Python numpy.nanmin() Examples

def fuzzify_mean(A):
    # output for fuzzified values
    R = np.zeros((A.shape[0], A.shape[1] * 3))

    cmin, cmax, cmean = np.nanmin(A, 0), np.nanmax(A, 0), np.nanmean(A, 0)
        
    left = np.array([cmin - (cmax - cmin), cmin, cmax]).T
    middle = np.array([cmin, cmean, cmax]).T
    right = np.array([cmin, cmax, cmax + (cmax - cmin)]).T

    mus = []

    for i in range(A.shape[1]):
        f_l = fl.TriangularSet(*left[i])
        f_m = fl.TriangularSet(*middle[i])
        f_r = fl.TriangularSet(*right[i])
        R[:,(i*3)] = f_l(A[:,i])
        R[:,(i*3)+1] = f_m(A[:,i])
        R[:,(i*3)+2] = f_r(A[:,i])
        mus.extend([(i, f_l), (i, f_m), (i, f_r)])

    return 3, R, mus 

def findminval_multirasters(FileList):
    """
    Loops through a list or array of rasters (np arrays)
    and finds the minimum single value in the set of arrays.
    """
    overall_min_val = 0

    for i in range (len(FileList)):

        raster_as_array = LSDMap_IO.ReadRasterArrayBlocks(FileList[i])
        this_min_val = np.nanmin(raster_as_array)

        if this_min_val > overall_min_val:
            overall_min_val = this_min_val
            print(overall_min_val)

    return overall_min_val 

def test_unsorted_index_lims(self):
        df = DataFrame({'y': [0., 1., 2., 3.]}, index=[1., 0., 3., 2.])
        ax = df.plot()
        xmin, xmax = ax.get_xlim()
        lines = ax.get_lines()
        assert xmin <= np.nanmin(lines[0].get_data()[0])
        assert xmax >= np.nanmax(lines[0].get_data()[0])

        df = DataFrame({'y': [0., 1., np.nan, 3., 4., 5., 6.]},
                       index=[1., 0., 3., 2., np.nan, 3., 2.])
        ax = df.plot()
        xmin, xmax = ax.get_xlim()
        lines = ax.get_lines()
        assert xmin <= np.nanmin(lines[0].get_data()[0])
        assert xmax >= np.nanmax(lines[0].get_data()[0])

        df = DataFrame({'y': [0., 1., 2., 3.], 'z': [91., 90., 93., 92.]})
        ax = df.plot(x='z', y='y')
        xmin, xmax = ax.get_xlim()
        lines = ax.get_lines()
        assert xmin <= np.nanmin(lines[0].get_data()[0])
        assert xmax >= np.nanmax(lines[0].get_data()[0]) 

def return_normalized_distance_matrix(self, input_vector):
        """Return the min-max normalized euclidean-distance matrix between the input vector and the SOM weights.

        A value of 0.0 means that the input/weights are equal.
        @param input_vector the vector to use for the comparison.
        """
        output_matrix = np.zeros((self._matrix_size, self._matrix_size))
        it = np.nditer(output_matrix, flags=['multi_index'])
        while not it.finished:
            #print "%d <%s>" % (it[0], it.multi_index),
            dist = self.return_euclidean_distance(input_vector, self._weights_matrix[it.multi_index[0], it.multi_index[1], :])
            output_matrix[it.multi_index[0], it.multi_index[1]] = dist
            it.iternext()
        #min-max normalization
        max_value = np.nanmax(output_matrix)
        min_value = np.nanmin(output_matrix)
        output_matrix = (output_matrix - min_value) / (max_value - min_value)
        return output_matrix 

def return_similarity_matrix(self, input_vector):
        """Return a similarity matrix where a value is 1.0 if the distance input/weight is zero.

        @param input_vector the vector to use for the comparison.
        """
        output_matrix = np.zeros((self._matrix_size, self._matrix_size))
        it = np.nditer(output_matrix, flags=['multi_index'])
        while not it.finished:
            #print "%d <%s>" % (it[0], it.multi_index),
            dist = self.return_euclidean_distance(input_vector, self._weights_matrix[it.multi_index[0], it.multi_index[1], :])
            output_matrix[it.multi_index[0], it.multi_index[1]] = dist
            it.iternext()
        #min-max normalization
        max_value = np.nanmax(output_matrix)
        min_value = np.nanmin(output_matrix)
        output_matrix = (output_matrix - min_value) / (max_value - min_value)
        output_matrix = 1.0 - output_matrix
        return output_matrix 

def scatter_lims(vals1, vals2=None, buffer=.05):
  if vals2 is not None:
    vals = np.concatenate((vals1, vals2))
  else:
    vals = vals1
  vmin = np.nanmin(vals)
  vmax = np.nanmax(vals)

  buf = .05 * (vmax - vmin)

  if vmin == 0:
    vmin -= buf / 2
  else:
    vmin -= buf
  vmax += buf

  return vmin, vmax


################################################################################
# nucleotides

