{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":53666,"databundleVersionId":6589269,"sourceType":"competition"},{"sourceId":154774503,"sourceType":"kernelVersion"}],"dockerImageVersionId":30626,"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","execution":{"iopub.status.busy":"2023-12-14T16:01:47.201430Z","iopub.execute_input":"2023-12-14T16:01:47.202718Z","iopub.status.idle":"2023-12-14T16:01:47.667276Z","shell.execute_reply.started":"2023-12-14T16:01:47.202675Z","shell.execute_reply":"2023-12-14T16:01:47.666212Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport gc\nimport time\nimport json\nfrom datetime import datetime\nimport matplotlib.pyplot as plt\nimport os, glob\nimport joblib\nimport random\nimport math\nfrom tqdm import tqdm \nfrom collections import OrderedDict\n\nfrom scipy.interpolate import interp1d\nfrom scipy import signal\nfrom scipy.signal import argrelmax\n\nfrom sklearn.metrics import mean_squared_error\n\nfrom math import pi, sqrt, exp\nimport sklearn,sklearn.model_selection\nimport torch\nfrom torch import nn,Tensor\nimport torch.nn.functional as F\nfrom torch.utils.data import DataLoader, Dataset, SubsetRandomSampler\nfrom torch.optim import AdamW\nfrom sklearn.metrics import average_precision_score\nfrom timm.scheduler import CosineLRScheduler\n\nfrom transformers import get_cosine_schedule_with_warmup\nfrom transformers import AutoTokenizer, AutoConfig\nfrom transformers import AutoModel\n\nplt.style.use(\"ggplot\")\n\nfrom pyarrow.parquet import ParquetFile\nimport pyarrow as pa \nimport ctypes","metadata":{"execution":{"iopub.status.busy":"2023-12-14T16:01:56.798589Z","iopub.execute_input":"2023-12-14T16:01:56.799092Z","iopub.status.idle":"2023-12-14T16:02:04.723620Z","shell.execute_reply.started":"2023-12-14T16:01:56.799059Z","shell.execute_reply":"2023-12-14T16:02:04.721811Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#print(meta_cts)\n#print(metadata)\ndata = pd.read_csv(\"/kaggle/input/80-features-dataprepare/train_csvs/038441c925bb.csv\")\n#print(data)\ndata['anglez_diff'] = data['anglez'].diff().fillna(0)\nonset_data = [abs(data[\"anglez_diff\"][i]) for i in range(4950,5050)]\n#plt.plot(onset_data)\n#plt.show()\nstartstep=1e6\nendstep=1e6\nnow_startstep = None\nunchanged_count = 0\nstart = 34560\nend = 51840\nfor i in range(start,end):\n    flag_lr=2\n    flag_num=2\n    diff_10,diff_50,diff_100,diff_200=0,0,0,0\n\n    mean_50_left,mean_50_right,mean_100_left,mean_100_right,mean_200_left,mean_200_right, mean_10_left,mean_10_right=0,0,0,0,0,0,0,0\n    \n    mean_50_left = sum(abs(data[\"anglez_diff\"][k]) for k in range(i-50, i)) / 50\n    mean_50_right = sum(abs(data[\"anglez_diff\"][k]) for k in range(i+1, i+51)) / 50\n    mean_100_left = sum(abs(data[\"anglez_diff\"][k]) for k in range(i-100, i)) / 100\n    mean_100_right = sum(abs(data[\"anglez_diff\"][k]) for k in range(i+1, i+101)) / 100\n    mean_200_left = sum(abs(data[\"anglez_diff\"][k]) for k in range(i-200, i)) / 200\n    mean_200_right = sum(abs(data[\"anglez_diff\"][k]) for k in range(i+1, i+201)) / 200\n    mean_10_left = sum(abs(data[\"anglez_diff\"][k]) for k in range(i-10, i)) / 10\n    mean_10_right = sum(abs(data[\"anglez_diff\"][k]) for k in range(i+1, i+11)) / 10\n    #print(mean_50_left,mean_50_right,mean_100_left,mean_100_right,mean_200_left,mean_200_right, mean_10_left,mean_10_right)\n    \n    flag_10=0\n    flag_50=0\n    flag_100=0\n    flag_200=0\n    if (mean_10_left > mean_10_right):\n        flag_10=1\n    else:\n        