{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","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"}],"dockerImageVersionId":31012,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np \nimport pandas as pd \nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n for filename in filenames:\n print(os.path.join(dirname, filename))\n\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:51:43.799283Z","iopub.execute_input":"2025-05-04T04:51:43.79959Z","iopub.status.idle":"2025-05-04T04:51:44.115789Z","shell.execute_reply.started":"2025-05-04T04:51:43.799567Z","shell.execute_reply":"2025-05-04T04:51:44.114911Z"}},"outputs":[{"name":"stdout","text":"/kaggle/input/child-mind-institute-detect-sleep-states/train_series.parquet\n/kaggle/input/child-mind-institute-detect-sleep-states/sample_submission.csv\n/kaggle/input/child-mind-institute-detect-sleep-states/train_events.csv\n/kaggle/input/child-mind-institute-detect-sleep-states/test_series.parquet\n","output_type":"stream"}],"execution_count":3},{"cell_type":"code","source":"!pip install pandarallel","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:51:47.947548Z","iopub.execute_input":"2025-05-04T04:51:47.948008Z","iopub.status.idle":"2025-05-04T04:51:55.070317Z","shell.execute_reply.started":"2025-05-04T04:51:47.947982Z","shell.execute_reply":"2025-05-04T04:51:55.069482Z"}},"outputs":[{"name":"stdout","text":"Collecting pandarallel\n Downloading pandarallel-1.6.5.tar.gz (14 kB)\n Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\nRequirement already satisfied: dill>=0.3.1 in /usr/local/lib/python3.11/dist-packages (from pandarallel) (0.3.8)\nRequirement already satisfied: pandas>=1 in /usr/local/lib/python3.11/dist-packages (from pandarallel) (2.2.3)\nRequirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from pandarallel) (7.0.0)\nRequirement already satisfied: numpy>=1.23.2 in /usr/local/lib/python3.11/dist-packages (from pandas>=1->pandarallel) (1.26.4)\nRequirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas>=1->pandarallel) (2.9.0.post0)\nRequirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas>=1->pandarallel) (2025.2)\nRequirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas>=1->pandarallel) (2025.2)\nRequirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.2->pandas>=1->pandarallel) (1.3.8)\nRequirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.2->pandas>=1->pandarallel) (1.2.4)\nRequirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.2->pandas>=1->pandarallel) (0.1.1)\nRequirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.2->pandas>=1->pandarallel) (2025.1.0)\nRequirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.2->pandas>=1->pandarallel) (2022.1.0)\nRequirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy>=1.23.2->pandas>=1->pandarallel) (2.4.1)\nRequirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas>=1->pandarallel) (1.17.0)\nRequirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.23.2->pandas>=1->pandarallel) (2024.2.0)\nRequirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.23.2->pandas>=1->pandarallel) (2022.1.0)\nRequirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy>=1.23.2->pandas>=1->pandarallel) (1.2.0)\nRequirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy>=1.23.2->pandas>=1->pandarallel) (2024.2.0)\nRequirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy>=1.23.2->pandas>=1->pandarallel) (2024.2.0)\nBuilding wheels for collected packages: pandarallel\n Building wheel for pandarallel (setup.py) ... \u001b[?25l\u001b[?25hdone\n Created wheel for pandarallel: filename=pandarallel-1.6.5-py3-none-any.whl size=16674 sha256=1e208221d0e9e53083f49b2ff8f9fd4f02615b6adf4534b3a52cd8648627982b\n Stored in directory: /root/.cache/pip/wheels/b9/c6/5a/829298789e94348b81af52ab42c19d49da007306bbcc983827\nSuccessfully built pandarallel\nInstalling collected packages: pandarallel\nSuccessfully installed pandarallel-1.6.5\n","output_type":"stream"}],"execution_count":4},{"cell_type":"code","source":"!pip install polars plotly pyarrow scikit-learn colorama tqdm","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:52:00.515346Z","iopub.execute_input":"2025-05-04T04:52:00.515674Z","iopub.status.idle":"2025-05-04T04:52:04.033557Z","shell.execute_reply.started":"2025-05-04T04:52:00.515647Z","shell.execute_reply":"2025-05-04T04:52:04.032509Z"}},"outputs":[{"name":"stdout","text":"Requirement already satisfied: polars in /usr/local/lib/python3.11/dist-packages (1.9.0)\nRequirement already satisfied: plotly in /usr/local/lib/python3.11/dist-packages (5.24.1)\nRequirement already satisfied: pyarrow in /usr/local/lib/python3.11/dist-packages (19.0.1)\nRequirement already satisfied: scikit-learn in /usr/local/lib/python3.11/dist-packages (1.2.2)\nRequirement already satisfied: colorama in /usr/local/lib/python3.11/dist-packages (0.4.6)\nRequirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (4.67.1)\nRequirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.11/dist-packages (from plotly) (9.0.0)\nRequirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from plotly) (24.2)\nRequirement already satisfied: numpy>=1.17.3 in /usr/local/lib/python3.11/dist-packages (from scikit-learn) (1.26.4)\nRequirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.11/dist-packages (from scikit-learn) (1.15.2)\nRequirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from scikit-learn) (1.4.2)\nRequirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn) (3.6.0)\nRequirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17.3->scikit-learn) (1.3.8)\nRequirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17.3->scikit-learn) (1.2.4)\nRequirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17.3->scikit-learn) (0.1.1)\nRequirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17.3->scikit-learn) (2025.1.0)\nRequirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17.3->scikit-learn) (2022.1.0)\nRequirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17.3->scikit-learn) (2.4.1)\nRequirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.17.3->scikit-learn) (2024.2.0)\nRequirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.17.3->scikit-learn) (2022.1.0)\nRequirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy>=1.17.3->scikit-learn) (1.2.0)\nRequirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy>=1.17.3->scikit-learn) (2024.2.0)\nRequirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy>=1.17.3->scikit-learn) (2024.2.0)\n","output_type":"stream"}],"execution_count":5},{"cell_type":"markdown","source":"EXPLORATORY DATA ANALYSIS:\n\n\nIMPORTS:","metadata":{}},{"cell_type":"code","source":"import gc \nimport matplotlib.pyplot as plt \nplt.style.use('ggplot')\nimport polars as pl\nimport seaborn as sns\nimport plotly.graph_objects as go\nfrom plotly.subplots import make_subplots\nimport plotly.express as px\nimport plotly.offline\n\nfrom colorama import Fore, Style, init\n\nimport pyarrow as pa\nimport datetime as dt\nimport torch\n\nfrom tqdm import tqdm\ntqdm.pandas()\n\nfrom pyarrow.parquet import ParquetFile\nfrom datetime import datetime as dts\nfrom pandarallel import pandarallel \npandarallel.initialize(progress_bar=True)\n\n\nimport warnings\nwarnings.filterwarnings('ignore')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:52:13.030097Z","iopub.execute_input":"2025-05-04T04:52:13.030435Z","iopub.status.idle":"2025-05-04T04:52:20.096947Z","shell.execute_reply.started":"2025-05-04T04:52:13.03039Z","shell.execute_reply":"2025-05-04T04:52:20.096121Z"}},"outputs":[{"name":"stdout","text":"INFO: Pandarallel will run on 2 workers.\nINFO: Pandarallel will use Memory file system to transfer data between the main process and workers.\n","output_type":"stream"}],"execution_count":6},{"cell_type":"markdown","source":"LOADING DATA:","metadata":{}},{"cell_type":"code","source":"class PATHS:\n MAIN_DIR = \"/kaggle/input/child-mind-institute-detect-sleep-states/\"\n # CSV FILES : \n SUBMISSION = MAIN_DIR + \"sample_submission.csv\"\n TRAIN_EVENTS = MAIN_DIR + \"train_events.csv\"\n # PARQUET FILES:\n TRAIN_SERIES = MAIN_DIR + \"train_series.parquet\"\n TEST_SERIES = MAIN_DIR + \"test_series.parquet\"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:52:26.240689Z","iopub.execute_input":"2025-05-04T04:52:26.24121Z","iopub.status.idle":"2025-05-04T04:52:26.246192Z","shell.execute_reply.started":"2025-05-04T04:52:26.241189Z","shell.execute_reply":"2025-05-04T04:52:26.245214Z"}},"outputs":[],"execution_count":7},{"cell_type":"code","source":"class CFG:\n DEMO_MODE = True\n VERBOSE = True\n \n BATCH_SIZE = 32\n DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:52:30.077337Z","iopub.execute_input":"2025-05-04T04:52:30.077707Z","iopub.status.idle":"2025-05-04T04:52:30.08492Z","shell.execute_reply.started":"2025-05-04T04:52:30.077671Z","shell.execute_reply":"2025-05-04T04:52:30.083821Z"}},"outputs":[],"execution_count":8},{"cell_type":"code","source":"class CMIDataReader:\n def __init__(self, demo_mode, verbose):\n super().__init__()\n # MAPPING FOR DATA LOADING :\n self.names_mapping = {\n \"submission\" : {\"path\" : PATHS.SUBMISSION, \"is_parquet\" : False, \"has_timestamp\" : False}, \n \"train_events\" : {\"path\" : PATHS.TRAIN_EVENTS, \"is_parquet\" : False, \"has_timestamp\" : True},\n \"train_series\" : {\"path\" : PATHS.TRAIN_SERIES, \"is_parquet\" : True, \"has_timestamp\" : True},\n \"test_series\" : {\"path\" : PATHS.TEST_SERIES, \"is_parquet\" : True, \"has_timestamp\" : True}\n }\n self.valid_names = [\"submission\", \"train_events\", \"train_series\", \"test_series\"]\n self.demo_mode = demo_mode\n self.verbose = verbose\n \n def verify(self, data_name):\n \"function for data name verification\"\n if data_name not in self.valid_names:\n print(\"PLEASE ENTER A VALID DATASET NAME, VALID NAMES ARE : \", valid_names)\n return\n \n def cleaning(self, data):\n \"cleaning function : drop na values\"\n before_cleaning = len(data)\n if self.verbose:\n print(\"Number of missing timestamps : \", len(data[data[\"timestamp\"].isna()]))\n data = data.dropna(subset=[\"timestamp\"])\n after_cleaning = len(data)\n if self.verbose:\n print(\"Percentage of removed rows : {:.1f}%\".format(100 * (before_cleaning - after_cleaning) / before_cleaning) )\n data = data.bfill()\n return data\n \n def reduce_memory_usage(self, data):\n \"iterate through all the columns of a dataframe and modify the data type to reduce memory usage.\"\n start_mem = data.memory_usage().sum() / 1024**2\n if self.verbose:\n print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n for col in data.columns:\n col_type = data[col].dtype \n if col_type != object:\n c_min = data[col].min()\n c_max = data[col].max()\n if str(col_type)[:3] == 'int':\n if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n data[col] = data[col].astype(np.int8)\n elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n data[col] = data[col].astype(np.int16)\n elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n data[col] = data[col].astype(np.int32)\n elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n data[col] = data[col].astype(np.int64) \n else:\n if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n data[col] = data[col].astype(np.float16)\n elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n data[col] = data[col].astype(np.float32)\n else:\n data[col] = data[col].astype(np.float64)\n else:\n data[col] = data[col].astype('category')\n\n end_mem = data.memory_usage().sum() / 1024**2\n if self.verbose:\n print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))\n print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))\n return data\n \n def load_data(self, data_name):\n \"function for data loading\"\n self.verify(data_name)\n data_props = self.names_mapping[data_name]\n if data_props[\"is_parquet\"]:\n if self.demo_mode:\n pf = ParquetFile(data_props[\"path\"]) \n demo_rows = next(pf.iter_batches(batch_size=10_000_000)) \n data = pa.Table.from_batches([demo_rows]).to_pandas()\n else:\n data = pd.read_parquet(data_props[\"path\"])\n else:\n if self.demo_mode:\n data = pd.read_csv(data_props[\"path\"], nrows=10_000_000)\n else:\n data = pd.read_csv(data_props[\"path\"])\n \n if data_props[\"has_timestamp\"]:\n data = self.cleaning(data)\n data[\"timestamp\"] = pd.to_datetime(data[\"timestamp\"])\n data = data.set_index(\"timestamp\")\n \n data = self.reduce_memory_usage(data)\n gc.collect()\n return data","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:52:38.987894Z","iopub.execute_input":"2025-05-04T04:52:38.988204Z","iopub.status.idle":"2025-05-04T04:52:39.005037Z","shell.execute_reply.started":"2025-05-04T04:52:38.988183Z","shell.execute_reply":"2025-05-04T04:52:39.004114Z"}},"outputs":[],"execution_count":9},{"cell_type":"code","source":"reader = CMIDataReader(demo_mode=CFG.DEMO_MODE, verbose=CFG.VERBOSE)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:52:47.344867Z","iopub.execute_input":"2025-05-04T04:52:47.345529Z","iopub.status.idle":"2025-05-04T04:52:47.349458Z","shell.execute_reply.started":"2025-05-04T04:52:47.345504Z","shell.execute_reply":"2025-05-04T04:52:47.34868Z"}},"outputs":[],"execution_count":10},{"cell_type":"code","source":"print(\"=\"*25)\nprint(\"LOAD SUBMISSION\")\nsubmission = reader.load_data(\"submission\")\nprint(submission.head(10))\nprint(\"LOADING FINISHED ! \")\nprint(\"=\"*25)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:52:50.661949Z","iopub.execute_input":"2025-05-04T04:52:50.662495Z","iopub.status.idle":"2025-05-04T04:52:50.855337Z","shell.execute_reply.started":"2025-05-04T04:52:50.662471Z","shell.execute_reply":"2025-05-04T04:52:50.854504Z"}},"outputs":[{"name":"stdout","text":"=========================\nLOAD SUBMISSION\nMemory usage of dataframe is 0.00 MB\nMemory usage after optimization is: 0.00 MB\nDecreased by -14.0%\n row_id series_id step event score\n0 0 038441c925bb 100 onset 0.0\n1 1 038441c925bb 105 wakeup 0.0\n2 2 03d92c9f6f8a 80 onset 0.5\n3 3 03d92c9f6f8a 110 wakeup 0.5\n4 4 0402a003dae9 90 onset 1.0\n5 5 0402a003dae9 120 wakeup 1.0\nLOADING FINISHED ! \n=========================\n","output_type":"stream"}],"execution_count":11},{"cell_type":"code","source":"print(\"LOAD TEST SERIES\")\ntest_series = reader.load_data(\"test_series\")\nprint(test_series.head(10))\nprint(\"LOADING FINISHED ! \")\nprint(\"=\"*25)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:57:47.591016Z","iopub.execute_input":"2025-05-04T04:57:47.591246Z","iopub.status.idle":"2025-05-04T04:57:49.34898Z","shell.execute_reply.started":"2025-05-04T04:57:47.591229Z","shell.execute_reply":"2025-05-04T04:57:49.348138Z"}},"outputs":[{"name":"stdout","text":"LOAD TEST SERIES\nNumber of missing timestamps : 0\nPercentage of removed rows : 0.0%\nMemory usage of dataframe is 0.01 MB\nMemory usage after optimization is: 0.01 MB\nDecreased by 45.4%\n series_id step anglez enmo\ntimestamp \n2018-08-14 15:30:00-04:00 038441c925bb 0.0 2.636719 0.021698\n2018-08-14 15:30:05-04:00 038441c925bb 1.0 2.636719 0.021500\n2018-08-14 15:30:10-04:00 038441c925bb 2.0 2.636719 0.021606\n2018-08-14 15:30:15-04:00 038441c925bb 3.0 2.636719 0.021301\n2018-08-14 15:30:20-04:00 038441c925bb 4.0 2.636719 0.021500\n2018-08-14 15:30:25-04:00 038441c925bb 5.0 2.636719 0.021698\n2018-08-14 15:30:30-04:00 038441c925bb 6.0 2.636719 0.021698\n2018-08-14 15:30:35-04:00 038441c925bb 7.0 2.636719 0.021805\n2018-08-14 15:30:40-04:00 038441c925bb 8.0 2.798828 0.022293\n2018-08-14 15:30:45-04:00 038441c925bb 9.0 3.083984 0.021698\nLOADING FINISHED ! \n=========================\n","output_type":"stream"}],"execution_count":15},{"cell_type":"code","source":"%time\nprint(\"=\"*25)\nprint(\"LOAD TRAIN SERIES\")\ntrain_series = reader.load_data(\"train_series\")\nprint(train_series.head(10))\nprint(\"LOADING FINISHED ! \")\nprint(\"=\"*25)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T04:57:53.728249Z","iopub.execute_input":"2025-05-04T04:57:53.728556Z","iopub.status.idle":"2025-05-04T05:02:38.323911Z","shell.execute_reply.started":"2025-05-04T04:57:53.728534Z","shell.execute_reply":"2025-05-04T05:02:38.323016Z"}},"outputs":[{"name":"stdout","text":"CPU times: user 4 µs, sys: 0 ns, total: 4 µs\nWall time: 8.11 µs\n=========================\nLOAD TRAIN SERIES\nNumber of missing timestamps : 0\nPercentage of removed rows : 0.0%\nMemory usage of dataframe is 267.03 MB\nMemory usage after optimization is: 162.13 MB\nDecreased by 39.3%\n series_id step anglez enmo\ntimestamp \n2018-08-14 15:30:00-04:00 038441c925bb 0.0 2.636719 0.021698\n2018-08-14 15:30:05-04:00 038441c925bb 1.0 2.636719 0.021500\n2018-08-14 15:30:10-04:00 038441c925bb 2.0 2.636719 0.021606\n2018-08-14 15:30:15-04:00 038441c925bb 3.0 2.636719 0.021301\n2018-08-14 15:30:20-04:00 038441c925bb 4.0 2.636719 0.021500\n2018-08-14 15:30:25-04:00 038441c925bb 5.0 2.636719 0.021698\n2018-08-14 15:30:30-04:00 038441c925bb 6.0 2.636719 0.021698\n2018-08-14 15:30:35-04:00 038441c925bb 7.0 2.636719 0.021805\n2018-08-14 15:30:40-04:00 038441c925bb 8.0 2.798828 0.022293\n2018-08-14 15:30:45-04:00 038441c925bb 9.0 3.083984 0.021698\nLOADING FINISHED ! \n=========================\n","output_type":"stream"}],"execution_count":16},{"cell_type":"code","source":"%time\nprint(\"=\"*25)\nprint(\"LOAD TRAIN EVENTS\")\ntrain_events = reader.load_data(\"train_events\")\nprint(train_events.head(10))\nprint(\"LOADING FINISHED ! \")\nprint(\"=\"*25)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:03:34.274388Z","iopub.execute_input":"2025-05-04T05:03:34.275043Z","iopub.status.idle":"2025-05-04T05:03:36.294769Z","shell.execute_reply.started":"2025-05-04T05:03:34.275017Z","shell.execute_reply":"2025-05-04T05:03:36.294093Z"}},"outputs":[{"name":"stdout","text":"CPU times: user 5 µs, sys: 0 ns, total: 5 µs\nWall time: 9.78 µs\n=========================\nLOAD TRAIN EVENTS\nNumber of missing timestamps : 4923\nPercentage of removed rows : 33.9%\nMemory usage of dataframe is 0.37 MB\nMemory usage after optimization is: 0.16 MB\nDecreased by 57.2%\n series_id night event step\ntimestamp \n2018-08-14 22:26:00-04:00 038441c925bb 1 onset 4992.0\n2018-08-15 06:41:00-04:00 038441c925bb 1 wakeup 10932.0\n2018-08-15 19:37:00-04:00 038441c925bb 2 onset 20244.0\n2018-08-16 05:41:00-04:00 038441c925bb 2 wakeup 27492.0\n2018-08-16 23:03:00-04:00 038441c925bb 3 onset 39996.0\n2018-08-17 05:10:00-04:00 038441c925bb 3 wakeup 44400.0\n2018-08-17 23:00:00-04:00 038441c925bb 4 onset 57240.0\n2018-08-18 06:48:00-04:00 038441c925bb 4 wakeup 62856.0\n2018-08-19 22:18:00-04:00 038441c925bb 6 onset 91296.0\n2018-08-20 07:25:00-04:00 038441c925bb 6 wakeup 97860.0\nLOADING FINISHED ! \n=========================\n","output_type":"stream"}],"execution_count":17},{"cell_type":"markdown","source":"DATA STATISTICS:","metadata":{}},{"cell_type":"code","source":"train_series.describe().T","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:03:41.591837Z","iopub.execute_input":"2025-05-04T05:03:41.592715Z","iopub.status.idle":"2025-05-04T05:03:45.097466Z","shell.execute_reply.started":"2025-05-04T05:03:41.592678Z","shell.execute_reply":"2025-05-04T05:03:45.096591Z"}},"outputs":[{"execution_count":18,"output_type":"execute_result","data":{"text/plain":" count mean std min 25% \\\nstep 10000000.0 245794.890625 162514.390625 0.0 113636.00000 \nanglez 10000000.0 NaN 0.000000 -90.0 -30.65625 \nenmo 10000000.0 NaN 0.000000 0.0 0.00090 \n\n 50% 75% max \nstep 227272.000000 348818.250000 778679.000000 \nanglez -6.734375 15.742188 89.750000 \nenmo 0.014900 0.039612 5.097656 ","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
countmeanstdmin25%50%75%max
step10000000.0245794.890625162514.3906250.0113636.00000227272.000000348818.250000778679.000000
anglez10000000.0NaN0.000000-90.0-30.65625-6.73437515.74218889.750000
enmo10000000.0NaN0.0000000.00.000900.0149000.0396125.097656
\n
"},"metadata":{}}],"execution_count":18},{"cell_type":"code","source":"train_events.describe().T","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:03:49.241097Z","iopub.execute_input":"2025-05-04T05:03:49.241796Z","iopub.status.idle":"2025-05-04T05:03:49.260494Z","shell.execute_reply.started":"2025-05-04T05:03:49.241763Z","shell.execute_reply":"2025-05-04T05:03:49.259829Z"}},"outputs":[{"execution_count":19,"output_type":"execute_result","data":{"text/plain":" count mean std min 25% 50% \\\nnight 9585.0 12.861555 8.168517 1.0 6.0 12.0 \nstep 9585.0 214352.125000 141268.312500 936.0 95436.0 200604.0 \n\n 75% max \nnight 19.0 43.0 \nstep 317520.0 739392.0 ","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
countmeanstdmin25%50%75%max
night9585.012.8615558.1685171.06.012.019.043.0
step9585.0214352.125000141268.312500936.095436.0200604.0317520.0739392.0
\n
"},"metadata":{}}],"execution_count":19},{"cell_type":"code","source":"print('='*25)\nprint(train_series.info())\nprint('='*25)\nprint(train_events.info())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:03:53.403715Z","iopub.execute_input":"2025-05-04T05:03:53.404524Z","iopub.status.idle":"2025-05-04T05:03:53.424663Z","shell.execute_reply.started":"2025-05-04T05:03:53.404501Z","shell.execute_reply":"2025-05-04T05:03:53.423859Z"}},"outputs":[{"name":"stdout","text":"=========================\n\nIndex: 10000000 entries, 2018-08-14 15:30:00-04:00 to 2019-02-03 09:53:15-05:00\nData columns (total 4 columns):\n # Column Dtype \n--- ------ ----- \n 0 series_id category\n 1 step float32 \n 2 anglez float16 \n 3 enmo float16 \ndtypes: category(1), float16(2), float32(1)\nmemory usage: 162.1+ MB\nNone\n=========================\n\nIndex: 9585 entries, 2018-08-14 22:26:00-04:00 to 2017-09-07 09:17:00-04:00\nData columns (total 4 columns):\n # Column Non-Null Count Dtype \n--- ------ -------------- ----- \n 0 series_id 9585 non-null category\n 1 night 9585 non-null int8 \n 2 event 9585 non-null category\n 3 step 9585 non-null float32 \ndtypes: category(2), float32(1), int8(1)\nmemory usage: 160.1+ KB\nNone\n","output_type":"stream"}],"execution_count":20},{"cell_type":"code","source":"print(\"\\nTrain Events Dataset Info:\")\nprint(f\"Shape: {train_events.shape}\")\n\nprint(\"\\nTrain Series Dataset Info:\")\nprint(f\"Shape: {train_series.shape}\")\n\nprint(\"\\nTest Series Dataset Info:\")\nprint(f\"Shape: {test_series.shape}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:03:58.340078Z","iopub.execute_input":"2025-05-04T05:03:58.340746Z","iopub.status.idle":"2025-05-04T05:03:58.345833Z","shell.execute_reply.started":"2025-05-04T05:03:58.34072Z","shell.execute_reply":"2025-05-04T05:03:58.344918Z"}},"outputs":[{"name":"stdout","text":"\nTrain Events Dataset Info:\nShape: (9585, 4)\n\nTrain Series Dataset Info:\nShape: (10000000, 4)\n\nTest Series Dataset Info:\nShape: (450, 4)\n","output_type":"stream"}],"execution_count":21},{"cell_type":"code","source":"train_series.reset_index(inplace = True)\ntrain_events.reset_index(inplace = True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:04:02.693589Z","iopub.execute_input":"2025-05-04T05:04:02.693984Z","iopub.status.idle":"2025-05-04T05:04:06.191124Z","shell.execute_reply.started":"2025-05-04T05:04:02.69396Z","shell.execute_reply":"2025-05-04T05:04:06.190312Z"}},"outputs":[],"execution_count":22},{"cell_type":"code","source":"train_series","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:04:10.108461Z","iopub.execute_input":"2025-05-04T05:04:10.1088Z","iopub.status.idle":"2025-05-04T05:04:10.122665Z","shell.execute_reply.started":"2025-05-04T05:04:10.108775Z","shell.execute_reply":"2025-05-04T05:04:10.121503Z"}},"outputs":[{"execution_count":23,"output_type":"execute_result","data":{"text/plain":" timestamp series_id step anglez \\\n0 2018-08-14 15:30:00-04:00 038441c925bb 0.0 2.636719 \n1 2018-08-14 15:30:05-04:00 038441c925bb 1.0 2.636719 \n2 2018-08-14 15:30:10-04:00 038441c925bb 2.0 2.636719 \n3 2018-08-14 15:30:15-04:00 038441c925bb 3.0 2.636719 \n4 2018-08-14 15:30:20-04:00 038441c925bb 4.0 2.636719 \n... ... ... ... ... \n9999995 2019-02-03 09:52:55-05:00 12d01911d509 431195.0 41.093750 \n9999996 2019-02-03 09:53:00-05:00 12d01911d509 431196.0 19.218750 \n9999997 2019-02-03 09:53:05-05:00 12d01911d509 431197.0 15.171875 \n9999998 2019-02-03 09:53:10-05:00 12d01911d509 431198.0 8.773438 \n9999999 2019-02-03 09:53:15-05:00 12d01911d509 431199.0 -8.968750 \n\n enmo \n0 0.021698 \n1 0.021500 \n2 0.021606 \n3 0.021301 \n4 0.021500 \n... ... \n9999995 0.114807 \n9999996 0.088806 \n9999997 0.123901 \n9999998 0.125244 \n9999999 0.142456 \n\n[10000000 rows x 5 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
timestampseries_idstepanglezenmo
02018-08-14 15:30:00-04:00038441c925bb0.02.6367190.021698
12018-08-14 15:30:05-04:00038441c925bb1.02.6367190.021500
22018-08-14 15:30:10-04:00038441c925bb2.02.6367190.021606
32018-08-14 15:30:15-04:00038441c925bb3.02.6367190.021301
42018-08-14 15:30:20-04:00038441c925bb4.02.6367190.021500
..................
99999952019-02-03 09:52:55-05:0012d01911d509431195.041.0937500.114807
99999962019-02-03 09:53:00-05:0012d01911d509431196.019.2187500.088806
99999972019-02-03 09:53:05-05:0012d01911d509431197.015.1718750.123901
99999982019-02-03 09:53:10-05:0012d01911d509431198.08.7734380.125244
99999992019-02-03 09:53:15-05:0012d01911d509431199.0-8.9687500.142456
\n

10000000 rows × 5 columns

\n
"},"metadata":{}}],"execution_count":23},{"cell_type":"code","source":"train_events","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:04:14.332506Z","iopub.execute_input":"2025-05-04T05:04:14.333158Z","iopub.status.idle":"2025-05-04T05:04:14.3466Z","shell.execute_reply.started":"2025-05-04T05:04:14.333126Z","shell.execute_reply":"2025-05-04T05:04:14.345852Z"}},"outputs":[{"execution_count":24,"output_type":"execute_result","data":{"text/plain":" timestamp series_id night event step\n0 2018-08-14 22:26:00-04:00 038441c925bb 1 onset 4992.0\n1 2018-08-15 06:41:00-04:00 038441c925bb 1 wakeup 10932.0\n2 2018-08-15 19:37:00-04:00 038441c925bb 2 onset 20244.0\n3 2018-08-16 05:41:00-04:00 038441c925bb 2 wakeup 27492.0\n4 2018-08-16 23:03:00-04:00 038441c925bb 3 onset 39996.0\n... ... ... ... ... ...\n9580 2017-09-05 09:26:00-04:00 fe90110788d2 32 wakeup 547152.0\n9581 2017-09-05 22:30:00-04:00 fe90110788d2 33 onset 556560.0\n9582 2017-09-06 04:07:00-04:00 fe90110788d2 33 wakeup 560604.0\n9583 2017-09-06 23:35:00-04:00 fe90110788d2 34 onset 574620.0\n9584 2017-09-07 09:17:00-04:00 fe90110788d2 34 wakeup 581604.0\n\n[9585 rows x 5 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
timestampseries_idnighteventstep
02018-08-14 22:26:00-04:00038441c925bb1onset4992.0
12018-08-15 06:41:00-04:00038441c925bb1wakeup10932.0
22018-08-15 19:37:00-04:00038441c925bb2onset20244.0
32018-08-16 05:41:00-04:00038441c925bb2wakeup27492.0
42018-08-16 23:03:00-04:00038441c925bb3onset39996.0
..................
