{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":70367,"databundleVersionId":9188054,"sourceType":"competition"}],"dockerImageVersionId":30746,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport seaborn as sns\nimport scipy.stats\nfrom tqdm import tqdm\n\nfrom sklearn.model_selection import cross_val_predict\nfrom sklearn.linear_model import Ridge\nfrom sklearn.metrics import r2_score, mean_squared_error\nimport itertools\nfrom astropy.stats import sigma_clip\nimport polars as pl\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-08-23T07:53:54.196683Z","iopub.execute_input":"2024-08-23T07:53:54.197082Z","iopub.status.idle":"2024-08-23T07:53:57.892167Z","shell.execute_reply.started":"2024-08-23T07:53:54.197047Z","shell.execute_reply":"2024-08-23T07:53:57.89091Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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')\ntrain_labels = pd.read_csv('/kaggle/input/ariel-data-challenge-2024/train_labels.csv',\n                           index_col='planet_id')\naxis_info = pd.read_parquet('/kaggle/input/ariel-data-challenge-2024/axis_info.parquet')","metadata":{"execution":{"iopub.status.busy":"2024-08-23T07:54:16.31751Z","iopub.execute_input":"2024-08-23T07:54:16.318097Z","iopub.status.idle":"2024-08-23T07:54:16.611253Z","shell.execute_reply.started":"2024-08-23T07:54:16.318066Z","shell.execute_reply":"2024-08-23T07:54:16.610044Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def apply_linear_corr(linear_corr,clean_signal):\n    linear_corr = np.flip(linear_corr, axis=0)\n    for x, y in itertools.product(\n                range(clean_signal.shape[1]), range(clean_signal.shape[2])\n            ):\n        poli = np.poly1d(linear_corr[:, x, y])\n        clean_signal[:, x, y] = poli(clean_signal[:, x, y])\n    return clean_signal\n\ndef clean_dark(signal, dark, dt):\n    dark = np.tile(dark, (signal.shape[0], 1, 1))\n    signal -= dark* dt[:, np.newaxis, np.newaxis]\n    return signal\n\ndef preproc(dataset, adc_info, sensor, binning = 15):\n    sensor_sizes_dict = {\"AIRS-CH0\":[[11250, 32, 356], [1, 32, 356]], \"FGS1\":[[135000, 32, 32], [1, 32, 32]]}\n    binned_dict = {\"AIRS-CH0\":[11250 // binning // 2, 356], \"FGS1\":[135000 // binning // 2]}\n    linear_corr_dict = {\"AIRS-CH0\":(6, 32, 356), \"FGS1\":(6, 32, 32)}\n    planet_ids = adc_info.index\n    \n    feats = []\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}/{sensor}_signal.parquet').cast(pl.Float32).to_numpy()\n        dark_frame = pl.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/dark.parquet').cast(pl.Float32).to_numpy()\n        dead_frame = pl.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/dead.parquet').cast(pl.Boolean).to_numpy()\n        flat_frame = pl.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/flat.parquet').cast(pl.Float32).to_numpy()\n        linear_corr = pl.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/linear_corr.parquet').cast(pl.Float32).to_numpy().reshape(linear_corr_dict[sensor])\n\n        signal = signal.reshape(sensor_sizes_dict[sensor][0]) \n        gain = adc_info[f'{sensor}_adc_gain'].values[i]\n        offset = adc_info[f'{sensor}_adc_offset'].values[i]\n        signal = signal / gain + offset\n        \n        hot = sigma_clip(\n            dark_frame, sigma=6, maxiters=5\n        ).mask\n        \n        if sensor != \"FGS1\":\n            signal = signal #11250 * 32 * 282\n            #dt = axis_info['AIRS-CH0-integration_time'].dropna().values\n            dt = np.ones(len(signal))*0.1 \n            dt[1::2] += 4.5\n        else:\n            dt = np.ones(len(signal))*0.1\n            dt[1::2] += 0.1\n            \n        signal = signal.clip(0)\n        linear_corr_signal = apply_linear_corr(linear_corr, signal)\n        signal = clean_dark(linear_corr_signal, dark_frame, dt)\n        \n        flat = flat_frame.reshape(sensor_sizes_dict[sensor][1])\n        flat[dead_frame.reshape(sensor_sizes_dict[sensor][1])] = np.nan\n        flat[hot.reshape(sensor_sizes_dict[sensor][1])] = np.nan\n        signal = signal / flat\n                \n        if sensor == \"FGS1\":\n            signal = signal.reshape((sensor_sizes_dict[sensor][0][0], sensor_sizes_dict[sensor][0][1]*sensor_sizes_dict[sensor][0][2]))\n        \n        mean_signal = np.nanmean(signal, axis=1) # mean over the 32*32(FGS1) or 32(CH0) pixels\n        cds_signal = (mean_signal[1::2] - mean_signal[0::2])\n        \n        binned = np.zeros((binned_dict[sensor]))\n        for j in range(cds_signal.shape[0] // binning):\n            binned[j] = cds_signal[j*binning:j*binning+binning].mean(axis=0)\n                   \n        if sensor == \"FGS1\":\n            binned = binned.reshape((binned.shape[0],1))\n            \n        feats.append(binned)\n        \n    return np.stack(feats)\n    \ntrain = np.concatenate([preproc('train', train_adc_info, \"FGS1\", 12), preproc('train', train_adc_info, \"AIRS-CH0\", 1)], axis=2)","metadata":{"execution":{"iopub.status.busy":"2024-08-23T08:00:07.729971Z","iopub.execute_input":"2024-08-23T08:00:07.730427Z","iopub.status.idle":"2024-08-23T08:01:14.158931Z","shell.execute_reply.started":"2024-08-23T08:00:07.730392Z","shell.execute_reply":"2024-08-23T08:01:14.157602Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"np.save('train_clean_full.npy', train)","metadata":{"execution":{"iopub.status.busy":"2024-08-10T09:38:16.059493Z","iopub.execute_input":"2024-08-10T09:38:16.060008Z","iopub.status.idle":"2024-08-10T09:38:16.787911Z","shell.execute_reply.started":"2024-08-10T09:38:16.059966Z","shell.execute_reply":"2024-08-10T09:38:16.786578Z"},"trusted":true},"execution_count":null,"outputs":[]}]}