{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# fastai 0.7.2\n!pip install git+https://github.com/fastai/fastai@e85667cfae2e6873b1bb026195b5d09a74dfcff9\n%load_ext autoreload\n%autoreload 2\n\n%matplotlib inline","execution_count":1,"outputs":[{"output_type":"stream","text":"Collecting git+https://github.com/fastai/fastai@e85667cfae2e6873b1bb026195b5d09a74dfcff9\n  Cloning https://github.com/fastai/fastai (to revision e85667cfae2e6873b1bb026195b5d09a74dfcff9) to /tmp/pip-req-build-m3h1can_\nRequirement already satisfied: bcolz in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (1.2.1)\nRequirement already satisfied: bleach in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (2.1.3)\nRequirement already satisfied: certifi in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (2019.3.9)\nRequirement already satisfied: cycler in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.10.0)\nRequirement already satisfied: decorator in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (4.3.0)\nRequirement already satisfied: entrypoints in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.2.3)\nRequirement already satisfied: feather-format in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.4.0)\nRequirement already satisfied: graphviz in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.8.4)\nRequirement already satisfied: html5lib in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (1.0.1)\nRequirement already satisfied: ipykernel in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (4.8.2)\nRequirement already satisfied: ipython in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (6.4.0)\nRequirement already satisfied: ipython-genutils in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.2.0)\nRequirement already satisfied: ipywidgets in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (7.2.1)\nRequirement already satisfied: isoweek in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (1.3.3)\nRequirement already satisfied: jedi in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.12.0)\nRequirement already satisfied: Jinja2 in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (2.10)\nRequirement already satisfied: jsonschema in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (2.6.0)\nRequirement already satisfied: jupyter in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (1.0.0)\nRequirement already satisfied: MarkupSafe in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (1.0)\nRequirement already satisfied: matplotlib in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (3.0.3)\nRequirement already satisfied: numpy in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (1.16.2)\nRequirement already satisfied: opencv-python in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (4.0.0.21)\nRequirement already satisfied: pandas in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.23.4)\nRequirement already satisfied: pandas_summary in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.0.6)\nRequirement already satisfied: pickleshare in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.7.4)\nRequirement already satisfied: Pillow in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (5.1.0)\nRequirement already satisfied: plotnine in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.4.0)\nRequirement already satisfied: ptyprocess in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.5.2)\nRequirement already satisfied: Pygments in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (2.2.0)\nRequirement already satisfied: pyparsing in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (2.2.0)\nRequirement already satisfied: python-dateutil in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (2.6.0)\nRequirement already satisfied: pytz in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (2018.4)\nRequirement already satisfied: PyYAML in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (3.12)\nRequirement already satisfied: pyzmq in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (17.0.0)\nRequirement already satisfied: scipy in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (1.1.0)\nRequirement already satisfied: seaborn in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.9.0)\nRequirement