# Thanks to Anshul Kundaje, Avanti Shrikumar
# https://github.com/kundajelab/deeplift/tree/master/deeplift/visualization 

def scatter_lims(vals1, vals2=None, buffer=.05):
  if vals2 is not None:
    vals = np.concatenate((vals1, vals2))
  else:
    vals = vals1
  vmin = np.nanmin(vals)
  vmax = np.nanmax(vals)

  buf = .05 * (vmax - vmin)

  if vmin == 0:
    vmin -= buf / 2
  else:
    vmin -= buf
  vmax += buf

  return vmin, vmax

################################################################################
# __main__
################################################################################ 

def quickMinMax(self, data):
        """
        Estimate the min/max values of *data* by subsampling.
        Returns [(min, max), ...] with one item per channel
        """
        while data.size > 1e6:
            ax = np.argmax(data.shape)
            sl = [slice(None)] * data.ndim
            sl[ax] = slice(None, None, 2)
            data = data[sl]
            
        cax = self.axes['c']
        if cax is None:
            return [(float(nanmin(data)), float(nanmax(data)))]
        else:
            return [(float(nanmin(data.take(i, axis=cax))), 
                     float(nanmax(data.take(i, axis=cax)))) for i in range(data.shape[-1])] 

def test_calc_f107a_daily_missing(self):
        """ Test the calc_f107a routine with some daily data missing"""

        self.testInst.data = pds.DataFrame({'f107': np.linspace(70, 200, 160)},
                                           index=[pysat.datetime(2009, 1, 1)
                                                  + pds.DateOffset(days=2*i+1)
                                                  for i in range(160)])
        sw_f107.calc_f107a(self.testInst, f107_name='f107', f107a_name='f107a')

        # Assert that new data and metadata exist
        assert 'f107a' in self.testInst.data.columns
        assert 'f107a' in self.testInst.meta.keys()

        # Assert the finite values have realistic means
        assert(np.nanmin(self.testInst['f107a'])
               > np.nanmin(self.testInst['f107']))
        assert(np.nanmax(self.testInst['f107a'])
               < np.nanmax(self.testInst['f107']))

        # Assert the expected number of fill values
        assert(len(self.testInst['f107a'][np.isnan(self.testInst['f107a'])])
               == 40) 

def fuzzify_partitions(p):
    def fuzzify_p(A):
        R = np.zeros((A.shape[0], A.shape[1] * p))

        cmin, cmax = np.nanmin(A, 0), np.nanmax(A, 0)
        psize = (cmax - cmin) / (p - 1)

        mus = []
        # iterate features
        for i in range(A.shape[1]):
            # iterate partitions
            mu_i = []
            offset = cmin[i]
            for j in range(p):
                f = fl.TriangularSet(offset - psize[i], offset, offset + psize[i])
                R[:, (i * p) + j] = f(A[:, i])
                mu_i.append(f)
                offset += psize[i]
            mus.append(mu_i)
        return p, R, mus
    return fuzzify_p 

def __call__(self, transform_xy, x1, y1, x2, y2):
        x_, y_ = np.linspace(x1, x2, self.nx), np.linspace(y1, y2, self.ny)
        x, y = np.meshgrid(x_, y_)
        lon, lat = transform_xy(np.ravel(x), np.ravel(y))

        with np.errstate(invalid='ignore'):
            if self.lon_cycle is not None:
                lon0 = np.nanmin(lon)
                # Changed from 180 to 360 to be able to span only
                # 90-270 (left hand side)
                lon -= 360. * ((lon - lon0) > 360.)
            if self.lat_cycle is not None:
                lat0 = np.nanmin(lat)
                # Changed from 180 to 360 to be able to span only
                # 90-270 (left hand side)
                lat -= 360. * ((lat - lat0) > 360.)

