{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.10.13"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":70367,"databundleVersionId":9188054,"sourceType":"competition"}],"dockerImageVersionId":30746,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false},"papermill":{"default_parameters":{},"duration":1087.424982,"end_time":"2024-08-03T13:00:18.164826","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2024-08-03T12:42:10.739844","version":"2.5.0"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Ariel Data Challenge 2024: Introductory model: training\n\nIn this notebook, we show how to train and cross-validate a model. At the end, we save the model so that it can be used for inference in the separate notebook [ADC24 Intro inference](https://www.kaggle.com/code/ambrosm/adc24-intro-inference).\n","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","papermill":{"duration":0.009657,"end_time":"2024-08-03T12:42:14.074227","exception":false,"start_time":"2024-08-03T12:42:14.06457","status":"completed"},"tags":[]}},{"cell_type":"code","source":"import pandas as pd\nimport polars as pl\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport seaborn as sns\nimport scipy.stats\nfrom tqdm import tqdm\nimport pickle\n\nfrom sklearn.model_selection import cross_val_predict\nfrom sklearn.linear_model import Ridge\nfrom sklearn.metrics import r2_score, mean_squared_error","metadata":{"_kg_hide-input":true,"papermill":{"duration":3.023083,"end_time":"2024-08-03T12:42:17.107326","exception":false,"start_time":"2024-08-03T12:42:14.084243","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-12-08T11:56:05.482167Z","iopub.execute_input":"2024-12-08T11:56:05.482584Z","iopub.status.idle":"2024-12-08T11:56:08.653172Z","shell.execute_reply.started":"2024-12-08T11:56:05.482536Z","shell.execute_reply":"2024-12-08T11:56:08.651777Z"},"trusted":true},"outputs":[],"execution_count":1},{"cell_type":"markdown","source":"# A look at the data\n\nWe start by reading the metadata:","metadata":{"papermill":{"duration":0.008428,"end_time":"2024-08-03T12:42:17.180297","exception":false,"start_time":"2024-08-03T12:42:17.171869","status":"completed"},"tags":[]}},{"cell_type":"code","source":"train_adc_info = pd.read_csv('/kaggle/input/ariel-data-challenge-2024/train_adc_info.csv',\n                           index_col='planet_id')\n# test_adc_info = pd.read_csv('/kaggle/input/ariel-data-challenge-2024/test_adc_info.csv',\n#                            index_col='planet_id')\ntrain_labels = pd.read_csv('/kaggle/input/ariel-data-challenge-2024/train_labels.csv',\n                           index_col='planet_id')\nwavelengths = pd.read_csv('/kaggle/input/ariel-data-challenge-2024/wavelengths.csv')\naxis_info = pd.read_parquet('/kaggle/input/ariel-data-challenge-2024/axis_info.parquet')\n","metadata":{"papermill":{"duration":0.188106,"end_time":"2024-08-03T12:42:17.37713","exception":false,"start_time":"2024-08-03T12:42:17.189024","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-12-08T11:56:18.258761Z","iopub.execute_input":"2024-12-08T11:56:18.259432Z","iopub.status.idle":"2024-12-08T11:56:18.597225Z","shell.execute_reply.started":"2024-12-08T11:56:18.259398Z","shell.execute_reply":"2024-12-08T11:56:18.596135Z"},"trusted":true},"outputs":[],"execution_count":2},{"cell_type":"markdown","source":"Some facts about the data:\n- We have 673 planets for training. These planets belong to two different stars.\n- There will be roughly 800 planets for testing (but the test data is hidden).\n- The competition is a multi-output regression task with 283 targets to predict.","metadata":{"papermill":{"duration":0.008486,"end_time":"2024-08-03T12:42:17.394634","exception":false,"start_time":"2024-08-03T12:42:17.386148","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"## The FGS1 data\n\nHaving read the metadata, we'll tackle the FGS1 data (Fine Guidance System). The FGS1 measurements consist of one file per planet (673 files for 673 planets for training). For now, we ignore the calibration files.\n\nEach file contains 135,000 rows of images taken at 0.1 second time steps. Each row is a 32\\*32 image at a single wavelength.\n\nWe read a sample file:","metadata":{"papermill":{"duration":0.008446,"end_time":"2024-08-03T12:42:17.411955","exception":false,"start_time":"2024-08-03T12:42:17.403509","status":"completed"},"tags":[]}},{"cell_type":"code","source":"planet_id = 14485303\nf_signal = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/train/{planet_id}/FGS1_signal.parquet')\nf_signal","metadata":{"papermill":{"duration":1.759363,"end_time":"2024-08-03T12:42:19.180097","exception":false,"start_time":"2024-08-03T12:42:17.420734","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-12-08T11:56:21.311729Z","iopub.execute_input":"2024-12-08T11:56:21.312129Z","iopub.status.idle":"2024-12-08T11:56:23.29905Z","shell.execute_reply.started":"2024-12-08T11:56:21.3121Z","shell.execute_reply":"2024-12-08T11:56:23.297669Z"},"trusted":true},"outputs":[{"execution_count":3,"output_type":"execute_result","data":{"text/plain":"        column_0  column_1  column_2  column_3  column_4  column_5  column_6  \\\n0            315       313       308       301       311       315       307   \n1            286       325       303       309       307       332       300   \n2            304       292       303       318       313       308       300   \n3            312       300       299       347       300       317       320   \n4            324       313       300       334       326       312       319   \n...          ...       ...       ...       ...       ...       ...       ...   \n134995       317       318       312       306       309       321       317   \n134996       312       333       321       337       311       292       315   \n134997       316       311       312       303       290       304       301   \n134998       302       309       313       306       323       315       307   \n134999       300       305       302       325       311       322       331   \n\n        column_7  column_8  column_9  ...  column_1014  column_1015  \\\n0            298       315       320  ...          