already satisfied: simplegeneric in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.8.1)\nRequirement already satisfied: sklearn_pandas in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (1.8.0)\nRequirement already satisfied: spacy in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (2.0.18)\nRequirement already satisfied: testpath in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.3.1)\nCollecting torch<0.4 (from fastai==0.7.0)\n\u001b[?25l  Downloading https://files.pythonhosted.org/packages/5b/a5/e8b50b55b1abac9f1e3346c4242f1e42a82d368a8442cbd50c532922f6c4/torch-0.3.1-cp36-cp36m-manylinux1_x86_64.whl (496.4MB)\n\u001b[K    100% |████████████████████████████████| 496.4MB 71kB/s  eta 0:00:01    75% |████████████████████████        | 373.0MB 75.1MB/s eta 0:00:02\n\u001b[?25hRequirement already satisfied: torchtext in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.3.1)\nRequirement already satisfied: torchvision in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.2.2)\nRequirement already satisfied: tornado in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (5.0.2)\nRequirement already satisfied: tqdm in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (4.31.1)\nRequirement already satisfied: traitlets in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (4.3.2)\nRequirement already satisfied: wcwidth in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.1.7)\nRequirement already satisfied: webencodings in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (0.5.1)\nRequirement already satisfied: widgetsnbextension in /opt/conda/lib/python3.6/site-packages (from fastai==0.7.0) (3.2.1)\nRequirement already satisfied: six in /opt/conda/lib/python3.6/site-packages (from bleach->fastai==0.7.0) (1.12.0)\nRequirement already satisfied: pyarrow>=0.4.0 in /opt/conda/lib/python3.6/site-packages (from feather-format->fastai==0.7.0) (0.10.0)\nRequirement already satisfied: jupyter_client in /opt/conda/lib/python3.6/site-packages (from ipykernel->fastai==0.7.0) (5.2.3)\nRequirement already satisfied: prompt-toolkit<2.0.0,>=1.0.15 in /opt/conda/lib/python3.6/site-packages (from ipython->fastai==0.7.0) (1.0.15)\nRequirement already satisfied: pexpect; sys_platform != \"win32\" in /opt/conda/lib/python3.6/site-packages (from ipython->fastai==0.7.0) (4.5.0)\nRequirement already satisfied: backcall in /opt/conda/lib/python3.6/site-packages (from ipython->fastai==0.7.0) (0.1.0)\nRequirement already satisfied: setuptools>=18.5 in /opt/conda/lib/python3.6/site-packages (from ipython->fastai==0.7.0) (39.1.0)\nRequirement already satisfied: nbformat>=4.2.0 in /opt/conda/lib/python3.6/site-packages (from ipywidgets->fastai==0.7.0) (4.4.0)\nRequirement already satisfied: parso>=0.2.0 in /opt/conda/lib/python3.6/site-packages (from jedi->fastai==0.7.0) (0.2.0)\nRequirement already satisfied: notebook in /opt/conda/lib/python3.6/site-packages (from jupyter->fastai==0.7.0) (5.5.0)\nRequirement already satisfied: qtconsole in /opt/conda/lib/python3.6/site-packages (from jupyter->fastai==0.7.0) (4.3.1)\nRequirement already satisfied: jupyter-console in /opt/conda/lib/python3.6/site-packages (from jupyter->fastai==0.7.0) (5.2.0)\nRequirement already satisfied: nbconvert in /opt/conda/lib/python3.6/site-packages (from jupyter->fastai==0.7.0) (5.3.1)\nRequirement already satisfied: kiwisolver>=1.0.1 in /opt/conda/lib/python3.6/site-packages (from matplotlib->fastai==0.7.0) (1.0.1)\nRequirement already satisfied: patsy>=0.4.1 in /opt/conda/lib/python3.6/site-packages (from plotnine->fastai==0.7.0) (0.5.0)\nRequirement already satisfied: descartes>=1.1.0 in /opt/conda/lib/python3.6/site-packages (from plotnine->fastai==0.7.0) (1.1.0)\nRequirement already satisfied: statsmodels>=0.8.0 in /opt/conda/lib/python3.6/site-packages (from plotnine->fastai==0.7.0) (0.9.0)\nRequirement already satisfied: geopandas>=0.3.0 in /opt/conda/lib/python3.6/site-packages (from plotnine->fastai==0.7.0) (0.4.1)\nRequirement already satisfied: mizani>=0.4.5 in /opt/conda/lib/python3.6/site-packages (from plotnine->fastai==0.7.0) (0.5.3)\nRequirement already satisfied: scikit-learn>=0.15.0 in /opt/conda/lib/python3.6/site-packages (from