95802017-09-05 09:26:00-04:00fe90110788d232wakeup547152.0
95812017-09-05 22:30:00-04:00fe90110788d233onset556560.0
95822017-09-06 04:07:00-04:00fe90110788d233wakeup560604.0
95832017-09-06 23:35:00-04:00fe90110788d234onset574620.0
95842017-09-07 09:17:00-04:00fe90110788d234wakeup581604.0
\n

9585 rows × 5 columns

\n
"},"metadata":{}}],"execution_count":24},{"cell_type":"code","source":"# Ensure it's in datetime format\ntrain_events[\"timestamp\"] = pd.to_datetime(train_events[\"timestamp\"], utc = True)\n\n# Extract datetime components\ntrain_events[\"year\"] = train_events[\"timestamp\"].dt.year\ntrain_events[\"month\"] = train_events[\"timestamp\"].dt.month\ntrain_events[\"day\"] = train_events[\"timestamp\"].dt.day\ntrain_events[\"hour\"] = train_events[\"timestamp\"].dt.hour","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:04:19.082797Z","iopub.execute_input":"2025-05-04T05:04:19.083117Z","iopub.status.idle":"2025-05-04T05:04:19.112933Z","shell.execute_reply.started":"2025-05-04T05:04:19.083095Z","shell.execute_reply":"2025-05-04T05:04:19.11208Z"}},"outputs":[],"execution_count":25},{"cell_type":"code","source":"train_events","metadata":{"trusted":true},"outputs":[{"execution_count":26,"output_type":"execute_result","data":{"text/plain":" timestamp series_id night event step year \\\n0 2018-08-15 02:26:00+00:00 038441c925bb 1 onset 4992.0 2018 \n1 2018-08-15 10:41:00+00:00 038441c925bb 1 wakeup 10932.0 2018 \n2 2018-08-15 23:37:00+00:00 038441c925bb 2 onset 20244.0 2018 \n3 2018-08-16 09:41:00+00:00 038441c925bb 2 wakeup 27492.0 2018 \n4 2018-08-17 03:03:00+00:00 038441c925bb 3 onset 39996.0 2018 \n... ... ... ... ... ... ... \n9580 2017-09-05 13:26:00+00:00 fe90110788d2 32 wakeup 547152.0 2017 \n9581 2017-09-06 02:30:00+00:00 fe90110788d2 33 onset 556560.0 2017 \n9582 2017-09-06 08:07:00+00:00 fe90110788d2 33 wakeup 560604.0 2017 \n9583 2017-09-07 03:35:00+00:00 fe90110788d2 34 onset 574620.0 2017 \n9584 2017-09-07 13:17:00+00:00 fe90110788d2 34 wakeup 581604.0 2017 \n\n month day hour \n0 8 15 2 \n1 8 15 10 \n2 8 15 23 \n3 8 16 9 \n4 8 17 3 \n... ... ... ... \n9580 9 5 13 \n9581 9 6 2 \n9582 9 6 8 \n9583 9 7 3 \n9584 9 7 13 \n\n[9585 rows x 9 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
timestampseries_idnighteventstepyearmonthdayhour
02018-08-15 02:26:00+00:00038441c925bb1onset4992.020188152
12018-08-15 10:41:00+00:00038441c925bb1wakeup10932.0201881510
22018-08-15 23:37:00+00:00038441c925bb2onset20244.0201881523
32018-08-16 09:41:00+00:00038441c925bb2wakeup27492.020188169
42018-08-17 03:03:00+00:00038441c925bb3onset39996.020188173
..............................
95802017-09-05 13:26:00+00:00fe90110788d232wakeup547152.020179513
95812017-09-06 02:30:00+00:00fe90110788d233onset556560.02017962
95822017-09-06 08:07:00+00:00fe90110788d233wakeup560604.02017968
95832017-09-07 03:35:00+00:00fe90110788d234onset574620.02017973
95842017-09-07 13:17:00+00:00fe90110788d234wakeup581604.020179713
\n

9585 rows × 9 columns

\n
"},"metadata":{}}],"execution_count":26},{"cell_type":"code","source":"df_onset = train_events[train_events['event'] == 'onset']\ndf_wakeup = train_events[train_events['event'] == 'wakeup']\n\nfig = make_subplots(rows=1, cols=2, subplot_titles=('Hourly Distribution of Onset Events',\n 'Hourly Distribution of Wakeup Events',\n ))\n\nfig.add_trace(go.Histogram(x=df_onset['hour'].dropna(), nbinsx=24), row=1, col=1)\nfig.add_trace(go.Histogram(x=df_wakeup['hour'].dropna(), nbinsx=24), row=1, col=2)\nfig.update_layout(\n showlegend=False,\n width=800,\n height=400,\n autosize=False,\n margin=dict(t=20, b=4, l=5, r=4),\n template=\"plotly_white\"\n \n)\nfig.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:04:29.579648Z","iopub.execute_input":"2025-05-04T05:04:29.579984Z","iopub.status.idle":"2025-05-04T05:04:31.386215Z","shell.execute_reply.started":"2025-05-04T05:04:29.579959Z","shell.execute_reply":"2025-05-04T05:04:31.385348Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":27},{"cell_type":"code","source":"df_onset = train_events[train_events['event'] == 'onset']\ndf_wakeup = train_events[train_events['event'] == 'wakeup']\n\nfig = make_subplots(rows=1, cols=2, subplot_titles=('day Distribution of Onset Events',\n 'day Distribution of Wakeup Events',\n ))\n\nfig.add_trace(go.Histogram(x=df_onset['day'].dropna(), nbinsx=24), row=1, col=1)\nfig.add_trace(go.Histogram(x=df_wakeup['day'].dropna(), nbinsx=24), row=1, col=2)\nfig.update_layout(\n showlegend=False,\n width=800,\n height=400,\n autosize=False,\n margin=dict(t=20, b=4, l=5, r=4),\n template=\"plotly_white\"\n \n)\nfig.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:04:39.208753Z","iopub.execute_input":"2025-05-04T05:04:39.209212Z","iopub.status.idle":"2025-05-04T05:04:39.261097Z","shell.execute_reply.started":"2025-05-04T05:04:39.209182Z","shell.execute_reply":"2025-05-04T05:04:39.260176Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":28},{"cell_type":"code","source":"plt.figure(figsize=(10,4))\n# plt.subplot(121)\nplt.title('Hour distribution with onset and wakeup')\nsns.histplot(x=train_events.dropna().hour, hue=train_events.dropna().event, stat='density', bins=24, binrange=(-0.5, 23.5))\nsns.kdeplot(train_events.dropna().hour, bw_adjust=0.45)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:04:44.882912Z","iopub.execute_input":"2025-05-04T05:04:44.883615Z","iopub.status.idle":"2025-05-04T05:04:45.438235Z","shell.execute_reply.started":"2025-05-04T05:04:44.883589Z","shell.execute_reply":"2025-05-04T05:04:45.437352Z"}},"outputs":[{"execution_count":29,"output_type":"execute_result","data":{"text/plain":""},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":29},{"cell_type":"code","source":"plt.figure(figsize=(10,4))\n# plt.subplot(121)\nplt.title('day distribution with onset and wakeup')\nsns.histplot(x=train_events.dropna().day, hue=train_events.dropna().event, stat='density', bins=24, binrange=(-0.5, 23.5))\nsns.kdeplot(train_events.dropna().day, bw_adjust=0.45)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:04:50.310206Z","iopub.execute_input":"2025-05-04T05:04:50.310494Z","iopub.status.idle":"2025-05-04T05:04:50.78399Z","shell.execute_reply.started":"2025-05-04T05:04:50.310474Z","shell.execute_reply":"2025-05-04T05:04:50.783232Z"}},"outputs":[{"execution_count":30,"output_type":"execute_result","data":{"text/plain":""},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"iVBORw0KGgoAAAANSUhEUgAAA2MAAAGOCAYAAAAadNt8AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAACaXklEQVR4nOzdeXxU1f3/8deZ7CEbYUsgkBBWWQQRRBZlE0WwCIpKpdaWirvUX1ut2rovSPlatVKXutuqgAtaFrGKoCCoILIElMgS9iWBLCSBbHN+f1wyEpNAQiaZSfJ+Ph55ZObOnXs/d+5kcj9zzvkcY621iIiIiIiISJ1y+ToAERERERGRxkjJmIiIiIiIiA8oGRMREREREfEBJWMiIiIiIiI+oGRMRERERETEB5SMiYiIiIiI+ICSMRERERERER9QMiYiIiIiIuIDSsZERERERER8QMmYiNSqpKQkkpKSfB1GlTzwwAMYY1i6dGmZ5cYYhg4d6pOYoOLX8LXXXsMYw2uvveaTmEr5+rWpDUOHDsUYU63n+Mv5kJrx98+rpUuXYozhgQce8HUoIuIlSsZERGpRWloaxhh+85vf+DqU0+LvF6d1RRfBVVfZlxoiIlJeoK8DEBHxd99//z3h4eE+2//ixYt9tu9T8fVrUxveeOMN8vPzfR2GiIg0AkrGREROoWvXrj7df4cOHXy6/5Px9WtTG9q1a+frEEREpJFQN0URqTFrLTNnzqR79+6EhobSpk0bbr31VrKzsytcPzs7mxkzZjB8+HASEhIIDg6mRYsWjB07lpUrV5ZZNzMzk/DwcDp06IC1tsLt/eIXv8AYw+rVq6sU77fffsuoUaOIjIwkKiqKCy64oNx+T1TRuKgjR47w8MMP06NHD6KiooiMjKRDhw5cddVVfPvtt4DTXat9+/YAvP766xhjPD+lY4tO7P72zTffMGbMGGJjYzHGkJaWBpy6q+CCBQsYOHAgTZo0oWnTpkyYMIEff/yx3HonGwv18zFPpXHt2LGDHTt2lIn9xC6XlY0Zy87O5u6776ZLly6EhobStGlTLrroIj799NNy6574Gqxdu5YxY8YQExNDeHg4Q4YMYcWKFZUe+4lyc3MJDg5m0KBBZZYfPXqU0NBQjDH8+9//LvPYc889hzGGV155pdLX6Te/+Q3Dhg0D4MEHHyzzWlTUFW/JkiUMHTrU8/4aM2YM33//fZWOoZTb7eb555+nX79+RERE0KRJE/r168dzzz2H2+0ut37pecjIyOD6668nPj6ekJAQunfvzquvvlpufWstr7/+OgMHDqRFixaEhobStm1bLrroImbPnl1u/d27d3PrrbeSnJxMSEgIzZo1Y+zYsaxatarMeklJSTz44IMADBs2rMxrdSqFhYXMnDmT0aNHk5iYSEhICLGxsVxwwQV89NFHFT6n9G8jLy+PO+64g3bt2hESEkLHjh2ZPn16hZ8Z1f28qkzr1q1p06ZNueWJiYkYY3j44YfLLP/oo48wxnDfffd5lqWmpnLXXXfRt29fWrRoQUhICImJiVx//fXs3r27yrEcO3aMCRMmYIzhlltuKfMeefvttxk2bBgxMTGEhoZyxhln8Mgjj1BQUFBmG6fqUl3R58eJf7srV67kggsuIDo6msjISC666KIqfyaLNGZqGRORGrv99tv5xz/+QXx8PNdffz1BQUF8+OGHfP311xQWFhIcHFxm/e+//56//OUvnH/++YwZM4amTZuyc+dO/vvf//LRRx8xb948Ro0aBUDTpk2ZOHEir776Kp9++ikjR44ss61du3bx0UcfcfbZZ9O3b99TxrpixQouuOACCgsLueyyy+jYsSNr165l6NChDB8+vErHa61l1KhRrFixggEDBnDdddcRGBjI7t27WbJkCeeddx5nn302Q4cOJSsri6effppevXoxbtw4zzZ69+5dZpsrV65k2rRpDB48mMmTJ5ORkVHudavI+++/z0cffcT48eMZOnQoa9eu5b333mPJkiWsWLGCLl26VOmYfi4pKYn777+fp556CnDOcWWx/1xWVhaDBg1i06ZN9OvXj9tvv52MjAzmzJnDhRdeyHPPPccNN9xQ7nmrV6/mb3/7m+c13blzJ++99x4jRoxg7dq1pzyWiIgIzjnnHL7++muOHDlCZGQkAF9++aXnwnPx4sVcc801nueUdgEdMWJEpdstPW+vv/46Q4YMKZN8/jxJnj9/Ph9++CEXX3wxN954I5s2bWLhwoWsWrWKTZs20bx585MeQ6lrrrmGt956i7Zt23LddddhjGHu3LncfPPNLF++nDfffLPcc0pf9+DgYCZMmEBBQQHvvPMOkydPxuVyce2113rW/ctf/sK0adNo3749V155JdHR0ezbt49Vq1bxzjvvcNVVV3nWXbNmDRdeeCGHDx/moosu4rLLLiMjI4MPPviAwYMHM3fuXEaPHg0475MPPviAzz//nGuvvbZa4w0PHz7M73//ewYOHMjIkSNp0aIF+/btY968eYwePZoXX3yR6667rtzzioqKuOiii9i7dy8XX3wxgYGBfPDBB9x1110cO3aM+++/v8z61f28qszw4cN58803+eGHHzwtxFu2bGHnzp2A89669957PetX9F57//33ef755xk2bBgDBw4kODiYjRs38tJLLzFv3jxWr15dYcJ3oszMTMaOHcuXX37JtGnTuOuuuzyPTZ48mVdffZWEhAQuv/xyYmJi+Oqrr7j33ntZvHgxn3zyCYGBNb8U/Prrr5k2bRoXXHABt9xyC1u2bOH999/niy++4H//+x/nnXdejfch0mBZEZEa+PLLLy1gO3ToYA8dOuRZfvToUXvuuedawCYmJpZ5TlZWlk1PTy+3rV27dtn4+HjbtWvXMstXrVplAXv55ZeXe879999vAfuvf/3rlLG63W7bpUsXC9gPPvigzGNPPfWUBSxglyxZUuYxwA4ZMsRzf/369Raw48aNK7ePkpISe/jwYc/97du3W8Bee+21Fca0ZMkSz36ff/75CtdJTEws9xq++uqrnufNmzevwmMZPnx4meVDhgyxlX3sl27v1VdfPeW+T/Tz18Zaa6+//noL2Ouvv9663W7P8tTUVBsVFWWDg4Pt9u3bPctPfA1+vv/nn3/eAvamm26qNIYT3XvvvRaw8+fP9yy76667bEBAgB0+fLhNSEjwLC8pKbGxsbE2OTm5zDYqep1KY7z//vsr3G/p6xcQEGA//fTTMo/dddddFrDTp0+v0jG89dZbFrBnnXWWPXLkiGd5bm6uPfvssy1g33zzzTLPKX39fve739ni4mLP8o0bN9qAgAB7xhlnlFk/NjbWtmnTxubl5ZXb/4l/m0VFRbZDhw42JCTELl26tMx6e/bssa1bt7ZxcXH22LFjnuWlf5M//zs6lWPHjtldu3aVW56VlWW7d+9umzZtavPz88s8lpiYaAF78cUXl3nswIEDNjo62kZHR9vCwkLP8tP5vKrMyy+/bAE7c+ZMz7LS9+vIkSNtcHBwmde3d+/eNiwszBYUFHiW7d69u8xrV+rjjz+2LpfL3njjjWWW//x9mJaWZs844wwbFBRk//Of/5RZt/Q9OX78+HKvW+k5euqppzzLTvVZdbK/C8A+88wzZR774IMPLGA7duxoS0pKKtymiFirbooiUiOlXaD+8pe/EBsb61keGhrKtGnTKnxOdHR0hS0ECQkJTJgwgR9++MHz7TJA37596du3Lx9++CH79+/3LC8pKeHll18mMjKSX/7yl6eMdcWKFWzevJnzzz+fSy+9tMxjt956a7XHZoWFhZVb5nK5aNq0abW2A05rU0WtRacyfPhwLrnkkjLLSo/ls88+Y8eOHdXeZk0UFhbyn//8h4iICKZNm1amW1OnTp2YOnUqhYWFvPHGG+WeO2jQoHJdpCZPnkxgYCDffPNNlfZf2upwYtGTxYsXc/bZZ3PZZZexe/duUlNTAVi7di2HDx8+aatYdU2cOLHc9q6//nqAKh9DaZfJxx9/nIiICM/yJk2aMH36dABeeumlcs8LDw/n73//OwEBAZ5l3bp1Y9CgQXz//ffk5uaWWT8oKKjMuqVO/NtcsGABW7du5bbbbmPIkCFl1mvdujV33nkn+/fv90qRmZCQEBISEsotj46OZvLkyWRmZpbrFlnqH//4R5m/x5YtW3LppZeSnZ3N5s2bPctP5/OqMpW911q1auV5ny9fvhyAQ4cOsW7dOgYPHlym5a1NmzaEhISU2/aFF15I9+7d+fjjjyvd/9q1axkwYAB79uzho48+YtKkSWUef/rppwkMDOSVV14p91l177330qxZswpbWE9Hx44dufnmm8ssu/TSSxkyZAhbtmxh2bJlXtmPSEOkbooiUiNr1qwBKHehBjB48OAKL/bA6Tr29NNPs3LlSg4ePEhhYWGZx/fs2VOmkMLNN9/M5MmTeeWVV7jnnnsAWLhwIbt37+amm24qc9F6OrEGBAQwePBgtm7desrtdOvWjd69e/P222+zY8cOLr30UgYPHkzfvn2r3MXp584555zTet6pjuW7774jMTHxtLZ9OjZv3kx+fj6DBg0qc7Fbavjw4TzyyCN899135R6rqJtpUFAQrVq1IjMzs0r7HzBgAGFhYZ4L5OzsbNasWcOdd97p6Ya6ePFiOnfuzGeffeaJyVsqOoa2bdsCVPkY1qxZg8vlqnAs3pAhQwgICKjw9evUqRNRUVEn3X/p38mkSZN45pln6NatG1deeSVDhgxhwIABREdHl3lu6VjKHTt2VFjWv3Rs4vfff+/pqlgTGzduZMaMGXzxxRfs27ePY8eOlXl8z5495Z4THR1Nx44dyy2v6HU/3c+riiQmJpKcnMzSpUtxu92eMYQXXHABQ4YMITAwkMWLF3PhhReyZMkSrLXl3mvWWt58801ee+011q1bR2ZmJiUlJZ7HK/s8Wb58OX//+9+JjIzkiy++oFevXmUez8/PZ926dTRv3tzT1fjnQkJCqj2WsTLnnXceLlf57/eHDh3K559/znfffVfhay4iSsZEpIZKB723atWq3GOBgYEVtoDNnTuXCRMmEBoaysiRI+nQoQNNmjTB5XKxdOlSPv/883KDyydOnMgf//hHXnzxRe666y5cLhf/+te/AKrconSyWAHi4uKqtJ2AgAA+++wzHnroId59913+/Oc/AxAZGcm1117LtGnTqpQcns6+f+5Ux1LdogQ1Vbq/+Pj4Ch8vXZ6VlVXusZiYmAqfExgYWOYC9WSCg4MZPHgwn376Kenp6axYsYKSkhJGjBjBGWecQXx8PIsXL+amm25i8eLFGGO8moxVdAylY3KqegzZ2dnExsZWeCFe+jd18ODBKu27sv0/+eSTJCcn8+qrr/L444/z+OOPExgYyOjRo3niiSc8yc2hQ4cAeOedd04a889b3U7HV199xfDhwykuLmbEiBGMHTuWqKgoXC4Xa9eu5cMPPyz3uQDVO+7T+bw6mREjRvDiiy+yZs0agoKCSE9PZ8SIEURGRtKvXz/PlwKVjU38wx/+wFNPPUV8fDwXXXQRbdq08bRivfbaa5W2bH/33XccOXKEgQMHVljRNDMzE2st6enpnoIqtcnfPodE6hMlYyJSI6XfpB84cIDk5OQyjxUXF5ORkVGu69G9995LcHAwq1ev5owzzijz2A033MDnn39ebj9hYWH85je/4cknn+R///sf3bt356OPPqJ///7lvhWuSqwVObEL5Kk0bdqUJ598kieffJItW7bw+eef88ILLzBz5kyysrLKVe07lapUm6vIqY7lxJaO0m+ui4uLyw3aryg5Oh2l+6vstdy3b1+5uLxt+PDhfPLJJyxevJgVK1YQGhrqqbA4fPhwPvroIwoKCli2bBndu3enZcuWtRbL6YiOjubw4cMUFRURFBRU5rHSv6mKWsCqIyAggNtvv53bb7+dgwcPsnz5cmbNmsU777zDxo0b2bhxIyEhIZ7z9OGHHzJ27Nga7fNUHnnkEY4ePeqpRnmiadOm8eGHH9Z4H6fzeXUyw4cP58UXX+TTTz/1JM+lCdfw4cOZNm0ahw8fZvHixURHR9OnTx/Pcw8ePMg//vEPevTowYoVKzwFZ0q9/fbble731ltv5eDBgzz//POMHTuWDz74oExXxNLjPOusszytgady4udDRU72GVGdzyERKUtjxkSkRkovLipKoJYvX15ha8CWLVvo1q1buUTM7XZ7xlhU5KabbsIYwwsvvMDLL79MSUlJtcZZnSzWkpKSk+77ZDp27Mjvfvc7Pv/8cyIiIspcNJZ2e6pqq0h1nepYzjrrLM/y0rFsu3btKvecykpQBwQEVCv2Ll26EB4ezrp16yq8eFuyZAlAmYtSbztxLM9nn33GwIEDCQ0N9Tx2+PBhnnvuOfLy8qo8Xqy2z+OJzjrrLNxuN1988UW5x7744gtKSkq8+vq1bNmSyy67jDlz5jB8+HC2bt1KSkoKAOeeey5Atcb8nO5rtWXLFmJjYyvsnlnR+/x0nM7n1ckMHz4cY4znvZacnOypIDlixAjcbjdvvPEGP/74I0OHDi3TDXLbtm243W4uvPDCconY7t272bZtW6X7Ncbw3HPPcfvtt/O///2PMWPGkJeX53k8IiKC7t27s3HjRg4fPlylYznZ50NOTo5nrGVFli9fXuGUC6VTP5z4OSQiZSkZE5EaKS248Oijj5b5p3/s2DHuvvvuCp+TlJTEjz/+yN69ez3LrLU88MADbNq0qdJ9derUiREjRjB//nyef/55YmJimDhxYpVjHThwIF26dOGLL74o9y37zJkzqzReDGD79u0VXihlZmZSUFBQ5hvqpk2bYowpU5DEmz777DPmz59fZlnpsQwbNqzMeLHScWkvvvhimfUXL15c6bfwzZo1Iz09naNHj1YpnuDgYCZNmsSRI0fKlPUG2Lp1K//4xz8ICgoqU17e2/r06UN0dDQffvghGzduLJNwlXZJLC3WUNUuis2aNQOotfN4osmTJwNw9913k5+f71men5/vKVv+u9/97rS3X1BQwJdffllueVFRkedvODw8HHCKMHTo0IF//vOfLFy4sMLtrVy5skycp/taJSUlcfjwYdavX19m+csvv3zSQhbVcTqfVyfTsmVLunfvzpdffskXX