304          317   \n1            299       334       319  ...          306          315   \n2            316       335       356  ...          329          330   \n3            319       333       350  ...          316          313   \n4            305       341       317  ...          294          300   \n...          ...       ...       ...  ...          ...          ...   \n134995       316       316       330  ...          332          319   \n134996       332       315       321  ...          338          298   \n134997       319       321       338  ...          301          324   \n134998       320       304       340  ...          308          299   \n134999       325       309       339  ...          306          309   \n\n        column_1016  column_1017  column_1018  column_1019  column_1020  \\\n0               304          284          321          312          314   \n1               304          302          312          327          318   \n2               305          314          302          291          314   \n3               310          294          319          298          310   \n4               313          326          334          316          293   \n...             ...          ...          ...          ...          ...   \n134995          310          312          309          327          293   \n134996          312          317          298          304          296   \n134997          298          330          314          328          295   \n134998          324          308          321          294          312   \n134999          301          311          331          308          309   \n\n        column_1021  column_1022  column_1023  \n0               340          297          310  \n1               270          299          302  \n2               323          315          310  \n3               291          287          319  \n4               322          310          305  \n...             ...          ...          ...  \n134995          334          333          317  \n134996          280          308          297  \n134997          332          308          317  \n134998          329          315          304  \n134999          304          300          318  \n\n[135000 rows x 1024 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>column_0</th>\n      <th>column_1</th>\n      <th>column_2</th>\n      <th>column_3</th>\n      <th>column_4</th>\n      <th>column_5</th>\n      <th>column_6</th>\n      <th>column_7</th>\n      <th>column_8</th>\n      <th>column_9</th>\n      <th>...</th>\n      <th>column_1014</th>\n      <th>column_1015</th>\n      <th>column_1016</th>\n      <th>column_1017</th>\n      <th>column_1018</th>\n      <th>column_1019</th>\n      <th>column_1020</th>\n      <th>column_1021</th>\n      <th>column_1022</th>\n      <th>column_1023</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>315</td>\n      <td>313</td>\n      <td>308</td>\n      <td>301</td>\n      <td>311</td>\n      <td>315</td>\n      <td>307</td>\n      <td>298</td>\n      <td>315</td>\n      <td>320</td>\n      <td>...</td>\n      <td>304</td>\n      <td>317</td>\n      <td>304</td>\n      <td>284</td>\n      <td>321</td>\n      <td>312</td>\n      <td>314</td>\n      <td>340</td>\n      <td>297</td>\n      <td>310</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>286</td>\n      <td>325</td>\n      <td>303</td>\n      <td>309</td>\n      <td>307</td>\n      <td>332</td>\n      <td>300</td>\n      <td>299</td>\n      <td>334</td>\n      <td>319</td>\n      <td>...</td>\n      <td>306</td>\n      <td>315</td>\n      <td>304</td>\n      <td>302</td>\n      <td>312</td>\n      <td>327</td>\n      <td>318</td>\n      <td>270</td>\n      <td>299</td>\n      <td>302</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>304</td>\n      <td>292</td>\n      <td>303</td>\n      <td>318</td>\n      <td>313</td>\n      <td>308</td>\n      <td>300</td>\n      <td>316</td>\n      <td>335</td>\n      <td>356</td>\n      <td>...</td>\n      <td>329</td>\n      <td>330</td>\n      <td>305</td>\n      <td>314</td>\n      <td>302</td>\n      <td>291</td>\n      <td>314</td>\n      <td>323</td>\n      <td>315</td>\n      <td>310</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>312</td>\n      <td>300</td>\n      <td>299</td>\n      <td>347</td>\n      <td>300</td>\n      <td>317</td>\n      <td>320</td>\n      <td>319</td>\n      <td>333</td>\n      <td>350</td>\n      <td>...</td>\n      <td>316</td>\n      <td>313</td>\n      <td>310</td>\n      <td>294</td>\n      <td>319</td>\n      <td>298</td>\n      <td>310</td>\n      <td>291</td>\n      <td>287</td>\n      <td>319</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>324</td>\n      <td>313</td>\n      <td>300</td>\n      <td>334</td>\n      <td>326</td>\n      <td>312</td>\n      <td>319</td>\n      <td>305</td>\n      <td>341</td>\n      <td>317</td>\n      <td>...</td>\n      <td>294</td>\n      <td>300</td>\n      <td>313</td>\n      <td>326</td>\n      <td>334</td>\n      <td>316</td>\n      <td>293</td>\n      <td>322</td>\n      <td>310</td>\n      <td>305</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>134995</th>\n      <td>317</td>\n      <td>318</td>\n      <td>312</td>\n      <td>306</td>\n      <td>309</td>\n      <td>321</td>\n      <td>317</td>\n      <td>316</td>\n      <td>316</td>\n      <td>330</td>\n      <td>...</td>\n      <td>332</td>\n      <td>319</td>\n      <td>310</td>\n      <td>312</td>\n      <td>309</td>\n      <td>327</td>\n      <td>293</td>\n      <td>334</td>\n      <td>333</td>\n      <td>317</td>\n    </tr>\n    <tr>\n      <th>134996</th>\n      <td>312</td>\n      <td>333</td>\n      <td>321</td>\n      <td>337</td>\n      <td>311</td>\n      <td>292</td>\n      <td>315</td>\n      <td>332</td>\n      <td>315</td>\n      <td>321</td>\n      <td>...</td>\n      <td>338</td>\n      <td>298</td>\n      <td>312</td>\n      <td>317</td>\n      <td>298</td>\n      <td>304</td>\n      <td>296</td>\n      <td>280</td>\n      <td>308</td>\n      <td>297</td>\n    </tr>\n    <tr>\n      <th>134997</th>\n      <td>316</td>\n      <td>311</td>\n      <td>312</td>\n      <td>303</td>\n      <td>290</td>\n      <td>304</td>\n      <td>301</td>\n      <td>319</td>\n      <td>321</td>\n      <td>338</td>\n      <td>...