sklearn_pandas->fastai==0.7.0) (0.20.3)\nRequirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /opt/conda/lib/python3.6/site-packages (from spacy->fastai==0.7.0) (1.0.0)\nRequirement already satisfied: cymem<2.1.0,>=2.0.2 in /opt/conda/lib/python3.6/site-packages (from spacy->fastai==0.7.0) (2.0.2)\nRequirement already satisfied: preshed<2.1.0,>=2.0.1 in /opt/conda/lib/python3.6/site-packages (from spacy->fastai==0.7.0) (2.0.1)\nRequirement already satisfied: thinc<6.13.0,>=6.12.1 in /opt/conda/lib/python3.6/site-packages (from spacy->fastai==0.7.0) (6.12.1)\n","name":"stdout"},{"output_type":"stream","text":"Requirement already satisfied: plac<1.0.0,>=0.9.6 in /opt/conda/lib/python3.6/site-packages (from spacy->fastai==0.7.0) (0.9.6)\nRequirement already satisfied: ujson>=1.35 in /opt/conda/lib/python3.6/site-packages (from spacy->fastai==0.7.0) (1.35)\nRequirement already satisfied: dill<0.3,>=0.2 in /opt/conda/lib/python3.6/site-packages (from spacy->fastai==0.7.0) (0.2.9)\nRequirement already satisfied: regex==2018.01.10 in /opt/conda/lib/python3.6/site-packages (from spacy->fastai==0.7.0) (2018.1.10)\nRequirement already satisfied: requests<3.0.0,>=2.13.0 in /opt/conda/lib/python3.6/site-packages (from spacy->fastai==0.7.0) (2.21.0)\nRequirement already satisfied: jupyter_core in /opt/conda/lib/python3.6/site-packages (from jupyter_client->ipykernel->fastai==0.7.0) (4.4.0)\nRequirement already satisfied: terminado>=0.8.1 in /opt/conda/lib/python3.6/site-packages (from notebook->jupyter->fastai==0.7.0) (0.8.1)\nRequirement already satisfied: Send2Trash in /opt/conda/lib/python3.6/site-packages (from notebook->jupyter->fastai==0.7.0) (1.5.0)\nRequirement already satisfied: mistune>=0.7.4 in /opt/conda/lib/python3.6/site-packages (from nbconvert->jupyter->fastai==0.7.0) (0.8.3)\nRequirement already satisfied: pandocfilters>=1.4.1 in /opt/conda/lib/python3.6/site-packages (from nbconvert->jupyter->fastai==0.7.0) (1.4.2)\nRequirement already satisfied: pyproj in /opt/conda/lib/python3.6/site-packages (from geopandas>=0.3.0->plotnine->fastai==0.7.0) (2.1.1)\nRequirement already satisfied: fiona in /opt/conda/lib/python3.6/site-packages (from geopandas>=0.3.0->plotnine->fastai==0.7.0) (1.8.6)\nRequirement already satisfied: shapely in /opt/conda/lib/python3.6/site-packages (from geopandas>=0.3.0->plotnine->fastai==0.7.0) (1.6.4.post2)\nRequirement already satisfied: palettable in /opt/conda/lib/python3.6/site-packages (from mizani>=0.4.5->plotnine->fastai==0.7.0) (3.1.1)\nRequirement already satisfied: msgpack<0.6.0,>=0.5.6 in /opt/conda/lib/python3.6/site-packages (from thinc<6.13.0,>=6.12.1->spacy->fastai==0.7.0) (0.5.6)\nRequirement already satisfied: msgpack-numpy<0.4.4 in /opt/conda/lib/python3.6/site-packages (from thinc<6.13.0,>=6.12.1->spacy->fastai==0.7.0) (0.4.3.2)\nRequirement already satisfied: cytoolz<0.10,>=0.9.0 in /opt/conda/lib/python3.6/site-packages (from thinc<6.13.0,>=6.12.1->spacy->fastai==0.7.0) (0.9.0.1)\nRequirement already satisfied: wrapt<1.11.0,>=1.10.0 in /opt/conda/lib/python3.6/site-packages (from thinc<6.13.0,>=6.12.1->spacy->fastai==0.7.0) (1.10.11)\nRequirement already satisfied: chardet<3.1.0,>=3.0.2 in /opt/conda/lib/python3.6/site-packages (from requests<3.0.0,>=2.13.0->spacy->fastai==0.7.0) (3.0.4)\nRequirement already satisfied: idna<2.9,>=2.5 in /opt/conda/lib/python3.6/site-packages (from requests<3.0.0,>=2.13.0->spacy->fastai==0.7.0) (2.6)\nRequirement already satisfied: urllib3<1.25,>=1.21.1 in /opt/conda/lib/python3.6/site-packages (from requests<3.0.0,>=2.13.0->spacy->fastai==0.7.0) (1.22)\nRequirement already satisfied: click-plugins>=1.0 in /opt/conda/lib/python3.6/site-packages (from fiona->geopandas>=0.3.0->plotnine->fastai==0.7.0) (1.0.4)\nRequirement already satisfied: click<8,>=4.0 in /opt/conda/lib/python3.6/site-packages (from fiona->geopandas>=0.3.0->plotnine->fastai==0.7.0) (7.0)\nRequirement already satisfied: munch in /opt/conda/lib/python3.6/site-packages (from fiona->geopandas>=0.3.0->plotnine->fastai==0.7.0) (2.3.2)\nRequirement already satisfied: attrs>=17 in /opt/conda/lib/python3.6/site-packages (from fiona->geopandas>=0.3.0->plotnine->fastai==0.7.0) (18.1.0)\nRequirement already satisfied: cligj>=0.5 in /opt/conda/lib/python3.6/site-packages (from fiona->geopandas>=0.3.0->plotnine->fastai==0.7.0) (0.5.0)\nRequirement already satisfied: toolz>=0.8.0 in /opt/conda/lib/python3.6/site-packages (from cytoolz<0.10,>=0.9.0->thinc<6.13.0,>=6.12.1->spacy->fastai==0.7.0) (0.9.0)\nBuilding wheels for collected packages: fastai\n  Building wheel for fastai (setup.py) ... \u001b[?25ldone\n\u001b[?25h  Stored in directory: /tmp/pip-ephem-wheel-cache-__ylatn2/wheels/45/27/d3/efc22827a5cfab07661c0a112b73d41001257f998e970dcd9b\nSuccessfully built fastai\nInstalling collected packages: torch, fastai\n  Found existing installation: torch 1.0.1.post2\n    Uninstalling torch-1.0.1.post2:\n      Successfully uninstalled torch-1.0.1.post2\n  Found existing installation: fastai 1.0.50.post1\n    Uninstalling fastai-1.0.50.post1:\n      Successfully uninstalled fastai-1.0.50.post1\nSuccessfully installed fastai-0.7.0 torch-0.3.1\n","name":"stdout"}]},{"metadata":{"trusted":true,"_uuid":"938cac652a99033363106b1e10465055a0cb78fc"},"cell_type":"code","source":"from fastai.imports import *\nfrom fastai.structured import *\n\nfrom sklearn.ensemble import RandomForestRegressor, RandomForestClassifier\nfrom IPython.display import display\n\nfrom sklearn import metrics\n\nfrom tqdm import tqdm","execution_count":2,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ba5aa640872366ed356368db4f173ee34d87c411"},"cell_type":"code","source":"def display_all(df):\n    with pd.option_context(\"display.max_rows\", 1000, \"display.max_columns\", 1000, \"display.precision\", 15): \n        display(df)","execution_count":3,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"path = Path(\"../input\")","execution_count":4,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(path/'train.csv', dtype={'acoustic_data': np.int16, 'time_to_failure': np.float32})","execution_count":5,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data from air\nFrom https://www.kaggle.com/gpreda/lanl-earthquake-eda-and-prediction"},{"metadata":{"trusted":true},"cell_type":"code","source":"rows = 150000\nsegments = int(np.floor(train_df.shape[0] / rows))","execution_count":6,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_X = pd.DataFrame(index=range(segments), dtype=np.float64)\ntrain_y = pd.DataFrame(index=range(segments), dtype=np.float64, columns=['time_to_failure'])","execution_count":7,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import warnings\nfrom scipy import stats\nfrom scipy.signal import hann\nimport matplotlib.pyplot as plt\nfrom scipy.signal import hilbert\nfrom scipy.signal import convolve\nfrom sklearn.svm import NuSVR, SVR\nfrom sklearn.kernel_ridge import KernelRidge\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.metrics import mean_absolute_error\nfrom sklearn.preprocessing import StandardScaler\nfrom tqdm import tqdm\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.model_selection import KFold,StratifiedKFold, RepeatedKFold\nwarnings.filterwarnings(\"ignore\")","execution_count":8,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def add_trend_feature(arr, abs_values=False):\n    idx = np.array(range(len(arr)))\n    if abs_values:\n        arr = np.abs(arr)\n    lr = LinearRegression()\n    lr.fit(idx.reshape(-1, 1), arr)\n    return lr.coef_[0]\n\ndef classic_sta_lta(x, length_sta, length_lta):\n    sta = np.cumsum(x ** 2)\n    # Convert to float\n    sta = np.require(sta, dtype=np.float)\n    # Copy for LTA\n    lta = sta.copy()\n    # Compute the STA and the LTA\n    sta[length_sta:] = sta[length_sta:] - sta[:-length_sta]\n    sta /= length_sta\n    lta[length_lta:] = lta[length_lta:] - lta[:-length_lta]\n    lta /= length_lta\n    # Pad zeros\n    sta[:length_lta - 1] = 0\n    # Avoid division by zero by setting zero values to tiny float\n    dtiny = np.finfo(0.0).tiny\n    idx = lta < dtiny\n    lta[idx] = dtiny\n    return sta / lta","execution_count":9,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def create_features(seg_id, seg, X):\n    xc = pd.Series(seg['acoustic_data'].values)\n    zc = np.fft.fft(xc)\n    \n    X.loc[seg_id, 'mean'] = xc.mean()\n    X.loc[seg_id, 'std'] = xc.std()\n    X.loc[seg_id, 'max'] = xc.max()\n    X.loc[seg_id, 