updates spatial suppression for an arbitrary domain

            raise AttributeError('This edge does not yet have any matches computed.')

        matches, mask = self.clean(clean_keys)

        domain = self.source.geodata.raster_size

        rs = self.source.geodata.raster_size

        domain = [0, 0, rs[0], rs[1]]

        # Massage the dataframe into the correct structure

        coords = self.source.get_keypoint_coordinates()

        merged = matches.merge(coords, left_on=['source_idx'], right_index=True)

    return mask

def spatial_suppression(df, domain, min_radius=1.5, k=250, error_k=0.1):

def spatial_suppression(df, bounds, xkey='lon', ykey='lat', k=60, error_k=0.05, nsteps=250):

    """

    Spatial suppression using disc based method.

    Apply the spatial suppression algorithm over an arbitrary domain for all of the spatial

    data in the provided data frame.

    Attributes

    Parameters

    ----------

    df : dataframe

         Input dataframe used for suppressing

    mask : series

           pandas boolean series

    df : object

         Pandas data frame with coordinates

    max_radius : float

                 Maximum allowable point radius

    bounds : list

             In the form xmin, ymin, xmax, ymax

    min_radius : float

                 The smallest allowable radius size

    xkey : str

           The column name for the x coordinates

    nvalid : int

             The number of valid points after suppression

    ykey : str

           The column name for the y coordinates

    k : int

        The number of points to be saved

        The desired number of points after suppression

    error_k : float

              [0,1] the acceptable error in k

              The percentage of allowable error in the domain [0,1]

    domain : tuple

             The (x,y) extent of the input domain

    nsteps : int

             The granularity of the search. This controls the number of

             buckets in the x and y dimension. More granular search adds processing

             time, but can result in a more accurate solution.

    Returns

    -------

    mask : pd.Series

           Boolean suppression mask

    k : int

        The number of unsuppressed observations

    References

    ----------

    [Gauglitz2011]_

    mask : nd.array

           A boolean mask of the valid points

    len(result) : int

                  The numer of valud points

    """

    columns = df.columns

    for i in ['x', 'y', 'strength']:

        if i not in columns:

            raise ValueError('The dataframe is missing a {} column.'.format(i))

    df = df.sort_values(by=['strength'], ascending=False).copy()

    # Compute the bounding area inside of which the suppression will be applied

    minx = min(bounds[0], bounds[2])

    maxx = max(bounds[0], bounds[2])

    miny = min(bounds[1], bounds[3])

    maxy = max(bounds[1], bounds[3])

    domain = (maxx-minx),(maxy-miny)

    min_radius = min(domain) / 20

    max_radius = max(domain)

    mask = pd.Series(False, index=df.index)

    process = True

    if k > len(df):

        warnings.warn('Only {} valid points, but {} points requested'.format(len(df), k))

        k = len(df)

        result = df.index

        process = False

    nsteps = max(domain) * 0.95

    search_space = np.linspace(min_radius, max_radius, nsteps)

    cell_sizes = search_space / math.sqrt(2)

    min_idx = 0

    max_idx = len(search_space) - 1

    # Setup flags to watch for looping

    prev_min = None

    prev_max = None

    while process:

        # Setup to store results

        result = []

    # Sort the dataframe (hard coded to ascending as lower strength (cost) is better)

    df = df.sort_values(by=['strength'], ascending=True).copy()

    df = df.reset_index(drop=True)

    mask = pd.Series(False, index=df.index)

    process = True

    while process:

        # Binary search

        mid_idx = int((min_idx + max_idx) / 2)

        if min_idx == mid_idx or mid_idx == max_idx:

            warnings.warn('Unable to optimally solve.  Returning with {} points'.format(len(result)))

            warnings.warn('Unable to optimally solve.')

            process = False

        else:

            # Setup to store results

            result = []

        # Get the current cell size and grid the domain

        cell_size = cell_sizes[mid_idx]

        n_x_cells = int(domain[0] / cell_size)

        n_y_cells = int(domain[1] / cell_size)

        grid = np.zeros((n_x_cells, n_y_cells), dtype=np.bool)

        n_x_cells = int(round(domain[0] / cell_size, 0)) - 1

        n_y_cells = int(round(domain[1] / cell_size, 0)) - 1

        if n_x_cells <= 0:

            n_x_cells = 1

        if n_y_cells <= 0:

            n_y_cells = 1

        grid = np.zeros((n_y_cells, n_x_cells), dtype=np.bool)

        # Assign all points to bins

        x_edges = np.linspace(0, domain[0], n_x_cells)

        y_edges = np.linspace(0, domain[1], n_y_cells)

        xbins = np.digitize(df['x'], bins=x_edges)

        ybins = np.digitize(df['y'], bins=y_edges)

        # Convert bins to cells

        xbins -= 1

        ybins -= 1

        pts = []

        x_edges = np.linspace(minx, maxx, n_x_cells)

        y_edges = np.linspace(miny, maxy, n_y_cells)

        xbins = np.digitize(df[xkey], bins=x_edges)

        ybins = np.digitize(df[ykey], bins=y_edges)

        # Starting with the best point, start assigning points to grid cells

        for i, (idx, p) in enumerate(df.iterrows()):

            x_center = xbins[i]

            y_center = ybins[i]

            x_center = xbins[i] - 1

            y_center = ybins[i] - 1

            cell = grid[y_center, x_center]

            if cell == False:

                result.append(idx)

                pts.append((p[['x', 'y']]))

                if len(result) > k + k * error_k:

                    # Too many points, break

                    min_idx = mid_idx

                    break

                y_min = y_center - int(round(cell_size, 0))

                if y_min < 0:

                    y_min = 0

                x_min = x_center - int(round(cell_size, 0))

                if x_min < 0:

                    x_min = 0

                # Set the cell to True

                grid[y_center, x_center] = True

                y_max = y_center + int(round(cell_size, 0))

                if y_max > grid.shape[0]:

                    y_max = grid.shape[0]

            # If everything is already 'covered' break from the list

            if grid.all() == False:

                continue

                x_max = x_center + int(round(cell_size, 0))

                if x_max > grid.shape[1]:

                    x_max = grid.shape[1]

                # Cover the necessary cells

                grid[y_min: y_max,

                     x_min: x_max] = True

        #  Check break conditions

        # Check to see if the algorithm is completed, or if the grid size needs to be larger or smaller

        if k - k * error_k <= len(result) <= k + k * error_k:

            # Success, in bounds

            process = False

        elif len(result) < k - k * error_k:

            # The radius is too large

            max_idx = mid_idx

                process = False

            if min_idx == max_idx:

                process = False

    mask = pd.Series(False, df.index)

        elif len(result) > k + k * error_k:

            # Too many points, break

            min_idx = mid_idx

    mask.loc[list(result)] = True

    return mask, k

    return mask, len(result)

def self_neighbors(matches):

        y = seed.randint(0, 100, 100).astype(np.float32)

        strength = seed.rand(100)

        data = np.vstack((x, y, strength)).T

        self.df = pd.DataFrame(data, columns=['x', 'y', 'strength'])

        self.domain = (100,100)

        self.df = pd.DataFrame(data, columns=['lon', 'lat', 'strength'])

        self.domain = (0,0, 100, 100)

    def test_suppress_non_optimal(self):

        with warnings.catch_warnings(record=True) as w:

    def test_suppress(self):

        mask, k = cpu_outlier_detector.spatial_suppression(self.df, self.domain, k=25)

            self.assertEqual(len(w), 1)

            self.assertEqual(w[0].category, UserWarning)

        self.assertEqual(mask.sum(), 25)

        self.assertEqual(mask.sum(), 28)

    def test_suppress(self):

        mask, k = cpu_outlier_detector.spatial_suppression(self.df, self.domain, k=30)

        self.assertIn(mask.sum(), list(range(27, 35)))

        mask, k = cpu_outlier_detector.spatial_suppression(self.df, self.domain, k=30, error_k=.15)

        self.assertEqual(mask.sum(), 34)

    def test_suppress_non_optimal(self):

        with warnings.catch_warnings(record=True) as w:

            mask, k = cpu_outlier_detector.spatial_suppression(self.df, self.domain, k=101)

            mask, k = cpu_outlier_detector.spatial_suppression(self.df, self.domain, k=30)

            self.assertEqual(len(w), 1)

            self.assertEqual(k, 59)

            self.assertTrue(issubclass(w[0].category, UserWarning))

class testSuppressionRanges(unittest.TestCase):

        cls.r = np.random.RandomState(12345)

    def test_min_max(self):

        df = pd.DataFrame(self.r.uniform(0,2,(500, 3)), columns=['x', 'y', 'strength'])

        mask, k = cpu_outlier_detector.spatial_suppression(df, (1.5,1.5), k = 1)

        df = pd.DataFrame(self.r.uniform(0,2,(500, 3)), columns=['lon', 'lat', 'strength'])

        mask, k = cpu_outlier_detector.spatial_suppression(df, (0, 0, 1.5, 1.5), k = 1)

        self.assertEqual(len(df[mask]), 1)

    def test_point_overload(self):

        df = pd.DataFrame(self.r.uniform(0,15,(500, 3)), columns=['x', 'y', 'strength'])

        mask, k = cpu_outlier_detector.spatial_suppression(df, (15,15), k = 200)

        self.assertEqual(len(df[mask]), 69)

        df = pd.DataFrame(self.r.uniform(0,15,(500, 3)), columns=['lon', 'lat', 'strength'])

        mask, k = cpu_outlier_detector.spatial_suppression(df, (0, 0, 15, 15), k = 200)

        self.assertEqual(len(df[mask]), 195)

    def test_small_distribution(self):

        df = pd.DataFrame(self.r.uniform(0,25,(500, 3)), columns=['x', 'y', 'strength'])

        mask, k = cpu_outlier_detector.spatial_suppression(df, (25,25), k = 25)

        self.assertEqual(len(df[mask]), 28)

        mask, k = cpu_outlier_detector.spatial_suppression(df, (0, 0, 25, 25), k = 25, xkey='x', ykey='y')

        self.assertEqual(len(df[mask]), 25)

    def test_normal_distribution(self):

        df = pd.DataFrame(self.r.uniform(0,100,(500, 3)), columns=['x', 'y', 'strength'])

        mask, k = cpu_outlier_detector.spatial_suppression(df, (100,100), k = 15)

        mask, k = cpu_outlier_detector.spatial_suppression(df, (0, 0, 100, 100), k = 15, xkey='x', ykey='y')

        self.assertEqual(len(df[mask]), 17)

package:

  name: autocnet

  version: 0.2.0

  version: 0.2.1

channels:

  - conda-forge

with open('README.rst', 'r') as f:

    long_description = f.read()

VERSION = autocnet.__version__

def setup_package():

    examples = set()

    for i in available():

    setup(

        name = "autocnet",

        version = VERSION,

        version = '0.2.1',

        author = "Jay Laura",

        author_email = "jlaura@usgs.gov",

        description = ("I/O API to support planetary data formats."),