</td>\n      <td>301</td>\n      <td>324</td>\n      <td>298</td>\n      <td>330</td>\n      <td>314</td>\n      <td>328</td>\n      <td>295</td>\n      <td>332</td>\n      <td>308</td>\n      <td>317</td>\n    </tr>\n    <tr>\n      <th>134998</th>\n      <td>302</td>\n      <td>309</td>\n      <td>313</td>\n      <td>306</td>\n      <td>323</td>\n      <td>315</td>\n      <td>307</td>\n      <td>320</td>\n      <td>304</td>\n      <td>340</td>\n      <td>...</td>\n      <td>308</td>\n      <td>299</td>\n      <td>324</td>\n      <td>308</td>\n      <td>321</td>\n      <td>294</td>\n      <td>312</td>\n      <td>329</td>\n      <td>315</td>\n      <td>304</td>\n    </tr>\n    <tr>\n      <th>134999</th>\n      <td>300</td>\n      <td>305</td>\n      <td>302</td>\n      <td>325</td>\n      <td>311</td>\n      <td>322</td>\n      <td>331</td>\n      <td>325</td>\n      <td>309</td>\n      <td>339</td>\n      <td>...</td>\n      <td>306</td>\n      <td>309</td>\n      <td>301</td>\n      <td>311</td>\n      <td>331</td>\n      <td>308</td>\n      <td>309</td>\n      <td>304</td>\n      <td>300</td>\n      <td>318</td>\n    </tr>\n  </tbody>\n</table>\n<p>135000 rows × 1024 columns</p>\n</div>"},"metadata":{}}],"execution_count":3},{"cell_type":"markdown","source":"Every row of the file corresponds to an image of a star. The images come in pairs, and the second image is lighter than the first one:","metadata":{"papermill":{"duration":0.009711,"end_time":"2024-08-03T12:42:19.199727","exception":false,"start_time":"2024-08-03T12:42:19.190016","status":"completed"},"tags":[]}},{"cell_type":"code","source":"_, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 4))\nsns.heatmap(f_signal.iloc[0].values.reshape(32, 32), ax=ax1, vmin=0, vmax=52000)\nax1.set_aspect('equal')\nsns.heatmap(f_signal.iloc[1].values.reshape(32, 32), ax=ax2, vmin=0, vmax=52000)\nax2.set_aspect('equal')\nplt.suptitle('A pair of FGS1 images')\nplt.show()","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.559852,"end_time":"2024-08-03T12:42:19.769794","exception":false,"start_time":"2024-08-03T12:42:19.209942","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-12-08T11:56:25.848129Z","iopub.execute_input":"2024-12-08T11:56:25.848504Z","iopub.status.idle":"2024-12-08T11:56:26.654011Z","shell.execute_reply.started":"2024-12-08T11:56:25.848478Z","shell.execute_reply":"2024-12-08T11:56:26.652849Z"},"trusted":true},"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1200x400 with 4 Axes>","image/png":"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"},"metadata":{}}],"execution_count":4},{"cell_type":"markdown","source":"To see the time series, we first have to compute the difference between the even and the odd frames to get the net signal (67500 time steps). We then take the mean over all 1024 pixels. The net signal is very noisy, and we smoothen it by computing a moving average. The plot of the smoothened signal clearly shows that the signal intensity is reduced (i.e., the image gets darker) while the planet passes in front of the star (between time steps 23500 and 44000).\n\nThe left diagram shows a planet with a strong reduction of the signal intensity, the right diagram shows a planet with a weak reduction:","metadata":{"papermill":{"duration":0.011386,"end_time":"2024-08-03T12:42:19.791847","exception":false,"start_time":"2024-08-03T12:42:19.780461","status":"completed"},"tags":[]}},{"cell_type":"code","source":"_, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2, 2, sharex=True, figsize=(12, 4))\n\nplanet_id = 14485303\nf_signal = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/train/{planet_id}/FGS1_signal.parquet')\n\nmean_signal = f_signal.values.mean(axis=1)\nnet_signal = mean_signal[1::2] - mean_signal[0::2]\ncum_signal = net_signal.cumsum()\nwindow=800\nsmooth_signal = (cum_signal[window:] - cum_signal[:-window]) / window\n\nax1.set_title('FGS1: time series of planet with strong signal')\nax1.plot(net_signal, label='raw signal')\nax1.legend()\nax3.plot(smooth_signal, color='c', label='smoothened signal')\nax3.legend()\nax3.set_xlabel('time step')\nfor time_step in [20500, 23500, 44000, 47000]:\n    ax3.axvline(time_step, color='gray')\n\nplanet_id = 4249337798\nf_signal = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/train/{planet_id}/FGS1_signal.parquet')\n\nmean_signal = f_signal.values.mean(axis=1)\nnet_signal = mean_signal[1::2] - mean_signal[0::2]\ncum_signal = net_signal.cumsum()\nwindow=800\nsmooth_signal = (cum_signal[window:] - cum_signal[:-window]) / window\n\nax2.set_title('FGS1: time series of planet with weak signal')\nax2.plot(net_signal, label='raw signal')\nax2.legend()\nax4.plot(smooth_signal, color='c', label='smoothened signal')\nax4.legend()\nax4.set_xlabel('time step')\nfor time_step in [20500, 23500, 44000, 47000]:\n    ax4.axvline(time_step, color='gray')\n\n# plt.suptitle('FGS1 time series', y=0.96)\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-12-08T11:56:30.205184Z","iopub.execute_input":"2024-12-08T11:56:30.205577Z","iopub.status.idle":"2024-12-08T11:56:35.376471Z","shell.execute_reply.started":"2024-12-08T11:56:30.205544Z","shell.execute_reply":"2024-12-08T11:56:35.374981Z"},"trusted":true},"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1200x400 with 4 Axes>","image/png":"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"},"metadata":{}}],"execution_count":5},{"cell_type":"markdown","source":"## The AIRS data\n\nAIRS is the other sensor of the satellite. It produces one file per planet as well. Each file contains 11,250 rows of images captured at constant time steps. Each 32 x 356 image has been flattened into 11392 columns.","metadata":{"papermill":{"duration":0.077595,"end_time":"2024-08-03T13:00:12.362301","exception":false,"start_time":"2024-08-03T13:00:12.284706","status":"completed"},"tags":[]}},{"cell_type":"code","source":"planet_id = 4249337798\na_signal = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/train/{planet_id}/AIRS-CH0_signal.parquet')\na_signal","metadata":{"papermill":{"duration":2.313418,"end_time":"2024-08-03T13:00:14.755198","exception":false,"start_time":"2024-08-03T13:00:12.44178","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-12-08T11:56:38.512187Z","iopub.execute_input":"2024-12-08T11:56:38.512581Z","iopub.status.idle":"2024-12-08T11:56:41.411642Z","shell.execute_reply.started":"2024-12-08T11:56:38.51255Z","shell.execute_reply":"2024-12-08T11:56:41.41045Z"},"trusted":true},"outputs":[{"execution_count":6,"output_type":"execute_result","data":{"text/plain":"       column_0  column_1  column_2  column_3  column_4  column_5  column_6  \\\n0           840       833       820       836       821       845       824   \n1           824       818       826       818       843       833       827   \n2           824       818       814       823       824       842       836   \n3           826       834       821       812       819       837       811   \n4           826       817       788       848       831       804       819   \n...         ...       ...       ...       ...       ...       ...       ...   \n11245       816       815       811       812       802       801       825   \n11246       817       834       830       813       829       822       798   \n11247       821       852       817       813       810       801       830   \n11248       820       826       811       803       815       809       809   \n11249       842       826       826       842       840       801       800   \n\n       column_7  column_8  column_9  ...  column_11382  column_11383  \\\n0           830       828       825  ...           825           811   \n1           806       819       846  ...           807           824   \n2           820       815       818  ...           857           806   \n3           833       822       816  ...           840           816   \n4           854       823       826  ...           831           810   \n...         ...       ...       ...  ...           ...           ...   \n11245       814       825       831  ...           830           809   \n11246       828       811       844  ...           829           825   \n11247       819       836       826  ...           807           837   \n11248       810       823       827  ...           821           845   \n11249       803       836       826  ...           815           825   \n\n       column_11384  column_11385  column_11386  column_11387  column_11388  \\\n0               840           820           833           806           808   \n1               822           815           829           827           817   \n2               800           798           848           817           820   \n3               798           825           820           827           811   \n4               820           799           828           860           815   \n...             ...           ...           ...           ...           ...   \n11245           807           826           816           813           799   \n11246           812           820           808           809           819   \n11247           808           822           846           796           833   \n11248           839           827           804           819           810   \n11249           833           843           844           855           802   \n\n       column_11389  column_11390  column_11391  \n0               831           824           826  \n1               828           810           816  \n2               825           819           822  \n3               818           842           830  \n4               815           818           791  \n...             ...           ...           ...  \n11245           841           827           816  \n11246           813           834           810  \n11247           818           816           820  \n11248           813           813           802  \n11249           818           850           828  \n\n[11250 rows x 11392 columns]","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>column_0</th>\n      <th>column_1</th>\n      <th>column_2</th>\n      <th>column_3</th>\n      <th>column_4</th>\n      <th>column_5</th>\n      <th>column_6</th>\n      <th>column_7</th>\n      <th>column_8</th>\n      <th>column_9</th>\n      <th>...</th>\n      <th>column_11382</th>\n      <th>column_11383</th>\n      <th>column_11384</th>\n      <th>column_11385</th>\n      <th>column_11386</th>\n      <th>column_11387</th>\n      <th>column_11388</th>\n      <th>column_11389</th>\n      <th>column_11390</th>\n      <th>column_11391</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>840</td>\n      <td>833</td>\n      <td>820</td>\n      <td>836</td>\n      <td>821</td>\n      <td>845</td>\n      <td>824</td>\n      <td>830</td>\n      <td>828</td>\n      <td>825</td>\n      <td>...</td>\n      <td>825</td>\n      <td>811</td>\n      <td>840</td>\n      <td>820</td>\n      <td>833</td>\n      <td>806</td>\n      <td>808</td>\n      <td>831</td>\n      <td>824</td>\n      <td>826</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>824</td>\n      <td>818</td>\n      <td>826</td>\n      <td>818</td>\n      <td>843</td>\n      <td>833</td>\n      <td>827</td>\n      <td>806</td>\n      <td>819</td>\n      <td>846</td>\n      <td>...</td>\n      <td>807</td>\n      <td>824</td>\n      <td>822</td>\n      <td>815</td>\n      <td>829</td>\n      <td>827</td>\n      <td>817</td>\n      <td>828</td>\n      <td>810</td>\n      <td>816</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>824</td>\n      <td>818</td>\n      <td>814</td>\n      <td>823</td>\n      <td>824</td>\n      <td>842</td>\n      <td>836</td>\n      <td>820</td>\n      <td>815</td>\n      <td>818</td>\n      <td>...</td>\n      <td>857</td>\n      <td>806</td>\n      <td>800</td>\n      <td>798</td>\n      <td>848</td>\n      <td>817</td>\n      <td>820</td>\n      <td>825</td>\n      <td>819</td>\n      <td>822</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>826</td>\n      <td>834</td>\n      <td>821</td>\n      <td>812</td>\n      <td>819</td>\n      <td>837</td>\n      <td>811</td>\n      <td>833</td>\n      <td>822</td>\n      <td>816</td>\n      <td>...