flag_10=2\n        \n    if (mean_50_left > mean_50_right):\n        flag_50=1\n    else:\n        flag_50=2\n        \n    if (mean_100_left > mean_100_right):\n        flag_100=1\n    else:\n        flag_100=2\n        \n    if (mean_200_left > mean_200_right):\n        flag_200=1\n    else:\n        flag_200=2\n        \n    diff_10 = abs(mean_10_right - mean_10_left)\n    diff_50 = abs(mean_50_right - mean_50_left)\n    diff_100 = abs(mean_100_right - mean_100_left)\n    diff_200 = abs(mean_200_right - mean_200_left)\n    #print(diff_10,diff_50,diff_100,diff_200)\n    if(flag_10==1 and flag_50==1 and flag_100==1 and flag_200==1):\n        flag_lr = 0\n        \n    if (diff_10>0.01 and diff_50 > 1.8 and diff_100> 4.5 and diff_200> 6.5):\n        flag_num =1\n        \n    if (flag_lr == 0 and flag_num == 1 and (data[\"hour\"][i] > 16 or data[\"hour\"][i] < 4)):\n        startstep =i\n    now_timestep =i\n    if (now_timestep - startstep >=100):\n        #print(now_timestep)\n        break\n\nfor i in range(startstep,end):\n    flag_lr=2\n    flag_num=2\n    diff_10,diff_50,diff_100,diff_200=0,0,0,0\n\n    mean_50_left,mean_50_right,mean_100_left,mean_100_right,mean_200_left,mean_200_right, mean_10_left,mean_10_right=0,0,0,0,0,0,0,0\n    \n    mean_50_left = sum(abs(data[\"anglez_diff\"][k]) for k in range(i-50, i)) / 50\n    mean_50_right = sum(abs(data[\"anglez_diff\"][k]) for k in range(i+1, i+51)) / 50\n    mean_100_left = sum(abs(data[\"anglez_diff\"][k]) for k in range(i-100, i)) / 100\n    mean_100_right = sum(abs(data[\"anglez_diff\"][k]) for k in range(i+1, i+101)) / 100\n    mean_200_left = sum(abs(data[\"anglez_diff\"][k]) for k in range(i-200, i)) / 200\n    mean_200_right = sum(abs(data[\"anglez_diff\"][k]) for k in range(i+1, i+201)) / 200\n    mean_10_left = sum(abs(data[\"anglez_diff\"][k]) for k in range(i-10, i)) / 10\n    mean_10_right = sum(abs(data[\"anglez_diff\"][k]) for k in range(i+1, i+11)) / 10\n    #print(mean_50_left,mean_50_right,mean_100_left,mean_100_right,mean_200_left,mean_200_right, mean_10_left,mean_10_right)\n    \n    flag_10=0\n    flag_50=0\n    flag_100=0\n    flag_200=0\n    if (mean_10_left > mean_10_right):\n        flag_10=1\n    else:\n        flag_10=2\n        \n    if (mean_50_left > mean_50_right):\n        flag_50=1\n    else:\n        flag_50=2\n        \n    if (mean_100_left > mean_100_right):\n        flag_100=1\n    else:\n        flag_100=2\n        \n    if (mean_200_left > mean_200_right):\n        flag_200=1\n    else:\n        flag_200=2\n        \n    diff_10 = abs(mean_10_right - mean_10_left)\n    diff_50 = abs(mean_50_right - mean_50_left)\n    diff_100 = abs(mean_100_right - mean_100_left)\n    diff_200 = abs(mean_200_right - mean_200_left)\n    #print(diff_10,diff_50,diff_100,diff_200)\n    if(flag_10==2 and flag_50==2 and flag_100==2 and flag_200==2):\n        flag_lr = 0\n        \n    if (diff_10>0.015 and diff_50 > 2 and diff_100> 4.8 and diff_200> 6.8):\n        flag_num =1\n        \n    if (flag_lr == 0 and flag_num == 1 and (data[\"hour\"][i] > 0 and data[\"hour\"][i] < 13)):\n        endstep =i\n        break\n\nprint(startstep,endstep)\n        \n\n","metadata":{"execution":{"iopub.status.busy":"2023-12-14T17:48:15.799584Z","iopub.execute_input":"2023-12-14T17:48:15.799958Z","iopub.status.idle":"2023-12-14T17:49:12.956693Z","shell.execute_reply.started":"2023-12-14T17:48:15.799928Z","shell.execute_reply":"2023-12-14T17:49:12.955450Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}