        lon_min, lon_max = np.nanmin(lon), np.nanmax(lon)
        lat_min, lat_max = np.nanmin(lat), np.nanmax(lat)

        lon_min, lon_max, lat_min, lat_max = \
            self._adjust_extremes(lon_min, lon_max, lat_min, lat_max)

        return lon_min, lon_max, lat_min, lat_max 

def netcdf_to_geojson(ncfile, var, fourth_dim=None):
    realpath = os.path.realpath(ncfile)
    name, ext = os.path.splitext(realpath)
    X, Y, Z, levels, unit = setup(ncfile, var)
    figure = plt.figure()
    ax = figure.add_subplot(111)
    for t in range(len(Z.time)):
        third = Z.isel(time=t)
        position = 0
        if len(third.dims) == 3:
            position = len(getattr(third, third.dims[0]))-1
            third = third[position, ]
        # local min max
        levels = np.linspace(start=np.nanmin(third),
                             stop=np.nanmax(third), num=20)
        contourf = ax.contourf(X, Y, third, levels=levels, cmap=plt.cm.viridis)
        geojsoncontour.contourf_to_geojson(
            contourf=contourf,
            geojson_filepath='{}_{}_t{}_{}.geojson'.format(name, var,
                                                           t, position),
            ndigits=3,
            min_angle_deg=None,
            unit=unit
        ) 

def apply_cmap(zs, cmap, vmin=None, vmax=None, unit=None, logrescale=False):
    '''
    apply_cmap(z, cmap) applies the given cmap to the values in z; if vmin and/or vmax are passed,
      they are used to scale z.

    Note that this function can automatically rescale data into log-space if the colormap is a
    neuropythy log-space colormap such as log_eccentricity. To enable this behaviour use the
    optional argument logrescale=True.
    '''
    zs = pimms.mag(zs) if unit is None else pimms.mag(zs, unit)
    zs = np.asarray(zs, dtype='float')
    if pimms.is_str(cmap): cmap = matplotlib.cm.get_cmap(cmap)
    if logrescale:
        if vmin is None: vmin = np.log(np.nanmin(zs))
        if vmax is None: vmax = np.log(np.nanmax(zs))
        mn = np.exp(vmin)
        u = zdivide(nanlog(zs + mn) - vmin, vmax - vmin, null=np.nan)
    else:        
        if vmin is None: vmin = np.nanmin(zs)
        if vmax is None: vmax = np.nanmax(zs)
        u = zdivide(zs - vmin, vmax - vmin, null=np.nan)
    u[np.isnan(u)] = -np.inf
    return cmap(u) 

def default_fuzzifier(idx, F):
    """Default fuzzifier function.

    Creates three fuzzy sets with triangular membership functions: (low, med, hig) from min and max data points.
    """
    # get min/max from data
    v_min = np.nanmin(F)
    v_max = np.nanmax(F)
    # blarg
    return [ Leaf(idx, "low", fl.TriangularSet(v_min - (v_max - v_min) ** 2, v_min, v_max)),
             Leaf(idx, "med", fl.TriangularSet(v_min, v_min + ((v_max - v_min) / 2), v_max)),
             Leaf(idx, "hig", fl.TriangularSet(v_min, v_max, v_max + (v_max - v_min) ** 2)) ] 

def test_unsorted_index_xlim(self):
        ser = Series([0., 1., np.nan, 3., 4., 5., 6.],
                     index=[1., 0., 3., 2., np.nan, 3., 2.])
        _, ax = self.plt.subplots()
        ax = ser.plot(ax=ax)
        xmin, xmax = ax.get_xlim()
        lines = ax.get_lines()
        assert xmin <= np.nanmin(lines[0].get_data(orig=False)[0])
        assert xmax >= np.nanmax(lines[0].get_data(orig=False)[0]) 

def min_max_normalize(X):
    nmin, nmax = np.nanmin(X), np.nanmax(X)
    return (X - nmin) / (nmax - nmin) 

def build_memberships(X, factory):
    mins = np.nanmin(X, 0)
    maxs = np.nanmax(X, 0)
    means = np.nanmean(X, 0)
    return [ (i, factory(means[i] - ((maxs[i] - mins[i]) / 2.0),
                         means[i], means[i] + ((maxs[i] - mins[i]) / 2.0))) for i in range(X.shape[1]) ] 

def _get_xlim(lines):
    left, right = np.inf, -np.inf
    for l in lines:
        x = l.get_xdata(orig=False)
        left = min(np.nanmin(x), left)
        right = max(np.nanmax(x), right)
    return left, right 

def build_memberships(X, factory):
    mins = np.nanmin(X, 0)
    maxs = np.nanmax(X, 0)
    means = np.nanmean(X, 0)
    return [ factory(means[i] - ((maxs[i] - mins[i]) / 2.0),
                     means[i],
                     means[i] + ((maxs[i] - mins[i]) / 2.0))
             for i in range(len(X.T)) ] 

def min(X, axis=-1):
    return np.nanmin(X, axis) 

def adjust_SVM(self):
        Cs = np.logspace(0, 10, 15, base=2)
        gammas = np.logspace(-7, 4, 15, base=2)
        scores = np.zeros((len(Cs), len(gammas)))
        scores[:] = np.nan

