{"cells":[{"metadata":{},"cell_type":"markdown","source":"This is a part of a series of copy or reproduction of below kernel  \nRef: https://www.kaggle.com/vettejeep/masters-final-project-model-lb-1-392  \n"},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import os\nimport time\nimport warnings\nimport traceback\nimport numpy as np\nimport pandas as pd\nfrom scipy import stats\nimport scipy.signal as sg\nimport multiprocessing as mp\nfrom scipy.signal import hann\nfrom scipy.signal import hilbert\nfrom scipy.signal import convolve\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.preprocessing import StandardScaler\n\nimport xgboost as xgb\nimport lightgbm as lgb\nfrom sklearn.model_selection import KFold\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.metrics import mean_absolute_error\n\nfrom tqdm import tqdm\nwarnings.filterwarnings(\"ignore\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"OUTPUT_DIR = ''\nDATA_DIR = '../input/'\n\nSIG_LEN = 150000\nNUM_SEG_PER_PROC = 4000\nNUM_THREADS = 6\n\nNY_FREQ_IDX = 75000  # the test signals are 150k samples long, Nyquist is thus 75k.\nCUTOFF = 18000\nMAX_FREQ_IDX = 20000\nFREQ_STEP = 2500","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv(os.path.join('../input/train.csv'), dtype={'acoustic_data': np.int16, 'time_to_failure': np.float32})\nmax_start_index = len(df.index) - SIG_LEN\nslice_len = int(max_start_index / 6)\n\n# for i in range(NUM_THREADS):\nfor i in range(3):\n    print('working', i)\n    df0 = df.iloc[slice_len * i: (slice_len * (i + 1)) + SIG_LEN]\n    df0.to_csv('raw_data_%d.csv' % i, index=False)\n    del df0\n\ndel df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Verify\ntemp = pd.read_csv('raw_data_0.csv', dtype={'acoustic_data': np.int16, 'time_to_failure': np.float32})\nprint(temp.shape)\ndisplay(temp.head(5))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Verify\ntemp = pd.read_csv('raw_data_1.csv', dtype={'acoustic_data': np.int16, 'time_to_failure': np.float32})\nprint(temp.shape)\ndisplay(temp.head(5))","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}