'min'] = xc.min()\n    \n    #FFT transform values\n    realFFT = np.real(zc)\n    imagFFT = np.imag(zc)\n    X.loc[seg_id, 'Rmean'] = realFFT.mean()\n    X.loc[seg_id, 'Rstd'] = realFFT.std()\n    X.loc[seg_id, 'Rmax'] = realFFT.max()\n    X.loc[seg_id, 'Rmin'] = realFFT.min()\n    X.loc[seg_id, 'Imean'] = imagFFT.mean()\n    X.loc[seg_id, 'Istd'] = imagFFT.std()\n    X.loc[seg_id, 'Imax'] = imagFFT.max()\n    X.loc[seg_id, 'Imin'] = imagFFT.min()\n    X.loc[seg_id, 'Rmean_last_5000'] = realFFT[-5000:].mean()\n    X.loc[seg_id, 'Rstd__last_5000'] = realFFT[-5000:].std()\n    X.loc[seg_id, 'Rmax_last_5000'] = realFFT[-5000:].max()\n    X.loc[seg_id, 'Rmin_last_5000'] = realFFT[-5000:].min()\n    X.loc[seg_id, 'Rmean_last_15000'] = realFFT[-15000:].mean()\n    X.loc[seg_id, 'Rstd_last_15000'] = realFFT[-15000:].std()\n    X.loc[seg_id, 'Rmax_last_15000'] = realFFT[-15000:].max()\n    X.loc[seg_id, 'Rmin_last_15000'] = realFFT[-15000:].min()\n    \n    X.loc[seg_id, 'mean_change_abs'] = np.mean(np.diff(xc))\n    X.loc[seg_id, 'mean_change_rate'] = np.mean(np.nonzero((np.diff(xc) / xc[:-1]))[0])\n    X.loc[seg_id, 'abs_max'] = np.abs(xc).max()\n    \n    X.loc[seg_id, 'std_first_50000'] = xc[:50000].std()\n    X.loc[seg_id, 'std_last_50000'] = xc[-50000:].std()\n    X.loc[seg_id, 'std_first_10000'] = xc[:10000].std()\n    X.loc[seg_id, 'std_last_10000'] = xc[-10000:].std()\n    \n    X.loc[seg_id, 'avg_first_50000'] = xc[:50000].mean()\n    X.loc[seg_id, 'avg_last_50000'] = xc[-50000:].mean()\n    X.loc[seg_id, 'avg_first_10000'] = xc[:10000].mean()\n    X.loc[seg_id, 'avg_last_10000'] = xc[-10000:].mean()\n    \n    X.loc[seg_id, 'min_first_50000'] = xc[:50000].min()\n    X.loc[seg_id, 'min_last_50000'] = xc[-50000:].min()\n    X.loc[seg_id, 'min_first_10000'] = xc[:10000].min()\n    X.loc[seg_id, 'min_last_10000'] = xc[-10000:].min()\n    \n    X.loc[seg_id, 'max_first_50000'] = xc[:50000].max()\n    X.loc[seg_id, 'max_last_50000'] = xc[-50000:].max()\n    X.loc[seg_id, 'max_first_10000'] = xc[:10000].max()\n    X.loc[seg_id, 'max_last_10000'] = xc[-10000:].max()\n    \n    X.loc[seg_id, 'max_to_min'] = xc.max() / np.abs(xc.min())\n    X.loc[seg_id, 'max_to_min_diff'] = xc.max() - np.abs(xc.min())\n    X.loc[seg_id, 'sum'] = xc.sum()\n    \n    X.loc[seg_id, 'mean_change_rate_first_50000'] = np.mean(np.nonzero((np.diff(xc[:50000]) / xc[:50000][:-1]))[0])\n    X.loc[seg_id, 'mean_change_rate_last_50000'] = np.mean(np.nonzero((np.diff(xc[-50000:]) / xc[-50000:][:-1]))[0])\n    X.loc[seg_id, 'mean_change_rate_first_10000'] = np.mean(np.nonzero((np.diff(xc[:10000]) / xc[:10000][:-1]))[0])\n    X.loc[seg_id, 'mean_change_rate_last_10000'] = np.mean(np.nonzero((np.diff(xc[-10000:]) / xc[-10000:][:-1]))[0])\n    \n    X.loc[seg_id, 'q95'] = np.quantile(xc, 0.95)\n    X.loc[seg_id, 'q99'] = np.quantile(xc, 0.99)\n    X.loc[seg_id, 'q05'] = np.quantile(xc, 0.05)\n    X.loc[seg_id, 'q01'] = np.quantile(xc, 0.01)\n    \n    X.loc[seg_id, 'abs_q95'] = np.quantile(np.abs(xc), 0.95)\n    X.loc[seg_id, 'abs_q99'] = np.quantile(np.abs(xc), 0.99)\n    X.loc[seg_id, 'abs_q05'] = np.quantile(np.abs(xc), 0.05)\n    \n    X.loc[seg_id, 'trend'] = add_trend_feature(xc)\n    X.loc[seg_id, 'abs_trend'] = add_trend_feature(xc, abs_values=True)\n    X.loc[seg_id, 'abs_mean'] = np.abs(xc).mean()\n    X.loc[seg_id, 'abs_std'] = np.abs(xc).std()\n    \n    X.loc[seg_id, 'mad'] = xc.mad()\n    X.loc[seg_id, 'kurt'] = xc.kurtosis()\n    X.loc[seg_id, 'skew'] = xc.skew()\n    \n    X.loc[seg_id, 'Hilbert_mean'] = np.abs(hilbert(xc)).mean()\n    X.loc[seg_id, 'Hann_window_mean'] = (convolve(xc, hann(150), mode='same') / sum(hann(150))).mean()\n    X.loc[seg_id, 'classic_sta_lta1_mean'] = classic_sta_lta(xc, 500, 10000).mean()\n    X.loc[seg_id, 'classic_sta_lta2_mean'] = classic_sta_lta(xc, 5000, 100000).mean()\n    X.loc[seg_id, 'classic_sta_lta3_mean'] = classic_sta_lta(xc, 3333, 6666).mean()\n    X.loc[seg_id, 'classic_sta_lta4_mean'] = classic_sta_lta(xc, 10000, 25000).mean()\n    X.loc[seg_id, 'Moving_average_700_mean'] = xc.rolling(window=700).mean().mean(skipna=True)\n    X.loc[seg_id, 'Moving_average_1500_mean'] = xc.rolling(window=1500).mean().mean(skipna=True)\n    X.loc[seg_id, 