3xR5r1W+iVAZe+10qTt50lgbm4uU6ZMqbSF6kRPPvkkd999N0uWLOGiiy4iJyfH89gf/vAHCgsLmTx5coVfjGRmZpZpNYuMjKRr1658+eWXZT6HS0pK+MMf/nDSz4Aff/yRZ599tsyyDz/8kM8//5yOHTuqtL3ISaiboojUyKBBg7jtttt45pln6NGjBxMmTPDM29O0adMKxw79v//3/7jxxhs566yzuPzyywkKCvJcAPziF79g3rx5le7v5ptv5tNPP+XAgQPcdtttFVY0rIwxhpdffpmRI0dy+eWXl5lnbPHixYwaNYpFixadcjvr1q3jsssuo1+/fpxxxhm0bt2a9PR0PvzwQ4qKijxjyMD5hrp///4sW7aMSZMm0blzZwICAhg7dixnnnlmlWOvzC9+8QvGjx/P+PHjPcfy0UcfERsbW+7i6Le//S0zZsxg2rRprFu3jm7dupGamuqZp+y9994rt/0RI0awatUqRo0axfnnn09ISAi9evXiF7/4RaUxPf744yxbtoyZM2eyatUqhg0b5pln7MiRI8ycOdMzGXZtCAgIYOjQoZ6E+8QL5MTERDp06MDWrVsJCAioclGBLl260KZNG2bNmkVQUJBnYt9rrrnG6wVSrr76aj788EPmzJlD9+7dGTduHMYYPvjgA7Zv385VV11VrnJedRw9epTBgwfTsWNHzj77bBITEzl27BiffPIJ33//PWPHjvW0WgcFBfH+++9z0UUXMWbMGAYOHEjv3r0JDw9n165drFq1im3btrFv3z5PAjds2DBcLhd33303KSkpnhaXv/71ryeN6/bbb+fjjz9m8ODBnrnPVq9ezfLly5kwYQLvvvvuaR9zqdP5vDqVESNGeFoST3yvhYSEMGjQoErHi8XFxTFx4kRmzZpF7969ufDCC8nOzuaTTz4hNDSU3r17s3bt2lPu/7HHHiM0NJT777+fkSNHsmjRIpo2bcrkyZP59ttvefbZZ+nQoQMXXXQR7dq14/Dhw2zfvp0vvviC3/72tzz//POebd1xxx387ne/Y9CgQVxxxRWEhoayZMkSioqK6NWrF+vWraswhlGjRvHHP/6Rjz76iF69ennmGQsNDeWVV16psLiHiBzn28r6ItIQuN1u+8wzz9iuXbva4OBgGx8fb2+++WablZVV6TxVr776qu3Vq5cNDw+3zZo1s+PGjbPr168/5RxFxcXFtnnz5hawKSkppxXv6tWr7UUXXWQjIiJsRESEHTFihF2xYkWl++Znc2nt2rXL3n333XbgwIG2VatWNjg42LZp08aOGjXKLly4sNz+fvzxR3vJJZfY2NhYa4wpM5/Wqeavsvbk84y9+uqrdt68efbcc8+14eHhNjo62l522WV28+bNFW4rJSXFXnzxxTYiIsI2adLEDhkyxC5durTSecZyc3PtjTfeaNu0aWMDAgLKzUP089emVGZmpr3zzjttx44dbXBwsI2OjrYXXHCB/fjjj8ute6rX4FRznVXkH//4hwVsVFRUmXm3rP1pHrRzzjmnwudWNh/bN998Y4cPH26joqI857H0vVLZ61eqstepMiUlJfaf//ynPfvss21YWJgNCwuzffr0sTNnzqxwzqaTbf/aa6+1gGdut8LCQjt9+nQ7atQo27ZtWxsSEmKbN29u+/fvb5977rky82CVOnDggP3zn/9su3fvbsPCwmyTJk1sx44d7eWXX27//e9/26KiojLr//vf/7a9evWyoaGhnnmoqmLevHm2f//+NiIiwkZHR9uRI0fazz///LTmwavs7/l0Pq9O5r///a8FrDHGHjhwoMxjjz32mAVsq1atKnxuXl6eveeeezxzuSUkJNibb77ZZmRkVHu+u7/97W+e+elOnCtu3rx5dsyYMbZFixY2KCjItmrVyvbr18/+5S9/sd9//3257bz00ku2W7duNjg42LZq1cpef/31VYpnxYoVdsSIETYyMtJGRETYkSNH2m+++aaqL6NIo2WstbYukj4REW/Ytm0bHTt2ZNCgQZq7RkTEh5YuXcqwYcO4//77K5z6QEROTe3GIlKv/N///R/WWm699VZfhyIiIiJSIxozJiJ+b+fOnbz11lv8+OOPvPrqq/Tq1YsrrrjC12GJiIiI1IiSMRHxe9u2bePuu+8mPDyckSNH8txzz2lAuIiIiNR7GjMmIiIiIiLiA/pqWURERERExAeUjImIiIiIiPiAkjEREREREREfUDImIiIiIiLiA6qm6GWZmZkUFxf7OgyvatGiBenp6b4OQyqh8+PfdH78m86P/9M58m86P/5N58d3AgMDadq06anXq4NYGpXi4mKKiop8HYbXGGMA57hUeNP/6Pz4N50f/6bz4/90jvybzo9/0/mpH9RNUURERERExAeUjImIiIiIiPiAkjEREREREREfUDImIiIiIiLiAyrgISIiIiLixwoKCigoKKj2844ePUphYWEtRCQAISEhhISE1GgbSsZERERERPxUXl4exhgiIyM9FRKrKigoqEFV+fYn1lqOHj1KXl4eTZo0Oe3tqJuiiIiIiIifKi4uJjw8vNqJmNQuYwzh4eE1nl9YyZiIiIiIiJ9SEubfanp+lIyJiIiIiIj4gJIxERERERERH1ABDxERERE/ZEtKYE8adttm2LkNjIGIaIiMwsQ2h07dMZHRvg5TRGpAyZiIiIiIH7FZh7Dv/xv77ZdQWHE5c1t6o217TLfemF79oeMZGl8kDdqECRPo1q0bDz30kK9D8RolYyIiIiJ+wBYVYT/9L3bBbCg45iwMawLtO2GSOkNAAORmw5Ec7P7dsDsNdm3H7tqO/XgutIzHDByBOXcYplkLnx6LiFSNkjERERERH7O7t+N+7nE4uM9Z0KErrgm/heQuGFfFQ/xtTib2+/WQsgb73Uo4uA/7wX+wH76FOXsg5uIJmHbJdXgU0pC53W7++c9/8uabb5Kenk779u25/fbbGT16NP369WPq1Klce+21nvVTUlIYNWoUX331FQkJCWRnZ/Pwww/z8ccfU1hYyJlnnskDDzxA9+7dAXjiiSdYtGgRN9xwAzNmzCA7O5thw4YxY8YMIiIiuP3221m5ciUrV67k5ZdfBuCrr76ibdu2Pnk9vEXJmIiIiIgP2c0puP/5CBzNh+hYzOXXYvoPqTQJK2WimmL6D4H+Q7DHbsSuWYldsRg2b8CuXo5dvRx69MF1yURMh651dDTSUD3zzDO8//77PP7447Rv356vvvqKqVOn0qxZM8aNG8cHH3xQJhl7//336devHwkJCQDccMMNhIaG8p///IfIyEj+85//cNVVV7Fs2TKaNm0KwI4dO/j44495/fXXyc7O5sYbb2TmzJncddddPPTQQ2zbto2uXbvypz/9CYBmzZrV/QvhZUrGRERERHzErlmJ+8X/g+Ii6NQN1y1/xTSJqPZ2TGgYZuBwGDgcu3s79qP3sKuWQ8oa3ClrMOecj7n8N07hD5FqKigo4JlnnmHWrFn07dsXgMTERFatWsV//vMfbrrpJl544QX27NlDmzZtcLvdfPjhh/z+978H4JtvvmHt2rWsW7eOkJAQAO677z4+/vhjFixYwK9+9SvAaX178skniYhw/gYuv/xyli9fDkBUVBTBwcGEhobSsmXLun4Jao2SMREREREfcC/7H/bfz4J1Q+9zcU35IyY4pMbbNQntMVP+hL10EnbhO9gVi7HffIFd+zVm9BWYC8djgoK8cATSWKSlpXH06FF++ctfllleVFREjx496NGjB506dWLu3LnceuutrFy5kkOHDnHJJZcAsGnTJvLy8ujRo0eZ5x87dowdO3Z47rdt29aTiAG0bNmSQ4cO1eKR+Z5fJmOLFi1i3rx5ZGVlkZiYyOTJk+nYsWOl669cuZLZs2eTnp5OXFwckyZNok+fPp7H58yZw4oVKzh06BCBgYEkJyczceJEOnXq5FnnlltuIT09vcx2r776asaNG+f14xMREZHGzf3VUuwbMwEw512ImXQTJiDAq/swLeMxv5mKHTYG96x/wZbvnTFl33yBa/LtmMTKr61ETpSXlwfAG2+8QVxcXJnHgoODARg/fjwffPABt956Kx988AFDhw4lNjbW8/yWLVvy7rvvltt2dPRP0zMEBpZNTYwxuN1urx6Lv/G7ZGzFihW88cYbTJkyhU6dOrFgwQIeffRRnnrqqTInq9TmzZt5+umnufrqq+nTpw/Lly9nxowZTJ8+nXbt2gHQunVrJk+eTKtWrSgsLGTBggU88sgjPPPMM0RFRXm2deWVV3LBBRd47oeGhtb+AYuIiEijYtevwr76FABm+CWYiVNqtSS9SeyA687Hndax2S/B3p24H/uT00o25kpMoFrJ5OQ6d+5MSEgIe/bsYcCAARWuM378eP72t7+xfv16FixYwLRp0zyP9ezZk/T0dAIDA2tUcCMoKKjBJWcnHxnqA/Pnz2fEiBEMGzaMhIQEpkyZQnBwMEuWLKlw/YULF9K7d2/Gjh1LQkICEydOJDk5mUWLFnnWGTx4MGeeeSatWrWibdu2/PrXv+bo0aNlmkUBwsLCiImJ8fwoGRMRERFvsqkbcT8/HdxuzLlDMVddVydzgxljcPUfguvBf2L6Dga3Gzt/Nu5H/4Tdtb3W9y/1W0REBDfccAMPPPAAc+bMIS0tjQ0bNvDKK68wZ84cwOli2LdvX/74xz9SUlLChRde6Hn+eeedx9lnn83kyZP5/PPP2bVrF6tWreLxxx9n3bp1VY6jbdu2fPfdd+zatYvDhw83iMTMr1rGiouL2bZtW5mugS6Xi549e5Kamlrhc1JTUz39UUv16tWLVatWVbqPTz/9lPDwcBITE8s89sEHH/Dee+/RvHlzBg8ezJgxYwiopMtAUVERRUVFnvvGGMLCwjy3G4rSY2lIx9SQ6Pz4N50f/6bz4/8a2jmyO7fhnvkwFBVizuyL6ze/93rXxFMxUdFw459xrxqI+83nYPd23I/+wam4ePEETGDVLw0b2vmRk7vzzjtp1qwZM2fOZOfOnURFRdGzZ09uu+02zzrjx4/nnnvuYcKECZ7rYnDeI//+97+ZPn06f/jDHzh06BAtWrTg3HPPpXnzqheVueGGG7j99tsZOnQox44d85vS9jX5GzDWWnvq1erG4cOHufHGG3nkkUfo3LmzZ/l//vMfNm3axGOPPVbuOb/85S+55ZZbGDx4sGfZxx9/zLvvvsuLL77oWfbtt9/y1FNPUVhYSExMDHfccUeZcWjz58+nffv2REREsHnzZt5++22GDh1apkTniebMmVOm32v79u2ZPn16jY5fREREGqaiPTs5eOd1uLMOE9y9Ny0emonLxz1wSjIPkfnPxzm60ul9FNShK7G/v5fgDl18GpeUtW3bNiIjI30dhlTiyJEjJCef/nx+ftUyVpu6d+/OjBkzyMnJYfHixTz55JM89thjnnFoJ7auJSYmEhgYyIsvvsjVV19NUAUVh8aPH1/mOaUZcXp6OsXFxbV8NHXHGENcXBz79+/Hj/J2OU7nx7/p/Pg3nR//11DOkc08RMnjd0LWYWjbnpIb/syBzExfhwWAnfz/cPXog/vNFyja+gMHfn8NZujFuMb96pQl9hvK+fF3hYWFZXpjVUdQUNBpP1eqprCwkH379pVbHhgYSIsWLU75fL9KxqKionC5XGRlZZVZnpWVRUxMTIXPiYmJITs7u8yy7OzscuuHhoYSFxdHXFwcnTt3ZurUqXz22WeMHz++wu126tSJkpIS0tPTad26dbnHg4KCKkzSgAb5gWStbZDH1VDo/Pg3nR//pvPj/+rzObJ5R3D//V44dBBaxuO6/QEIa+JXx2POGYKrc0/snJexq5ZhlyygZPVyzPhrMAOGn7LrYn0+PyLeUJP3v18lY6Vl51NSUjjnnHMAZ/K3lJQURo0aVeFzOnfuzIYNGxgzZoxn2fr168uUra+Itfak3xSkpaVhjClTbVFERKQhs0VFcCQL8vOcn6N5WM/tXDh6FAqPQcExbGEBxrggIAACAyEkDGKbQ2wLTGwLiEs4rcmLGxKbl4v76Qdh3y6IicX1/x7CRDX1dVgVMjGxmOvvwJ53Ie63/wX7dmHfmIldMAcz6nLMoAs0N5lILfCrZAyc7oL//Oc/SU5OpmPHjixcuJCCggKGDh0KwMyZM4mNjeXqq68GYPTo0TzwwAPMmzePPn368OWXX7J161auv/56wJlM7v3336dv3740bdqUI0eOsGjRIg4fPuwpzZmamsqPP/5I9+7dCQsLIzU1lddff53zzjuvzMRzIiIiDYF1u2HvTmxqCmzbjM044LTcZB2u3nZOtTy2BbRtj2mbjGmbBG2ToXmrRlHwweZk4X7yfti9HZpE4rr9IUzzVr4O65TMGb1w3fcU9rMF2EXvwaGD2Defwy6YjRkyCjNwhJNsi4hX+F0yNnDgQHJycpgzZw5ZWVkkJSVxzz33eLodZmRklPkQ79KlC1OnTmXWrFm8/fbbxMfHc8cdd3jmGHO5XOzdu5cnnniCI0eOEBkZSYcOHXjwwQc91VcCAwNZsWIF77zzDkVFRbRs2ZIxY8aUq9IoIiJSX1m3GzZvwC77H3bTWsg7UvGKAYEQ3gTCI5zfYU0w4U2c26HhEBICIaEQHALWQnExlBTD0Tw4nIE9nO4kdocz4HA6HE7HrvvmpwQtLBxatcE0awnNWznJWfPjt5u1xAQF19ErUnvs4QzcT94L+/dAVIzTItamna/DqjITGIS5cBx2yMXY5f/DfjwXMjOwH76F/e8s6N4bM/ACXL36+TpUkXrPr6opNgTp6ekNaqCkMYb4+Hj27dun/uB+SOfHv+n8+LfGcn7skWzsisXYLz6GgycMMg8JhQ5dMZ26YeLbQrOW0KwVRER6peXK5ufB7jRnDqtd25zfe3c4ydvJxMRC8zhMizhMy3hie51NZlQziPbP7n0/Z/fvxv3UA05CGtsc1/97GBPXxtdh1YgtKsKuXo5d/gmkpvz0QHAwYf0GU9CtD/TogwlXb6LakJOTc9rDZlTAo/ZVdn6CgoKqVMBDyZiXKRmTuqTz4990fvxbQz4/1lpITcF+vgj73cqfEqDQMGei4XOHQWLHas0p5ZW4iovhwB44uM/TNdJmHIDSn4JjlT85OhaSOmISO2ISOzi3/Wz8lXvVMuzrM6HgqFOs4w+PYJo1rC599sBe7JefYlctc85ZKeNyzkm33pgzekHbZKdFVWpMyZh/UzLmZ5SMSV3S+fFvOj/+rSGeH5ubg13xGXbZx04XuVKJHZ3xPv3Ow4SGVb4BH7LWQu4RyNiPTd8P6fvhwB4C9u6geGcaWHf5J8XEQrsOmHYdMG3bQ3xbaBFX90lmURH2nZexSxY6Czp3x3XDnX6XLHqTtRazaxvhm9dz5ItPYP/u8is1bwUJ7TEtWkFUDETFYCKjITj0eHfXsBO6vYZCYGCjGE9YXUrG/FtNkzG/GzMmIiIiVWeLCuGH9divP8d+uwKKj194hYRh+p+POX+U05Lk54wxEBkFkVGY9p09y+Lj49mbth27cys2bQvs2IrdscW5+M86DFmHsetX/TQmLSAQWsZDfAImrq3zO74txLXBhHh/kmW7eQPu2S/Bru1OzBdPwFw6CRMQ4PV9+RNjDCaxIzHnnsfRCy/DfeigMxZx01rs1h+c8YLHWzxP/KrjpF97BAY6CVyLeEzLeGjdDtOhK8S3xbhctXtAIj6iZExERKQesdbCgb3YrT9g16+Cjd853eJKteuAGXIR5pzzMaHhvgvUi0xIKHTshunYzbPMHjsKu7djd2yDHVuwe3c6CVrBMaeU/L5dWFY665Y+qVlLJzlL6oTp1B2Su5x2S6HdsxP3+6/D+lXOgiaRuH73/zA9+9bgSOsvE9sCM3gkDB4JOPOrsWs7dvd2yDwMOVnYnCzIzTk+PUKBc64Kj/3Ujba42GnR3b/Hc84sOEVf2nfGJHfFdOjinDeNTyPIXfLTly+VMEUFBHmj5T8wiCJXw/6CwVeUjImIiHiJ09UuxyneUHDMmYMrIMj5xj+8CTSJcFqsqtAVy7rdkJvtjK8qvUDdkwbbUiE/t+zKMc0wvftjBo3AJJ18ns2GwoSGlU/Q3G7IPOQkYvt3wb7d2H3Ob895OXQQm7LGuch3uZwunJ26Yzp3h45nYJpEVrpPm5OJXfs1ds1K2LTO6Trpcjmtj7+4qkF3S6wu0yQSup6J6XrmKde1JSXO30veEacl7eA+OLgXu2MrbE+Fo/lOi9umtT8l1i1bQ0IipnWiU6kytoXTbTWqaZ13U/WZ4iIKFr1/0lVcrgDc7pIa7ypk1GUQXL+Ssf79+3PdddcxZcoUX4dyUo3k3SoiVWGLiyEn0+n6U1wETZs7F3ma6FOkQrawADanON3kNm+AQwegsPDkTwoIdJKyJpHO79Jv+EtLxB87CtmZzuTLJZVcRAUFQ2IHTJeemN79nYRCY22crmzNWkCzFpgefco8Zo/kOEna3h2w9QdnjrXDGbA9Fbs9Ffu/uWAMNG0GsS2dwhuR0ZB3BHsk2zknu9Occv6lzjoX12W/xsQl1O2BNjAmIOD4dApNnDF/Z/TyPGZLSmBPGnbrZtj2g9MFMn0/HNzrJGxrVpbv+hgeAaFhzk9YuDM2LSzMSeBDw396LDTM+XsE59wbFxgAc/z+8R9wplxoGQctW2OCQ+riZZFGQsmYSCNmj+XDxrXOHEDfr618wteoGKeLSLfemO59oGW8Lvyk0bKZh7AbVmHXr4bv11acfEXHOheWJcVOklVU6MzDVZpw5WQ5P6dijPOlSFyCUx49PsEZT9UmqfF8++8lJjIKIo+3gA0dDYA9dBD740ZI3ej83r/n+PxoGdgtlWwosSOmzwBMn4H1vmR9fWACAjxFWhh2/LzlZDldVPfshD07nNbPrMNOwlxS7LQc/7z1mFOMVzsFz3OP/02ajmdg+g52Svo3gLnxakNBQQGPPPIIH374Ibm5uZx55pk88MAD9O7dmxUrVnDFFVcwa9YsHnvsMVJTU+nevTt///vf6dixIwAbN27k/vvvZ/369RhjaN++PdOnT6dXLydZ/+abb5g2bRrr16+nadOmXHzxxdx9992Eh4czYcIEdu/ezQMPPMADDzwAwJ49eyoL1adUTdHLVE1R6tLpnB9rLXy/DveSBZDybfk5fwICnfl8AgOd7j5FFVxotohzxqOcO0wXIyehvx//VtXzY91uSPvRaf1av8pTqMGjaXNMz76Ynn2gdTto2qLC1mRrrZO45R2B/CNO5cC8XGzpRWOg053RBIc4f4PRsRAZ3aiTrrr+G7JHcpzWltKJq3NzoEkUREVjIqIhIanBlaqvCX/7jLNut/P3lZvjtDAf/7FH851xlUfzT1ie74w7dLud1s7SH0pvc8Jt63SjPLC3fJIXGobpfS5m5FgnYawFlVbrKzxWp90Ui4KrVwDnvvvuY8GCBcyYMYOEhASeffZZPvnkE5YvX87333/PFVdcwVlnncVf/vIXmjVrxl133UVJSQkffvghAMOHD6d79+78/ve/x+VysXHjRpKTk+nevTtpaWmMHDmSO++8kxEjRnDo0CH++te/0q1bN5588kkyMzMZOXIkkyZNYtKkSQC0bNmyxq9DRVRNUUSqxBYcc0pefza/bAnilvGYXudgzuwHbRKhSaSnalWZUtM/bMBu+g62bIL0/dgFc7AL5jgtZoMvwPQfWiuVykTqmi0udrpFbdvsdGfbtBaOZP+0gjFOAYGefZ2/m4SkKrUUG2OOl/EOgdjmPy2vhWOQ02NKqzl26OrrUOQ0GJfL6VoaGV12uZe27xkTuncXdv032NXLnVbUr5Zgv1oCvc/F9YuJmHbJXtpj/ZWfn88bb7zBk08+yfDhwwGYMWMG5557LrNmzfK0bv35z39mwIABANxyyy38+te/5tixY4SGhrJnzx5uvPFGT0tZcvJPr+vMmTMZP368ZzxYcnIyDz/8MJdffjnTpk2jadOmBAQEEBERUWtJmLcoGRNp4OzRfOzShdhPPvzpgjIkDDNwOGbIxdC6baUXkuVKTV98uZPUrV+FXbkENq75abzFe29gBo/EDBuNad6qDo9QpOo8rVP5uZCTydFdW3Bv34pN34c94BQN4MDe8i3CYeFOF92efTE9z3bmShKRRsX5nxgNXaIxXXpgL/8NbNuMXbIQu+oLWPsV7rVfQZ+BuK74baP+X5iWlkZRURH9+vXzLAsKCqJ37978+OOPnmSsW7efCvC0auW8XocOHaJNmzZcf/313HHHHbz33nucd955XHLJJSQlJQGwadMmvv/+e+bOnet5vrUWt9vNrl276NSp/hQyUjIm0kDZvCPYxfOwi+dBfp6zsHkrzAWXOolY2OmVvDYhoZh+50G/85zKYl99jl260Gkt+99c7CcfYgYMw/xiYqP+RyS1xx7Lhx83Oa21B/Y4Y7Hycp0uSJV1lbLWKaFd2i3puIzKdhIeAcmdMe07Yzr3cKr2NeLugiJSnnG5nAqcHc/AXnIVdv5sJylbswL3htWYiy7DjLocE6KCH5UJrOBz1X38M/qPf/wj48aNY/HixSxZsoQnnniCZ599losvvpi8vDx+9atfMXny5HLPb9Omfg2f0H8WkQbG5mRi//chdulHP809FJeAGX2FM87LixORmqimmAvHYS/4BWxYg/uzeU754RWLsV9/jjnvQsyYKzExsV7bpzRO1u12LnA+/a9T6vqEhOq0uFwQFUNQ81YUhzVx5p9qFY9p2Rri2jiTzqpIjYhUkYlPwEz5I3b0BNyzXnQmYp8/C7tiMa4rJ0OfgY3qMyUpKYng4GBWrVpFQoJTbbSoqIi1a9dWq9R8hw4d6NChA9dffz0333wzs2fP5uKLL6Znz56kpqbSvn37Sp8bFBRESWUVaf2IkjGRBsLm5WI/ege7ZMFP1d0SknCNuRL6DMDU4mSNxhUAvfoR0Ksfdttm3B/8B75f53SP/HopZsJvMIMv9IxFE6kqay1sXIN77r9h57afHmgRh+nS06lsFxHpVC4MawIne5+HhBwvZx0OwSG4AgKI86PiAyJS/5k2ibj+8DCsWYl7zstwOB3389Oh65m4Jl7vzInWCISHh3PNNdfwyCOPEBMTQ5s2bXj22Wc5duwYEydOZNOmTSd9/tGjR3nkkUcYM2YM7dq1Y9++faxbt47Ro52KmjfffDO/+MUv+Mtf/sIvf/lLwsPD+fHHH/niiy949NFHAWjbti1ff/01l156KSEhIcTG+ucXw0rGROo5W1iAe9H7uBfO+ak7YvvOThJ2Zr86/ybOJHch4A8PYzdvwP3ua04Vun8/i/36C1y/vhXTqnWdxiP1l83OxP3y3+H7dc6C0DDMyHHOxMbN/HtAtog0XsYYOHsgrh5nYz9+D7voffhhPe6HpmKGjcGM/SWmdH7BmggMciZjPkUsXvmyKbD6843ec889WGuZOnUqeXl5nHnmmbz55pvExMSc8rkBAQFkZmby+9//noyMDGJjY7n44ov54x//CDhjzd577z2mT5/OZZddhrWWxMRExo4d69nGn/70J/785z8zaNAgCgoKVNq+sVBpe6lLdt0qzJyXKDm4z1nQJhHX+F/DmX39ojuEdZdgP5uPnfsfKCyAoGDMlZMxQy72i/hqm/5+Tp9N3Yj7X39z5g0KDMIMH4MZNcGpduclOj/+T+fIv+n8VI3NOID7nVdgzUpnQWQ0Zvw1mEEXVKnHSGWl06siKCioQV2X+iOVthdphOzhdNxvvwhrv3IWNG2OuXQSZsDQWu2OWF3GFYC54FJsr/64//1Pp+vim8/D5hT49a2nXUREGi5rLfbT/2LffdUZF9a6Ha6b7sLEJfg6NBGR02KatyLgpruxm77DPesl2LcL+8ZM7Bcf45p0Iyap/lT+E+9TMib1js3Pw379OexOcyqpHdjjVFILDXN+wppATKxTya95K89vmreq9xf/tqTEqZD437ecCSgDAogc/yvyh10Cwf5brcm0iMP1/x7CfvIh9v3XsauXY3dswXXjn2ttkkypf2xJCfbf/8R++SkA5pwhmF/fovnrRKRBMN3OwnXf09glC7Dz3oa0H3E/dofT8j9uEia0fl+jyOlRMib1hi0scOby+OhdyDtSfoWiwp/m0dq5ldIOE2U6TjSJhKbNILopJqopRP/0Y6KaQos4aNrML7vQ2W2bcf/7Wdi93VnQ8QwCrrmFmL7ncrQedBExxjiVFzt0xf2vGZC+H/e0OzBXXddoui1K5WxREe6X/s/pxmNczvti+Bi9L0SkQTGBgZiRl2LPOR/7zivYrz93vmRds9JpJet1jq9DlDqmZEzqBbt6Oe7ZL0PWIWdBXAKmzwBo1QYT1waiYpyWoqP5cDQPezgDMg5AxgFsxgHI2A+5R5wkLu+I06r2832U3oiIgrbtMe06YHr0gU7dvVoOvrpsbg72wzexny9y5koKj3CqEw66wKdxnS7ToSuu+57C/erTsO4bp9viDxucbovhTXwdnviALTiG+9nHYNNaCAzENeUO5+9bRKSBMtFNMdf9ETtgOO7/PAsZB3DPfAQzeKTzZVRomK9DlDqiZEz8nv3uK6clxVqIbeFUITp32EkTkYq+S7fH8iHjIGQdxmZnQk6mUxwgOxObkwlZh50ELjfHGdv0/Trsx+87yc+ZfTFnDXAKY5xGRaHTYYuLsZ8vcrok5uc6xzVgGOaKyZjI6DqJobaYJpG4bvmLMzbovdew336J3bkV1w1/xiSq22JjYvNycT/zEGz9AUJCcd18D6Zbb1+HJSJSJ0z3s3A9MBP737ewn3yAXf4JNnUjruv+iGmvsWSNgZIx8Wt2+49O1yVrnW+Lrr4BExR8WtsyoeGQkAQJSRUma+B0hWTvTuzObbDle+yG1ZCbg/1qKfarpdAkEnPOeZgBwyGpU610obLuElj7jTNX175dzsI2ibh+eb0zr1IDYYxxumqc2G3x8TswV/4OM3S0uqc1AjY7E/dT98PuNAiPwDX1PkyHrr4OS0SkTpmQEMwVv8X2PBv3y0/Cwb24p9+JuezXmJHjfB2e1DKVtvcylbb3HptxAPe0OyAnC3r0wXXrvXXeLc+6S2DrZuzar7DffOG0npWKS8AMHI7pPxQT27zm+zp2FLtiMfbT/0L6fmdhRCTm0l9hzruwwmNvKGWFbV4u7teehrVfOwvOHojr17fV+26LDeX81AabcQD3k/fBwX0Q3RTX7Q9iEpLqNAadH/+nc+TfdH68z+YdcaoPf7sCANN/CEcmTCY6pulpbU+l7WtfTUvbKxnzMiVj3mHz83A/fqfTMpSQhOvOx31eCdG6S+D79dgVn2HXroTCQucBY6BTN0zXXk7LVXLnKndltBkHsBu/w6asgR/WwbGjzgPhEZghozAXXYZpUvnEkA3pH6G1Frv4v9h3X4OSEohtgevKydBnYL1tJWtI58eb7L5duP9+nzMGtHkrXP/vIUzL+DqPQ+fH/+kc+Tedn9phrXUqLs5+Cdxucm+5l6gevU9rmISSsdqnecakQbILZjuJWEwsrtvu83kiBs6cWXQ/C9P9LOzRfGec08rPIHUjpG7Epm50ioAEB0OLeGd8W7OWTkEQLLgtlBRD5iFs+j5nfFpp9cdSLVtjLhjrtLg1snLexhhnTrLk490WDx3E/fx06Nwd11XXqQR+A2G3fI/7mYedcZDxbZ1ErGkzX4clIuI3jDGY4Zdg2yQ6/wePHXXmJmvZutFdGzQGSsbE79i8XOznHwPg+vWtXukC6G0mLBwzeCQMHum0bqWsgc0bsJs3OAnWnh2wZ0e5io3luFyQ3BXTo49TubFtMsblqotD8FsmuQuuB2diP37fKaCSuhH3I3+AswbgumAsdDyj3raUNXZ27ddOol1UCO07O2PEIsp/mygiImC69MT1lydg106nx8iBPdiW8Z75yEpMAEXuk19pFBRZrK35dUWQyxBgS2q8ndM1YcIEunXrxkMPPeSzGGqLkjHxO3bpQig4Cm0SocfZvg7nlEzzVpihF8PQi51uGgf2OiX1Dx+EQxlOC4AxTuJlXM6E1C1aQfM4aBmv8rUVMCGhmLFXYweNdKotrloGa1bgXrMC2nXADBuN6d1fF/L1iHvZ/7D/fhasG3r2xXXDnfqGV0TkFEzzVhAQ5FwXHcuHA3uxLeIw4REUuS1zNxw46fNdrgDc7ponUeN7tiJA34PWCiVj4ldsUSF28TwAzKjL6l0LiDEG4tpAXJtKKzZK1ZlmLTDX34EdfQX2s/lORcudW7GvP4P99z+dOeB6n4Pp1B1at6typU1bUACH0+HQAWzGQTh00JnmoKQErBtbUoIJCYHIaKebaUSU05Uuphk0bQ7hTerde9NXrLsE+/4b2I/nAjjz411zS72cI09ExBdMQCC0jHeGN+TnwsH92OYtoUmMr0MTL1AyJn7FrvjM6eYX2wLT9zxfhyN+wiQkYX59K3b8r7HLPnZaynanebqGWnBaHuPbOolwWBMIDYfQUGcy8LxcbN4RpzJnRWP1KlDppODgjAs8npiZmFiIjIEoJ3EzkdFOEhcZDdEx3nkB6il7LB/3i0/A+lUAmEsmOvMEKpEVEakW43JhW8Q5Xx7m5jjzpob6b++QTz75hKlTp5KSkkJAQAApKSlcdNFF3HLLLdxzzz0A/OlPf6KgoIAHH3yQv/71r3z99ddkZWWRlJTEbbfdxrhx4yrd/qeffsqtt97KY489xmWXXcaePXt46KGH+OKLL3C5XJxzzjk89NBDtG3bFqi4m+PkyZOJioriqaeeAqB///5MnDiRH3/8kf/9739ER0dz22238Zvf/Ka2XiZAyZj4Eesuwf7v+LfnIy/FBOrtKWWZyCjM6Ctg9BXY9P3YdV9jN3wLO7ZC3pGqj9UDCA2DZi2heStMbAto2gwCAiEgwEnsjh1z/uEdycYeyXYq/2UdgtwjTiXNg/vg4L6TJ23AnuimuFvEYVq1hlZtPL9pGX/ac+bVBzZ9P+5/Puqck8AgzG+m4uo/xNdhiYjUW8YYbLOWzp3cHCgqwhYX++X1Uv/+/cnNzSUlJYVevXrx1VdfERsby4oVKzzrrFy5kltuuYWCggLOPPNMbr75ZiIjI1m8eDFTp04lMTGRs846q9y2586dy1133cXMmTMZOXIkRUVFTJo0ibPPPpv333+fwMBAnn76aSZNmsSnn35KcHDV/9c+//zz3Hbbbfzxj3/k888/57777iM5OZnzzz/fK69LRfzv7Enj9d1XzgVuk0jMeRf6Ohrxc6ZFHOaCS+GCS52xepmHYNc2bMYBp/JU6U9wCEREOu+ryGgnAWvW8rS7GtrCAme+uaxD2MzjCdqRbDiS4yRtJ/4UFuDOzoTsTOyW753new7AOF0eW8Q5Zd1bxnt+0yK+Xo+nsmu/xv3qU5Cf58whdstfMO07+zosEZF6z5OQuUsAC3lHsBFRftf1Oyoqiu7du7Ny5Up69erFypUrmTJlCk8++SR5eXnk5OSQlpbGueeeS3x8PDfeeKPnuZMnT2bp0qXMmzevXDL22muvMX36dF577TUGDBgAwH//+1/cbjf/93//5/m//ve//50zzjiDlStXMmRI1b8I7NevH7feeisAHTp0YNWqVbz44ouNLxlbtGgR8+bNIysri8TERCZPnkzHjh0rXX/lypXMnj2b9PR04uLimDRpEn369PE8PmfOHFasWMGhQ4cIDAwkOTmZiRMn0qlTJ886ubm5vPLKK3z77bcYY+jfvz+//e1vCQ2tvxdE9Y170fsATnGGenwhKnXPGAOxzSG2ea2P1TPBIU7C1DL+1PsqOEpzdxHpKeuxB3Y7A68P7IX9e+BonjNu7XC6U4WTn7WqRcU4iVqLOGfKg3YdoH1HTNTpTfxZF2xxMXbuvz0t3LTvjOvGu/yyIqqISH1ljME2j4MiN1gLuUewkVF+V4353HPPZcWKFdxwww18/fXX3H333cybN49vvvmGrKws4uLiSE5OpqSkhH/84x/Mnz+f/fv3U1hYSGFhIWFhZQucLViwgEOHDvHBBx/Qu3dvz/JNmzaRlpZG585lv/QrKCggLS2tWsnY2WefXe7+Sy+9VP2Drwa/S8ZWrFjBG2+8wZQpU+jUqRMLFizg0Ucf5amnniI6Orrc+ps3b+bpp5/m6quvpk+fPixfvpwZM2Ywffp02rVrB0Dr1q2ZPHkyrVq1orCwkAULFvDII4/wzDPPeCZp+8c//kFmZiZ//etfKSkp4dlnn+WFF17g97//fZ0ef2NlD+6DtB8hIAAz/BJfhyPiFSY0nOD4eFzh0WUmRLXWOi1nB/dh0/f/1OUxfR+k73O6QuZkQU4WdusPznNKnxzbHNO5B6bXOdCjj6fEsa/Zg3txv/IUHI/XXDAWc/m1pzVJqYiInJxxuSAoEFwBTitZfh62SST+NCR34MCBzJ49m40bNxIUFETHjh0ZMGAAK1euJCsri3PPPReA5557jpdffpkHH3yQrl27Eh4ezv33319usuoePXqQkpLCrFmz6NWrl6cVLC8vjzPPPJNnnnmmXAzNmjnzWFbUE8ZfJsP2u2Rs/vz5jBgxgmHDhgEwZcoU1qxZw5IlSyocyLdw4UJ69+7N2LFjAZg4cSIbNmxg0aJFXH/99QAMHjy4zHN+/etf89lnn7Fjxw569uzJ7t27Wbt2LdOmTaNDB2di2cmTJzNt2jSuueYaYmNja/GIBcBu/M650eEMpyuZSANmjHFavqJiMB3PKPe4zc+F9AOQvg+bfgD27cSmbYH9u+FwBvarpU5lycBA6NoL038I5qwBTgXIOmZLSrCf/hf74ZvO/GFhTXD95jZMn4F1HouISKNigCYRcCQHioucglV+1KPrnHPOITc3lxdffNGTeA0cOJCZM2eSnZ3NDTfcAMCqVau46KKLuPzyywFwu91s27atXEtXYmIi9913H1dccQUBAQE8+uijAPTs2ZN58+bRvHlzIiMjK4ylWbNmHDjw0zQAJSUlbN68mYEDy/6vWrNmTbn7J/akqw1+lYwVFxezbdu2MkmXy+WiZ8+epKamVvic1NRULrmkbEtKr169WLVqVaX7+PTTTwkPDycxMdGzjSZNmngSMXBOrDGGLVu2cM4555TbTlFRUZmM2hjjaU5tSJXCSo+l1o9pk5OMuXr0aVCvX22rs/Mjp+V0z49p4oxxI6ls92x7LB+7/UfshtXYtV87LWop32JTvsWGhGH6DsI1cLhT8r8OuqvYHVtw//tZp1UbMGf0ciZqbxFX6/v2Bv39+D+dI/+m8+N7JiAAGxbudH0/lg9BQU4hKj8QExPDGWecwdy5c3nkkUcAp7DHjTfeSFFRkSdBa9++PQsWLGDVqlXExMTwr3/9i4yMjHLJGDjjuObMmeNJyB566CEuu+wynnvuOX77299yxx13EB8fz+7du/noo4+46aabaN26NYMGDeLBBx/k008/JSkpiX/961/k5OSU2/6qVat49tlnueiii1i2bBnz58/njTfeOOWx1uRvwK+SsZycHNxuNzExMWWWx8TEsHfv3gqfk5WVVa77YnR0NFlZWWWWffvttzz11FMUFhYSExPDX//6V08XxaysLM/tUgEBAURERJTbTqm5c+fy7rvveu63b9+e6dOn06JFiyocaf0TF1d7F1e2qIg9x8fMtBh6IcHx8bW2r4aqNs+P1JxXz0/7DjB8FNZaindtJ3/ZJ+QtXkjJgT3YLz+l5MtPCWjVmvBhowkfMYag1m29t+/jClI3kvP2Sxz7ZhkApkkEMb+7nSYXXlovL8r09+P/dI78m85P7Tp69ChBQeW7fNsSuOxM55rJFhY4c2W6XM7YZi9/Fge7DEGnkeQNGjSIjRs3cv755xMUFETLli3p3Lkz6enpnHGG0zPkT3/6E7t27WLSpEmEhYXx61//mosvvpicnBzPcRtjCAgIICgoiDPOOIP333+fcePGERQUxEMPPcR///tfHn74YaZMmUJubi5xcXGcf/75xMbGEhQUxDXXXMMPP/zA7bffTkBAADfeeCODBg3C5XKV2cdNN93Ehg0bePLJJ4mIiOChhx5i5MiRJ39tgoOJr8G1q18lY7Wpe/fuzJgxg5ycHBYvXsyTTz7JY489VuE4tKoYP358mRa50guQ9PR0iouLvRKzPzDGEBcXx/79+8uMefEm9w8bsEfzITKGjNBIzL59tbKfhqguzo+cvlo/P0FhMHwsDL2EgC3f416xGLt6OSUH9pIz6yVyZr0Erdtiup+N6dEH06mb80/6NNgj2dj1q7DfLMNuPN6Nw7gw55yH64rfciSmGUf27/fiwdU+/f34P50j/6bzUzcKCwsrHN9kAM8negDYA3ugpNjpAh/rNA4EBQV5Z2yU26kXUl33338/999/P/DTGK3//e9/Ze5HRETw8ssvV/j80nXeeeedMvfbt2/PunXrPMtiY2N58sknT7qNRx991NO1saLHrbWEh4fz3HPPVfh4ZQoLC9lXwbVrYGBglRpp/CoZi4qKwuVylWuNysrKKtdaViomJobs7LITuGZnZ5dbPzQ0lLi4OOLi4ujcuTNTp07ls88+Y/z48cTExJRrqiwpKSE3N7fS/QYFBVX4LQXQID+QrLW1dlw25VsATPezwJgG+frVtto8P1JztX5+jIFO3XB16oadeD127VfYlZ/BpnWwdxd27y7sJx8486e1bI1JSII27ZxJqyOjnUmrw8KOVwmxzrermYecaQIyDmC3fg/bNjtVu8BJws4dghl9BSYuwXOM9ZX+fvyfzpF/0/nxAwEB0LwlHNgLOdnYiGhMNebXkpqpyfvfr5Kx0rLzKSkpnnFabreblJQURo0aVeFzOnfuzIYNGxgzZoxn2fr160852M5a68l0O3fuTF5eHtu2bSM5ORmAlJQUrLUnLakv3uH5lr17+Yn9RKR6TEgIpv8Q6D8Em3cEu2kdbPzWKZKTdRj278bu3w2rnfWr9e+jbXtMr3MwA4ZhWraujfBFROQ0mbAm2PAmzhyPWYecaVjE7/lVMgZwySWX8M9//pPk5GQ6duzIwoULKSgoYOjQoQDMnDmT2NhYrr76agBGjx7NAw88wLx58+jTpw9ffvklW7du9VRSPHbsGO+//z59+/aladOmHDlyhEWLFnH48GHPZHEJCQn07t2bF154gSlTplBcXMwrr7zCwIEDVUmxltnsTNi1HYxxWsZExGtMk0hMv8HQb7DzrV32Ydidht2d5rSYHcmCnGynjH7BMaeFrfQnJhaat8I0bwXxCZgeZ3u6vYiIiJ+KaQb5+ZCf63yuV9KLS8r7+uuvfbJfv0vGBg4cSE5ODnPmzCErK4ukpCTuueceT3fBjIyMMgPEu3TpwtSpU5k1axZvv/028fHx3HHHHZ45xlwuF3v37uWJJ57gyJEjREZG0qFDBx588EHatv1pYPvUqVN5+eWXeeihhzyTPk+ePLlOj70x8pS0b9dBJe1FapExxvknHdMM0+PsUz9BRETqHRMcgo2IhNwcbOYhiKi41Lv4D2PVyder0tPT/WYSOW8wxhAfH8++fftqpT+4+8UnsN98jhl9Ja7xv/L69hu62j4/UjM6P/5N58f/6Rz5N52fupGTk1Ou6vfJ2KIi2LsDrCWwTSIlQRo7VpsqOz9BQUFVKuBR+xPRiFTCut3Y4/OLqYuiiIiISMXc7qqXMjRBQXC8t1FJxsHaCkmo3nmpjJIx8Z2dWyE3B8LCIbmLr6MRERER8Tvh4eEcOXKkehf+0U3B5cIWHMXm59ZecI2Y2+3myJEjhIeH12g7fjdmTBoPz3ixrmdiAvVWFBEREfm5wMBAmjRpQm5u9ZIqW1AEhw7CkVxMYodaiq5xa9KkCYE1vIbVFbD4jE3bAoDp3N3HkYiIiIj4r8DAwGqNGwOg6BglM/4M1uJ6+DlMXJvaCU5qRN0UxXd2bQPAtNW3NSIiIiLeZJq3IrTvIADsso99HI1URsmY+ITNz3WazgHaJvk0FhEREZGGKGL05QDYLxdjiwp9HI1URMmY+MauNOd3s5aY8AifhiIiIiLSEIWePRBiW0DeEezqL30djlRAyZj4hD3eRZG2yb4NRERERKSBMgEBuM6/CAD7+Uc+jkYqomRMfGPXdgBM2/Y+DkRERESk4TKDR0JAAGz9Abt7u6/DkZ9RMiY+UdoyZtopGRMRERGpLSYmFnr3B8B+rkIe/kbJmNQ5W1wEe3c5d1RJUURERKRWuYZcDID9eim2qMjH0ciJlIxJ3du7C0qKITwCYpv7OhoRERGRhq1LT4hpBkfzYdNaX0cjJ1AyJnXOHh8vRtv2GGN8G4yIiIhIA2dcLkyfAQDYb1VV0Z8oGZO655nsWZUURUREROqCOXsgAHbd186QEfELSsakzp3YMiYiIiIidaDjGRAVA/l58MMGX0cjxykZkzplrf2prL0qKYqIiIjUCeMK+Kmr4poVPo5GSikZk7p16CAczYPAQIhL8HU0IiIiIo2G6XO8q+J3K7ElJT6ORkDJmNS10i6KrdthAoN8G4uIiIhIY9K5B0REQu4RSE3xdTSCkjGpY57JnjVeTERERKROmYAAzFmqquhPlIxJnfqpeIcqKYqIiIjUtZ+6Kn6Fdauroq8pGZO6VVq8Qy1jIiIiInWv65kQHgE5WbDle19H0+gpGZM6Y/NznQIeAAlJPo1FREREpDEygYGYXucAYNd+7eNoRMmY1J0D+5zfMbGY8AjfxiIiIiLSWPXsC4Dd+J2PAxElY1Jn7MG9zo2W8b4NRERERKQRM2ecCcbA3p3YzEO+DqdRUzImdSfdaRkzLZSMiYiIiPiKiYiCpE4A2E1qHfMlJWNSdw4e76aoljERERERnzLdz3JuqKuiTykZkzpjjydjRsmYiIiIiE+VJmN201qVuPchJWNSd9QyJiIiIuIfkjpDWDjkHYEd23wdTaOlZEzqhM3PgyPZzh2NGRMRERHxKRMY6Mw5BtiNa3wcTeMV6OsAKrJo0SLmzZtHVlYWiYmJTJ48mY4dO1a6/sqVK5k9ezbp6enExcUxadIk+vTpA0BxcTGzZs3iu+++4+DBg4SHh9OzZ0+uvvpqYmNjPdu45ZZbSE9PL7Pdq6++mnHjxtXKMTY66fud35HRmLBw38YiIiIiIpjufbDffeWUuL/kKl+H0yj5XTK2YsUK3njjDaZMmUKnTp1YsGABjz76KE899RTR0dHl1t+8eTNPP/00V199NX369GH58uXMmDGD6dOn065dOwoLC9m+fTuXX345SUlJ5Obm8tprr/G3v/2Nxx9/vMy2rrzySi644ALP/dDQ0Fo/3sbCqouiiIiIiF8x3XpjAbb9gD2ary/MfcDvuinOnz+fESNGMGzYMBISEpgyZQrBwcEsWbKkwvUXLlxI7969GTt2LAkJCUycOJHk5GQWLVoEQHh4OPfeey8DBw6kdevWdO7cmcmTJ7Nt2zYyMjLKbCssLIyYmBjPj5IxLzo+x5iKd4iIiIj4B9MiDlq2Brcbfljv63AaJb9qGSsuLmbbtm1luga6XC569uxJampqhc9JTU3lkksuKbOsV69erFq1qtL95OfnY4whPLxs9v/BBx/w3nvv0bx5cwYPHsyYMWMICAiocBtFRUUUFRV57htjCAsL89xuKEqPpcbHdLybomnZukG9Pr7mtfMjtULnx7/p/Pg/nSP/pvPj36p6fkyPPtjP9mI3foerz4C6CE1O4FfJWE5ODm63m5iYmDLLY2Ji2Lt3b4XPycrKKtd9MTo6mqysrArXLyws5M0332TQoEFlkrGLL76Y9u3bExERwebNm3n77bfJzMzk2muvrXA7c+fO5d133/Xcb9++PdOnT6dFixZVONL6Jy4urkbPP5h1iAIgpvMZNIlX65i31fT8SO3S+fFvOj/+T+fIv+n8+LdTnZ+j540g47P5uH5YT7yu0eqcXyVjta24uJgnn3wSgOuuu67MYye2riUmJhIYGMiLL77I1VdfTVBQULltjR8/vsxzSr91SE9Pp7i4uDbC9wljDHFxcezfvx9r7Wlvp3j3DgCyg8PI2bfPW+E1et46P1I7dH78m86P/2uI5yigpASKi069YnUEBlFSSU+e2tQQz09DUtXzY1u0gYAASg7sYW/KOkyzlnUYZcMVGBhYpUYav0rGoqKicLlc5Vq1srKyyrWWlYqJiSE7O7vMsuzs7HLrlyZiGRkZ3HfffeW6KP5cp06dKCkpIT09ndatW5d7PCgoqMIkDWiQH0jW2tM+LltwDLIPO7dbxEMDfH18rSbnR2qfzo9/0/nxfw3qHBUXsub1/3h1k32u/RXW5btx7g3q/DRApzw/IaHQrgNsT8WdmoLr3GF1F5z4VwGPwMBAkpOTSUlJ8Sxzu92kpKTQuXPnCp/TuXNnNmzYUGbZ+vXr6dSpk+d+aSK2f/9+7r33XiIjI08ZS1paGsYYoqKiTvNoxCP9eEtYRCSmSYRvYxERERGRMkyn7s6N1I2+DaQR8qtkDJzugosXL2bp0qXs3r2bl156iYKCAoYOHQrAzJkzeeuttzzrjx49mnXr1jFv3jz27NnDnDlz2Lp1K6NGjQKcROzvf/8727Zt47bbbsPtdpOVlUVWVpanO2FqaioLFiwgLS2NAwcOsGzZMl5//XXOO+88IiKUPNRYaVl7TfYsIiIi4ndMp24A2B83+TiSxsevuikCDBw4kJycHObMmUNWVhZJSUncc889nm6HGRkZZarCdOnShalTpzJr1izefvtt4uPjueOOO2jXrh0Ahw8fZvXq1QDceeedZfZ1//330717dwIDA1mxYgXvvPMORUVFtGzZkjFjxpSr0iinp3SOMZW1FxEREfFDHc9wfu/fjc3JwkTF+DScxsTvkjGAUaNGeVq2fu6BBx4ot2zAgAEMGFBxKc6WLVsyZ86ck+4vOTmZRx99tNpxShVpwmcRERERv2UioqBNIuzZAVs2QZ+Bvg6p0fC7borS8FglYyIiIiJ+TV0VfUPJmNS+4wU8jMaMiYiIiPinjkrGfEHJmNQqW1gAhzOcOy3LTxEgIiIiIr7nqai4cxv2aL5vg2lElIxJ7co44PwOawIRp55SQERERETqnoltDs1bgXXD1h98HU6joWRMatcJ48VOrIIpIiIiIv5F48bqnpIxqVUqay8iIiJSTxzvqmh/TPFxII2HkjGpXema8FlERESkPvCMG9v+I7aoyLfBNBJKxqRW2YyDzo3mLX0biIiIiIicXKvWEBkNxUWQ9qOvo2kU/HLSZ2lAMp1KiqZpcx8HIiLSOJSYAIrc1mvbi7DFmOJCr20PgMAgilwB3t2miNSYMcbpqrhmBTY1xTOGTGqPkjGpXceTMWKVjImI1IWgkiJys/O8tr2o8EByF33gte0BNLn4MghWMibij0zHM7BrVmC3p/o6lEZByZjUGnvsKOQfvyBQMiYiUidcxYXseHe217bX4ppJ/HDQe8kdQB+813InIt5l2ndy/kK3p2KtVTXsWqZkTGpPaatYWBNMaLhvYxGvd10CCHIZAmyJV7cp4q+C3CXOOApvaqTd9VyuAAILj1VhTUP6jjQCrIVTJXCBwRS7NBRepMbadgCXC3KynGu52Ba+jqhBUzImtefw8WSsaTPfxiEAFLktczcc8Oo2x/dsRYC+MJPGoriIgkXve3WTIaMaaXe94mLW/PvNKq0aHBxMYeGpx6z1/e2vCSp21zSyshppsiyNmwkJgdaJsHu7U8RDyVitUjImXvPzb42L0/fhBlwxsQRV6RvQCugfodeE22JGtw31+jbdRt9ES83UnxYnQ7H17rcPIejbDK8pLiHv4w+8ukmNbZPGyrTvhN29Hbv9R0yfgb4Op0GrUTL22GOPcf7553POOecQHBzsrZikvvrZt8Z28wYA3Lk5p/1tcqP91rgWeHscCUCza3+FO9i7CZ40QvWkxcliNXbKz+n8iHhJ+86w7H9YlbevdTVKxg4cOMAzzzxDaGgo/fr14/zzz6dnz54a6Ndolf3W2Bw9igtwhzbBnua3yfrWWERERKRumaTjRTzSfsS63RiNx6w1NUrGnn76abZs2cKyZctYuXIly5YtIyYmhsGDB3PeeeeRlJTkpTClPvj5t8aJ2UeIAPYVBZB1mt9W6ltJkcZA3f9ERPxK63YQHAzHjsKBPRDf1tcRNVg1HjPWsWNHOnbsyLXXXsv69etZtmwZn376KfPnzychIYHzzz+fwYMH06yZijg0NoGFRwEoCg7zcSQi4s8ac/e/qlcVrMY2bf049vrBcMx6t0Wgib4okHrABARAu46wZZMzbkzJWK3xWgEPl8tF79696d27N3l5efzrX//iq6++4q233uLtt9+me/fujBkzhj59+nhrl+LPrCVIyViD53K5Tr84S2VUtEUak2pUFayqvtdM8ur2GjNr8XoV2l91ifLq9kRqi0nqhN2yCdJSYeBwX4fTYHm1muIPP/zAF198wddff01ubi5t27bl/PPPJzAwkCVLljB9+nQuu+wyrrrqKm/uVvyQq6SYALcz/1SRnxV40HxbXqTqZeK3qtCiYQ270zMpdLs45RxWqEVDRBqZ9p0AsGlbfBxIw1bjZGz37t188cUXfPnll2RkZBAdHc2QIUM4//zzy4wZGz16NC+88AIff/yxkrFGoLRVrDggCBvgXzMo1Jf5tqpa7jt7724CqzAHj6mlrkuNtXuZ+LeqtWgYIiMjOHIkl6okY2rRaHwCAlxenxIkAC/PhSZSS0z7zs4n465t2OIiTGCQr0NqkGp0lXzHHXewc+dOgoKC6Nu3L9dddx29evXCVUnFle7du/PZZ5/VZJdST3i6KIaoi+JpKy4m76O5p1jJcCwggJKSEk51MRlx0ThvRSbi96p2EW0ICHBTEhNKVZIxXUQ3QsXFXp8SpIW6kUp90bwVRERC7hHYnQZJnXwdUYNUo2SsSZMm3HDDDZx77rmEh4efcv1+/foxc+bMmuxS6glPy1iNx4t5f/C0rSddjapa1CA4OJjCKrSM9fVGUCL1RRUvoqv69wO6iBaRxsUY4yRgKWucIh5KxmpFjZKxW2+9laioqEonfC4sLCQnJ4fmzZsDEBISQosWLWqyS6knSos61LR4h8vloiAr2xsheTSNauLV7YmIiIg0RCapMzZlDWxPhWGjfR1Og1SjZOyWW27htttuY/DgwRU+vnr1ap5++mlmz/ZuE7/4v5/K2tewr30tdBGJ/fU1Xt2eiIiISENUOvmzTfvR16E0WLVaWaG4uLjS8WPSsPlzWfvaGJAdbotxG73XRUREpAFp39H5vX839mg+JuzUw5KkeqqdjOXn55Ofn++5f+TIETIyMsqtl5eXx4oVK4iJialRgFI/BRX4bzJWG61tza79FW4/K+EvIiIiUhMmqik0bQ6ZGU4Rj07dfB1Sg1PtZGzBggW8++67nvuvvfYar732WqXrq4x9I2QtQUXeGTMm4g1VnSagWjQ5tYiINAYJSZCZgd29HaNkzOuqnYz16tWL0NBQrLW8+eabDBo0iPbt25dZxxhDSEgIycnJdOjQwWvBSv0QUFyE6/iEz8VqLRJ/UKVpAqpHk1OLiEhjYNq2x25YDbu2+zqUBqnayVjnzp3p3LkzAAUFBfTv35927dp5PTCpvzxl7QODsY2k5cDlcnkqSHpLbU3S3BhVdZqA6ujrMlU651WdlBvABgaTa7w7lDfIZQiwJV7dpoiINCIJTqOL3Z3m2zgaqBr917/iiiu8FUcZixYtYt68eWRlZZGYmMjkyZPp2LFjpeuvXLmS2bNnk56eTlxcHJMmTaJPnz6AU0Rk1qxZfPfddxw8eJDw8HB69uzJ1VdfTWxsrGcbubm5vPLKK3z77bcYY+jfvz+//e1vCQ1Vy051Bfpx8Y5aU1xMwf8+8OomQy8c59XtiZdV6ZwbgiMjKDiSS1UmFQ4edRlzfzjkjeg8xvdsRUD9mFpPRET8kGmb5PwH25OGdZdgGskX7XWlWslY6Vixyy67DJfLVWbs2MlMmDChyvtYsWIFb7zxBlOmTKFTp04sWLCARx99lKeeeoro6Ohy62/evJmnn36aq6++mj59+rB8+XJmzJjB9OnTadeuHYWFhWzfvp3LL7+cpKQkcnNzee211/jb3/7G448/7tnOP/7xDzIzM/nrX/9KSUkJzz77LC+88AK///3vqxy7OPy5kqKIiIiIVEPLeAgOgcICOLAP4hN8HVGDUq1k7J133gFg3LhxuFwuz/1TqU4yNn/+fEaMGMGwYcMAmDJlCmvWrGHJkiWMGzeu3PoLFy6kd+/ejB07FoCJEyeyYcMGFi1axPXXX094eDj33ntvmedMnjyZe+65h4yMDJo3b87u3btZu3Yt06ZN84xxmzx5MtOmTeOaa64p04Imp9Y4kzFDsfV280Njbc4wHLPenSagSa28llU554acvGOUVPG9EdRoz7mIiPgr4wqANomwPdUp4qFkzKuqlYz9fPJmb0/mXFxczLZt28okXS6Xi549e5Kamlrhc1JTU7nkkkvKLOvVqxerVq2qdD/5+fkYYwgPD/dso0mTJmWKjfTs2RNjDFu2bOGcc84pt42ioiKKin6qzmaMISwszHO7oSg9lqodk7NO6TiaopDG1cXT62OSvLq1+sPlclGQlePVbUaF106Xiqqc8+DgYAqrOGasr8vF6Lbe/RIj3BZ7dexmMS6K3F7bHFBbybJIY2J8cu1RvWsEqWvePD+mbXvs9lTYnYY55/wab09+UquTPldXTk4Obre73NxkMTEx7N27t8LnZGVlleu+GB0dTVZWVoXrFxYWeqpAliZjWVlZREVFlVkvICCAiIiISrczd+7cMt0027dvz/Tp02nRosVJjrD+iouLO+U66TvSCA4OJvh4WXsbHklwcHCN9+2NbTT0bXp7verw+jaLi9n33/e9uskWV11RL85PbRx786sn0iLBe99iHtyzl6NH8k+9YjUEhLjqx/mp5roNaZu+jrFBfcbVwjaNMcTHx3t1m9VRlWsE8R1vnJ8j3XuT9cXHhBzcSwsfvtcaIq8nYwUFBXz55ZcUFxdz1lln+VVyUlxczJNPPgnAddddV6NtjR8/vkyLXOm3Dunp6RQXF9do2/7EGENcXBz79+/HnqK6X4C1FBYWEljgXKgdcwVVuUXgZLyxjYa8zeq0vDSk464v26zO+anqNqvDWsu+ffu8tr2AogK2zX7La9sDiL1mUqM9P/Vlm76MUZ9xp+btv/Oqqs41gtQ9b54fG+UM2Tm25XufvNfqo8DAwCrlQTVKxp577jm2bNnCE088ATjJzl/+8hd27doFQHh4OPfdd1+5ecgqExUVhcvlKtcalZWVVa61rFRMTAzZ2dlllmVnZ5dbvzQRy8jI4L777vO0ipVuIyenbLeokpIScnNzK91vUFAQQUFBFT7WED+QrLVVOC4L1hJYqAmfRfxHVf52q7c9EfE33v47r+beq3SNIL7ijfNjExKdG1mHcedkYyKjTv4EqbIajZLfuHFjmfFUy5cvZ9euXdx222088cQTxMTEVLnIBzgZZHJyMikpKZ5lbreblJQUz9xmP9e5c2c2bNhQZtn69evp1KmT535pIrZ//37uvfdeIiMjy20jLy+Pbdu2eZalpKRgrT1pSX0pL6C4AJd1Y4GioMY1ZkxERESkITKh4dDieHfH3Zr82ZtqlIxlZWWVaX775ptvSE5OZvDgwSQkJDBixAi2bNlSrW1ecsklLF68mKVLl7J7925eeuklCgoKGDp0KAAzZ87krbd+6iIzevRo1q1bx7x589izZw9z5sxh69atjBo1CnASsb///e9s27aN2267DbfbTVZWFllZWZ7uhAkJCfTu3ZsXXniBLVu28MMPP/DKK68wcOBAVVKspqACp1WsOCgEXN6tiCci1edyBRBYeMxrPy59+y0i0ji1PT758y4lY95Uo26KISEh5Oc744NKSkrYtGmTJwkCCA0N9TxeVQMHDiQnJ4c5c+aQlZVFUlIS99xzj6e7YEZGRpmqMF26dGHq1KnMmjWLt99+m/j4eO644w7atWsHwOHDh1m9ejUAd955Z5l93X///XTv3h2AqVOn8vLLL/PQQw95Jn2ePHly9V4QaaRl7UX8WHExa/79ptc21/eaSV7bloiI1B8moT12zUpQMuZVNUrGkpOTWbx4Md27d2f16tUcPXqUvn1/Ksh94MCBCidqPpVRo0aVSepO9MADD5RbNmDAAAYMGFDh+i1btmTOnDmn3GdERIQmePYCJWMiIiIiDY9pm4QFrLopelWN+pFNnDiR7Oxs7rrrLt5991369+9fZozVN998Q5cuXWocpNQfpclYsZIxERERkYYj4XhBvn27scVFJ19XqqxGLWMdOnTgqaeeYvPmzTRp0oRu3bp5HsvLy+Oiiy4qs0waPs+Ez8Eq3iEiIiLSYDRrCWFN4Gge7NvtGUMmNVPjecaioqLo169fueVNmjRh9OjRNd281DOB6qYoIiIi0uAYY6BtEqRuxO7ahlEy5hVemfT56NGjpKenk5eXV+E8Bmodazw0ZkxERESkYTIJ7bGpG2FXmq9DaTBqlIwdOXKEl19+ma+//hq3213perNnz67JbqSesG73T90UQ5SMiYiIiDQoCUkA2L07fBtHA1KjZOyFF17g22+/5eKLL6Zr165ERER4Ky6pj3KyMFgshmJN+CwiIiLSoJjW7bAAe3f5OpQGo0bJ2Lp16xgzZgy/+tWvvBWP1GM28xBwvHjHCXPBiYiIiEgDEJ/g/M46hM3PxYSrIaamalTaPiQkhBYtWngrFqnnSpOxYlVSFBEREWlwTHgExDRz7uzb7dtgGogaJWPnnXce33zzjbdikXrOZmUAKt4hIiIi0mC1bguA3bvTx4E0DDXqpnjuueeyadMmHn30US644AKaNWuGy1U+v0tOTq7JbqS+8HRTVDImIiIi0hCZ+LbYTWs1bsxLapSM3XfffZ7b69evr3Q9VVNsHKySMREREZGGrXU7AOw+tYx5Q42SsZtuuslbcUgDYLNOKOAhIiIiIg2Oad3Wqai4Ty1j3lCjZGzo0KFeCkMaArWMiYiIiDRw8U7LGIczsEfzMWHhvo2nnqtRAY8TZWZmkpaWxrFjx7y1SalHbEkJZGcCUKxkTERERKRBMk0iIDrWuaPWsRqrcTK2atUqbr/9dm688Ub+/Oc/s2XLFgBycnK48847VW2xscg6DNbiNobioBBfRyMiIiIitUUVFb2mRsnY6tWr+b//+z8iIyO54ooryjwWFRVFbGwsS5curckupL7ITAegOChMEz6LiIiINGAm3knG1DJWczVKxt577z26devGww8/zEUXXVTu8c6dO7N9+/aa7ELqCXv4+BxjISreISIiItKglVZUVHn7GqtRMrZz504GDBhQ6ePR0dHk5OTUZBdSX6h4h4iIiEij4GkZUzfFGqtRMhYSEnLSgh0HDhwgIiKiJruQ+iLzeMuYkjERERGRhu34mDEOp2OP5fs2lnquRslY9+7d+fzzzykpKSn3WFZWFosXL6ZXr1412YXUE/bw8TFjSsZEREREGjQTEQVRMc6dfXt8Gkt9V6Nk7Je//CWHDx/m7rvv5pNPPgFg7dq1zJo1iz/+8Y8ATJgwoeZRiv8rHTOmCZ9FREREGr54VVT0hholY61bt+ahhx4iMjKS2bNnAzBv3jzmzp1Lu3btePDBB2nZsqVXAhU/p26KIiIiIo2GOV7Eg31KxmoisKYbaNu2Lffeey+5ubns378fay2tWrUiKirKG/FJPWCLiiAnC1AyJiIiItIoeOYaU0XFmjjtZKyoqIhly5axbt06Dhw4wNGjRwkLCyMuLo7evXszePBgAgNrnOtJfZDlVFIkKIiSwGDfxiIiIiIitc7Et8OCKirW0GllSzt37uRvf/sb6elO0Ybw8HBCQ0PJyclh+/btrFy5kvfff58777yThIQErwYsfuh4F0UT00wTPouIiIg0BqXdFA8dxBYcw2iu2dNS7WTs2LFjTJ8+nZycHH75y19y/vnnExsb63n88OHDfP7557z//vtMnz6dGTNmEBqqk9OQlU74TEwz3wYiIiIiInXCREZBZDQcyYZ9uyCpk69DqpeqXcBjyZIlZGRkcNdddzFu3LgyiRhAbGws48eP589//jMHDx5k6dKl3opV/FVpy1hTJWMiIiIijUZcGwDsfpW3P13VTsbWrFlDr1696N69+0nX69GjB2eeeSbffvvtaQcn9cRhJWMiIiIijY2JOz4c6YCSsdNV7WRs586ddOvWrUrr9ujRg507NaivobNqGRMRERFpfI63jKGWsdNW7TFjubm5xMTEVGnd6OhocnNzq7X9RYsWMW/ePLKyskhMTGTy5Ml07Nix0vVXrlzJ7NmzSU9PJy4ujkmTJtGnTx/P419//TWffPIJ27ZtIzc3l7/97W8kJSWV2cYDDzzApk2byiy74IILuP7666sVe6N12CnkQtPmwEGfhiIiIiIidcPEJWABu3+3r0Opt6qdjBUXF1e5ZH1AQADFxcVV3vaKFSt44403mDJlCp06dWLBggU8+uijPPXUU0RHR5dbf/PmzTz99NNcffXV9OnTh+XLlzNjxgymT59Ou3ZOhZeCggK6du3KgAEDeOGFFyrd94gRI7jqqqs894ODVaK9yjKd0vZqGRMRERFpREpbxg7sxbrdGFe1O901eqdV2v7gwYNs27atSutVx/z58xkxYgTDhg0DYMqUKaxZs4YlS5Ywbty4cusvXLiQ3r17M3bsWAAmTpzIhg0bWLRokadV6/zzz69SLCEhIVVu8ZOf2MICyM0Bjpe2FxEREZHGoVkrCAyEokKnp1TzVr6OqN45rWRs9uzZzJ4926uBFBcXs23btjJJl8vlomfPnqSmplb4nNTUVC655JIyy3r16sWqVauqvf9ly5axbNkyYmJiOPvss7n88ssJCQmpdP2ioiKKioo8940xhIWFeW43FKXHUukxZR12fgeHQHhEHUUlIiIiPzE+ufY45TWC+FRdnB8TGIi7ZTzs3QUH9mJaxNXavhqqaidjN910U23EQU5ODm63u1zrVExMDHv37q3wOVlZWeW6L0ZHR5OVlVWtfQ8ePJjmzZsTGxvLjh07ePPNN9m7dy9/+tOfKn3O3Llzeffddz3327dvz/Tp02nRokW19l1fxMVV/Md17OBu0oHAlnG4XK5a6d6pbdb9etWhbXp33/Xh2OtDjNXZZkM7P7WxTV/HqM+4kzPGEB8f79VtVkdl1wjiH2r7/GQkduTo3l1E5ecQ6cP3YX1V7WRs6NChtRCGb11wwQWe2+3ataNp06Y89NBD7N+/v9I38Pjx48u0ypV+65Cenl6tcXL+zhhDXFwc+/fvx1pb7nH3j5sBKIlsSoC1FBYWej0GbfPkgoODq7zvhnTc9WWb1Tk/Vd1mdXl7m/UhxqpusyGen9rYpi9j1GfcqVlr2bdvn1e3WRWnukYQ36qr81PStDkA2ambyPXB+9BfBQYGVqmR5rS6KdaGqKgoXC5XuVatrKysSsdyxcTEkJ2dXWZZdnZ2jcd+lVZvPFkyFhQURFBQUIWPNcQPJGtthcdlSyspxjYDGt5xi4iI+L+K/0fX2d4ruUYQ/1Dr56dVa2c/+3brfXAa/KbkSWBgIMnJyaSkpHiWud1uUlJS6Ny5c4XP6dy5Mxs2bCizbP369XTq1KlGsaSlpQHQtGnTGm2nUTheSZGmDbN7poiIiIhUThM/14zfJGMAl1xyCYsXL2bp0qXs3r2bl156iYKCAk/XyJkzZ/LWW2951h89ejTr1q1j3rx57Nmzhzlz5rB161ZGjRrlWSc3N5e0tDR273bmP9i7dy9paWmeFrj9+/fz7rvvsm3bNg4ePMjq1av55z//yRlnnEFiYmKdHXt9VTrhMyprLyIiItL4lJa3zzqMPZrv21jqIb/ppggwcOBAcnJymDNnDllZWSQlJXHPPfd4uh1mZGSUqQjTpUsXpk6dyqxZs3j77beJj4/njjvu8MwxBrB69WqeffZZz/2nnnoKgAkTJnDllVcSGBjIhg0bWLhwIQUFBTRr1oz+/ftz2WWX1ckx13vHuyma2OY+DkRERERE6poJj4CoGMjJclrHkmrWQ62x8atkDGDUqFFlWrZO9MADD5RbNmDAAAYMGFDp9oYOHXrSoiPNmzfnwQcfrG6YUsrTMqZuiiIiIiKNUlwbyMnC7t+NUTJWLX7VTVHqF3vsKOTnOXfUMiYiIiLSKHnGje3XuLHqUjImp6+0VSwsHBMW7ttYRERERMQ3Wh0fN6ZkrNqUjMnp83RRVKuYiIiISGNl4p2WMbt/t48jqX+UjMlps4dVSVFERESk0SttGTu4D+su8W0s9YySMTl9x5MxE6viHSIiIiKNVvOWEBgIRYVwKN3X0dQrSsbk9KmbooiIiEijZ1wB0LK1c0eTP1eLkjE5bZ5uiqqkKCIiItK4xWnc2OlQMian73jLmFHLmIiIiEijZuJUUfF0KBmT05epljERERER4YSWMSVj1aFkTE6Lzc+DY0edO2oZExEREWnU1DJ2epSMyekpbRULj8CEhPo2FhERERHxrdLy9tmHsUfzfRtLPaJkTE6PineIiIiIyHEmvAlEN3XuqHWsypSMyWmxmcfnkFAXRREREREBVVQ8DUrG5PR4JnxWMiYiIiIiYFpp3Fh1KRmT03NYEz6LiIiIyAninWTMHlDLWFUpGZPTYrMOOTeUjImIiIgIYFo53RTVMlZ1Ssbk9KibooiIiIicqLS8/YG9WHeJb2OpJ5SMSbVZa6G0gIeSMREREREBaNYCAoOguAgOpfs6mnpByZhUX94RKCx0bqubooiIiIgAxhUArVo7d9RVsUqUjEn1lRbviIzGBAX7NhYRERER8R/HuyqqvH3VKBmT6jusOcZEREREpDwTpyIe1aFkTKrNHjro3GjeyreBiIiIiIh/UctYtSgZk+rLcJIx07yljwMREREREX/iKW9/QC1jVaFkTKrNHjrg3GimZExERERETlBa3j47E5uf59tY6gElY1J9GU4yZtRNUUREREROYMLCITrWuaPWsVNSMibVVzpmrJmSMRERERH5mdJxY/s0buxUlIxJtdj8XChtcm7WwrfBiIiIiIjfMaVdFdUydkpKxqR6jhfvICIKExrm21hERERExP8cL29vVd7+lJSMSfWorL2IiIiInISnZUzl7U9JyZhUS2klRaNKiiIiIiJSkdKJnw/uxbpLfBuLnwv0dQA/t2jRIubNm0dWVhaJiYlMnjyZjh07Vrr+ypUrmT17Nunp6cTFxTFp0iT69Onjefzrr7/mk08+Ydu2beTm5vK3v/2NpKSkMtsoLCzkjTfeYMWKFRQVFdGrVy+uu+46YmJiauko67HSboqaY0xEREREKhLbAoKCoajQuXZsGe/riPyWX7WMrVixgjfeeIMJEyYwffp0EhMTefTRR8nOzq5w/c2bN/P0008zfPhwpk+fTr9+/ZgxYwY7d+70rFNQUEDXrl2ZNGlSpft9/fXX+fbbb/nDH/7Agw8+SGZmJk888YTXj68hsMfL2qubooiIiIhUxLhc0Kq1c0cVFU/Kr5Kx+fPnM2LECIYNG0ZCQgJTpkwhODiYJUuWVLj+woUL6d27N2PHjiUhIYGJEyeSnJzMokWLPOucf/75TJgwgZ49e1a4jfz8fD777DOuvfZaevToQXJyMjfffDObN28mNTW1Vo6zXjs+ZsyorL2IiIiIVMLEtwXA7t/l40j8m990UywuLmbbtm2MGzfOs8zlctGzZ89Kk6LU1FQuueSSMst69erFqlWrqrzfbdu2UVJSUiZZa9OmDc2bNyc1NZXOnTtX+LyioiKKioo8940xhIWFeW43FKXHYozBWvtTMta8VQXH2XCOW0REpP4wPrn2OPEaQfyPr8+Pad0OC7B3l94jJ+E3yVhOTg5ut7vcOK2YmBj27t1b4XOysrKIjo4usyw6OpqsrKwq7zcrK4vAwECaNGlSre3MnTuXd99913O/ffv2TJ8+nRYtGubcW3FxcbiP5LDnaL5zv/uZuEJDy6yTviON4OBgr+9b26z79apD2/TuvuvDsdeHGKuzzYZ2fmpjm76OUZ9xJ2eMIT7ed2Ny4uLifLZvOTVfnZ/87mdy6MM3CcrYTysfvj/9nd8kY/XN+PHjy7TKlWb86enpFBcX+yosrzPGEBcXx/79+3Gn/egsjIrhQGZmuXUDrKWwsNDrMWibJxccHFzlfTek464v26zO+anqNqvL29usDzFWdZsN8fzUxjZ9GaM+407NWsu+ffu8us2qOPEawVpb5/uXk/P1+bGhkQAU7tjG3r17G13rWGBgYJUaafwmGYuKisLlcpVrjcrKyqq0qmFMTEy54h7Z2dnVqoIYExNDcXExeXl5ZVrHTrWdoKAggoKCKnysIX4gWWt/Kt7RrGUlx9jwjltERMT/WZ9ee1jr2/3Lyfnq/NgWcRAQAAVHsYfTnQqLUo7fFPAIDAwkOTmZlJQUzzK3201KSkql47Y6d+7Mhg0byixbv349nTp1qvJ+k5OTCQgIKLOdvXv3kpGRUel+Gyub8dN4MRERERGRypjAQGh5vKLiXhXxqIzfJGMAl1xyCYsXL2bp0qXs3r2bl156iYKCAoYOHQrAzJkzeeuttzzrjx49mnXr1jFv3jz27NnDnDlz2Lp1K6NGjfKsk5ubS1paGrt3O2U19+7dS1pamqcFLjw8nOHDh/PGG2+QkpLCtm3bePbZZ+ncubOSsZ87XrwDTfgsIiIiIqfS+nhFxX1KxirjN90UAQYOHEhOTg5z5swhKyuLpKQk7rnnHk93wYyMjDL9Tbt06cLUqVOZNWsWb7/9NvHx8dxxxx20a9fOs87q1at59tlnPfefeuopACZMmMCVV14JwLXXXosxhieeeILi4mLPpM9SluYYExEREZGqMvHtsKwAJWOV8qtkDGDUqFFlWrZO9MADD5RbNmDAAAYMGFDp9oYOHeppWatMcHAw1113nRKwU/HMMaaWMRERERE5hdKWsb07fRyI//Krboriv6y1cHzMGM2VjImIiIjIyZVO/My+XSryUgklY1I1eUeg4KhzWy1jIiIiInIqrdqAcUF+HmSXnxZJlIxJVZWOF4uOxQR5fwJMEREREWlYTFAQtDw+4bPGjVVIyZhUiVUXRRERERGprvjScWNKxiqiZEyq5pDTMqbiHSIiIiJSVaZ16bgxFfGoiJIxqZKfWsZU1l5EREREqihec42djJIxqZrSMWNqGRMRERGRKvK0jKmbYoWUjEmV2PR9ABi1jImIiIhIVbVKAGMgNwd7JNvX0fgdJWNySra4GNL3O3fiEnwbjIiIiIjUGyYk5KdhLmodK0fJmJxS8f7dUFICIaHQtJmvwxERERGR+sQzbkxFPH5OyZicUvGuNOdGqzYYY3wai4iIiIjULyZe48Yqo2RMTqlodxoARl0URURERKS6WpfONaaWsZ9TMianVLR7h3Mjvo1vAxERERGRese0SXRu7EnDWuvbYPyMkjE5peLjyZhaxkRERESk2lq3A5cLco9A5iFfR+NXlIzJSVlrKT7eTVGVFEVERESkukxQsKeIB7u2+TYYP6NkTE7uSDbu3BxnfohWrX0djYiIiIjUQ6ZtMgB2p5KxEykZk5Pbv9v53ayl862GiIiIiEh1tTuejKllrAwlY3JSdp+TjGm8mIiIiIicLtO2vXNDLWNlKBmTk7L79zg34pWMiYiIiMhpOt5NkUMHsfm5vo3FjygZk5Pbr5YxEREREakZ0yQCmrV07uza7ttg/IiSMTkpW5qMqWVMRERERGqircaN/ZySMamULSqEjAPOHbWMiYiIiEgNmONFPDRu7CdKxqRyB/aCtZgmkRAZ7etoRERERKQeKy3iofL2P1EyJpU73kUxqG0SxhgfByMiIiIi9Vppy9j+3U4PLFEyJpUrraQYmJDk20BEREREpP5r2hyaREJJCezd6eto/IKSMalcactYQqKPAxERERGR+s4Y89Pkz+qqCCgZk5MobRkLUsuYiIiIiHiBZ/JnVVQElIxJJay1npaxwLZJvg1GRERERBoGT3l7zTUGSsakMpmHoOAYBAQQqLL2IiIiIuIF5ngyxq40rNvt22D8QKCvA6jIokWLmDdvHllZWSQmJjJ58mQ6duxY6forV65k9uzZpKenExcXx6RJk+jTp4/ncWstc+bMYfHixeTl5dG1a1euu+464uPjPevccsstpKenl9nu1Vdfzbhx47x+fPXC8VYxWsRhAv3ybSIiIiIi9U1cGwgKhoKjkL4fWrX2dUQ+5XctYytWrOCNN95gwoQJTJ8+ncTERB599FGys7MrXH/z5s08/fTTDB8+nOnTp9OvXz9mzJjBzp0/VWj58MMP+eijj5gyZQqPPfYYISEhPProoxQWli2peeWVV/Kvf/3L8zNq1KhaPVZ/Vtp0bNqoeIeIiIiIeIcJCIDj15d2xxYfR+N7fpeMzZ8/nxEjRjBs2DASEhKYMmUKwcHBLFmypML1Fy5cSO/evRk7diwJCQlMnDiR5ORkFi1aBDitYgsXLuSyyy6jX79+JCYmcuutt5KZmcmqVavKbCssLIyYmBjPT2hoaK0fr9/angqASers40BEREREpCExyV2cG1s2+TYQP+BX/c+Ki4vZtm1bma6BLpeLnj17kpqaWuFzUlNTueSSS8os69WrlyfROnjwIFlZWZx55pmex8PDw+nYsSOpqakMGjTIs/yDDz7gvffeo3nz5gwePJgxY8YQEBBQ4X6LioooKiry3DfGEBYW5rld39m0HwEwyU4yVrVjqv/HLSIiUv8Yn1x7lO6zIVz3NET+fH5M5+7Yz+Zjf9zkl/HVJb9KxnJycnC73cTExJRZHhMTw969eyt8TlZWFtHR0WWWRUdHk5WV5Xm8dFll6wBcfPHFtG/fnoiICDZv3szbb79NZmYm1157bYX7nTt3Lu+++67nfvv27Zk+fTotWrSowpH6t5LMQ+w9dBCMIe6cgQDExcWd8nnpO9IIDg72ejzaZt2vVx3apnf3XR+OvT7EWJ1tNrTzUxvb9HWM+ow7OWNMmXHwda0q1wjiO/54fkoGDWPv89Nhzw5aRUbgioj0dUg+41fJmC+d2LqWmJhIYGAgL774IldffTVBQUHl1h8/fnyZ55Rm9enp6RQXF9d+wLXIve4b50Z8AgdzcokLj2D//v1OufuTCLC23Dg8b9A2Ty44OLjK+25Ix11ftlmd81PVbVaXt7dZH2Ks6jYb4vmpjW36MkZ9xp2atZZ9+/Z5dZtVYYwhLi6uStcIUvf8/vy0jIeD+9j35VJcZ/b1dTReFxgYWKVGGr9KxqKionC5XGVarMBp3fp5a1mpmJiYcsU9srOzPeuX/s7OzqZp06Zl1klKSqo0lk6dOlFSUkJ6ejqtW5ev8hIUFFRhkgb45xu+Guz2410Ukzp7jsVaW4Xjqt/HLSIiUj9V5X90Le69StcI4iv+en5Mp27Yg/uwP6Zge57t63B8xq8KeAQGBpKcnExKSopnmdvtJiUlhc6dKy4k0blzZzZs2FBm2fr16+nUqRMALVu2JCYmpsw6+fn5bNmypdJtAqSlpWGMISoqqiaHVC/ZtOPj85I6+TYQEREREWmYOnUHwP7YuIt4+FUyBk53wcWLF7N06VJ2797NSy+9REFBAUOHDgVg5syZvPXWW571R48ezbp165g3bx579uxhzpw5bN261VOW3hjD6NGjef/991m9ejU7d+5k5syZNG3alH79+gFOEZAFCxaQlpbGgQMHWLZsGa+//jrnnXceERERdf4a+JK1FkpbxtorGRMRERER7zOdujk30n7EFnm/O3B94VfdFAEGDhxITk4Oc+bMISsri6SkJO655x5Pd8OMjIwyVVe6dOnC1KlTmTVrFm+//Tbx8fHccccdtGvXzrPOpZdeSkFBAS+88AL5+fl07dqVe+65xzOANjAwkBUrVvDOO+9QVFREy5YtGTNmTLkqjY1C+n7IOwKBgZCQ5OtoRERERKQhahEP0U0hO9OZUqlzD19H5BN+l4wBjBo1qtIJlx944IFyywYMGMCAAQMq3Z4xhquuuoqrrrqqwseTk5N59NFHTyvWhsYen1+MtsmYwIrHxImIiIiI1IQxBjqeAd+ucErcN9JkzO+6KYqPlc4vpvFiIiIiIlKLTOm4sUY8+bOSMSmjdLJn2lde3EREREREpKY848a2/oB1l/g2GB9RMiYetrgYdm4FVLxDRERERGpZQhKEhcPRfNid5utofELJmPxk704oLISwJtCy/NxqIiIiIiLeYlwB0KEr0HhL3CsZE4+f5hfriHHprSEiIiIitct0dLoq2h83+jgS39AVt/xku4p3iIiIiEjdKS3iweaURjluTMmYeNhtmwEwKt4hIiIiInUhuQuER0BuDjTCropKxgQAe+igM2bMuOB4c7GIiIiISG0ygYGY3v0BsN+u8HE0dU/JmABg137j3OjYFRMZ5dtgRERERKTRMH0GAmC/W4l1u30cTd1SMiYA2HVfA3i+mRARERERqRPdekNoGGQdhu2pvo6mTikZE2x+LqSmAErGRERERKRumaAgzJn9ALBrGldXRSVjgt3wLZSUQHxbjOYXExEREZE65umq+O0KrLU+jqbuKBkTWKsuiiIiIiLiQz36QHAwHDoIO7f5Opo6o2SskbNFRdiUbwElYyIiIiLiGyYkFHqcDTSuropKxhq7zevh2FGIjgVN9iwiIiIiPuLpqrim8XRVVDLWyNnSLoq9zsG49HYQEREREd8wZ/aDwEDYvwf27vJ1OHVCV9+NmHW7seuc+cXURVFEREREfMmEhUO3swCwy//n42jqhpKxxmzHVmc+h5Aw6Hqmr6MRERERkUbONWwMAPaLj7FHcnwcTe1TMtaI2c8XAmB6no0JCvJxNCIiIiLS6HU/CxI7QmEB9tP/+jqaWqdkrJGy6fuxK5cAYEZe6uNoRERERETAGINr9AQA7JIF2Pw8H0dUu5SMNVL2o3fB7YbuZ2GSu/g6HBERERERR+9zIb4tHM3DLl3o62hqlZKxRsgeOohdsRgA1yUTfRyNiIiIiMhPjMuFufh469in/8UWFPg4otqjZKwRsgvfhZISOKMXpuMZvg5HRERERKQMc8750LwVHMnGLvvY1+HUGiVjjYw9nI798lNArWIiIiIi4p9MQABm1OUA2EXvYY9k+zii2qFkrJGxH70HJcXQpSemc3dfhyMiIiIiUiEzcATEtYHsTNwv/h/WXeLrkLxOyVgjYtd9g/18EQCuX6hVTERERET8lwkKwnXj3RAcAt+vw86b5euQvE7JWCNhd2zF/a8ZYN2Y8y7EdOnp65BERERERE7KtGmHueYWAOz82dgN3/o4Iu9SMtYI2MMZuGc+DIUF0K035uobfR2SiIiIiEiVuM4dihl6MQDul/+OPbDXtwF5kZKxBs7m5+J+5mHIOgzxbXHd8GdMYKCvwxIRERERqTJz5XWQ1AnyjuB+9A/Yb7/0dUheoWSsgbLWYlcvx/3/27v/oCive4/j710XRCDrggzCFlwuEYIdFYKiN5GKQcdYr9dYa4mxnSax0GTU2mmuaTKhMdGIc42NV1OdlttgI038sfHaUSNaU0pU/DEaNTaISi0qKkWlYaGyiuju/SN1mw0YYyM8S/i8ZhjZs2fPfh+/HuS75zzPM3cWnDsFVhvm2XMxhYYZHZqIiIiIyB0xBQVhnpkP/QfAFTeeXy3Cs/pXeFuvGR3alxKQSyTbtm1j8+bNuFwuHA4H06dPp3///rfsv3fvXtatW8elS5eIiYnhu9/9Lunp6b7nvV4vTqeT0tJSmpubSUlJITc3l9jYWF+fy5cvs3LlSg4ePIjJZGL48OE8+eSThISEdOixdgTvpTo8qwuh4h97aqPtmJ96FlNUX2MDExERERH5F5lskZj/qwDvprfxbv0/vGUleI8dwTTqPzD9+yhMYeFGh3jHAm5lbM+ePRQXFzNlyhQWLVqEw+GgoKCAxsb27y1w4sQJli1bRnZ2NosWLSIjI4PFixdTU1Pj67Nx40a2bt1KXl4eCxcupGfPnhQUFHDt2j8r6ddff52zZ8/ys5/9jOeff55jx45RWFjY4cd7t3nPnMTz0qxPCjGLBdN/TsX88uuY+t1rdGgiIiIiIl+KyWLBPPlxzLNfgnAr1J3Hu/Z/8Tz7BJ6i/8F7stLoEO9IwBVj7777LqNHj+ahhx4iLi6OvLw8goODKSsra7d/SUkJaWlpTJw4kbi4OKZOnUpiYiLbtn1yCXev10tJSQmTJ08mIyMDh8PBrFmzaGho4MCBAwCcO3eODz/8kKeffpqkpCRSUlKYPn06e/bs4eOPP+60Y78r4v8N7P0gZTDml17HPHEapqBgo6MSEREREblrTIOGYC74FaZpT0FcArRew7uvDM97m4wO7Y4E1DbF69evU11dzaRJk3xtZrOZQYMGUVVV1e5rqqqqmDBhgl9bamqqr9C6ePEiLpeLwYMH+54PDQ2lf//+VFVVMWLECKqqqggLC+Pee/+5ejRo0CBMJhMnT55k2LBhbd63tbWV1tZW32OTyUSvXr2wGH5xjCB4/r+h1905N8xkMn0yalAQXq/3c/v2wIs1JuauvK9vzOBgjXkblqAgrn/q3+KXHe9OaMy7l587GfNO3O0xu0KMdzLmVy0/HTGm0THqZ9ztWYJ7YgoKuqtjfhF38juCdL5ukZ/eETB20idf52vwHNqDaeAQQ+bDZ33RmsDkDaDsfPzxxzz99NMsWLCA5ORkX/tbb71FZWUlCxcubPOaxx57jJkzZ5KZmelr+/3vf8/69ev59a9/zYkTJ3jxxRcpLCwkIiLC12fJkiWYTCZ+8pOfsGHDBnbs2MGyZcv8xs7NzSUnJ4exY8e2eV+n08n69et9j0eMGMGPf/zjL3X8IiIiIiLSfQTcNsWu4lvf+hZvvvmm7ysvL89vpeyr4sqVKzz33HNcuXLF6FCkHcpPYFN+ApvyE/iUo8Cm/AQ25adrMHpPnR+r1YrZbMblcvm1u1wubDZbu6+x2WxtLu7R2Njo63/zz8bGRr+VscbGRhISEnx9mpqa/Ma4ceMGly9fvuX7BgUFERQAS6Adzev1curUqa/u8nYXp/wENuUnsCk/gU85CmzKT2BTfrqGgFoZs1gsJCYmUlFR4WvzeDxUVFT4bVv8tOTkZD766CO/tj/96U8kJSUBEB0djc1m8+vjdrs5efKkb8zk5GSam5uprq729amoqMDr9X7uJfVFRERERET+VQFVjAFMmDCB0tJS3n//fc6dO8cbb7xBS0sLo0aNAmD58uWsXr3a13/8+PEcOXKEzZs3c/78eZxOJ3/5y18YN24c8MnJi+PHj2fDhg188MEH1NTUsHz5ciIiIsjIyAAgLi6OtLQ0CgsLOXnyJMePH2flypU8+OCDREZGdvrfgYiIiIiIfPUF1DZFgAcffJCmpiacTicul4uEhAReeOEF33bB+vp639VhAO677z5mz57N2rVrWbNmDbGxsTz77LP069fP1+eRRx6hpaWFwsJC3G43KSkpvPDCCwQH//OS77Nnz6aoqIj58+f7bvo8ffr0TjvuQBUUFMSUKVO6xZbMrkj5CWzKT2BTfgKfchTYlJ/Apvx0DQF1NUUREREREZHuIuC2KYqIiIiIiHQHKsZEREREREQMoGJMRERERETEACrGREREREREDBBwV1OUwLFt2zY2b96My+XC4XAwffp03XctQDidTtavX+/XZrfbWbp0qTEBdXOVlZVs2rSJU6dO0dDQwJw5cxg2bJjvea/Xi9PppLS0lObmZlJSUsjNzSU2NtbAqLuP2+VnxYoV7Nixw+81qamp5Ofnd3ao3dLvfvc79u/fz/nz5wkODiY5OZnvfe972O12X59r165RXFzMnj17aG1tJTU1ldzcXN+VlqXjfJH8vPzyy1RWVvq9bsyYMfzwhz/s7HC7ne3bt7N9+3YuXboEfHK7pilTpnD//fcDmjtdgYoxadeePXsoLi4mLy+PpKQktmzZQkFBAUuXLqV3795GhydAfHw8L774ou+x2ayFbqO0tLSQkJBAdnY2P//5z9s8v3HjRrZu3crMmTOJjo5m3bp1FBQUsGTJEr9bbEjHuF1+ANLS0pgxY4bvscWi/x47S2VlJQ8//DD33nsvN27cYM2aNSxYsIAlS5YQEhICwKpVqzh06BDPPPMMoaGhFBUV8dprr/HKK68YHP1X3xfJD8Do0aN59NFHfY/1s61zREZGMm3aNGJjY/F6vezYsYNXX32VV199lfj4eM2dLkC/vUm73n33XUaPHs1DDz1EXFwceXl5BAcHU1ZWZnRo8g9msxmbzeb7slqtRofUbd1///1MnTrVb7XlJq/XS0lJCZMnTyYjIwOHw8GsWbNoaGjgwIEDBkTb/Xxefm6yWCx+8yk8PLwTI+ze8vPzGTVqFPHx8SQkJDBz5kzq6+uprq4GwO1288c//pHHH3+cgQMHkpiYyIwZMzhx4gRVVVUGR//Vd7v83NSzZ0+/ORQaGmpQxN3L0KFDSU9PJzY2FrvdzmOPPUZISAh//vOfNXe6CH30J21cv36d6upqJk2a5Gszm80MGjRIkzeA1NXV8dRTTxEUFERycjLTpk0jKirK6LDkMy5evIjL5WLw4MG+ttDQUPr3709VVRUjRowwMDq5qbKyktzcXMLCwhg4cCBTp07lnnvuMTqsbsntdgP4CuLq6mpu3LjBoEGDfH2+9rWvERUVRVVVFcnJyYbE2V19Nj837dq1i127dmGz2RgyZAjf/va36dmzpxEhdlsej4e9e/fS0tJCcnKy5k4XoWJM2mhqasLj8bTZT2yz2aitrTUmKPGTlJTEjBkzsNvtNDQ0sH79eubOnctrr71Gr169jA5PPsXlcgG02d7bu3dv33NirLS0NIYPH050dDR1dXWsWbOGhQsXUlBQoO2/nczj8fDmm29y33330a9fP+CTOWSxWAgLC/PrqznU+drLD0BmZiZRUVFERkZy5swZ3n77bWpra5kzZ46B0XYfNTU15Ofn09raSkhICHPmzCEuLo7Tp09r7nQBKsZEuqCbJ+YCOBwOX3G2d+9esrOzDYxMpOv59Opkv379cDgc/OhHP+Lo0aN+nyhLxysqKuLs2bPMnz/f6FCkHbfKz5gxY3zf9+vXj4iICObPn09dXR0xMTGdHWa3Y7fbWbx4MW63m3379rFixQrmzZtndFjyBekjP2nDarViNpvbfGricrl09Z0AFRYWht1up66uzuhQ5DNuzpnGxka/9sbGRs2nANW3b1/uuecezadOVlRUxKFDh3jppZfo06ePr91ms3H9+nWam5v9+msOda5b5ac9N6+8rDnUOSwWCzExMSQmJjJt2jQSEhIoKSnR3OkiVIxJGxaLhcTERCoqKnxtHo+HiooK7S8OUFevXqWurk4/XANQdHQ0NpuNjz76yNfmdrs5efKk5lOA+tvf/sbly5eJiIgwOpRuwev1UlRUxP79+5k7dy7R0dF+zycmJtKjRw+/OVRbW0t9fb3mUCe4XX7ac/r0aQDNIYN4PB5aW1s1d7oIbVOUdk2YMIEVK1aQmJhI//79KSkpoaWlhVGjRhkdmgDFxcUMHTqUqKgoGhoacDqdmM1mMjMzjQ6tW7pZDN908eJFTp8+TXh4OFFRUYwfP54NGzYQGxtLdHQ0a9euJSIigoyMDAOj7j4+Lz/h4eG88847DB8+HJvNxoULF3jrrbeIiYkhNTXVwKi7j6KiIsrLy/npT39Kr169fLsyQkNDCQ4OJjQ0lOzsbIqLiwkPDyc0NJSVK1eSnJysXyg7we3yU1dXR3l5Oenp6YSHh1NTU8OqVasYMGAADofD2OC7gdWrV5OWlkZUVBRXr16lvLycyspK8vPzNXe6CJPX6/UaHYQEpm3btrFp0yZcLhcJCQk8+eSTJCUlGR2WAEuXLuXYsWP8/e9/x2q1kpKSwtSpU7U33yBHjx5td39+VlYWM2fO9N30+Q9/+ANut5uUlBR+8IMf+N00VTrO5+UnLy+PxYsXc+rUKZqbm4mMjGTw4ME8+uijWmnuJDk5Oe22z5gxw/cB4M0b1+7evZvr16/rxrWd6Hb5qa+v5xe/+AVnz56lpaWFPn36MGzYMCZPnqzL23eCX/7yl1RUVNDQ0EBoaCgOh4NHHnnEdwVfzZ3Ap2JMRERERETEADpnTERERERExAAqxkRERERERAygYkxERERERMQAKsZEREREREQMoGJMRERERETEACrGREREREREDKBiTERERERExAAqxkRERERERAygYkxEROQOOZ1OcnJyjA5DRES6OBVjIiIiIiIiBlAxJiIiIiIiYgAVYyIiIiIiIgawGB2AiIhIIDt+/DirVq2ipqaGyMhIJk6c2KZPWVkZO3fu5OzZs7jdbvr27cs3v/lNxo4d6+uzfPlyDh8+TGFhIRaL/3+/CxYs4NKlSyxbtqzDj0dERAKHijEREZFbqKmpYcGCBVitVr7zne9w48YNnE4nNpvNr9/27duJj49n6NCh9OjRg4MHD/LGG2/g8XgYN24cACNHjmTnzp0cOXKEIUOG+F7rcrmoqKhgypQpnXloIiISAFSMiYiI3MK6devwer3Mnz+fqKgoAIYPH86cOXP8+s2bN4/g4GDf43HjxlFQUMCWLVt8xdjAgQPp06cPu3bt8ivGysvL8Xq9jBw5shOOSEREAonOGRMREWmHx+PhyJEjZGRk+AoxgLi4OFJTU/36froQc7vdNDU18fWvf50LFy7gdrsBMJvNZGZm8sEHH3DlyhVf//LycpKTk4mOju7gIxIRkUCjlTEREZF2NDU1ce3aNWJjY9s8Z7fbOXz4sO/x8ePHeeedd6iqqqKlpcWvr9vtJjQ0FICsrCw2btzI/v37ycrKora2lurqavLy8jr2YEREJCCpGBMREfkS6urqeOWVV7Db7Xz/+9+nT58+WCwWDh8+zJYtW/B4PL6+cXFxJCYmsmvXLrKysti5cycWi4UHHnjAwCMQERGjqBgTERFph9VqJTg4mL/+9a9tnqutrfV9f/DgQVpbW3nuuef8tjMePXq03XFHjhxJcXExDQ0N7N69m/T0dMLDw+/+AYiISMDTOWMiIiLtMJvNpKamcuDAAerr633t586d48iRI379ALxer6/N7Xbz/vvvtztuZmYmJpOJ3/zmN1y4cIFvfOMbHXMAIiIS8LQyJiIicgs5OTl8+OGHzJ07l7Fjx+LxeNi6dSvx8fGcOXMGgNTUVCwWC4sWLWLMmDFcvXqV0tJSrFYrDQ0Nbca0Wq2kpqayb98+wsLCSE9P7+zDEhGRAKGVMRERkVtwOBzk5+djtVpxOp2UlZWRk5NDRkaGr4/dbueZZ57BZDLx29/+lvfee48xY8Ywfvz4W46blZUFwAMPPEBQUFCHH4eIiAQmk/fT+ypERESkwx04cIDFixczb948BgwYYHQ4IiJiEK2MiYiIdLLS0lL69u1LSkqK0aGIiIiBdM6YiIhIJ9m9ezdnzpzh0KFDPPHEE5hMJqNDEhERA6kYExER6STLli0jJCSE7OxsHn74YaPDERERg+mcMREREREREQPonDEREREREREDqBgTERERERExgIoxERERERERA6gYExERERERMYCKMREREREREQOoGBMRERERETGAijEREREREREDqBgTERERERExwP8DYlE/i1mBAjYAAAAASUVORK5CYII=\n"},"metadata":{}}],"execution_count":30},{"cell_type":"code","source":"plt.figure(figsize=(10,4))\n# plt.subplot(121)\nplt.title('month distribution with onset and wakeup')\nsns.histplot(x=train_events.dropna().month, hue=train_events.dropna().event, stat='density', bins=24, binrange=(-0.5, 23.5))\nsns.kdeplot(train_events.dropna().month, bw_adjust=0.45)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:04:55.447971Z","iopub.execute_input":"2025-05-04T05:04:55.448324Z","iopub.status.idle":"2025-05-04T05:04:55.915392Z","shell.execute_reply.started":"2025-05-04T05:04:55.4483Z","shell.execute_reply":"2025-05-04T05:04:55.91441Z"}},"outputs":[{"execution_count":31,"output_type":"execute_result","data":{"text/plain":""},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":31},{"cell_type":"code","source":"mask_nonull= (~train_events['step'].isnull()) & (~train_events['timestamp'].isnull()) \ntrain_events_nonull = train_events[mask_nonull]\n\n# Group by 'series_id' and calculate sleep duration for each night\nsleep_duration_df = train_events_nonull.groupby([train_events_nonull['series_id'], train_events_nonull['night']])['timestamp'].agg(['min', 'max']).reset_index()\nsleep_duration_df = sleep_duration_df.rename(columns={'min': 'onset', 'max': 'wakeup'})\nsleep_duration_df['sleep_duration'] = ((sleep_duration_df['wakeup'] - sleep_duration_df['onset']).dt.seconds / 3600).round(0)\n\ndfg = sleep_duration_df['sleep_duration'].value_counts().reset_index()\ndfg.columns = ['sleep_duration', 'number_of_observations']\nfig = px.bar(dfg, x='sleep_duration', y='number_of_observations', \n title='Sleep hour distribution, Training seria (hours)'\n ) \nfig.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:05:01.93333Z","iopub.execute_input":"2025-05-04T05:05:01.933643Z","iopub.status.idle":"2025-05-04T05:05:02.092111Z","shell.execute_reply.started":"2025-05-04T05:05:01.933596Z","shell.execute_reply":"2025-05-04T05:05:02.091268Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":32},{"cell_type":"code","source":"train_series.info()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:05:07.020012Z","iopub.execute_input":"2025-05-04T05:05:07.020784Z","iopub.status.idle":"2025-05-04T05:05:07.029482Z","shell.execute_reply.started":"2025-05-04T05:05:07.020756Z","shell.execute_reply":"2025-05-04T05:05:07.028386Z"}},"outputs":[{"name":"stdout","text":"\nRangeIndex: 10000000 entries, 0 to 9999999\nData columns (total 5 columns):\n # Column Dtype \n--- ------ ----- \n 0 timestamp object \n 1 series_id category\n 2 step float32 \n 3 anglez float16 \n 4 enmo float16 \ndtypes: category(1), float16(2), float32(1), object(1)\nmemory usage: 162.1+ MB\n","output_type":"stream"}],"execution_count":33},{"cell_type":"code","source":"sns.boxplot(x = train_series['anglez'])\nplt.title('box plot for train series enmo data')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:05:12.604566Z","iopub.execute_input":"2025-05-04T05:05:12.604941Z","iopub.status.idle":"2025-05-04T05:05:13.872441Z","shell.execute_reply.started":"2025-05-04T05:05:12.604918Z","shell.execute_reply":"2025-05-04T05:05:13.871756Z"}},"outputs":[{"execution_count":34,"output_type":"execute_result","data":{"text/plain":"Text(0.5, 1.0, 'box plot for train series enmo data')"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"iVBORw0KGgoAAAANSUhEUgAAAggAAAHMCAYAAACwbVBcAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAwN0lEQVR4nO3dd3SU5b728WuGZFJJQoiUKD3SWwAroUixgVRRA0ixcsAXBEXZihIQLIuNYjtiQcGtoIAF0Y2ytyQURRABqQoKUQQiYAgBQki73z9YMyfjnYQkJIQk389aLGae+rvnaVeeMuMwxhgBAADk4izrAgAAwMWHgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYBwASQmJsrhcGjEiBFlXUqp6Nq1qxwOR5nWsHHjRvXs2VMRERFyOBxq27ZtmdZzoTgcDnXt2rWsyygVCQkJcjgciouLK+tSUICKvA5WdgQEXDSKu6NJTU1Vr169tGHDBt1xxx2aMmWKRo0aVfIFnsOIESPkcDiUmJh4wecNlGcV/Y+o8sqnrAsAzteGDRt0+PBhzZgxQ4899lhZl3NB7dq1S4GBgWVdRqm48sortWvXLkVERJR1KUClREBAuXfw4EFJUmRkZBlXcuE1bdq0rEsoNYGBgRW6fcDFjksMF9hPP/2kfv36KTw8XEFBQYqJidGKFSvyHPbMmTN69tln1apVKwUGBiokJESdOnXSokWLvIb7+OOP5XA4dPXVVyszM9Or3/bt2xUYGKjIyEgdPnz4nPXFxcXJ4XAoISFB8+fPV3R0tAICAlSjRg3dddddSkpKKnRbc3JyNGfOHF1xxRUKDg5WUFCQrrjiCr322mvKycnxDDdv3jzPPQyrVq2Sw+Hw/Cvo+rP7tOTw4cMlSSNHjvSMN2/ePM9whw4d0pgxY1S/fn25XC5dcsklGjBggH744Qdrmu5a5s2bpy+//FJdu3ZVaGjoOe+xcDgcmj9/viSpQYMGnjrq16/vGcZ9r0ZGRoamTZumJk2ayM/Pz3Na9fjx45o5c6a6deumyy67zFNrnz59tG7dunzn+/fLMrmX4ZIlS3TllVcqMDBQ4eHhuuOOO3TgwIEC25JbRkaGXnrpJbVr107VqlVTYGCg6tevr759++q///2vNfxPP/2kESNGqE6dOnK5XKpZs6YGDx6sn3/+2RrWfUlm7969evnll9W6dWsFBAR42lPQPQjJycn6xz/+oWbNmikgIEChoaHq3r17nttSUduQn7S0ND3zzDNq27atgoKCFBwcrGuuuUYLFy60hs1d+5YtW9SrVy+FhYUpMDBQXbp00bfffmuNk3u5LVy4UO3bt/dsuxMmTNCZM2ckSStXrlTXrl0VEhKiatWq6c4779Rff/2VZ80//PCDBg4cqBo1asjPz0/16tXT6NGjdejQoUK3Wzr7GT711FNq1KiR/Pz81KBBA02ePNlT098dPHhQ06ZNU8eOHVWrVi25XC5FRkZq8ODB2rlzp9XuBg0aSJLmz5/vtf27t+OMjAy98soruvnmm1WvXj35+fkpPDxcPXr00PLly4vUFhSBQanbt2+fkWQ6d+5swsLCTKdOncykSZPM8OHDjb+/v3E6neaDDz7wGufMmTOmS5cuRpJp2rSpefjhh83o0aNNjRo1jCTzj3/8w2v4MWPGGElm4sSJnm6nTp0yzZo1M06n06xcubJQtU6ZMsVIMn369DH+/v5m+PDhZtKkSSYmJsZIMg0aNDCHDx/2Gsdd598NHjzYSDJ16tQx48aNMw8++KCpV6+ekWQGDx7sGW7z5s2e+darV89MmTLF8y8+Pj7fWo8dO2amTJli+vbtaySZvn37esbbvHmzMcaYvXv3msjISCPJdOvWzUyaNMkMGTLEuFwu43K5zLJly7ym+c477xhJplevXqZKlSqmd+/e5pFHHjG33377OT+3Nm3aGElm3LhxnjpeeOEF63Pq3bu3qVmzphkxYoR55JFHzD//+U9jjDHr1q0zvr6+pnv37ua+++4zjz76qImNjTVBQUHGx8fHLF++3JqvJNOlSxerFklm0KBBxs/PzwwaNMg8/PDDplOnTp71KT09vcD2uMXGxhpJpmXLlmbs2LHm0UcfNXfeeadp0KCBeeihh7yGXb58uQkICDA+Pj6mf//+ZuLEiSY2Ntb4+fmZkJAQ88MPP3gNP3z4cM/nERoaagYPHmweffRR89hjjxljjImPjzeSzJQpU7zGS0xMNPXr1zeSTKdOncyDDz5o7r33XlO7dm3jcDjMG2+8Uew25OfYsWMmOjraSDLt2rUzDzzwgBk9erRp1KiRkWQef/xxr+Hdtffq1csEBASYbt26mYceesgMGjTIOJ1O4+/vb3766SevcdzLbcCAASYgIMDExsaaCRMmmJYtWxpJZvjw4ebjjz82LpfL9O/f3zz00EPmmmuuMZLMjTfeaNW8bNky43K5jK+vr4mNjTWTJk0yPXv2NJJMZGSk2bt3b6HanpOT49nGGjVqZCZMmGAeeOABU7t2bdOnT58818GFCxeagIAAc/PNN5vRo0ebRx55xPTv39/4+vqaoKAgs2XLFq/Paty4cUaSadOmjdf2796ODx06ZJxOp4mJiTF33323Z/8ZHh5uJJk333yzUG1B0RAQLgB3QJBkHn74Ya9+33//vfHx8TFhYWHm+PHjnu5PP/20kWRuuukmk5mZ6en+559/eg6y33zzjad7enq6iY6ONg6Hw3MgGTFihJFknnzyyULX6t5J+fr6mk2bNnn1e/DBB40kc9ddd3l1zysgLFiwwEgy0dHR5sSJE57uJ0+eNO3btzeSzPvvv+81Tl47msJwH9Tfeecdq9/1119vJJnp06d7df/mm29MlSpVTHh4uFd97mnl/hwLy33A27dvX5793Z9Tq1atzJEjR6z+KSkpeXbfv3+/qV27tmnatKnVr6CAULVqVbN161avfu6D5YcffnjO9qSkpBiHw2Hat29vsrKyrP5Hjx71vE5OTjZhYWGmevXqZseOHV7Dbdu2zQQFBZno6Giv7u7PK7+DVX4BoUuXLsbhcJiFCxd6dT927Jhp06aN8ff3N0lJSUVuQ0HctT733HNe3U+fPm1uuOEG43A4PAez3LXntV7OmTPHSDL/8z//49XdvdxCQkLMzp07Pd3T09NN8+bNjdPpNOHh4SYhIcHTLzs72/To0cNI8pr/iRMnTHh4uHE6nWb16tVe83n22WeNJNOzZ89Ctf399983kszVV19tTp8+7en+119/mYYNG+a5Dv75558mNTXVmtaWLVtMUFCQFWjc+8jhw4fnWUN6errZv3+/1T0lJcW0aNHCVKtWzaSlpRWqPSg8AsIF4F75Q0ND89xo3DufefPmebpFRUUZh8Nhdu3aZQ3/1ltvGUlm5MiRXt13795tgoODzSWXXGJmzpzpOWuR144xP+6d1N9DgDFnN8bQ0FDj7+/v9RdoXgHBvdP66quvrOn897//NZLMdddd59W9pAPC/v37jSRTt25dk5GRYY03dOhQI8nMnz/fmla/fv2KXEdhA8Knn35a5Gn/v//3/4wk89tvv3l1Lygg/P2vWmOMWblypZFUqL+cjx8/biSZa6+91uTk5BQ47OzZs40k88orr+TZ3x0uc4cH9+c1e/bsPMfJKyBs2bLFSDK33nprnuN8+umnRpJ59dVXi9yG/Bw9etRUqVLFdOjQIc/+7ppyn71z196xY0dr+IyMDOPj42Pat2/v1d293CZPnmyNM3XqVCPJ3HnnnVa/efPmWfuP9957z0gysbGx1vCZmZmeMzB/X5/y4t6W8zoL6d5eirLd3nLLLcbPz89rmzxXQCjIrFmzjCSzatWqIo+LgnGT4gXUrl07Va1a1eretWtXzZ8/X5s3b9bw4cN14sQJ/fLLL7r00kvzvEmrW7dukqTNmzd7db/88ss1Z84cDR06VBMnTlRERIQWLFigKlWqFLnWLl26WN1CQ0PVtm1brVq1Srt27SrwuwY2bdokp9OZ52OLXbp0UZUqVaz6S5p7+p06dZKvr6/Vv1u3bnrvvfe0efNmDRs2zKvflVdeWWp1FTTtb775Ri+++KLWrVunw4cPKyMjw6v/gQMHVLdu3ULNp0OHDla3OnXqSJKOHTt2zvFDQkJ0yy23aNmyZWrbtq0GDhyoTp066aqrrrKenHDfI/Hjjz/mec/A7t27JZ196qJ58+Ze/YryWbvnc/z48Tznc+TIEc98itqG/Hz//ffKzs7O934I930/7nnmltcy8PX1Vc2aNfNdBnmN474Bt3379la/Sy+9VJL0xx9/eLpt2rRJ0v/tK3Lz8fFR586dlZiYqM2bN59zfXJvyzExMVa/gh5L/uKLLzRnzhxt3LhRR48eVVZWllf/o0ePqnbt2gXOO7cdO3Zo5syZWr16tQ4dOqT09HSv/kW5twaFQ0C4gGrWrJln91q1akk6u9PL/X9+G4+7e0pKitXv+uuvV0hIiFJTUzVo0CDPzqO0as3P8ePHFR4eLpfLZfXz8fFRREREoW6aPB/n8zm621ka8pv2J598oltvvVX+/v7q2bOnGjVqpKCgIDmdTiUkJGjVqlX53hSWl7CwMKubj8/ZTT47O7tQ0/jwww/13HPPacGCBZoyZYokyd/fX7feeqv++c9/etYT901yb775ZoHTO3nypNWtKJ+1ez7/+c9/9J///KdQ8ylsG841z++//17ff/99oebpltcykM4uh/yWQWhoaJ7Dn6tf7huUz2fd/zv3tpxXyM5v2b344ot68MEHVa1aNfXs2VN169ZVYGCgHA6HPv30U/34449FWpe/++47devWTVlZWerevbv69OmjkJAQOZ1ObdmyRUuXLi3S9FA4BIQL6M8//8yzu/vJAPfG7/4/vycG3Hcg/31nYYzRsGHDlJqaqoiICL3xxhu644471Llz51KrNT+hoaFKTk5WZmamtWPJysrS0aNHFRISUuS6iqK4n6OkUv1myPym/cQTT8jlcmnjxo1q1qyZV7/7779fq1atKrWa8hMQEKC4uDjFxcVp//79Wr16tebNm6f33ntPiYmJWrNmjaT/+wx//PFHtW7dukjzKMpn7Z7Piy++qLFjx5ZoG841z/Hjx+v5558vdK1l6XzW/bymld+2nNf0s7KyFBcXp1q1amnTpk1WSMnviZyCTJ8+XadPn1Z8fLx11uKZZ57R0qVLizxNnBuPOV5AmzZt0okTJ6zuCQkJkqTo6GhJUtWqVdWoUSMdOHBAe/bssYaPj4+XdPaSRW4zZ87Ul19+qSFDhmjlypXy9fXV4MGD830EqiB5HYyOHz+uLVu2yN/f3zqA/V10dLRycnK0evVqq9/q1auVnZ1t1e90Ogv9l21huD/PtWvXWqc3pfw/x+JyX8opbht++eUXNW/e3Ppsc3JytHbt2vOu73zVqVNHQ4YM0VdffaWoqCitXbvWs25dffXVknTOg+35Ot/5FNSG/Fx55ZVyOp2l3raS5F733fuW3LKysjxtKcy6365du3zXwbymf/ToUaWkpOjaa6+1wsHJkyc9lz9yO9e288svvyg8PDzPSxplEZwrCwLCBXT8+HFNmzbNq9vGjRv1/vvvKzQ0VP379/d0v+uuu2SM0cSJE702mqNHj+qpp57yDOP23Xff6fHHH1dUVJRee+01tWrVSi+88IIOHDig4cOHyxhTpFr/9a9/WfcIxMXF6fjx44qNjZWfn1+B47tr+8c//qG0tDRP97S0NE2aNEmSdPfdd3uNU716de3fv79IdRbksssuU8+ePZWYmKjZs2d79Vu/fr0WLFigatWqeX3u56N69eqSpN9//71Y49evX1979uzxfPGTdPasUFxcnPXs+IVw5MgRbdu2zep+6tQpnTx5Uj4+Pp5LSCNHjlRYWJimTp2qDRs2WOPk5OTkeTApqg4dOqhTp076+OOP9fbbb+c5zLZt2zyXr4rShvzUqFFDQ4YM0caNG/XUU0/leRD79ddftW/fvmK0qHS4v2tl4cKF+u6777z6zZ49W/v27VOPHj0KdT/LyJEjJUmPP/6413X/5ORkTZ8+3Rq+Ro0aCgwM1A8//OB12SUzM1Pjxo3T0aNHrXGqVasmh8OR77ZTv359JScna+vWrV7d586dq6+++uqcbUDxcInhAurcubPeeustrV+/Xh07dtShQ4f04YcfKicnR6+//rrXKfeHH35Yy5cv19KlS9WmTRvdfPPNSktL0+LFi3X48GE98sgjnpuGUlJSFBsbK6fTqQ8++MBzI+SoUaP09ddfa8mSJXr++ef10EMPFbrWm266SR07dtRtt92m2rVra+3atVq7dq3q16+vZ5999pzjDx48WEuXLtWiRYvUokUL9evXz3P9cd++fbr99ts1ZMgQr3G6d++uDz74QLfccovatWsnX19fde7cuViXSNzmzJmjjh07auLEiVqxYoU6dOig/fv3a/HixXI6nXrnnXfyvHG0OLp3766ZM2fq3nvv1cCBA1W1alWFhYXpgQceKNT448eP16hRoxQdHa2BAwfK19dX33zzjXbu3Om50e5COnDggKKjo9WqVSu1bt1aderUUWpqqj7//HMlJSVp7Nixns+uevXqWrJkifr376+rr75a3bt3V4sWLeRwOLR//36tW7dOf/31l3VjWXEsWLBA3bp10913362XXnpJV111lcLCwvTHH39o69at2r59u9atW6caNWoUqQ0FeeWVV7Rnzx49+eST+te//qWYmBjVrFlTBw8e1K5du/T9999r4cKFni/8KWvBwcF6++23NWjQIHXp0kWDBg1S3bp19cMPP2jFihWqVauWXn/99UJNKzY2Vh9++KE+++wztWzZUn379lVmZqaWLFmiK664Qr/++qvX8E6nU2PHjvV8yVvfvn2VkZGh+Ph4JScn67rrrvOcvctd71VXXaU1a9ZoyJAhaty4sapUqaI+ffqodevWevDBB/XVV18pJiZGt912m0JDQ7Vx40atXbtWt956q5YsWVJinx1yKduHKCqH3I/w7Ny50/Tp08eEhYWZgIAAc+2115ovv/wyz/FOnz5tZsyYYVq0aGH8/f1NcHCw6dixo1mwYIHXcAMGDDCSzPPPP29NIyUlxTRo0MD4+vqa9evXn7NW96NW8fHx5p133vE8Vx4REWFGjBhhDh48aI2T3xclZWdnm1dffdW0b9/eBAQEmICAANOuXTvzyiuvmOzsbGv4P//808TGxpoaNWoYp9OZ5zPweSnoexCMMeaPP/4wo0aNMnXr1jW+vr6mevXqpm/fvmbDhg1Fnta5zJo1yzRt2tS4XC7PFz+55fc5/X3+bdq0MYGBgaZ69eqmX79+ZuvWrV7LJTcV8JhjXl8yVZTHyY4dO2amTp1qrrvuOhMZGWlcLpepVauW6dKli1mwYEGejw3u27fPjBkzxkRFRRk/Pz9TtWpV06RJEzN06FDzySefeA17rsdC8/seBGOMSU1NNTNmzDDt2rUzQUFBxt/f39SvX9/cfPPN5vXXXzcnT54sdhvyc+bMGfPyyy+ba665xoSEhBiXy2Xq1KljunXrZl544QWv71QoqHZjjKlXr57XumFMwcutoPWyoHlt2LDB9OvXz0RERBhfX19Tp04dM2rUKHPgwIFCt9uYs22fOnWqadCggXG5XKZevXrmscceM+np6Xmug5mZmWbWrFmmWbNmxt/f39SsWdMMHTrUJCYm5rvc9+zZY3r37m3Cw8ONw+Gw2rts2TJz1VVXmeDgYBMaGmp69uxpVq1add7bLPLnMKaI555RocXFxWnq1Kl53gwEAKg8uAcBAABYCAgAAMBCQAAAABbuQQAAABbOIAAAAAsBAQAAWAgIAADAQkAAAACW8/6q5WPHjuX5QzgV0SWXXOL5vfnKprK2vbK2W6LttL1yqUzt9vHxUbVq1c493PnOKCsry+t3yCsq90/SZmVlFfmHj8q7ytr2ytpuibZLtL0ytb2ytvtcuMQAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgMWnrAsASpMxRhkZGcUa1+FwKD09XWfOnJExpoQrKx3GGGVmZkqSfH195XA4ijWd8tJ2l8tV7DYCKBgBARVaRkaGJk6cWNZloJTMnDlTfn5+ZV0GUCFxiQEAAFg4g4BKY6wrTb5lXUQpyzTSS5mBkqSxvmnyrYBn3zMlvZQRWNZlABUeAQGVhq8kVwU8YObH11FB23vx3hIBVChcYgAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYPEp6wJyM8YoIyNDkuRyueRwOMq4IgAAzl95PL5dVGcQMjIyNHHiRE2cONHzQQIAUN6Vx+PbRRUQAADAxYGAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWHzKugAAACqTiRMnFmn4l156qZQqKRhnEAAAKGVFDQW5jR07tgQrKTwCAgAAsFxUlxiMMZ7XGRkZZViJzeFwKD09XWfOnPGqszIoz23PvR4ZI8lRdrWgZOReBUtjP1Ge1/fzVVnbXtrtPp+zB25jx4694JcaCh0QMjMzlZmZ6XnvcDgUEBBQosXknv7jjz9eotMGsiT5lXUROG9ZuV6zn0BlcqFDQqEDwieffKIlS5Z43jdo0EDPPfdcqRQFAADKVqEDQv/+/dW7d2/Pe4ej5M/V+vr6el7PmDFDLperxOdRXA6HQ7Vq1VJSUlKlOvUmle+2Z2RkeP7KvKiup6HYci/H0thPlOf1/XxV1raXZrtL4vJCWSn0PtPX19frAF4acocOl8slP7+L54Sww+GQv7+//Pz8KtWGI1WctpdCpkUZyL0cS2M/UVHW9+KorG0vzXa/9NJLJfYUwoW+B4GnGAAAKEUlcWAvi+9CICAAAAALAQEAgFI2c+bMYo9bVt+kyH1bAABcQDNnzryo7rHLD2cQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAAi09ZF5Cby+XSzJkzPa8BAKgIyuPx7aIKCA6HQ35+fmVdBgAAJao8Ht+4xAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwOJT1gUAF0qmJJmyrqJ0ZZq8X1ckmWVdAFBJEBBQabyUEVjWJVxQL2VWrvYCKFlcYgAAABbOIKBCc7lcmjlzZrHGdTgcqlWrlpKSkmRM+Thfb4xRZubZk/C+vr5yOBzFmk55abvL5SrrEoAKi4CACs3hcMjPz6/Y4/r7+8vPz++iPkj+nb+//3lPo7y2HUDJ4RIDAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsBAQAACAhYAAAAAsBAQAAGAhIAAAAAsBAQAAWAgIAADAQkAAAAAWAgIAALAQEAAAgIWAAAAALAQEAABgISAAAAALAQEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQAAAABYCAgAAsPic9wR8znsS5Upla29ulbXtlbXdEm2vrCpr2ytLuwvbTocxxpRyLQAAoJzhEkMhnT59Wo8++qhOnz5d1qVccJW17ZW13RJtp+2Vq+2Vtd3nQkAoJGOM9u3bp8p4wqWytr2ytlui7bS9crW9srb7XAgIAADAQkAAAAAWAkIh+fr66tZbb5Wvr29Zl3LBVda2V9Z2S7SdtleutlfWdp8LTzEAAAALZxAAAICFgAAAACwEBAAAYCEgAAAAS+X44unzsGPHDk2dOjXPfk8//bSioqJ0+PBhPfDAA1b/6dOnq3HjxqVdYqkaM2aMjhw54tVt8ODB6tevn+f9b7/9prlz5+rXX39VSEiIbrzxRvXt2/cCV1pyDh8+rI8++kjbt29XSkqKwsPD1alTJw0YMMDzHeYVeZlL0pdffqlly5YpJSVF9erV01133aWoqKiyLqvEfPLJJ9qwYYMOHDggl8ulxo0ba+jQoYqMjPQMExcXp507d3qN16NHD913330XutwStWjRIi1ZssSrW2RkpGbPni1JysjI0Lvvvqtvv/1WmZmZatOmje655x6FhYVd+GJLWF77M0m6/vrrdc8991TYZV5cBIRzaNKkid544w2vbh988IG2b9+uRo0aeXV/4oknVKdOHc/74ODgC1JjabvtttvUo0cPz3t/f3/P67S0NE2fPl2tWrXSvffeq99//12vvfaagoKCvMYpTw4ePChjjO677z7VqlVL+/fv1+uvv6709HQNGzbMa9iKuMy//fZbvfvuu7r33nt1+eWX64svvtCMGTM0e/ZshYaGlnV5JWLnzp264YYb1KhRI2VnZ2vhwoWaPn26nn/+ea/1u3v37rr99ts9710uV1mUW+Lq1KmjJ554wvPe6fy/k8nz58/Xpk2bNGHCBAUGBmru3LmaNWuWnnrqqbIotUQ988wzysnJ8bz//fffNX36dF1zzTWebhV1mRcHAeEcfHx8vJJzVlaWNm7cqBtvvFEOh8Nr2KpVq1aIlP13AQEB+bZr7dq1ysrK0ujRo+Xj46M6deooMTFRn3/+ebkNCG3btlXbtm0972vWrKmDBw9qxYoVVkCoiMv8888/V/fu3XXddddJku69915t2rRJ8fHxXmeOyrPHH3/c6/2YMWN0zz33aO/evWrevLmnu5+fX4VbvtLZQJBXu9LS0rRy5UqNGzdOLVu2lCSNHj1a48eP1+7du8v92bGQkBCv959++qlq1qxZKZZ5cRAQimjjxo06ceKEZ+eZ23PPPafMzEzVrl1bffv2VYcOHcqgwpL36aef6qOPPlJERIRiYmLUq1cvValSRZK0e/duNWvWzOvnQ9u0aaOlS5fq5MmTFeIvaunsjjOvtlS0ZZ6VlaW9e/d6BQGn06lWrVpp9+7dZVdYKUtLS5NknwFas2aN1qxZo7CwMLVv314DBw6Un59fWZRYopKSknT//ffL19dXjRs31uDBgxUREaG9e/cqOztbrVq18gx76aWXKiIiokIEhNyysrK0Zs0a9erVy+uPvYq6zIuDgFBE8fHxatu2rapXr+7p5u/vr2HDhqlJkyZyOBxav369Zs6cqYkTJ5b7A8ZNN92kBg0aKDg4WD///LMWLlyoY8eOafjw4ZKklJQU1ahRw2scd/pOSUmpEAEhKSlJy5cv15133unpVlGXeWpqqnJycqy/oMLCwnTw4MGyKaqU5eTkaN68eWrSpInq1q3r6R4TE6OIiAiFh4frt99+0/vvv6+DBw/q4YcfLsNqz9/ll1+u0aNHKzIyUseOHdOSJUv05JNPatasWUpJSZGPj4+CgoK8xgkNDVVKSkrZFFxKNmzYoFOnTqlr166ebhV1mRdXpQ0I77//vpYuXVrgMC+88IIuvfRSz/u//vpLW7Zs0fjx472GCwkJUe/evT3vo6KidOzYMX322WcX5cGiKG3P3a569erJx8dHb775pgYPHlzuvpa0OMs8OTlZM2bM0DXXXON1yaS8LXPkb+7cudq/f7+mTZvm1T338q5bt66qVaumadOmKSkpSbVq1brQZZaY6Ohoz+t69ep5AsO6desq1fV29x974eHhnm4VdZkXV6UNCLfccotXcsxLzZo1vd7Hx8eratWqhToAREVFaevWredTYqkpTtvdLr/8cmVnZ+vIkSOKjIxUWFiY9ZeF+/3Fdh2vqO1OTk7W1KlT1aRJk0LdxXwxL/PCCgkJkdPpzHOZXmzLsyTMnTtXmzZt0tSpU73OCubF/RRHRTtYBAUFKTIyUklJSWrdurWysrJ06tQpr7MIx48fr1DL/8iRI9q6des5zwxU1GVeWJU2IISEhFg3rBTEGKOEhAR17tzZ63p7fhITE1WtWrXzKbHUFLXtuSUmJsrhcHjGb9y4sRYuXKisrCzP57J161ZFRkZedJcXitJudzho0KCBRo8e7XWXd34u5mVeWD4+PmrYsKG2b9+uK6+8UtLZU/Dbt2/XjTfeWMbVlRxjjN5++21t2LBBcXFx1mWyvCQmJkpSuV/Gf5eenq6kpCR16tRJDRs2VJUqVbRt2zZdffXVks4+1XP06NEKdf9BfHy8QkND1a5duwKHq6jLvLAqbUAoqu3bt+vw4cPq3r271S8hIUE+Pj5q0KCBJGn9+vWKj4/XqFGjLnSZJWr37t3as2ePWrRooYCAAO3evVvz589Xp06dPAf/mJgYLV68WHPmzFHfvn21f/9+LV++3HOPQnmUnJysuLg4XXLJJRo2bJhSU1M9/dx/RVXUZS5JvXv31quvvqqGDRsqKipK//73v3XmzJlznn0pT+bOnau1a9fqkUceUUBAgOeMSWBgoFwul5KSkrR27Vq1a9dOwcHB+v333zV//nw1a9ZM9erVK9viz9O7776rDh06KCIiQseOHdOiRYvkdDoVExOjwMBAdevWTe+++66Cg4MVGBiot99+W40bN64wASEnJ0cJCQnq0qWL52ZrSRV6mRcXAaGQVq5cqSZNmnhdn87to48+0tGjR+V0OnXppZdq/PjxngReXvn4+Ojbb7/V4sWLlZmZqRo1aqhXr15e194DAwM1efJkzZ07V5MmTVLVqlU1cODAcvuIo3T2DEhSUpKSkpKsA/6iRYs8ryviMpeka6+9VqmpqVq0aJFSUlJUv359PfbYYxXqFPOKFSsknf0ypNxGjx6trl27ysfHR9u2bfOEo+rVq+uqq67SgAEDyqDakpWcnKwXX3xRJ06cUEhIiJo2baoZM2Z4zq4NHz5cDodDs2bNUlZWlueLkiqKbdu26ejRo9aTaBV5mRcXP/cMAAAs/BYDAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABYCAgAAMBCQABQKDt27NBtt92mHTt2lHUpAC4AAgIAALAQEAAAgIWAAAAALPxYE1COHDlyREuXLvX84Iyfn59atmypoUOHev1kcUJCgv73f/9X06ZN0/r167V69WplZGSodevWuv/++71+9jonJ0dLlizR119/rVOnTunyyy/X3XffrWeeeUbNmzfXmDFjCqxpz549WrRokXbv3q3s7Gw1atRIsbGxatq0qSTp8OHDeuCBB/IdP/cPYAG4eBAQgHLk119/1c8//6yOHTsqPDxcR44c0YoVKzR16lQ9//zz8vPz8xr+nXfeUVBQkAYNGqTDhw/r3//+t+bOnavx48d7hlmwYIE+++wztW/fXm3atNFvv/2mGTNmKCMj45z1bN++XU8//bQaNmyoQYMGyeFwKCEhQdOmTdO0adMUFRWlkJAQKyBkZ2dr/vz58vFhFwRcrNg6gXKkXbt21k9Kt2/fXpMnT9b69evVuXNnr37BwcGaPHmyHA6HJMkYo+XLlystLU2BgYFKSUnRF198oSuuuEITJ070jLd48WItXry4wFqMMXrzzTfVokULPfbYY5559OzZUxMmTNAHH3ygyZMny9/f36rrrbfeUnp6uiZPnlzszwJA6eIeBKAccblcntdZWVk6ceKEatWqpaCgIO3du9cavkePHp4DtyQ1a9ZMOTk5OnLkiKSzZwCys7N1ww03eI130003nbOWxMREHTp0SDExMTpx4oRSU1OVmpqq9PR0tWzZUrt27VJOTo413qpVq7RixQoNHTpULVu2LHTbAVxYnEEAypGMjAx98sknSkhIUHJysowxnn5paWnW8BEREV7vg4KCJEmnTp2SJE9QqFWrltdwwcHBnmHzc+jQIUnSq6++mu8waWlpCg4O9rxPTEzUm2++qY4dO6p3794FTh9A2SIgAOXI22+/rfj4ePXq1UuNGzdWYGCgJOnFF1/0CgtuTmfeJwnzGrao3NMYOnSo6tevn+cw/v7+ntcnT57UrFmzVLt2bY0aNeq85w+gdBEQgHLku+++U5cuXTRs2DBPt4yMDM8ZgaK65JJLJElJSUleT0GcOHHinNOsWbOmJCkwMFCtW7cucNicnBy9/PLLOnXqlJ544gnrZkoAFx/uQQDKkbzOCHz55Zd5XusvjJYtW6pKlSpasWKFNc1zadiwoWrWrKlly5YpPT3d6p+amup5vWTJEm3ZskXjxo3zCiIALl6cQQDKkXbt2mn16tUKDAzUZZddpt27d2vbtm2qWrVqsaYXFhamm266SZ9//rmee+45tW3bVr/99ps2b96sqlWret3g+HdOp1OjRo3S008/rQkTJqhr164KDw9XcnKyduzYoYCAAE2aNEm///67PvroIzVr1kzHjx/X6tWrvabz9yccAFwcCAhAOTJy5Eg5nU6tWbNGmZmZatKkiZ544gnNmDGj2NMcOnSo/Pz89PXXX2vbtm1q3LixJk+erCeffFK+vr4FjtuiRQvNmDFDS5Ys0VdffaX09HSFhYUpKipKPXv2lHT2coUxRjt37tTOnTutaRAQgIuTw5TE3UoAKpRTp05p5MiRuuOOOzRgwICyLgdAGeAeBKCSy+sbE7/44gtJUvPmzS90OQAuElxiACq5b7/9VgkJCYqOjpa/v79++uknffPNN2rTpo3n9xQAVD4EBKCSq1u3rqpUqaLPPvtMaWlpCgsL080336w77rijrEsDUIa4BwEAAFi4BwEAAFgICAAAwEJAAAAAFgICAACwEBAAAICFgAAAACwEBAAAYCEgAAAACwEBAABY/j/EUyoFRzvQIQAAAABJRU5ErkJggg==\n"},"metadata":{}}],"execution_count":34},{"cell_type":"code","source":"train_series['anglez'] = pd.to_numeric(train_series['anglez'], errors='coerce').astype('float32')\n\n# Drop NaNs before plotting\nsns.histplot(train_series['anglez'].dropna(), bins=50,kde = True )\n\n# Plot labels\nplt.title('distribution of train_series anglez data')\nplt.xlabel('anglez')\nplt.ylabel('Frequency')\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:05:18.67241Z","iopub.execute_input":"2025-05-04T05:05:18.6731Z","iopub.status.idle":"2025-05-04T05:06:04.496349Z","shell.execute_reply.started":"2025-05-04T05:05:18.673073Z","shell.execute_reply":"2025-05-04T05:06:04.495381Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":35},{"cell_type":"code","source":"sns.boxplot(x = train_series['enmo'])\nplt.title('box plot for train series enmo data')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:06:08.540412Z","iopub.execute_input":"2025-05-04T05:06:08.540772Z","iopub.status.idle":"2025-05-04T05:06:13.132523Z","shell.execute_reply.started":"2025-05-04T05:06:08.540745Z","shell.execute_reply":"2025-05-04T05:06:13.131675Z"}},"outputs":[{"execution_count":36,"output_type":"execute_result","data":{"text/plain":"Text(0.5, 1.0, 'box plot for train series enmo data')"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":36},{"cell_type":"code","source":"train_series['enmo'] = pd.to_numeric(train_series['enmo'], errors='coerce').astype('float32')\n\n# Drop NaNs before plotting\nsns.histplot(train_series['enmo'].dropna(), bins=50,kde = True )\n\n# Plot labels\nplt.title('distribution of train_series enmo data')\nplt.xlabel('anglez')\nplt.ylabel('Frequency')\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:06:17.394156Z","iopub.execute_input":"2025-05-04T05:06:17.394469Z","iopub.status.idle":"2025-05-04T05:07:00.734714Z","shell.execute_reply.started":"2025-05-04T05:06:17.394446Z","shell.execute_reply":"2025-05-04T05:07:00.733673Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":37},{"cell_type":"code","source":"train_events","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:07:06.547544Z","iopub.execute_input":"2025-05-04T05:07:06.548265Z","iopub.status.idle":"2025-05-04T05:07:06.562488Z","shell.execute_reply.started":"2025-05-04T05:07:06.548241Z","shell.execute_reply":"2025-05-04T05:07:06.561532Z"}},"outputs":[{"execution_count":38,"output_type":"execute_result","data":{"text/plain":" timestamp series_id night event step year \\\n0 2018-08-15 02:26:00+00:00 038441c925bb 1 onset 4992.0 2018 \n1 2018-08-15 10:41:00+00:00 038441c925bb 1 wakeup 10932.0 2018 \n2 2018-08-15 23:37:00+00:00 038441c925bb 2 onset 20244.0 2018 \n3 2018-08-16 09:41:00+00:00 038441c925bb 2 wakeup 27492.0 2018 \n4 2018-08-17 03:03:00+00:00 038441c925bb 3 onset 39996.0 2018 \n... ... ... ... ... ... ... \n9580 2017-09-05 13:26:00+00:00 fe90110788d2 32 wakeup 547152.0 2017 \n9581 2017-09-06 02:30:00+00:00 fe90110788d2 33 onset 556560.0 2017 \n9582 2017-09-06 08:07:00+00:00 fe90110788d2 33 wakeup 560604.0 2017 \n9583 2017-09-07 03:35:00+00:00 fe90110788d2 34 onset 574620.0 2017 \n9584 2017-09-07 13:17:00+00:00 fe90110788d2 34 wakeup 581604.0 2017 \n\n month day hour \n0 8 15 2 \n1 8 15 10 \n2 8 15 23 \n3 8 16 9 \n4 8 17 3 \n... ... ... ... \n9580 9 5 13 \n9581 9 6 2 \n9582 9 6 8 \n9583 9 7 3 \n9584 9 7 13 \n\n[9585 rows x 9 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
timestampseries_idnighteventstepyearmonthdayhour
02018-08-15 02:26:00+00:00038441c925bb1onset4992.020188152
12018-08-15 10:41:00+00:00038441c925bb1wakeup10932.0201881510
22018-08-15 23:37:00+00:00038441c925bb2onset20244.0201881523
32018-08-16 09:41:00+00:00038441c925bb2wakeup27492.020188169
42018-08-17 03:03:00+00:00038441c925bb3onset39996.020188173
..............................