</td>\n      <td>840</td>\n      <td>816</td>\n      <td>798</td>\n      <td>825</td>\n      <td>820</td>\n      <td>827</td>\n      <td>811</td>\n      <td>818</td>\n      <td>842</td>\n      <td>830</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>826</td>\n      <td>817</td>\n      <td>788</td>\n      <td>848</td>\n      <td>831</td>\n      <td>804</td>\n      <td>819</td>\n      <td>854</td>\n      <td>823</td>\n      <td>826</td>\n      <td>...</td>\n      <td>831</td>\n      <td>810</td>\n      <td>820</td>\n      <td>799</td>\n      <td>828</td>\n      <td>860</td>\n      <td>815</td>\n      <td>815</td>\n      <td>818</td>\n      <td>791</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>11245</th>\n      <td>816</td>\n      <td>815</td>\n      <td>811</td>\n      <td>812</td>\n      <td>802</td>\n      <td>801</td>\n      <td>825</td>\n      <td>814</td>\n      <td>825</td>\n      <td>831</td>\n      <td>...</td>\n      <td>830</td>\n      <td>809</td>\n      <td>807</td>\n      <td>826</td>\n      <td>816</td>\n      <td>813</td>\n      <td>799</td>\n      <td>841</td>\n      <td>827</td>\n      <td>816</td>\n    </tr>\n    <tr>\n      <th>11246</th>\n      <td>817</td>\n      <td>834</td>\n      <td>830</td>\n      <td>813</td>\n      <td>829</td>\n      <td>822</td>\n      <td>798</td>\n      <td>828</td>\n      <td>811</td>\n      <td>844</td>\n      <td>...</td>\n      <td>829</td>\n      <td>825</td>\n      <td>812</td>\n      <td>820</td>\n      <td>808</td>\n      <td>809</td>\n      <td>819</td>\n      <td>813</td>\n      <td>834</td>\n      <td>810</td>\n    </tr>\n    <tr>\n      <th>11247</th>\n      <td>821</td>\n      <td>852</td>\n      <td>817</td>\n      <td>813</td>\n      <td>810</td>\n      <td>801</td>\n      <td>830</td>\n      <td>819</td>\n      <td>836</td>\n      <td>826</td>\n      <td>...</td>\n      <td>807</td>\n      <td>837</td>\n      <td>808</td>\n      <td>822</td>\n      <td>846</td>\n      <td>796</td>\n      <td>833</td>\n      <td>818</td>\n      <td>816</td>\n      <td>820</td>\n    </tr>\n    <tr>\n      <th>11248</th>\n      <td>820</td>\n      <td>826</td>\n      <td>811</td>\n      <td>803</td>\n      <td>815</td>\n      <td>809</td>\n      <td>809</td>\n      <td>810</td>\n      <td>823</td>\n      <td>827</td>\n      <td>...</td>\n      <td>821</td>\n      <td>845</td>\n      <td>839</td>\n      <td>827</td>\n      <td>804</td>\n      <td>819</td>\n      <td>810</td>\n      <td>813</td>\n      <td>813</td>\n      <td>802</td>\n    </tr>\n    <tr>\n      <th>11249</th>\n      <td>842</td>\n      <td>826</td>\n      <td>826</td>\n      <td>842</td>\n      <td>840</td>\n      <td>801</td>\n      <td>800</td>\n      <td>803</td>\n      <td>836</td>\n      <td>826</td>\n      <td>...</td>\n      <td>815</td>\n      <td>825</td>\n      <td>833</td>\n      <td>843</td>\n      <td>844</td>\n      <td>855</td>\n      <td>802</td>\n      <td>818</td>\n      <td>850</td>\n      <td>828</td>\n    </tr>\n  </tbody>\n</table>\n<p>11250 rows × 11392 columns</p>\n</div>"},"metadata":{}}],"execution_count":6},{"cell_type":"code","source":"a_signal = a_signal.values.reshape(11250, 32, 356)\n\nplt.figure(figsize=(10, 3))\nsns.heatmap(a_signal[1])\nplt.ylabel('spatial dimension')\nplt.xlabel('wavelength dimension')\nplt.show()","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.807236,"end_time":"2024-08-03T13:00:15.817499","exception":false,"start_time":"2024-08-03T13:00:15.010263","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-12-08T11:56:46.362405Z","iopub.execute_input":"2024-12-08T11:56:46.362774Z","iopub.status.idle":"2024-12-08T11:56:46.883002Z","shell.execute_reply.started":"2024-12-08T11:56:46.362744Z","shell.execute_reply":"2024-12-08T11:56:46.881901Z"},"trusted":true},"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 1000x300 with 2 Axes>","image/png":"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"},"metadata":{}}],"execution_count":7},{"cell_type":"markdown","source":"The data again is a time series, and we can see how the star is obscured while the planet is passing in front of it.","metadata":{"papermill":{"duration":0.08019,"end_time":"2024-08-03T13:00:15.979865","exception":false,"start_time":"2024-08-03T13:00:15.899675","status":"completed"},"tags":[]}},{"cell_type":"code","source":"mean_signal = a_signal.mean(axis=2).mean(axis=1)\nnet_signal = mean_signal[1::2] - mean_signal[0::2]\ncum_signal = net_signal.cumsum()\nwindow=80\nsmooth_signal = (cum_signal[window:] - cum_signal[:-window]) / window\n\n_, (ax1, ax2) = plt.subplots(2, 1, sharex=True)\nax1.plot(net_signal, label='raw net signal')\nax1.legend()\nax2.plot(smooth_signal, color='c', label='smoothened net signal')\nax2.legend()\nax2.set_xlabel('time')\nfor time_step in [20500, 23500, 44000, 47000]:\n    ax2.axvline(time_step * 11250 // 135000, color='gray')\nplt.suptitle('AIRS-CH0 time series', y=0.96)\nplt.show()\n","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.727242,"end_time":"2024-08-03T13:00:16.788841","exception":false,"start_time":"2024-08-03T13:00:16.061599","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-12-08T11:56:51.158347Z","iopub.execute_input":"2024-12-08T11:56:51.158695Z","iopub.status.idle":"2024-12-08T11:56:51.804329Z","shell.execute_reply.started":"2024-12-08T11:56:51.158668Z","shell.execute_reply":"2024-12-08T11:56:51.802903Z"},"trusted":true},"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 2 Axes>","image/png":"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"},"metadata":{}}],"execution_count":8},{"cell_type":"markdown","source":"# Reading the data\n\nWe now read the FGS1 data and the AIRS-CH0 data for all 673 training planets. As the dataset doesn't fit into RAM completely, we keep only two one-dimensional time series for every planet. At the end we'll have\n1. A time series with 67500 steps per planet taken from the FGS1 data, and\n2. A time series with 5625 steps per planet taken from the AIRS-CH0 data.