'Moving_average_3000_mean'] = xc.rolling(window=3000).mean().mean(skipna=True)\n    X.loc[seg_id, 'Moving_average_6000_mean'] = xc.rolling(window=6000).mean().mean(skipna=True)\n    ewma = pd.Series.ewm\n    X.loc[seg_id, 'exp_Moving_average_300_mean'] = (ewma(xc, span=300).mean()).mean(skipna=True)\n    X.loc[seg_id, 'exp_Moving_average_3000_mean'] = ewma(xc, span=3000).mean().mean(skipna=True)\n    X.loc[seg_id, 'exp_Moving_average_30000_mean'] = ewma(xc, span=6000).mean().mean(skipna=True)\n    no_of_std = 2\n    X.loc[seg_id, 'MA_700MA_std_mean'] = xc.rolling(window=700).std().mean()\n    X.loc[seg_id,'MA_700MA_BB_high_mean'] = (X.loc[seg_id, 'Moving_average_700_mean'] + no_of_std * X.loc[seg_id, 'MA_700MA_std_mean']).mean()\n    X.loc[seg_id,'MA_700MA_BB_low_mean'] = (X.loc[seg_id, 'Moving_average_700_mean'] - no_of_std * X.loc[seg_id, 'MA_700MA_std_mean']).mean()\n    X.loc[seg_id, 'MA_400MA_std_mean'] = xc.rolling(window=400).std().mean()\n    X.loc[seg_id,'MA_400MA_BB_high_mean'] = (X.loc[seg_id, 'Moving_average_700_mean'] + no_of_std * X.loc[seg_id, 'MA_400MA_std_mean']).mean()\n    X.loc[seg_id,'MA_400MA_BB_low_mean'] = (X.loc[seg_id, 'Moving_average_700_mean'] - no_of_std * X.loc[seg_id, 'MA_400MA_std_mean']).mean()\n    X.loc[seg_id, 'MA_1000MA_std_mean'] = xc.rolling(window=1000).std().mean()\n    \n    X.loc[seg_id, 'iqr'] = np.subtract(*np.percentile(xc, [75, 25]))\n    X.loc[seg_id, 'q999'] = np.quantile(xc,0.999)\n    X.loc[seg_id, 'q001'] = np.quantile(xc,0.001)\n    X.loc[seg_id, 'ave10'] = stats.trim_mean(xc, 0.1)\n    \n    for windows in [10, 100, 1000]:\n        x_roll_std = xc.rolling(windows).std().dropna().values\n        x_roll_mean = xc.rolling(windows).mean().dropna().values\n        \n        X.loc[seg_id, 'ave_roll_std_' + str(windows)] = x_roll_std.mean()\n        X.loc[seg_id, 'std_roll_std_' + str(windows)] = x_roll_std.std()\n        X.loc[seg_id, 'max_roll_std_' + str(windows)] = x_roll_std.max()\n        X.loc[seg_id, 'min_roll_std_' + str(windows)] = x_roll_std.min()\n        X.loc[seg_id, 'q01_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.01)\n        X.loc[seg_id, 'q05_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.05)\n        X.loc[seg_id, 'q95_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.95)\n        X.loc[seg_id, 'q99_roll_std_' + str(windows)] = np.quantile(x_roll_std, 0.99)\n        X.loc[seg_id, 'av_change_abs_roll_std_' + str(windows)] = np.mean(np.diff(x_roll_std))\n        X.loc[seg_id, 'av_change_rate_roll_std_' + str(windows)] = np.mean(np.nonzero((np.diff(x_roll_std) / x_roll_std[:-1]))[0])\n        X.loc[seg_id, 'abs_max_roll_std_' + str(windows)] = np.abs(x_roll_std).max()\n        \n        X.loc[seg_id, 'std_roll_mean_' + str(windows)] = x_roll_mean.std()\n        X.loc[seg_id, 'max_roll_mean_' + str(windows)] = x_roll_mean.max()\n        X.loc[seg_id, 'min_roll_mean_' + str(windows)] = x_roll_mean.min()\n        X.loc[seg_id, 'q01_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.01)\n        X.loc[seg_id, 'q05_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.05)\n        X.loc[seg_id, 'q95_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.95)\n        X.loc[seg_id, 'q99_roll_mean_' + str(windows)] = np.quantile(x_roll_mean, 0.99)\n        X.loc[seg_id, 'av_change_abs_roll_mean_' + str(windows)] = np.mean(np.diff(x_roll_mean))\n        X.loc[seg_id, 'av_change_rate_roll_mean_' + str(windows)] = np.mean(np.nonzero((np.diff(x_roll_mean) / x_roll_mean[:-1]))[0])\n        X.loc[seg_id, 'abs_max_roll_mean_' + str(windows)] = np.abs(x_roll_mean).max()","execution_count":10,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2589334d2c5e6ddfcdd1757a2f3eae6578bf3a16"},"cell_type":"code","source":"for seg_id in tqdm(range(segments)):\n    seg = train_df.iloc[seg_id*rows:seg_id*rows+rows]\n    create_features(seg_id, seg, train_X)\n    train_y.loc[seg_id, 'time_to_failure'] = seg['time_to_failure'].values[-1]","execution_count":11,"outputs":[{"output_type":"stream","text":"100%|██████████| 4194/4194 [25:06<00:00,  2.84it/s]\n","name":"stderr"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv(path/'sample_submission.csv', index_col='seg_id')\ntest_X = pd.DataFrame(columns=train_X.columns, dtype=np.float64, index=submission.index)","execution_count":12,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for seg_id in tqdm(test_X.index):\n    seg = pd.read_csv(path/f'test/{seg_id}.csv')\n    create_features(seg_id, seg, test_X)","execution_count":13,"outputs":[{"output_type":"stream","text":"100%|██████████| 2624/2624 [17:19<00:00,  2.49it/s]\n","name":"stderr"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_X.reset_index(inplace=True)","execution_count":14,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = test_X","execution_count":15,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = pd.concat([train_X, train_y], axis=1); df.shape","execution_count":16,"outputs":[{"output_type":"execute_result","execution_count":16,"data":{"text/plain":"(4194, 148)"},"metadata":{}}]},{"metadata":{"_uuid":"0575490720788feb72e221004a1e15ff9f06536f"},"cell_type":"markdown","source":"# Make it stupid"},{"metadata":{"trusted":true},"cell_type":"code","source":"def print_score(m):\n    res = [metrics.mean_absolute_error(m.predict(X_train), y_train), metrics.mean_absolute_error(m.predict(X_valid), y_valid),\n                m.score(X_train, y_train), m.score(X_valid, y_valid)]\n    if hasattr(m, 'oob_score_'): res.append(m.oob_score_)\n    print(res)","execution_count":17,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ef0bd751dcc4f89819dc76da39a2f319d77d6728"},"cell_type":"code","source":"df_trn, y_trn, nas = proc_df(df, 'time_to_failure')","execution_count":18,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"20b16193a9d77efdc48e4fcaff67d3074c9c529f"},"cell_type":"code","source":"def split_vals(a,n): \n    return a[:n].copy(), a[n:].copy()\n    \ntrain_required_ratio = 0.80\nn_trn = int(len(df_trn) * train_required_ratio)\n\nX_train, X_valid = split_vals(df_trn, n_trn)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         \ny_train, y_valid = split_vals(y_trn, n_trn)\nX_train.shape, X_valid.shape","execution_count":19,"outputs":[{"output_type":"execute_result","execution_count":19,"data":{"text/plain":"((3355, 147), (839, 147))"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"m = RandomForestRegressor(n_estimators=100, n_jobs=-1)\nm.fit(X_train, y_train)\nprint_score(m)","execution_count":20,"outputs":[{"output_type":"stream","text":"[0.749212389127233, 2.5554441703371618, 0.9269022387556956, 0.3456851469462269]\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = df_trn.copy()\nX_train.drop(df_trn.loc[100:349].index, inplace=True)\nX_valid = df_trn.iloc[100:350]\n\ny_train = np.concatenate([y_trn[:100], y_trn[350:]])\ny_valid = y_trn[100:350]\n\n# y_train, y_valid = split_vals(y_trn, n_trn)\nX_train.shape, X_valid.shape, len(y_train), len(y_valid)","execution_count":21,"outputs":[{"output_type":"execute_result","execution_count":21,"data":{"text/plain":"((3944, 147), (250, 147), 3944, 250)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"m = RandomForestRegressor(n_estimators=100, n_jobs=-1)\nm.fit(X_train, y_train)\nprint_score(m)","execution_count":22,"outputs":[{"output_type":"stream","text":"[0.7853756018552569, 1.7733821842880615, 0.9245729553813196, 0.5569387801406146]\n","name":"stdout"}]},{"metadata":{"trusted":true,"_uuid":"25991ab69815a1fc87d7e8a52f5d910aa46c5ebe"},"cell_type":"code","source":"# preds = np.stack([t.predict(X_valid) for t in m.estimators_])\n# preds[:,0], np.mean(preds[:,0]), y_valid[0]","execution_count":23,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"87f701da079aabf84ef5f631e81eff883761dc65"},"cell_type":"code","source":"# plt.plot([metrics.r2_score(y_valid, np.mean(preds[:i+1], axis=0)) for i in range(100)]);","execution_count":24,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"c34bd6933ec563c589626b449d2ab287fa24f02d"},"cell_type":"code","source":"set_rf_samples(50_000)","execution_count":25,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"273ad931f92a5ee48f12d41c05ad18f5adc8be89"},"cell_type":"code","source":"m = RandomForestRegressor(n_estimators=40, min_samples_leaf=3, max_features=0.5,\n                          n_jobs=-1, oob_score=True)\nm.fit(X_train, y_train)\nprint_score(m)","execution_count":26,"outputs":[{"output_type":"stream","text":"[0.2810106675566052, 