{"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":"# 5. 1.0 submission: submitting the test file\n### Airbus Ship Detection Challenge - A quick overview for computer vision noobs\n\n \n\nHi, and welcome! This is the fifth kernel of the series `Airbus Ship Detection Challenge - A quick overview for computer vision noobs.` This short and trivial kernel creates a 1.0 submission using the data shared by the Challenge organizers in response to the discovery of an important data leak.\n\n\nThe full series consist of the following notebooks:\n1. [Loading and visualizing the images](https://www.kaggle.com/julian3833/1-loading-and-visualizing-the-images)\n2. [Understanding and plotting rle bounding boxes](https://www.kaggle.com/julian3833/2-understanding-and-plotting-rle-bounding-boxes) \n3. [Basic exploratory analysis](https://www.kaggle.com/julian3833/3-basic-exploratory-analysis)\n4. [Exploring public models](https://www.kaggle.com/julian3833/4-exploring-models-shared-by-the-community)\n5. *[1.0 submission: submitting the test file](https://www.kaggle.com/julian3833/5-1-0-submission-submitting-the-test-file)*\n","metadata":{"_uuid":"87e2845b5d029ca1cfc46c352e9c6b6100e1b261"}},{"cell_type":"markdown","source":"## 1. Context","metadata":{"_uuid":"6c517aae87a0027dcdb835d3665867e1ea055fbf"}},{"cell_type":"markdown","source":"As we will discuss in a *future notebook* of the series, a severe [data leakage](https://www.kaggle.com/c/airbus-ship-detection/discussion/64355) was reported on August 28th, trivializing the full competition. The organizers [recognized the leak ](https://www.kaggle.com/c/airbus-ship-detection/discussion/64388) very fast and proposed a plan to address the situation. Following that plan, they [released the segmentations for the test set](https://www.kaggle.com/c/airbus-ship-detection/discussion/64702) and will soon provide a new test set and reset the scoreboard.\n\nUntil this reset, we can trivially generate a 1.0 scoring submission just resending the `test_ship_segmentations.csv` file as follows.","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true}},{"cell_type":"markdown","source":"## 2. Submission","metadata":{"_uuid":"808c5b12f90cab0252eca6e5328420f42e29bdea"}},{"cell_type":"code","source":"import os\nimport pandas as pd\n\ntest_files = [f for f in os.listdir(\"../input/test_v2/\")]\ndf = pd.read_csv(\"../input/test_ship_segmentations.csv\")\ndf = df[df['ImageId'].isin(test_files)].drop_duplicates(subset=\"ImageId\")\ndf.to_csv(\"submission.csv\", index=False)\nlen(df)","metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","execution":{"iopub.status.busy":"2021-08-14T16:37:13.08135Z","iopub.execute_input":"2021-08-14T16:37:13.081637Z","iopub.status.idle":"2021-08-14T16:37:13.89154Z","shell.execute_reply.started":"2021-08-14T16:37:13.081599Z","shell.execute_reply":"2021-08-14T16:37:13.89047Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!head submission.csv","metadata":{"_uuid":"932b1767ce20ec61dae65dc0a9ba1fa683e537cb","execution":{"iopub.status.busy":"2021-08-14T16:33:27.892655Z","iopub.status.idle":"2021-08-14T16:33:27.893015Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### References\n* [Severe leak](https://www.kaggle.com/c/airbus-ship-detection/discussion/64355)\n* [Test Segmentations Now Available](https://www.kaggle.com/c/airbus-ship-detection/discussion/64702)\n* [Data Leak and Next Steps](https://www.kaggle.com/c/airbus-ship-detection/discussion/64388)\n\n\n### What's next?\nThis is the last notebook  of the series for now. Stay tuned, we are currently working on a notebook which aims to understand and exploit the leak (not submitting the shared solution but generating it from the leakage itself)!","metadata":{"_uuid":"577a41167767d37a3ba4bd80edbfda4caeed7428"}}]}