csv(\"/kaggle/input/aptos2019-blindness-detection/train.csv\")\nprint(\"APTOS CSV columns:\", aptos_csv.columns.tolist())\nprint(\"APTOS shape:\", aptos_csv.shape)\n\n\n# --- CREATE IMAGE PATHS ---\n\n# Messidor image folder\nmessidor_images = \"/kaggle/input/messidor2preprocess/messidor-2\"\n\nmessidor_csv[\"image_path\"] = messidor_csv[\"id_code\"].apply(\n    lambda x: f\"{messidor_images}/{x}.png\"\n)\n\n# APTOS image folder\naptos_images = \"/kaggle/input/aptos2019-blindness-detection/train_images\"\n\naptos_csv[\"image_path\"] = aptos_csv[\"id_code\"].apply(\n    lambda x: f\"{aptos_images}/{x}.png\"\n)\n\n\n# --- MATCH LABEL COLUMN NAMES ---\n\n# Both have 'diagnosis' already\nmessidor_csv = messidor_csv.rename(columns={\"diagnosis\": \"label\"})\naptos_csv = aptos_csv.rename(columns={\"diagnosis\": \"label\"})\n\n\n# --- KEEP ONLY FINAL COLUMNS ---\n\nmessidor_final = messidor_csv[[\"image_path\", \"label\"]]\naptos_final   = aptos_csv[[\"image_path\", \"label\"]]\n\nprint(\"Messidor final shape:\", messidor_final.shape)\nprint(\"APTOS final shape:\", aptos_final.shape)\n\n\n# --- COMBINE DATASETS ---\n\ncombined_csv = pd.concat([messidor_final, aptos_final], ignore_index=True)\nprint(\"Combined shape:\", combined_csv.shape)\n\n\n# --- SAVE COMBINED CSV ---\n\ncombined_csv.to_csv(\"/kaggle/working/retinal_combined.csv\", index=False)\nprint(\" Saved: /kaggle/working/retinal_combined.csv\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-12-30T08:15:01.131138Z","iopub.execute_input":"2025-12-30T08:15:01.131439Z","iopub.status.idle":"2025-12-30T08:15:01.188903Z","shell.execute_reply.started":"2025-12-30T08:15:01.131414Z","shell.execute_reply":"2025-12-30T08:15:01.187733Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"combined_csv.to_csv(\"/kaggle/working/retinal_combined.csv\", index=False)","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}