\n\nWe use the Jupyter `%%writefile` cell magic to save the function code to a file. This ensures that the inference notebook will process the test data in exactly the same way as this notebook processes the training data.","metadata":{"papermill":{"duration":0.011189,"end_time":"2024-08-03T12:42:20.928036","exception":false,"start_time":"2024-08-03T12:42:20.916847","status":"completed"},"tags":[]}},{"cell_type":"code","source":"%%writefile f_read_and_preprocess.py\n\ndef f_read_and_preprocess(dataset, adc_info, planet_ids):\n    \"\"\"Read the FGS1 files for all planet_ids and extract the time series.\n    \n    Parameters\n    dataset: 'train' or 'test'\n    adc_info: metadata dataframe, either train_adc_info or test_adc_info\n    planet_ids: list of planet ids\n    \n    Returns\n    dataframe with one row per planet_id and 67500 values per row\n    \n    \"\"\"\n    f_raw_train = np.full((len(planet_ids), 67500), np.nan, dtype=np.float32)\n    for i, planet_id in tqdm(list(enumerate(planet_ids))):\n        f_signal = pl.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/{planet_id}/FGS1_signal.parquet')\n        mean_signal = f_signal.cast(pl.Int32).sum_horizontal().cast(pl.Float32).to_numpy() / 1024 # mean over the 32*32 pixels\n        net_signal = mean_signal[1::2] - mean_signal[0::2]\n        f_raw_train[i] = net_signal\n    return f_raw_train\n    ","metadata":{"papermill":{"duration":1067.258124,"end_time":"2024-08-03T13:00:08.197814","exception":false,"start_time":"2024-08-03T12:42:20.93969","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-12-08T11:56:57.289463Z","iopub.execute_input":"2024-12-08T11:56:57.28984Z","iopub.status.idle":"2024-12-08T11:56:57.296768Z","shell.execute_reply.started":"2024-12-08T11:56:57.289812Z","shell.execute_reply":"2024-12-08T11:56:57.295404Z"},"trusted":true},"outputs":[{"name":"stdout","text":"Overwriting f_read_and_preprocess.py\n","output_type":"stream"}],"execution_count":10},{"cell_type":"code","source":"%%time\nexec(open('f_read_and_preprocess.py', 'r').read())\nf_raw_train = f_read_and_preprocess('train', train_adc_info, train_labels.index)\nwith open('f_raw_train.pickle', 'wb') as f:\n    pickle.dump(f_raw_train, f)\n","metadata":{"papermill":{"duration":1067.258124,"end_time":"2024-08-03T13:00:08.197814","exception":false,"start_time":"2024-08-03T12:42:20.93969","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-08-04T10:16:27.461497Z","iopub.execute_input":"2024-08-04T10:16:27.461961Z","iopub.status.idle":"2024-08-04T10:27:09.214198Z","shell.execute_reply.started":"2024-08-04T10:16:27.461928Z","shell.execute_reply":"2024-08-04T10:27:09.212147Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%writefile a_read_and_preprocess.py\ndef a_read_and_preprocess(dataset, adc_info, planet_ids):\n    \"\"\"Read the AIRS-CH0 files for all planet_ids and extract the time series.\n    \n    Parameters\n    dataset: 'train' or 'test'\n    adc_info: metadata dataframe, either train_adc_info or test_adc_info\n    planet_ids: list of planet ids\n    \n    Returns\n    dataframe with one row per planet_id and 5625 values per row\n    \n    \"\"\"\n    a_raw_train = np.full((len(planet_ids), 5625), np.nan, dtype=np.float32)\n    for i, planet_id in tqdm(list(enumerate(planet_ids))):\n        signal = pl.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/{planet_id}/AIRS-CH0_signal.parquet')\n        mean_signal = signal.cast(pl.Int32).sum_horizontal().cast(pl.Float32).to_numpy() / (32*356) # mean over the 32*356 pixels\n        net_signal = mean_signal[1::2] - mean_signal[0::2]\n        a_raw_train[i] = net_signal\n    return a_raw_train\n    ","metadata":{"execution":{"iopub.status.busy":"2024-08-04T12:27:27.791719Z","iopub.execute_input":"2024-08-04T12:27:27.792857Z","iopub.status.idle":"2024-08-04T12:27:27.800511Z","shell.execute_reply.started":"2024-08-04T12:27:27.792811Z","shell.execute_reply":"2024-08-04T12:27:27.799003Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%time\nexec(open('a_read_and_preprocess.py', 'r').read())\na_raw_train = a_read_and_preprocess('train', train_adc_info, train_labels.index)\nwith open('a_raw_train.pickle', 'wb') as f:\n    pickle.dump(a_raw_train, f)\n","metadata":{"execution":{"iopub.status.busy":"2024-08-04T10:49:43.17432Z","iopub.execute_input":"2024-08-04T10:49:43.1748Z","iopub.status.idle":"2024-08-04T11:10:07.5598Z","shell.execute_reply.started":"2024-08-04T10:49:43.174748Z","shell.execute_reply":"2024-08-04T11:10:07.557469Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"As a plausibility check, we plot the means of all time series:","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize=(6, 2))\nplt.plot(f_raw_train.mean(axis=0))\nfor time_step in [20500, 23500, 44000, 47000]:\n    plt.axvline(time_step, color='gray')\nplt.xlabel('time step')\nplt.title('FGS1: Overall mean')\nplt.show()\n\nplt.figure(figsize=(6, 2))\nplt.plot(a_raw_train.mean(axis=0))\nfor time_step in [20500, 23500, 44000, 47000]:\n    plt.axvline(time_step * 11250 // 135000, color='gray')\nplt.xlabel('time step')\nplt.title('AIRS-CH0: Overall mean')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-08-04T11:21:05.261032Z","iopub.execute_input":"2024-08-04T11:21:05.262209Z","iopub.status.idle":"2024-08-04T11:21:05.753651Z","shell.execute_reply.started":"2024-08-04T11:21:05.262167Z","shell.execute_reply":"2024-08-04T11:21:05.752301Z"},"_kg_hide-input":true,"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Feature engineering\n\nWe want to know how much darker the images get when the planet obscures the star. The time series diagrams above show that the planets reduce the brightness of the stars (on average) by 0.2 % (from 228.2 to 227.6 or from 1371 to 1368).","metadata":{}},{"cell_type":"code","source":"%%writefile feature_engineering.py\n\ndef feature_engineering(f_raw, a_raw):\n    \"\"\"Create a dataframe with two features from the raw data.