{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","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"},{"sourceId":196522559,"sourceType":"kernelVersion"}],"dockerImageVersionId":30761,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# *readme*","metadata":{}},{"cell_type":"markdown","source":"Original baseline:https://www.kaggle.com/code/vyacheslavbolotin/ariel-ensemble-of-solutions?scriptVersionId=198592783   \nmade by :@vyacheslavbolotin\n\nmodel1 baseline:https://www.kaggle.com/code/hideyukizushi/ariel-only-correlation-paramupd-9-22imprvelb-522?scriptVersionId=197773699\nmade by:@hideyukizushi\n\nmodel2 baseline:https://www.kaggle.com/code/xiaocao123/lb-0-545?scriptVersionId=196798500\nmade by:@xiaocao123\n\nThanks to the above users for their open source solutions, they are the promoters of the spirit of open source.\n\nThanks a lot to user @vyacheslavbolotin for the integration solution, but it seems a bit cumbersome for newbies and there may be missing **planet_id** columns in the final output of submissions, so I removed some more than content and modified the final merged output.\n\n\nThere is a lot that can be optimized about the functions in these models, at least for me\n\nIf you have questions about the code, feel free to leave them in the comments section, I should be able to answer questions in Chinese Japanese and English using the translator!","metadata":{}},{"cell_type":"markdown","source":"# model 1","metadata":{}},{"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 scipy.optimize import minimize\nfrom functools import partial\nimport random, os\nfrom astropy.stats import sigma_clip\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-09-10T12:20:46.854085Z","iopub.execute_input":"2024-09-10T12:20:46.854536Z","iopub.status.idle":"2024-09-10T12:20:49.179273Z","shell.execute_reply.started":"2024-09-10T12:20:46.854495Z","shell.execute_reply":"2024-09-10T12:20:49.178167Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_adc_info = pd.read_csv('/kaggle/input/ariel-data-challenge-2024/test_adc_info.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":"2024-09-10T12:20:49.181676Z","iopub.execute_input":"2024-09-10T12:20:49.182193Z","iopub.status.idle":"2024-09-10T12:20:49.368917Z","shell.execute_reply.started":"2024-09-10T12:20:49.182153Z","shell.execute_reply":"2024-09-10T12:20:49.367715Z"},"trusted":true},"outputs":[],"execution_count":null},{"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    cut_inf, cut_sup = 39, 321\n    sensor_sizes_dict = {\"AIRS-CH0\":[[11250, 32, 356], [1, 32, cut_sup-cut_inf]], \"FGS1\":[[135000, 32, 32], [1, 32, 32]]}\n    binned_dict = {\"AIRS-CH0\":[11250 // binning // 2, 282], \"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 = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/{planet_id}/{sensor}_signal.parquet').to_numpy()\n        dark_frame = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/dark.parquet', engine='pyarrow').to_numpy()\n        dead_frame = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/dead.parquet', engine='pyarrow').to_numpy()\n        flat_frame = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/flat.parquet', engine='pyarrow').to_numpy()\n        linear_corr = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/linear_corr.parquet').values.astype(np.float64).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=8, maxiters=5\n        ).mask\n        \n        if sensor != \"FGS1\":\n            signal = signal[:, :, cut_inf:cut_sup] #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 #@bilzard idea\n            linear_corr = linear_corr[:, :, cut_inf:cut_sup]\n            dark_frame = dark_frame[:, cut_inf:cut_sup]\n            dead_frame = dead_frame[:, cut_inf:cut_sup]\n            flat_frame = flat_frame[:, cut_inf:cut_sup]\n            hot = hot[:, cut_inf:cut_sup]\n        else:\n            dt = np.ones(len(signal))*0.1\n            dt[1::2] += 0.1\n            \n        signal = signal.clip(0) #@graySnow idea\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    \npre_train = np.concatenate([preproc('test', test_adc_info, \"FGS1\", 30*12), preproc('test', test_adc_info, \"AIRS-CH0\", 30)], axis=2)","metadata":{},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def phase_detector(signal):\n    phase1, phase2 = None, None\n    best_drop = 0\n    for i in range(50//2,150//2):        \n        t1 = signal[i:i+20//2].max() - signal[i:i+20//2].min()\n        if t1 > best_drop:\n            phase1 = i+(20+5)//2\n            best_drop = t1\n    \n    best_drop = 0\n    for i in range(200//2,250//2):\n        t1 = signal[i:i+20//2].max() - signal[i:i+20//2].min()\n        if t1 > best_drop:\n            phase2 = i-5//2\n            best_drop = t1\n    \n    return phase1, phase2\n\ndef try_s(signal, p1, p2, deg, s):\n    out = list(range(p1-30)) + list(range(p2+30,signal.shape[0]))\n    x, y = out, signal[out].tolist()\n    x = x + list(range(p1,p2))\n\n    y = y + (signal[p1:p2] * (1 + s[0])).tolist()\n    z = np.polyfit(x, y, deg)\n    p = np.poly1d(z)\n    q = np.abs(p(x) - y).mean()\n\n    if s < 1e-4:\n        return q + 1e3\n\n    return q\n    \ndef calibrate_signal(signal):\n    p1,p2 = phase_detector(signal)\n\n    best_deg, best_score = 1, 1e12\n    for deg in range(1, 6):\n        f = partial(try_s, signal, p1, p2, deg)\n        r = minimize(f, [0.001], method = 'Nelder-Mead')\n        s = r.x[0]\n\n        out = list(range(p1-30)) + list(range(p2+30,signal.shape[0]))\n        x, y = out, signal[out].tolist()\n        x = x + list(range(p1,p2))\n        y = y + (signal[p1:p2] * (1 + s)).tolist()\n    \n        z = np.polyfit(x, y, deg)\n        p = np.poly1d(z)\n        q = np.abs(p(x) - y).mean()\n        \n        if q < best_score:\n            best_score = q\n            best_deg = deg\n        \n        print(deg, q)\n            \n    z = np.polyfit(x, y, best_deg)\n    p = np.poly1d(z)\n\n    return s, x, y, p(x)\n\ndef calibrate_train(signal):\n    p1,p2 = phase_detector(signal)\n    \n    best_deg, best_score = 1, 1e12\n    for deg in range(1, 6):\n        f = partial(try_s, signal, p1, p2, deg)\n        r = minimize(f, [0.0001], method = 'Nelder-Mead')\n        s = r.x[0]\n\n        out = list(range(p1-30)) + list(range(p2+30,signal.shape[0]))\n        x, y = out, signal[out].tolist()\n        x = x + list(range(p1,p2))\n        y = y + (signal[p1:p2] * (1 + s)).tolist()\n    \n        z = np.polyfit(x, y, deg)\n        p = np.poly1d(z)\n        q = np.abs(p(x) - y).mean()\n        \n        if q < best_score:\n            best_score = q\n            best_deg = deg\n            \n    z = np.polyfit(x, y, best_deg)\n    p = np.poly1d(z)\n    \n    return s, p(np.arange(signal.shape[0])), p1, p2\n\n\ntrain = pre_train.copy()\nall_s = []\nfor i in range(len(test_adc_info)):\n    signal = train[i,:,1:].mean(axis=1)\n    s, p, p1, p2 = calibrate_train(pre_train[i,:,1:].mean(axis=1))\n    all_s.append(s)\n        \n#copy answer 283 times because we predict mean value\ntrain_s = np.repeat(np.array(all_s), 283).reshape((len(all_s), 283))        \ntrain_sigma = np.ones_like(train_s) * 0.000176","metadata":{"execution":{"iopub.status.busy":"2024-09-10T12:20:49.37053Z","iopub.execute_input":"2024-09-10T12:20:49.370899Z","iopub.status.idle":"2024-09-10T12:21:00.787544Z","shell.execute_reply.started":"2024-09-10T12:20:49.370862Z","shell.execute_reply":"2024-09-10T12:21:00.786442Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ss = pd.read_csv('/kaggle/input/ariel-data-challenge-2024/sample_submission.csv')\n\npreds = train_s.clip(0)\nsigmas = train_sigma\nsubmission = pd.DataFrame(np.concatenate([preds,sigmas], axis=1), columns=ss.columns[1:])\nsubmission.index = test_adc_info.index\nsubmission.to_csv('submission_v1.csv')","metadata":{"execution":{"iopub.status.busy":"2024-09-10T12:27:17.329167Z","iopub.execute_input":"2024-09-10T12:27:17.329626Z","iopub.status.idle":"2024-09-10T12:27:17.373243Z","shell.execute_reply.started":"2024-09-10T12:27:17.329587Z","shell.execute_reply":"2024-09-10T12:27:17.372174Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submission","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# model 2","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport matplotlib.pyplot as plt\nimport numpy as np\nfrom tqdm import tqdm\nimport joblib\n\nfrom sklearn.linear_model import Ridge\nfrom sklearn.metrics import r2_score, mean_squared_error\nimport itertools\n\nfrom scipy.optimize import minimize\nfrom scipy import optimize\n\nfrom astropy.stats import sigma_clip","metadata":{},"outputs":[],"execution_count":null},{"cell_type":"code","source":"dataset = 'test'\nadc_info = pd.read_csv('/kaggle/input/ariel-data-challenge-2024/'+f'{dataset}_adc_info.csv',index_col='planet_id')\naxis_info = pd.read_parquet('/kaggle/input/ariel-data-challenge-2024/axis_info.parquet')","metadata":{},"outputs":[],"execution_count":null},{"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    cut_inf, cut_sup = 39, 321\n    sensor_sizes_dict = {\"AIRS-CH0\":[[11250, 32, 356], [1, 