        print('adjusting SVM (may take a long time) ...')
        def f(job):
            i, j = job
            samples, labels = self.get_dataset()
            params = dict(C = Cs[i], gamma=gammas[j])
            score = cross_validate(SVM, params, samples, labels)
            return i, j, score

        ires = self.run_jobs(f, np.ndindex(*scores.shape))
        for count, (i, j, score) in enumerate(ires):
            scores[i, j] = score
            print('%d / %d (best error: %.2f %%, last: %.2f %%)' %
                  (count+1, scores.size, np.nanmin(scores)*100, score*100))
        print(scores)

        print('writing score table to "svm_scores.npz"')
        np.savez('svm_scores.npz', scores=scores, Cs=Cs, gammas=gammas)

        i, j = np.unravel_index(scores.argmin(), scores.shape)
        best_params = dict(C = Cs[i], gamma=gammas[j])
        print('best params:', best_params)
        print('best error: %.2f %%' % (scores.min()*100))
        return best_params 

def _get_ind(self, y):
        if self.ind is None:
            # np.nanmax() and np.nanmin() ignores the missing values
            sample_range = np.nanmax(y) - np.nanmin(y)
            ind = np.linspace(np.nanmin(y) - 0.5 * sample_range,
                              np.nanmax(y) + 0.5 * sample_range, 1000)
        elif is_integer(self.ind):
            sample_range = np.nanmax(y) - np.nanmin(y)
            ind = np.linspace(np.nanmin(y) - 0.5 * sample_range,
                              np.nanmax(y) + 0.5 * sample_range, self.ind)
        else:
            ind = self.ind
        return ind 

def test_nanmin(self):
        tgt = np.min(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanmin(mat), tgt) 

def test_object_array(self):
        arr = np.array([[1.0, 2.0], [np.nan, 4.0], [np.nan, np.nan]], dtype=object)
        assert_equal(np.nanmin(arr), 1.0)
        assert_equal(np.nanmin(arr, axis=0), [1.0, 2.0])

        with warnings.catch_warnings(record=True) as w:
            warnings.simplefilter('always')
            # assert_equal does not work on object arrays of nan
            assert_equal(list(np.nanmin(arr, axis=1)), [1.0, 4.0, np.nan])
            assert_(len(w) == 1, 'no warning raised')
            assert_(issubclass(w[0].category, RuntimeWarning)) 

def test_masked(self):
        mat = np.ma.fix_invalid(_ndat)
        msk = mat._mask.copy()
        for f in [np.nanmin]:
            res = f(mat, axis=1)
            tgt = f(_ndat, axis=1)
            assert_equal(res, tgt)
            assert_equal(mat._mask, msk)
            assert_(not np.isinf(mat).any()) 

def min(s, v):
        return np.nanmin(v) 

def setup(filename, var):
    data = xr.open_dataset(filename)
    lon_range = data.variables['lon'].data
    lat_range = data.variables['lat'].data
    lon_range, lat_range
    X, Y = np.meshgrid(lon_range, lat_range)
    mini = np.nanmin(data.variables[var].data)
    maxi = np.nanmax(data.variables[var].data)
    unit = data.variables[var].attrs['units']
    n_contours = 20
    levels = np.linspace(start=mini, stop=maxi, num=n_contours)
    Z = getattr(data, var)
    return X, Y, Z, levels, unit 

def test_nanmin(self):
        tgt = np.min(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanmin(mat), tgt) 

def test_masked(self):
        mat = np.ma.fix_invalid(_ndat)
        msk = mat._mask.copy()
        for f in [np.nanmin]:
            res = f(mat, axis=1)
            tgt = f(_ndat, axis=1)
            assert_equal(res, tgt)
            assert_equal(mat._mask, msk)
            assert_(not np.isinf(mat).any()) 

def volume_to_level(self, node, waterlevel):
        if node.current_vol > 0:
            maxelev = node.parent.elev
            if node.elev:
                minelev = node.elev
            else:
                # TODO: This bound could be a lot better
                minelev = np.nanmin(self.dem)
            target_vol = node.current_vol
            elev = optimize.bisect(self.compute_vol, minelev, maxelev,
                                   args=(node, target_vol))
            if node.name:
                mask = self.ws[node.level] == node.name
            else:
                leaves = []
                self.enumerate_leaves(node, level=node.level, stack=leaves)
                mask = np.isin(self.ws[node.level], leaves)
                boundary = list(chain.from_iterable([self.b[node.level].setdefault(pair, [])
                                                     for pair in combinations(leaves, 2)]))
                mask.flat[boundary] = True
            mask = np.flatnonzero(mask & (self.dem < elev))
            waterlevel.flat[mask] = elev
        else:
            if node.l:
                self.volume_to_level(node.l, waterlevel)
            if node.r:
                self.volume_to_level(node.r, waterlevel)