\n    \n    Parameters:\n    f_raw: ndarray of shape (n_planets, 67500)\n    a_raw: ndarray of shape (n_planets, 5625)\n    \n    Return value:\n    df: DataFrame of shape (n_planets, 2)\n    \"\"\"\n    obscured = f_raw[:, 23500:44000].mean(axis=1)\n    unobscured = (f_raw[:, :20500].mean(axis=1) + f_raw[:, 47000:].mean(axis=1)) / 2\n    f_relative_reduction = (unobscured - obscured) / unobscured\n    obscured = a_raw[:, 1958:3666].mean(axis=1)\n    unobscured = (a_raw[:, :1708].mean(axis=1) + a_raw[:, 3916:].mean(axis=1)) / 2\n    a_relative_reduction = (unobscured - obscured) / unobscured\n\n    df = pd.DataFrame({'a_relative_reduction': a_relative_reduction,\n                       'f_relative_reduction': f_relative_reduction})\n    \n    return df\n","metadata":{"execution":{"iopub.status.busy":"2024-08-04T11:49:32.362734Z","iopub.execute_input":"2024-08-04T11:49:32.363268Z","iopub.status.idle":"2024-08-04T11:49:32.371284Z","shell.execute_reply.started":"2024-08-04T11:49:32.363232Z","shell.execute_reply":"2024-08-04T11:49:32.370079Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"exec(open('feature_engineering.py', 'r').read())\n\ntrain = feature_engineering(f_raw_train, a_raw_train)","metadata":{"execution":{"iopub.status.busy":"2024-08-04T11:33:15.805608Z","iopub.execute_input":"2024-08-04T11:33:15.806053Z","iopub.status.idle":"2024-08-04T11:33:15.833728Z","shell.execute_reply.started":"2024-08-04T11:33:15.806018Z","shell.execute_reply":"2024-08-04T11:33:15.832575Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"The following scatterplot shows a strong correlation between the signal reduction when the planet is in front of the star and one of the targets we want to predict. The other targets have a similarly high correlation.","metadata":{"papermill":{"duration":0.073746,"end_time":"2024-08-03T13:00:08.349433","exception":false,"start_time":"2024-08-03T13:00:08.275687","status":"completed"},"tags":[]}},{"cell_type":"code","source":"\ncolor_array = np.array(plt.rcParams['axes.prop_cycle'].by_key()['color'])\nplt.scatter(train.a_relative_reduction, train_labels.wl_1, s=15, alpha=0.5,\n            c=color_array[train_adc_info.star])\nplt.xlabel('relative signal reduction when planet is in front')\nplt.ylabel('target')\nplt.title('Correlation between relative signal reduction and target')\nplt.gca().set_aspect('equal')\npoints = [plt.Line2D([0], [0], label=f'star {i}', marker='o', markersize=3,\n         markeredgecolor=color_array[i], markerfacecolor=color_array[i], linestyle='') for i in range(2)]\n\nplt.legend(handles=points)\nplt.show()","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.478644,"end_time":"2024-08-03T13:00:08.902093","exception":false,"start_time":"2024-08-03T13:00:08.423449","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-08-04T11:33:18.162145Z","iopub.execute_input":"2024-08-04T11:33:18.162554Z","iopub.status.idle":"2024-08-04T11:33:18.521622Z","shell.execute_reply.started":"2024-08-04T11:33:18.162523Z","shell.execute_reply":"2024-08-04T11:33:18.520319Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# The model and the cross-validation\n\nTo keep things simple, we predict the targets with ridge regression.\n\nWe are interested in three cross-validation metrics:\n1. The R2 score is above 0.9, which confirms the correlation we've seen in the scatterplot.\n2. The root mean squared error will be the predicted uncertainty.\n3. The competition metric gives an indication of the leaderboard score. Unfortunately the competition metric depends on the value of `sigma_true`, which I don't know.","metadata":{"papermill":{"duration":0.076791,"end_time":"2024-08-03T13:00:09.056736","exception":false,"start_time":"2024-08-03T13:00:08.979945","status":"completed"},"tags":[]}},{"cell_type":"code","source":"model = Ridge(alpha=1e-12)\n\noof_pred = cross_val_predict(model, train, train_labels)\n\nprint(f\"# R2 score: {r2_score(train_labels, oof_pred):.3f}\")\nsigma_pred = mean_squared_error(train_labels, oof_pred, squared=False)\nprint(f\"# Root mean squared error: {sigma_pred:.6f}\")\n# R2 score: 0.971\n# Root mean squared error: 0.000293","metadata":{"papermill":{"duration":0.700113,"end_time":"2024-08-03T13:00:09.837053","exception":false,"start_time":"2024-08-03T13:00:09.13694","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-08-04T11:33:20.382678Z","iopub.execute_input":"2024-08-04T11:33:20.383118Z","iopub.status.idle":"2024-08-04T11:33:20.508765Z","shell.execute_reply.started":"2024-08-04T11:33:20.383083Z","shell.execute_reply":"2024-08-04T11:33:20.507443Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"col = 1\nplt.scatter(oof_pred[:,col], train_labels.iloc[:,col], s=15, c='lightgreen')\nplt.gca().set_aspect('equal')\nplt.xlabel('y_pred')\nplt.ylabel('y_true')\nplt.title('Comparing y_true and y_pred')\nplt.show()","metadata":{"papermill":{"duration":0.700113,"end_time":"2024-08-03T13:00:09.837053","exception":false,"start_time":"2024-08-03T13:00:09.13694","status":"completed"},"tags":[],"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-08-04T11:33:24.335234Z","iopub.execute_input":"2024-08-04T11:33:24.33565Z","iopub.status.idle":"2024-08-04T11:33:24.628829Z","shell.execute_reply.started":"2024-08-04T11:33:24.335622Z","shell.execute_reply":"2024-08-04T11:33:24.627451Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%writefile competition_score.py\n# Adapted from https://www.kaggle.com/code/metric/ariel-gaussian-log-likelihood\nclass ParticipantVisibleError(Exception):\n    pass\n\ndef competition_score(\n        solution: pd.DataFrame,\n        submission: pd.DataFrame,\n        naive_mean: float,\n        naive_sigma: float,\n        sigma_true: float,\n        row_id_column_name='planet_id',\n    ) -> float:\n    '''\n    This is a Gaussian Log Likelihood based metric. For a submission, which contains the predicted mean (x_hat) and variance (x_hat_std),\n    we calculate the Gaussian Log-likelihood (GLL) value to the provided ground truth (x). We treat each pair of x_hat,\n    x_hat_std as a 1D gaussian, meaning there will be 283 1D gaussian distributions, hence 283 values for each test spectrum,\n    the GLL value for one spectrum is the sum of all of them.\n\n    Inputs:\n        - solution: Ground Truth spectra (from test set)\n            - shape: (nsamples, n_wavelengths)\n        - submission: Predicted spectra and errors (from participants)\n            - shape: (nsamples, n_wavelengths*2)\n        naive_mean: (float) mean from the train set.\n        naive_sigma: (float) standard deviation from the train set.\n        sigma_true: (float) essentially sets the scale of the outputs.