32, cut_sup-cut_inf]], \"FGS1\":[[135000, 32, 32], [1, 32, 32]]}\n    binned_dict = {\"AIRS-CH0\":[11250 // binning // 2, 282], \"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 = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/{planet_id}/{sensor}_signal.parquet').to_numpy()\n        dark_frame = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/dark.parquet', engine='pyarrow').to_numpy()\n        dead_frame = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/dead.parquet', engine='pyarrow').to_numpy()\n        flat_frame = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/flat.parquet', engine='pyarrow').to_numpy()\n        linear_corr = pd.read_parquet(f'/kaggle/input/ariel-data-challenge-2024/{dataset}/' + str(planet_id) + '/' + sensor + '_calibration/linear_corr.parquet').values.astype(np.float64).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=5, maxiters=5\n        ).mask\n        \n        if sensor != \"FGS1\":\n            signal = signal[:, :, cut_inf:cut_sup] \n            dt = np.ones(len(signal))*0.1 \n            dt[1::2] += 4.5 #@bilzard idea\n            linear_corr = linear_corr[:, :, cut_inf:cut_sup]\n            dark_frame = dark_frame[:, cut_inf:cut_sup]\n            dead_frame = dead_frame[:, cut_inf:cut_sup]\n            flat_frame = flat_frame[:, cut_inf:cut_sup]\n            hot = hot[:, cut_inf:cut_sup]\n        else:\n            dt = np.ones(len(signal))*0.1\n            dt[1::2] += 0.1\n            \n        signal = signal.clip(0) #@graySnow idea\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        \n        if sensor == \"FGS1\":\n            signal = signal[:,10:22,10:22] # **** updates ****\n            signal = signal.reshape(sensor_sizes_dict[sensor][0][0],144) # # **** updates ****\n\n        if sensor != \"FGS1\":\n            signal = signal[:,10:22,:] # **** updates ****\n\n        mean_signal = np.nanmean(signal, axis=1) \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    \npre_train = np.concatenate([preproc(f'{dataset}', adc_info, \"FGS1\", 30*12), preproc(f'{dataset}', adc_info, \"AIRS-CH0\", 30)], axis=2)","metadata":{},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def phase_detector(signal):\n    \n    MIN = np.argmin(signal[30:140])+30\n    signal1 = signal[:MIN ]\n    signal2 = signal[MIN :]\n\n    first_derivative1 = np.gradient(signal1)\n    first_derivative1 /= first_derivative1.max()\n    first_derivative2 = np.gradient(signal2)\n    first_derivative2 /= first_derivative2.max()\n\n    phase1 = np.argmin(first_derivative1)\n    phase2 = np.argmax(first_derivative2) + MIN\n\n    return phase1, phase2\n    \ndef objective(s):\n    \n    best_q = 1e10\n    for i in range(4) :\n        delta = 2\n        x = list(range(signal.shape[0]-delta*4))\n        y = signal[:p1-delta].tolist() + (signal[p1+delta:p2 - delta] * (1 + s)).tolist() + signal[p2+delta:].tolist()\n        \n        z = np.polyfit(x, y, deg=i)\n        p = np.poly1d(z)\n        q = np.abs(p(x) - y).mean()\n    \n    if q < best_q :\n        best_q = q\n    \n    return q\n\n\nall_s = []\nfor i in tqdm(range(len(adc_info))):\n    \n    signal = pre_train[i,:,1:].mean(axis=1)\n    p1,p2 = phase_detector(signal)\n \n    r = minimize(\n                objective,\n                [0.0001],\n                method= 'Nelder-Mead'\n                  )\n    s = r.x[0]\n    all_s.append(s)\n    \nall_s = np.repeat(np.array(all_s), 283).reshape((len(all_s), 283))        ","metadata":{},"outputs":[],"execution_count":null},{"cell_type":"code","source":"sigma = np.ones_like(all_s) * 0.000140985\npred = all_s.clip(0) \nsubmission = pd.DataFrame(np.concatenate([pred,sigma], axis=1), columns=ss.columns[1:])\nsubmission.index = adc_info.index\nsubmission.to_csv('submission_v2.csv')\nsubmission","metadata":{},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Submission","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\n\n# read 2 csv file\ndf1 = pd.read_csv('submission_v1.csv', index_col='planet_id')\ndf2 = pd.read_csv('submission_v2.csv', index_col='planet_id')\n\n# make sure have same index\nassert df1.index.equals(df2.index), \"the planet_id in 2 files couldnt match\"\n\n# Calculation of weighted average\nweighted_avg = 0.0303215 * df1 + 0.9696785 * df2\n\n# save file\nweighted_avg.to_csv('submission.csv',  float_format='%.8f')\n#you may config number of decimal places, i delete index=false to avoid loss plant_id\n\n\nprint(\"the file has save as submission.csv\")","metadata":{},"outputs":[],"execution_count":null}]}