95802017-09-05 13:26:00+00:00fe90110788d232wakeup547152.020179513
95812017-09-06 02:30:00+00:00fe90110788d233onset556560.02017962
95822017-09-06 08:07:00+00:00fe90110788d233wakeup560604.02017968
95832017-09-07 03:35:00+00:00fe90110788d234onset574620.02017973
95842017-09-07 13:17:00+00:00fe90110788d234wakeup581604.020179713
\n

9585 rows × 9 columns

\n
"},"metadata":{}}],"execution_count":38},{"cell_type":"code","source":"# Create 'missing_event' column: True if 'step' is missing, else False\ntrain_events['missing_event'] = train_events['step'].isnull()\n\n# Group by 'series_id' and aggregate\naggregated = train_events.groupby('series_id').agg(\n tot_events=('event', 'count'),\n tot_nights=('night', 'last'),\n tot_missing_events=('missing_event', 'sum')\n).reset_index()\n\n# Compute 'tot_missing_nights'\naggregated['tot_missing_nights'] = (aggregated['tot_missing_events'] // 2).astype('int32')\n\n# Compute 'tot_recorded_events' and 'tot_recorded_nights'\naggregated['tot_recorded_events'] = aggregated['tot_events'] - aggregated['tot_missing_events']\naggregated['tot_recorded_nights'] = aggregated['tot_nights'] - aggregated['tot_missing_nights']\n\n# Plot: Nights of sleep per user\nfig, ax = plt.subplots(figsize=(10, 6))\naggregated['tot_recorded_nights'].hist(bins=50, ax=ax, color='skyblue')\nax.set_title('Total Recorded Nights of Sleep per User')\nax.set_ylabel('Nights of Sleep')\nax.set_xlabel('Number of Users')\n\n# Describe the 'tot_recorded_nights' column\naggregated[['tot_recorded_nights']].describe().T\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:07:12.115199Z","iopub.execute_input":"2025-05-04T05:07:12.116135Z","iopub.status.idle":"2025-05-04T05:07:12.461109Z","shell.execute_reply.started":"2025-05-04T05:07:12.116096Z","shell.execute_reply":"2025-05-04T05:07:12.460247Z"}},"outputs":[{"execution_count":39,"output_type":"execute_result","data":{"text/plain":" count mean std min 25% 50% 75% max\ntot_recorded_nights 269.0 21.375465 8.35077 1.0 17.0 22.0 25.0 43.0","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
countmeanstdmin25%50%75%max
tot_recorded_nights269.021.3754658.350771.017.022.025.043.0
\n
"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":39},{"cell_type":"code","source":"# Plot missing nights of sleep per user\nfig, ax = plt.subplots(figsize=(10, 6))\naggregated['tot_missing_nights'].hist(bins=50, ax=ax, color='maroon')\nax.set_title('Total Missing Nights of Sleep per User')\nax.set_ylabel('Missing Nights of Sleep')\nax.set_xlabel('Number of Users')\n\n# Describe\naggregated[['tot_missing_nights']].describe().T\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:07:21.184962Z","iopub.execute_input":"2025-05-04T05:07:21.185251Z","iopub.status.idle":"2025-05-04T05:07:21.45313Z","shell.execute_reply.started":"2025-05-04T05:07:21.185232Z","shell.execute_reply":"2025-05-04T05:07:21.452293Z"}},"outputs":[{"execution_count":40,"output_type":"execute_result","data":{"text/plain":" count mean std min 25% 50% 75% max\ntot_missing_nights 269.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
countmeanstdmin25%50%75%max
tot_missing_nights269.00.00.00.00.00.00.00.0
\n
"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":40},{"cell_type":"markdown","source":"A single sleep period must be at least 30 minutes in length\n\n\n\nWindowing the training data\n\n\nAs the target is to detect an event, \n\n\nSo, extracting timesteps 30 min before and after the events. ","metadata":{}},{"cell_type":"code","source":"\ndef window(df, win_size):\n ind=df.index[df['event'].isna()==False]\n c=0\n df['window']=np.nan\n for i in tqdm(ind):\n a=i-win_size\n b=i+win_size\n df['window'].loc[a:i]=int(c)\n c=c+1\n df['window'].loc[i:b]=int(c)\n c=c+1\n df['window'].dropna(inplace=True)\n return df[df['window'].isna()==False]\n\n ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:07:34.676342Z","iopub.execute_input":"2025-05-04T05:07:34.67668Z","iopub.status.idle":"2025-05-04T05:07:34.682836Z","shell.execute_reply.started":"2025-05-04T05:07:34.676648Z","shell.execute_reply":"2025-05-04T05:07:34.681845Z"}},"outputs":[],"execution_count":41},{"cell_type":"markdown","source":"Removing the steps where change in enmo and anglez is insignificant (device is supposed not to be worn).","metadata":{}},{"cell_type":"code","source":"def inactive_periods(df):\n print(\"shape before application: \",df.shape)\n df['diff_anglez']=df['anglez'].diff()\n df=df[(df['enmo']!=0.0) | (df['diff_anglez']!=0.0)]\n print(\"shape after application: \",df.shape)\n df.drop('diff_anglez', inplace=True, axis=1)\n print(\"shape after completion: \",df.shape)\n print(\"removed \")\n return df\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:07:39.311606Z","iopub.execute_input":"2025-05-04T05:07:39.312382Z","iopub.status.idle":"2025-05-04T05:07:39.317349Z","shell.execute_reply.started":"2025-05-04T05:07:39.312356Z","shell.execute_reply":"2025-05-04T05:07:39.31635Z"}},"outputs":[],"execution_count":42},{"cell_type":"markdown","source":"CLUSTERING THE ENMO AND ANGELZ","metadata":{}},{"cell_type":"code","source":"def clustering(df):\n from sklearn.cluster import KMeans\n from sklearn.preprocessing import StandardScaler \n X=df[['anglez','enmo']]\n#Scalling the data\n scaler=StandardScaler()\n X_scaled=scaler.fit_transform(X)\n#perform clustering\n model=KMeans(n_clusters=4,algorithm=\"elkan\" )\n model.fit(X_scaled)\n return model.labels_\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:07:44.497914Z","iopub.execute_input":"2025-05-04T05:07:44.498773Z","iopub.status.idle":"2025-05-04T05:07:44.503484Z","shell.execute_reply.started":"2025-05-04T05:07:44.498747Z","shell.execute_reply":"2025-05-04T05:07:44.502474Z"}},"outputs":[],"execution_count":43},{"cell_type":"code","source":"def rollingstd(series_df):\n# Creating columns with nans\n series_df['sd_enmo_1']=np.nan # 1 min rolling std: enmo\n series_df['sd_anglez_1']=np.nan # 1 min rolling std: anglez\n series_df['m_enmo_2']=np.nan # 2 min rolling mean: enmo\n series_df['m_anglez_2']=np.nan # 2 min rolling std: anglez \n print('anglez rolling std 12')\n series_df['sd_anglez_1'] = (series_df.groupby('series_id')['anglez']\n .rolling(12)\n .std()\n .reset_index(level=0, drop=True))\n print('anglez rolling std 2')\n series_df['sd_anglez_1'][series_df['sd_anglez_1'].isna()==True] = (series_df.groupby('series_id')['anglez']\n .rolling(2)\n .std()\n .reset_index(level=0, drop=True))\n print('enmo rolling std 12')\n series_df['sd_enmo_1'] = (series_df.groupby('series_id')['enmo']\n .rolling(12)\n .std()\n .reset_index(level=0, drop=True))\n print('enmo rolling mean 24')\n series_df['m_enmo_2'] = (series_df.groupby('series_id')['enmo']\n .rolling(24)\n .mean()\n .reset_index(level=0, drop=True))\n print('anglez rolling mean 24')\n series_df['m_anglez_2'] = (series_df.groupby('series_id')['anglez']\n .rolling(24)\n .mean()\n .reset_index(level=0, drop=True))\n print('enmo rolling std 2')\n print('Nans in sd_emno_1: ',series_df['sd_enmo_1'].isnull().sum())\n series_df['sd_enmo_1'][series_df['sd_enmo_1'].isna()==True] = (series_df.groupby('series_id')['enmo']\n .rolling(2)\n .std()\n .reset_index(level=0, drop=True))\n print('enmo rolling mean 2')\n series_df['m_enmo_2'][series_df['m_enmo_2'].isna()==True] = (series_df.groupby('series_id')['enmo']\n .rolling(2)\n .mean()\n .reset_index(level=0, drop=True))\n print('anglez rolling mean 2')\n series_df['m_anglez_2'][series_df['m_anglez_2'].isna()==True] = (series_df.groupby('series_id')['anglez']\n .rolling(2)\n .mean()\n .reset_index(level=0, drop=True))\n#Series wise rolling std and mean\n# filling rest of nans\n print('Nans in sd_emno_1: ',series_df['sd_enmo_1'].isnull().sum())\n series_df['sd_enmo_1'].fillna(0.0, inplace=True)\n series_df['sd_anglez_1'].fillna(0.0, inplace=True)\n series_df['m_enmo_2'].fillna(0.0, inplace=True)\n series_df['m_anglez_2'].fillna(0.0, inplace=True)\n print('Nans after removal: ',series_df['sd_enmo_1'].isnull().sum())\n\n return(series_df)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:07:55.07012Z","iopub.execute_input":"2025-05-04T05:07:55.071Z","iopub.status.idle":"2025-05-04T05:07:55.082245Z","shell.execute_reply.started":"2025-05-04T05:07:55.070971Z","shell.execute_reply":"2025-05-04T05:07:55.081308Z"}},"outputs":[],"execution_count":44},{"cell_type":"code","source":"def scale(X):\n from sklearn import preprocessing\n scaler = preprocessing.StandardScaler().fit(X)\n return (scaler.transform(X))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:08:04.171598Z","iopub.execute_input":"2025-05-04T05:08:04.171955Z","iopub.status.idle":"2025-05-04T05:08:04.176846Z","shell.execute_reply.started":"2025-05-04T05:08:04.171931Z","shell.execute_reply":"2025-05-04T05:08:04.175969Z"}},"outputs":[],"execution_count":46},{"cell_type":"code","source":"df_series = train_series\ndf_events = train_events","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:08:08.684459Z","iopub.execute_input":"2025-05-04T05:08:08.684814Z","iopub.status.idle":"2025-05-04T05:08:08.688977Z","shell.execute_reply.started":"2025-05-04T05:08:08.684789Z","shell.execute_reply":"2025-05-04T05:08:08.687961Z"}},"outputs":[],"execution_count":47},{"cell_type":"code","source":"print(type(df_series)) # should output: \nprint(type(df_events))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:08:12.556461Z","iopub.execute_input":"2025-05-04T05:08:12.556801Z","iopub.status.idle":"2025-05-04T05:08:12.561229Z","shell.execute_reply.started":"2025-05-04T05:08:12.556778Z","shell.execute_reply":"2025-05-04T05:08:12.560186Z"}},"outputs":[{"name":"stdout","text":"\n\n","output_type":"stream"}],"execution_count":48},{"cell_type":"code","source":"\n# Merging the datasets\nprint('Merging the training datasets...')\nevents = df_events[['series_id', 'step', 'event']]\nseries_df = pd.merge(df_series, events, on=[\"step\", \"series_id\"], how='left')\nseries_df['sleep']=np.nan\nseries_df.loc[series_df[\"event\"]==\"onset\", \"sleep\"] = 1\nseries_df.loc[series_df[\"event\"]==\"wakeup\", \"sleep\"] = 0\nseries_df['sleep'].fillna(method='ffill', inplace=True)\nseries_df['sleep'].fillna(value=0, inplace=True)\nprint('Datasets Merged...')\nprint('______________________________________')\n\n# Removing the periods of inactivity\nprint('Removing the periods of Inactivity...')\nseries_df=inactive_periods(series_df)\nprint('______________________________________')\n\n# Forming Windows\nwin_size=720 #60mins\nprint('Creating Windows each size: ',win_size)\nseries_df=window(series_df,win_size)\nprint('Windows formed...')\nprint('______________________________________')\n\n# Adding the columns of Standard Deviation (1 min)\nprint('Adding columns to account for deviation in enmo and anglez 1 min rolling...')\nseries_df=rollingstd(series_df)\nseries_df['sd_anglez_1']=pd.to_numeric(series_df['sd_anglez_1'])\nseries_df['sd_enmo_1']=pd.to_numeric(series_df['sd_enmo_1'])\nseries_df['m_anglez_2']=pd.to_numeric(series_df['m_anglez_2'])\nseries_df['m_enmo_2']=pd.to_numeric(series_df['m_enmo_2'])\nprint('Std columns added...')\nprint('______________________________________')\n\n# Clustering the Data\nprint('Clustering the data based on enmo and anglez...')\nseries_df['cluster']=(clustering(series_df)+1)/4\nprint('Added clusters...')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:08:17.038949Z","iopub.execute_input":"2025-05-04T05:08:17.039996Z","iopub.status.idle":"2025-05-04T05:08:31.358285Z","shell.execute_reply.started":"2025-05-04T05:08:17.03996Z","shell.execute_reply":"2025-05-04T05:08:31.35736Z"}},"outputs":[{"name":"stdout","text":"Merging the training datasets...\nDatasets Merged...\n______________________________________\nRemoving the periods of Inactivity...\nshape before application: (10000000, 7)\nshape after application: (8643738, 8)\nshape after completion: (8643738, 7)\nremoved \n______________________________________\nCreating Windows each size: 720\n","output_type":"stream"},{"name":"stderr","text":"100%|██████████| 509/509 [00:00<00:00, 3052.90it/s]\n","output_type":"stream"},{"name":"stdout","text":"Windows formed...\n______________________________________\nAdding columns to account for deviation in enmo and anglez 1 min rolling...\nanglez rolling std 12\nanglez rolling std 2\nenmo rolling std 12\nenmo rolling mean 24\nanglez rolling mean 24\nenmo rolling std 2\nNans in sd_emno_1: 231\nenmo rolling mean 2\nanglez rolling mean 2\nNans in sd_emno_1: 21\nNans after removal: 0\nStd columns added...\n______________________________________\nClustering the data based on enmo and anglez...\nAdded clusters...\n","output_type":"stream"}],"execution_count":49},{"cell_type":"code","source":"series_df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:08:40.327794Z","iopub.execute_input":"2025-05-04T05:08:40.328643Z","iopub.status.idle":"2025-05-04T05:08:40.345871Z","shell.execute_reply.started":"2025-05-04T05:08:40.328593Z","shell.execute_reply":"2025-05-04T05:08:40.344985Z"}},"outputs":[{"execution_count":50,"output_type":"execute_result","data":{"text/plain":" timestamp series_id step anglez enmo \\\n4272 2018-08-14 21:26:00-04:00 038441c925bb 4272.0 -73.312500 0.042603 \n4273 2018-08-14 21:26:05-04:00 038441c925bb 4273.0 -1.091797 0.180908 \n4274 2018-08-14 21:26:10-04:00 038441c925bb 4274.0 -19.390625 0.198364 \n4275 2018-08-14 21:26:15-04:00 038441c925bb 4275.0 0.344482 0.094116 \n4276 2018-08-14 21:26:20-04:00 038441c925bb 4276.0 -57.687500 0.163086 \n\n event sleep window sd_enmo_1 sd_anglez_1 m_enmo_2 m_anglez_2 \\\n4272 NaN 0.0 0.0 0.000000 0.000000 0.000000 0.000000 \n4273 NaN 0.0 0.0 0.097797 51.067749 0.111755 -37.202148 \n4274 NaN 0.0 0.0 0.012343 12.939225 0.189636 -10.241211 \n4275 NaN 0.0 0.0 0.073715 13.954828 0.146240 -9.523071 \n4276 NaN 0.0 0.0 0.048769 41.034808 0.128601 -28.671509 \n\n cluster \n4272 0.50 \n4273 0.75 \n4274 0.75 \n4275 0.75 \n4276 0.75 ","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
timestampseries_idstepanglezenmoeventsleepwindowsd_enmo_1sd_anglez_1m_enmo_2m_anglez_2cluster
42722018-08-14 21:26:00-04:00038441c925bb4272.0-73.3125000.042603NaN0.00.00.0000000.0000000.0000000.0000000.50
42732018-08-14 21:26:05-04:00038441c925bb4273.0-1.0917970.180908NaN0.00.00.09779751.0677490.111755-37.2021480.75
42742018-08-14 21:26:10-04:00038441c925bb4274.0-19.3906250.198364NaN0.00.00.01234312.9392250.189636-10.2412110.75
42752018-08-14 21:26:15-04:00038441c925bb4275.00.3444820.094116NaN0.00.00.07371513.9548280.146240-9.5230710.75
42762018-08-14 21:26:20-04:00038441c925bb4276.0-57.6875000.163086NaN0.00.00.04876941.0348080.128601-28.6715090.75
\n
"},"metadata":{}}],"execution_count":50},{"cell_type":"code","source":"series_df['cluster'].unique()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:08:45.189262Z","iopub.execute_input":"2025-05-04T05:08:45.189598Z","iopub.status.idle":"2025-05-04T05:08:45.203747Z","shell.execute_reply.started":"2025-05-04T05:08:45.189571Z","shell.execute_reply":"2025-05-04T05:08:45.202682Z"}},"outputs":[{"execution_count":51,"output_type":"execute_result","data":{"text/plain":"array([0.5 , 0.75, 0.25, 1. ])"},"metadata":{}}],"execution_count":51},{"cell_type":"code","source":"figure= px.imshow(series_df[['sd_anglez_1','sd_enmo_1','m_anglez_2','m_enmo_2','anglez','enmo','cluster','sleep']].corr(),text_auto=True, width=1200, height=1200)\nfigure.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:08:48.858232Z","iopub.execute_input":"2025-05-04T05:08:48.858537Z","iopub.status.idle":"2025-05-04T05:08:49.088493Z","shell.execute_reply.started":"2025-05-04T05:08:48.858515Z","shell.execute_reply":"2025-05-04T05:08:49.087579Z"}},"outputs":[{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":52},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX=series_df[['sd_anglez_1','sd_enmo_1','anglez','m_anglez_2','m_enmo_2','enmo','cluster']]\ny=series_df[['sleep']]\nX_scaled=scale(X)\nX_train, X_test, y_train, y_test =train_test_split(X_scaled,y,test_size=0.2, random_state=42)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:08:55.057116Z","iopub.execute_input":"2025-05-04T05:08:55.057495Z","iopub.status.idle":"2025-05-04T05:08:55.285166Z","shell.execute_reply.started":"2025-05-04T05:08:55.057471Z","shell.execute_reply":"2025-05-04T05:08:55.284381Z"}},"outputs":[],"execution_count":53},{"cell_type":"code","source":"X_train.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:08:59.220978Z","iopub.execute_input":"2025-05-04T05:08:59.221646Z","iopub.status.idle":"2025-05-04T05:08:59.226809Z","shell.execute_reply.started":"2025-05-04T05:08:59.22159Z","shell.execute_reply":"2025-05-04T05:08:59.225951Z"}},"outputs":[{"execution_count":54,"output_type":"execute_result","data":{"text/plain":"(492567, 7)"},"metadata":{}}],"execution_count":54},{"cell_type":"code","source":"print(X_train.shape, y_train.shape)\nprint(X_test.shape, y_test.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:09:04.085816Z","iopub.execute_input":"2025-05-04T05:09:04.086641Z","iopub.status.idle":"2025-05-04T05:09:04.090901Z","shell.execute_reply.started":"2025-05-04T05:09:04.086586Z","shell.execute_reply":"2025-05-04T05:09:04.090082Z"}},"outputs":[{"name":"stdout","text":"(492567, 7) (492567, 1)\n(123142, 7) (123142, 1)\n","output_type":"stream"}],"execution_count":55},{"cell_type":"code","source":"X.to_csv('X_data.csv')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:09:07.604152Z","iopub.execute_input":"2025-05-04T05:09:07.604705Z","iopub.status.idle":"2025-05-04T05:09:13.766329Z","shell.execute_reply.started":"2025-05-04T05:09:07.60467Z","shell.execute_reply":"2025-05-04T05:09:13.765402Z"}},"outputs":[],"execution_count":56},{"cell_type":"code","source":"y.to_csv('y_data.csv')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:09:18.513761Z","iopub.execute_input":"2025-05-04T05:09:18.514079Z","iopub.status.idle":"2025-05-04T05:09:19.182466Z","shell.execute_reply.started":"2025-05-04T05:09:18.514057Z","shell.execute_reply":"2025-05-04T05:09:19.181706Z"}},"outputs":[],"execution_count":57},{"cell_type":"code","source":"series_df.to_csv('final_series_df.csv')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:09:23.273282Z","iopub.execute_input":"2025-05-04T05:09:23.273856Z","iopub.status.idle":"2025-05-04T05:09:34.048505Z","shell.execute_reply.started":"2025-05-04T05:09:23.273828Z","shell.execute_reply":"2025-05-04T05:09:34.047736Z"}},"outputs":[],"execution_count":58},{"cell_type":"code","source":"y_test[['sleep']].value_counts()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:09:39.065433Z","iopub.execute_input":"2025-05-04T05:09:39.066333Z","iopub.status.idle":"2025-05-04T05:09:39.078509Z","shell.execute_reply.started":"2025-05-04T05:09:39.066305Z","shell.execute_reply":"2025-05-04T05:09:39.077691Z"}},"outputs":[{"execution_count":59,"output_type":"execute_result","data":{"text/plain":"sleep\n0.0 70073\n1.0 53069\nName: count, dtype: int64"},"metadata":{}}],"execution_count":59},{"cell_type":"markdown","source":"MACHINE LEARNING:","metadata":{}},{"cell_type":"code","source":"def evaluate(y_test,ypred):\n from sklearn.metrics import precision_score\n from sklearn.metrics import recall_score\n from sklearn.metrics import f1_score\n from sklearn.metrics import accuracy_score\n from sklearn.metrics import confusion_matrix\n print(\"Accuracy: \",accuracy_score(y_test,y_pred)) \n print(\"Precision Score : \", precision_score(y_test,y_pred)) #precision measures the proportion of true positive predictions among all positive instances. how many of survived predicted actually survived, doesn't verifies 0's 70 survived as preicted whereas actually 92 survived so 70/92 will be the precision. if we predicted 70 survived, so presion will tell how many of those 70 predicted survived matches the actual row by row data. It checkes all positives and verifies if the answer is true for each row?\n print(\"Recall Score: \", recall_score(y_test,y_pred, average='macro')) #Recall measures the proportion of true positive predictions among all actual positive instalnces. If we predicted 100 survived correctly whereas actually 100 survived out of which 67 predicted correctly so recall will be 0.67\n print(\"F1 Score: \",f1_score(y_test,y_pred)) #mean of recall and precision\n cm = confusion_matrix(y_test, y_pred)\n figure= px.imshow(cm,text_auto=True, width=1200, height=1200)\n figure.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:09:47.831605Z","iopub.execute_input":"2025-05-04T05:09:47.831964Z","iopub.status.idle":"2025-05-04T05:09:47.838429Z","shell.execute_reply.started":"2025-05-04T05:09:47.831941Z","shell.execute_reply":"2025-05-04T05:09:47.837409Z"}},"outputs":[],"execution_count":61},{"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\nrf =RandomForestClassifier(n_jobs=-1,verbose=1) \nprint ('Training the model')\nrf.fit(X_train,y_train)\nprint ('Saving the model')\nfrom joblib import dump, load\ndump(rf, 'rf_model.joblib')\ny_pred=rf.predict(X_test)\nevaluate(y_test,y_pred)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:09:53.38489Z","iopub.execute_input":"2025-05-04T05:09:53.385201Z","iopub.status.idle":"2025-05-04T05:11:13.608819Z","shell.execute_reply.started":"2025-05-04T05:09:53.385179Z","shell.execute_reply":"2025-05-04T05:11:13.607992Z"}},"outputs":[{"name":"stdout","text":"Training the model\n","output_type":"stream"},{"name":"stderr","text":"[Parallel(n_jobs=-1)]: Using backend ThreadingBackend with 4 concurrent workers.\n[Parallel(n_jobs=-1)]: Done 42 tasks | elapsed: 34.5s\n[Parallel(n_jobs=-1)]: Done 100 out of 100 | elapsed: 1.3min finished\n","output_type":"stream"},{"name":"stdout","text":"Saving the model\n","output_type":"stream"},{"name":"stderr","text":"[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n[Parallel(n_jobs=4)]: Done 42 tasks | elapsed: 0.6s\n[Parallel(n_jobs=4)]: Done 100 out of 100 | elapsed: 1.4s finished\n","output_type":"stream"},{"name":"stdout","text":"Accuracy: 0.9384369264751263\nPrecision Score : 0.9594376212023271\nRecall Score: 0.9331649714451314\nF1 Score: 0.9260916615483608\n","output_type":"stream"},{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":62},{"cell_type":"code","source":"def evaluate_train_data(y_train, train_pred):\n from sklearn.metrics import precision_score\n from sklearn.metrics import recall_score\n from sklearn.metrics import f1_score\n from sklearn.metrics import accuracy_score\n from sklearn.metrics import confusion_matrix\n print(\"Accuracy: \",accuracy_score(y_train, train_pred)) \n print(\"Precision Score : \", precision_score(y_train, train_pred)) #precision measures the proportion of true positive predictions among all positive instances. how many of survived predicted actually survived, doesn't verifies 0's 70 survived as preicted whereas actually 92 survived so 70/92 will be the precision. if we predicted 70 survived, so presion will tell how many of those 70 predicted survived matches the actual row by row data. It checkes all positives and verifies if the answer is true for each row?\n print(\"Recall Score: \", recall_score(y_train, train_pred, average='macro')) #Recall measures the proportion of true positive predictions among all actual positive instalnces. If we predicted 100 survived correctly whereas actually 100 survived out of which 67 predicted correctly so recall will be 0.67\n print(\"F1 Score: \",f1_score(y_train, train_pred)) #mean of recall and precision\n cm = confusion_matrix(y_train, train_pred)\n figure= px.imshow(cm,text_auto=True, width=1200, height=1200)\n figure.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:11:25.562657Z","iopub.execute_input":"2025-05-04T05:11:25.563507Z","iopub.status.idle":"2025-05-04T05:11:25.569548Z","shell.execute_reply.started":"2025-05-04T05:11:25.56348Z","shell.execute_reply":"2025-05-04T05:11:25.568537Z"}},"outputs":[],"execution_count":63},{"cell_type":"code","source":"train_pred = rf.predict(X_train)\ntest_pred = rf.predict(X_test)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:11:30.01338Z","iopub.execute_input":"2025-05-04T05:11:30.014226Z","iopub.status.idle":"2025-05-04T05:11:37.208918Z","shell.execute_reply.started":"2025-05-04T05:11:30.014199Z","shell.execute_reply":"2025-05-04T05:11:37.208056Z"}},"outputs":[{"name":"stderr","text":"[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n[Parallel(n_jobs=4)]: Done 42 tasks | elapsed: 2.5s\n[Parallel(n_jobs=4)]: Done 100 out of 100 | elapsed: 5.7s finished\n[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n[Parallel(n_jobs=4)]: Done 42 tasks | elapsed: 0.6s\n[Parallel(n_jobs=4)]: Done 100 out of 100 | elapsed: 1.4s finished\n","output_type":"stream"}],"execution_count":64},{"cell_type":"code","source":"evaluate_train_data(y_train, train_pred)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:11:44.786079Z","iopub.execute_input":"2025-05-04T05:11:44.786368Z","iopub.status.idle":"2025-05-04T05:11:46.533483Z","shell.execute_reply.started":"2025-05-04T05:11:44.786351Z","shell.execute_reply":"2025-05-04T05:11:46.532673Z"}},"outputs":[{"name":"stdout","text":"Accuracy: 0.999809163017417\nPrecision Score : 0.9995806950097995\nRecall Score: 0.9998295124224126\nF1 Score: 0.9997785254507243\n","output_type":"stream"},{"output_type":"display_data","data":{"text/html":"\n\n\n
\n
\n\n"},"metadata":{}}],"execution_count":65},{"cell_type":"code","source":"from sklearn.metrics import accuracy_score","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:11:52.31986Z","iopub.execute_input":"2025-05-04T05:11:52.320153Z","iopub.status.idle":"2025-05-04T05:11:52.324158Z","shell.execute_reply.started":"2025-05-04T05:11:52.320135Z","shell.execute_reply":"2025-05-04T05:11:52.323218Z"}},"outputs":[],"execution_count":66},{"cell_type":"code","source":"def check_model_fit(train_acc, test_acc):\n print(f\"\\n Train Accuracy: {train_acc:.4f}\")\n print(f\" Test Accuracy: {test_acc:.4f}\")\n if train_acc > 0.95 and (train_acc - test_acc) > 0.1:\n print(\" Model is likely OVERFITTING.\")\n elif train_acc < 0.70 and test_acc < 0.70:\n print(\" Model is likely UNDERFITTING.\")\n else:\n print(\" Model is likely a GOOD FIT.\")\ncheck_model_fit(\n train_acc=accuracy_score(y_train, train_pred),\n test_acc=accuracy_score(y_test, test_pred)\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:11:59.083892Z","iopub.execute_input":"2025-05-04T05:11:59.084235Z","iopub.status.idle":"2025-05-04T05:11:59.20652Z","shell.execute_reply.started":"2025-05-04T05:11:59.08421Z","shell.execute_reply":"2025-05-04T05:11:59.205818Z"}},"outputs":[{"name":"stdout","text":"\n Train Accuracy: 0.9998\n Test Accuracy: 0.9384\n Model is likely a GOOD FIT.\n","output_type":"stream"}],"execution_count":67},{"cell_type":"code","source":"print('Removing the periods of Inactivity...')\ntest_series = inactive_periods(test_series)\nprint('______________________________________')\n\nprint('Adding Features...')\ntest_series = rollingstd(test_series)\ntest_series['sd_anglez_1'] = pd.to_numeric(test_series['sd_anglez_1'])\ntest_series['sd_enmo_1'] = pd.to_numeric(test_series['sd_enmo_1'])\ntest_series['m_anglez_2'] = pd.to_numeric(test_series['m_anglez_2'])\ntest_series['m_enmo_2'] = pd.to_numeric(test_series['m_enmo_2'])\nprint('Features added...')\nprint('______________________________________')\n\nprint('Clustering the data based on enmo and anglez...')\ntest_series['cluster'] = (clustering(test_series) + 1) / 4\nprint('Added clusters...')\n\nX_test = test_series[['sd_anglez_1', 'sd_enmo_1', 'anglez', 'm_anglez_2', 'm_enmo_2', 'enmo', 'cluster']]\ny_pred = rf.predict(scale(X_test))\nX_test = []\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:12:03.722564Z","iopub.execute_input":"2025-05-04T05:12:03.722931Z","iopub.status.idle":"2025-05-04T05:12:03.833502Z","shell.execute_reply.started":"2025-05-04T05:12:03.722908Z","shell.execute_reply":"2025-05-04T05:12:03.832649Z"}},"outputs":[{"name":"stdout","text":"Removing the periods of Inactivity...\nshape before application: (450, 4)\nshape after application: (322, 5)\nshape after completion: (322, 4)\nremoved \n______________________________________\nAdding Features...\nanglez rolling std 12\nanglez rolling std 2\nenmo rolling std 12\nenmo rolling mean 24\nanglez rolling mean 24\nenmo rolling std 2\nNans in sd_emno_1: 33\nenmo rolling mean 2\nanglez rolling mean 2\nNans in sd_emno_1: 3\nNans after removal: 0\nFeatures added...\n______________________________________\nClustering the data based on enmo and anglez...\nAdded clusters...\n","output_type":"stream"},{"name":"stderr","text":"[Parallel(n_jobs=4)]: Using backend ThreadingBackend with 4 concurrent workers.\n[Parallel(n_jobs=4)]: Done 42 tasks | elapsed: 0.0s\n[Parallel(n_jobs=4)]: Done 100 out of 100 | elapsed: 0.0s finished\n","output_type":"stream"}],"execution_count":68},{"cell_type":"code","source":"test_series.reset_index(inplace = True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:12:10.947792Z","iopub.execute_input":"2025-05-04T05:12:10.948082Z","iopub.status.idle":"2025-05-04T05:12:10.95347Z","shell.execute_reply.started":"2025-05-04T05:12:10.948063Z","shell.execute_reply":"2025-05-04T05:12:10.952494Z"}},"outputs":[],"execution_count":69},{"cell_type":"code","source":"result_df=test_series[['series_id', 'step','timestamp']]\nresult_df['sleep']=y_pred\nresult_df['timestamp']=result_df[['timestamp']].progress_apply(lambda x: pd.to_datetime(x,utc=True))\ndf=result_df.copy()\ndf.index=df['timestamp']\nmean = df.groupby([df['series_id'], df.index.floor('5min')])['sleep'].mean() # Calculating the mean of predictions over an interval of 5 mins (Due to the nature of Testing Data Series). \nmean=mean.reset_index()\nmean['timestamp']=mean['timestamp']- pd.to_timedelta('5m') # Since the event is recorded at the end of the interval so subtracting 5 mins (Due to the nature of Testing Data Series) so it records the event at the start of the interval\nsummary=pd.merge(result_df,mean,on=[\"timestamp\",\"series_id\"],how='left') # merging the means into the original data based on timestamps and series ID.\nsummary=summary[summary['sleep_y'].isna()==False] # removing the Nan's of prediction mean. That'll ensure that we have a row every 5 mins (Due to the nature of Testing Data Series).\n# Creating Event Column\nsummary['event']=np.nan\nsummary.loc[summary[\"sleep_y\"]==1, \"event\"] = 'onset' # the mean prediction will be 1 if predicted onset for 30 mins consecutive\nsummary.loc[summary[\"sleep_y\"]==0, \"event\"] = 'wakeup' # the mean prediction will be 0 if predicted wakeup for 30 mins consecutive. Any duration in between will be considered disturbance as will be less tan 30 mins.\nsummary=summary[summary['event'].isna()==False] # Removing the rows with no event recorded. \nsubmission=summary[['series_id','step','event','sleep_y']] # Creating Submission\nsubmission = submission.rename(columns={'sleep_y': 'score'}) # Renaming a column\n\nsubmission.to_csv('submission.csv') # Saving the csv file","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:12:16.970144Z","iopub.execute_input":"2025-05-04T05:12:16.970784Z","iopub.status.idle":"2025-05-04T05:12:17.003076Z","shell.execute_reply.started":"2025-05-04T05:12:16.970759Z","shell.execute_reply":"2025-05-04T05:12:17.002171Z"}},"outputs":[{"name":"stderr","text":"100%|██████████| 1/1 [00:00<00:00, 584.33it/s]\n","output_type":"stream"}],"execution_count":70},{"cell_type":"code","source":"submission","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-05-04T05:12:21.290138Z","iopub.execute_input":"2025-05-04T05:12:21.290445Z","iopub.status.idle":"2025-05-04T05:12:21.300433Z","shell.execute_reply.started":"2025-05-04T05:12:21.290424Z","shell.execute_reply":"2025-05-04T05:12:21.299512Z"}},"outputs":[{"execution_count":71,"output_type":"execute_result","data":{"text/plain":" series_id step event score\n0 038441c925bb 0.0 onset 1.0\n60 038441c925bb 60.0 onset 1.0\n172 0402a003dae9 0.0 wakeup 0.0\n232 0402a003dae9 60.0 wakeup 0.0","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
series_idstepeventscore
0038441c925bb0.0onset1.0
60038441c925bb60.0onset1.0
1720402a003dae90.0wakeup0.0
2320402a003dae960.0wakeup0.0
\n
"},"metadata":{}}],"execution_count":71}]}