\n    '''\n\n    del solution[row_id_column_name]\n    del submission[row_id_column_name]\n\n    if submission.min().min() < 0:\n        raise ParticipantVisibleError('Negative values in the submission')\n    for col in submission.columns:\n        if not pd.api.types.is_numeric_dtype(submission[col]):\n            raise ParticipantVisibleError(f'Submission column {col} must be a number')\n\n    n_wavelengths = len(solution.columns)\n    if len(submission.columns) != n_wavelengths*2:\n        raise ParticipantVisibleError('Wrong number of columns in the submission')\n\n    y_pred = submission.iloc[:, :n_wavelengths].values\n    # Set a non-zero minimum sigma pred to prevent division by zero errors.\n    sigma_pred = np.clip(submission.iloc[:, n_wavelengths:].values, a_min=10**-15, a_max=None)\n    y_true = solution.values\n\n    GLL_pred = np.sum(scipy.stats.norm.logpdf(y_true, loc=y_pred, scale=sigma_pred))\n    GLL_true = np.sum(scipy.stats.norm.logpdf(y_true, loc=y_true, scale=sigma_true * np.ones_like(y_true)))\n    GLL_mean = np.sum(scipy.stats.norm.logpdf(y_true, loc=naive_mean * np.ones_like(y_true), scale=naive_sigma * np.ones_like(y_true)))\n\n    submit_score = (GLL_pred - GLL_mean)/(GLL_true - GLL_mean)\n    return float(GLL_pred)","metadata":{"_kg_hide-input":true,"papermill":{"duration":0.029243,"end_time":"2024-08-03T12:42:17.162838","exception":false,"start_time":"2024-08-03T12:42:17.133595","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-08-04T11:33:25.777887Z","iopub.execute_input":"2024-08-04T11:33:25.778327Z","iopub.status.idle":"2024-08-04T11:33:25.787298Z","shell.execute_reply.started":"2024-08-04T11:33:25.778293Z","shell.execute_reply":"2024-08-04T11:33:25.78591Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%%writefile postprocessing.py\n\ndef postprocessing(pred_array, index, sigma_pred):\n    \"\"\"Create a submission dataframe from its components\n    \n    Parameters:\n    pred_array: ndarray of shape (n_samples, 283)\n    index: pandas.Index of length n_samples with name 'planet_id'\n    sigma_pred: float\n    \n    Return value:\n    df: DataFrame of shape (n_samples, 566) with planet_id as index\n    \"\"\"\n    return pd.concat([pd.DataFrame(pred_array.clip(0, None), index=index, columns=wavelengths.columns),\n                      pd.DataFrame(sigma_pred, index=index, columns=[f\"sigma_{i}\" for i in range(1, 284)])],\n                     axis=1)\n\n","metadata":{"execution":{"iopub.status.busy":"2024-08-04T11:33:27.453077Z","iopub.execute_input":"2024-08-04T11:33:27.453955Z","iopub.status.idle":"2024-08-04T11:33:27.46076Z","shell.execute_reply.started":"2024-08-04T11:33:27.453914Z","shell.execute_reply":"2024-08-04T11:33:27.459579Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"exec(open('competition_score.py', 'r').read())\nexec(open('postprocessing.py', 'r').read())\n\noof_df = postprocessing(oof_pred, train_adc_info.index, sigma_pred)\ndisplay(oof_df)\n\ngll_score = competition_score(train_labels.copy().reset_index(),\n                              oof_df.copy().reset_index(),\n                              naive_mean=train_labels.values.mean(),\n                              naive_sigma=train_labels.values.std(),\n                              sigma_true=0.000003)\nprint(f\"# Estimated competition score: {gll_score:.3f}\")\n# Estimated competition score: 0.259","metadata":{"papermill":{"duration":0.231627,"end_time":"2024-08-03T13:00:10.149224","exception":false,"start_time":"2024-08-03T13:00:09.917597","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-08-04T11:33:28.166304Z","iopub.execute_input":"2024-08-04T11:33:28.166706Z","iopub.status.idle":"2024-08-04T11:33:28.266475Z","shell.execute_reply.started":"2024-08-04T11:33:28.166678Z","shell.execute_reply":"2024-08-04T11:33:28.265186Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Refitting and saving the model","metadata":{}},{"cell_type":"code","source":"# Refit the model to the full dataset\nmodel.fit(train, train_labels)\nwith open('model.pickle', 'wb') as f:\n    pickle.dump(model, f)\nwith open('sigma_pred.pickle', 'wb') as f:\n    pickle.dump(sigma_pred, f)\n","metadata":{"execution":{"iopub.status.busy":"2024-08-04T13:15:17.228909Z","iopub.execute_input":"2024-08-04T13:15:17.229421Z","iopub.status.idle":"2024-08-04T13:15:17.253336Z","shell.execute_reply.started":"2024-08-04T13:15:17.229387Z","shell.execute_reply":"2024-08-04T13:15:17.251897Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Submission","metadata":{"papermill":{"duration":0.077479,"end_time":"2024-08-03T13:00:10.305108","exception":false,"start_time":"2024-08-03T13:00:10.227629","status":"completed"},"tags":[]}},{"cell_type":"code","source":"# Load the data\ntest_adc_info = pd.read_csv('/kaggle/input/ariel-data-challenge-2024/test_adc_info.csv',\n                           index_col='planet_id')\nsample_submission = pd.read_csv('/kaggle/input/ariel-data-challenge-2024/sample_submission.csv',\n                                index_col='planet_id')\nf_raw_test = f_read_and_preprocess('test', test_adc_info, sample_submission.index)\na_raw_test = a_read_and_preprocess('test', test_adc_info, sample_submission.index)\ntest = feature_engineering(f_raw_test, a_raw_test)\n\n# Load the model\nwith open('model.pickle', 'rb') as f:\n    model = pickle.load(f)\nwith open('sigma_pred.pickle', 'rb') as f:\n    sigma_pred = pickle.load(f)\n\n# Predict\ntest_pred = model.predict(test)\n\n# Package into submission file\nsub_df = postprocessing(test_pred, sample_submission.index, sigma_pred)\ndisplay(sub_df)\nsub_df.to_csv('submission.csv')\n#!head submission.csv","metadata":{"papermill":{"duration":1.822768,"end_time":"2024-08-03T13:00:12.204995","exception":false,"start_time":"2024-08-03T13:00:10.382227","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-08-04T13:15:48.046438Z","iopub.execute_input":"2024-08-04T13:15:48.046918Z","iopub.status.idle":"2024-08-04T13:15:51.037458Z","shell.execute_reply.started":"2024-08-04T13:15:48.046886Z","shell.execute_reply":"2024-08-04T13:15:51.036278Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{},"outputs":[],"execution_count":null}]}