1.7744406944204152, 0.9841244894136691, 0.5518299638963496, -2.405488197037503]\n","name":"stdout"}]},{"metadata":{"trusted":true,"_uuid":"1a222d6b920adfa5070ea6f971c4d8a59790231c"},"cell_type":"code","source":"reset_rf_samples()","execution_count":27,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Final model"},{"metadata":{"trusted":true,"_uuid":"d9fc72c1f0e16beee3f0dd223dc7f5ba35ccab4e"},"cell_type":"code","source":"m = RandomForestRegressor(n_estimators=100, min_samples_leaf=2, max_features=0.5,\n                          n_jobs=-1, oob_score=True)\nm.fit(X_train, y_train)\nprint_score(m)","execution_count":28,"outputs":[{"output_type":"stream","text":"[0.839800563331672, 1.7502792543643095, 0.909006402022312, 0.5662550091496776, 0.45755602299496234]\n","name":"stdout"}]},{"metadata":{"trusted":true,"_uuid":"5d8f4dcc04cfdd7474193b36fcd223541ce0ce77"},"cell_type":"code","source":"fi = rf_feat_importance(m, df_trn)","execution_count":29,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a7988df38b2d938f1f56790a8cfdec0ea5c67ac3"},"cell_type":"code","source":"def plot_fi(fi): return fi.plot('cols', 'imp', 'barh', figsize=(12,7), legend=False)","execution_count":30,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"77e140255246b15fd561c780acef814a9591a994"},"cell_type":"code","source":"plot_fi(fi);","execution_count":31,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 864x504 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"important = fi[fi.imp>0.005]","execution_count":43,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"to_keep = fi[fi.imp>0.005].cols; len(to_keep)","execution_count":45,"outputs":[{"output_type":"execute_result","execution_count":45,"data":{"text/plain":"43"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train = df_trn[to_keep].copy()\nX_train.drop(df_trn[to_keep].loc[100:349].index, inplace=True)\nX_valid = df_trn[to_keep].iloc[100:350]\n\ny_train = np.concatenate([y_trn[:100], y_trn[350:]])\ny_valid = y_trn[100:350]\n\n# y_train, y_valid = split_vals(y_trn, n_trn)\nX_train.shape, X_valid.shape, len(y_train), len(y_valid)","execution_count":46,"outputs":[{"output_type":"execute_result","execution_count":46,"data":{"text/plain":"((3944, 43), (250, 43), 3944, 250)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"m = RandomForestRegressor(n_estimators=100, min_samples_leaf=2, max_features=0.5,\n                          n_jobs=-1, oob_score=True)\nm.fit(X_train, y_train)\nprint_score(m)","execution_count":47,"outputs":[{"output_type":"stream","text":"[0.8610105500886865, 1.7442663437965715, 0.9031323227504834, 0.5596976383066945, 0.4584106000805589]\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = m.predict(test_df[to_keep])","execution_count":50,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# preds = m.predict(test_df.drop(columns=\"seg_id\"))","execution_count":58,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subm_df = pd.DataFrame(test_df[\"seg_id\"])","execution_count":51,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subm_df[\"time_to_failure\"] = preds","execution_count":52,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"subm_df.head()","execution_count":53,"outputs":[{"output_type":"execute_result","execution_count":53,"data":{"text/plain":"       seg_id  time_to_failure\n0  seg_00030f         3.307157\n1  seg_0012b5         5.914957\n2  seg_00184e         4.967985\n3  seg_003339         8.085365\n4  seg_0042cc         6.726980","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>seg_id</th>\n      <th>time_to_failure</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>seg_00030f</td>\n      <td>3.307157</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>seg_0012b5</td>\n      <td>5.914957</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>seg_00184e</td>\n      <td>4.967985</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>seg_003339</td>\n      <td>8.085365</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>seg_0042cc</td>\n      <td>6.726980</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"subm_df.to_csv('submission.csv', index=False)","execution_count":54,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}