Python DataArray.mean方法代码示例

# 需要导入模块: from xarray import DataArray [as 别名]
# 或者: from xarray.DataArray import mean [as 别名]
def test_cftime_datetime_mean():
    times = cftime_range('2000', periods=4)
    da = DataArray(times, dims=['time'])

    assert da.isel(time=0).mean() == da.isel(time=0)

    expected = DataArray(times.date_type(2000, 1, 2, 12))
    result = da.mean()
    assert_equal(result, expected)

    da_2d = DataArray(times.values.reshape(2, 2))
    result = da_2d.mean()
    assert_equal(result, expected)

# 需要导入模块: from xarray import DataArray [as 别名]
# 或者: from xarray.DataArray import mean [as 别名]
def _pearsonr(x: xr.DataArray, y: xr.DataArray, monitor: Monitor) -> xr.Dataset:
    """
    Calculate Pearson correlation coefficients and p-values for testing
    non-correlation of lon/lat/time xarray datasets for each lon/lat point.

    Heavily influenced by scipy.stats.pearsonr

    The Pearson correlation coefficient measures the linear relationship
    between two datasets. Strictly speaking, Pearson's correlation requires
    that each dataset be normally distributed, and not necessarily zero-mean.
    Like other correlation coefficients, this one varies between -1 and +1
    with 0 implying no correlation. Correlations of -1 or +1 imply an exact
    linear relationship. Positive correlations imply that as x increases, so
    does y. Negative correlations imply that as x increases, y decreases.

    The p-value roughly indicates the probability of an uncorrelated system
    producing datasets that have a Pearson correlation at least as extreme
    as the one computed from these datasets. The p-values are not entirely
    reliable but are probably reasonable for datasets larger than 500 or so.

    :param x: lon/lat/time xr.DataArray
    :param y: xr.DataArray of the same spatiotemporal extents and resolution as x.
    :param monitor: Monitor to use for monitoring the calculation
    :return: A dataset containing the correlation coefficients and p_values on
    the lon/lat grid of x and y.

    References
    ----------
    http://www.statsoft.com/textbook/glosp.html#Pearson%20Correlation
    """
    with monitor.starting("Calculate Pearson correlation", total_work=6):
        n = len(x['time'])

        xm, ym = x - x.mean(dim='time'), y - y.mean(dim='time')
        xm.time.values = [i for i in range(0, len(xm.time))]
        ym.time.values = [i for i in range(0, len(ym.time))]
        xm_ym = xm * ym
        r_num = xm_ym.sum(dim='time')
        xm_squared = np.square(xm)
        ym_squared = np.square(ym)
        r_den = np.sqrt(xm_squared.sum(dim='time') * ym_squared.sum(dim='time'))
        r_den = r_den.where(r_den != 0)
        r = r_num / r_den

        # Presumably, if abs(r) > 1, then it is only some small artifact of floating
        # point arithmetic.
        # At this point r should be a lon/lat dataArray, so it should be safe to
        # load it in memory explicitly. This may take time as it will kick-start
        # deferred processing.
        # Comparing with NaN produces warnings that can be safely ignored
        default_warning_settings = np.seterr(invalid='ignore')
        with monitor.child(1).observing("task 1"):
            negativ_r = r.values < -1.0
        with monitor.child(1).observing("task 2"):
            r.values[negativ_r] = -1.0
        with monitor.child(1).observing("task 3"):
            positiv_r = r.values > 1.0
        with monitor.child(1).observing("task 4"):
            r.values[positiv_r] = 1.0
        np.seterr(**default_warning_settings)
        r.attrs = {'description': 'Correlation coefficients between'
                   ' {} and {}.'.format(x.name, y.name)}

        df = n - 2
        t_squared = np.square(r) * (df / ((1.0 - r.where(r != 1)) * (1.0 + r.where(r != -1))))

        prob = df / (df + t_squared)
        with monitor.child(1).observing("task 5"):
            prob_values_in = prob.values
        with monitor.child(1).observing("task 6"):
            prob.values = betainc(0.5 * df, 0.5, prob_values_in)
        prob.attrs = {'description': 'Rough indicator of probability of an'
                      ' uncorrelated system producing datasets that have a Pearson'
                      ' correlation at least as extreme as the one computed from'
                      ' these datsets. Not entirely reliable, but reasonable for'
                      ' datasets larger than 500 or so.'}

        retset = xr.Dataset({'corr_coef': r,
                             'p_value': prob})
    return retset

# 需要导入模块: from xarray import DataArray [as 别名]
# 或者: from xarray.DataArray import mean [as 别名]
def test_cftime_datetime_mean_dask_error():
    times = cftime_range('2000', periods=4)
    da = DataArray(times, dims=['time']).chunk()
    with pytest.raises(NotImplementedError):
        da.mean()