.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        Click :ref:`here <sphx_glr_download_auto_examples_plot_feature_rep.py>`     to download the full example code
    .. rst-class:: sphx-glr-example-title

    .. _sphx_glr_auto_examples_plot_feature_rep.py:


====================================================
Basic Feature Representation Classification Pipeline
====================================================

This is a basic example using the pipeline to learn a feature representation of the time series data




.. image:: /auto_examples/images/sphx_glr_plot_feature_rep_001.png
    :class: sphx-glr-single-img


.. rst-class:: sphx-glr-script-out

 Out:

 .. code-block:: none

    N series in train:  105
    N series in test:  35
    N segments in train:  3419
    N segments in test:  1258
    Accuracy score:  0.6836248012718601
    Pretend series y values:  [2 6 5]
    /home/david/Code/seglearn/examples/plot_feature_rep.py:66: UserWarning: Matplotlib is currently using agg, which is a non-GUI backend, so cannot show the figure.
      plt.show()
    /home/david/Code/seglearn/examples/plot_feature_rep.py:70: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray
      Xt = np.array(data['X'])
    CV Scores:     fit_time  score_time  test_score  train_score
    0  0.422009    0.075314    0.765787     0.999416
    1  0.435741    0.067579    0.812500     1.000000
    2  0.439884    0.068478    0.788967     0.999717
    3  0.426954    0.070049    0.766323     1.000000
    Features:  ['mean_0', 'mean_1', 'mean_2', 'mean_3', 'mean_4', 'mean_5', 'median_0', 'median_1', 'median_2', 'median_3', 'median_4', 'median_5', 'abs_energy_0', 'abs_energy_1', 'abs_energy_2', 'abs_energy_3', 'abs_energy_4', 'abs_energy_5', 'std_0', 'std_1', 'std_2', 'std_3', 'std_4', 'std_5', 'var_0', 'var_1', 'var_2', 'var_3', 'var_4', 'var_5', 'min_0', 'min_1', 'min_2', 'min_3', 'min_4', 'min_5', 'max_0', 'max_1', 'max_2', 'max_3', 'max_4', 'max_5', 'skew_0', 'skew_1', 'skew_2', 'skew_3', 'skew_4', 'skew_5', 'kurt_0', 'kurt_1', 'kurt_2', 'kurt_3', 'kurt_4', 'kurt_5', 'mse_0', 'mse_1', 'mse_2', 'mse_3', 'mse_4', 'mse_5', 'mnx_0', 'mnx_1', 'mnx_2', 'mnx_3', 'mnx_4', 'mnx_5']






|


.. code-block:: default

    # Author: David Burns
    # License: BSD

    import matplotlib.image as mpimg
    import matplotlib.pyplot as plt
    import numpy as np
    import pandas as pd
    from sklearn.ensemble import RandomForestClassifier
    from sklearn.metrics import f1_score, make_scorer
    from sklearn.model_selection import train_test_split, cross_validate
    from sklearn.preprocessing import StandardScaler

    from seglearn.base import TS_Data
    from seglearn.datasets import load_watch
    from seglearn.pipe import Pype
    from seglearn.transform import FeatureRep, Segment

    # seed RNGESUS
    np.random.seed(123124)

    # load the data
    data = load_watch()
    X = data['X']
    y = data['y']

    # create a feature representation pipeline
    clf = Pype([('segment', Segment()),
                ('features', FeatureRep()),
                ('scaler', StandardScaler()),
                ('rf', RandomForestClassifier(n_estimators=20))])

    # split the data
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25)

    clf.fit(X_train, y_train)
    score = clf.score(X_test, y_test)

    print("N series in train: ", len(X_train))
    print("N series in test: ", len(X_test))
    print("N segments in train: ", clf.N_train)
    print("N segments in test: ", clf.N_test)
    print("Accuracy score: ", score)

    # lets make a pretend series with different activities
    X_series = np.concatenate(X_test[1:4], axis=0)
    y_series = np.concatenate([np.full(len(X_test[i]), y_test[i]) for i in range(1, 4)])
    print("Pretend series y values: ", y_test[1:4])

    # plot the prediction
    yp = clf.predict_unsegmented([X_series], categorical_target=True)
    yp0 = yp[0]  # we only predicted one series
    t = np.arange(len(yp0)) * 0.02   # This data has 50 Hz sampling rate
    plt.plot(t, yp0, label='predicted')
    plt.plot(t, y_series, label='actual')
    plt.ylabel("Prediction")
    plt.xlabel("Time [seconds]")
    plt.legend()
    plt.show()

    # let's try some context data
    Xc = np.column_stack((data['side'], data['subject']))
    Xt = np.array(data['X'])
    X = TS_Data(Xt, Xc)
    y = np.array(data['y'])

    # and a cross validation
    scoring = make_scorer(f1_score, average='macro')
    cv_scores = cross_validate(clf, X, y, cv=4, return_train_score=True)
    print("CV Scores: ", pd.DataFrame(cv_scores))

    # lets see what feature we used
    print("Features: ", clf.steps[1][1].f_labels)


.. rst-class:: sphx-glr-timing

   **Total running time of the script:** ( 0 minutes  3.483 seconds)


.. _sphx_glr_download_auto_examples_plot_feature_rep.py:


.. only :: html

 .. container:: sphx-glr-footer
    :class: sphx-glr-footer-example



  .. container:: sphx-glr-download sphx-glr-download-python

     :download:`Download Python source code: plot_feature_rep.py <plot_feature_rep.py>`



  .. container:: sphx-glr-download sphx-glr-download-jupyter

     :download:`Download Jupyter notebook: plot_feature_rep.ipynb <plot_feature_rep.ipynb>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_