def _masked_column_median(arr, masked_value):
"""Compute the median of each column in the 2D array arr, ignoring any
instances of masked_value"""
mask = _get_mask(arr, masked_value)
if arr.size == 0:
return cp.full(arr.shape[1], cp.nan)
arr_sorted = arr.copy()
if not cp.isnan(masked_value):
# If nan is not the missing value, any column with nans should
# have a median of nan
nan_cols = cp.any(cp.isnan(arr), axis=0)
arr_sorted[mask] = cp.nan
else:
nan_cols = cp.full(arr.shape[1], False)
# nans are always sorted to end of array
arr_sorted = cp.sort(arr_sorted, axis=0)
count_missing_values = mask.sum(axis=0)
# Ignore missing values in determining "halfway" index of sorted
# array
n_elems = arr.shape[0] - count_missing_values
# If no elements remain after removing missing value, median for
# that colum is nan
nan_cols = cp.logical_or(nan_cols, n_elems <= 0)
col_index = cp.arange(arr_sorted.shape[1])
median = (arr_sorted[cp.floor_divide(n_elems - 1, 2), col_index] +
arr_sorted[cp.floor_divide(n_elems, 2), col_index]) / 2
median[nan_cols] = cp.nan
return median
def corr_pairwise(x, y, return_pearson=False):
"""Covariance and Pearson product-moment correlation coefficients on the GPU for paired data with tolerance of NaNs.
Curently only supports rows as samples and columns as observations.
Parameters
----------
x : array_like
The baseline array of values.
y : array_like
The comparison array of values.
Returns
-------
corr : cupy ndarray
Array of correlation values
"""
def _cov_pairwise(x1, x2, factor):
return cupy.nansum(x1 * x2, axis=1, keepdims=True) * cupy.true_divide(
1, factor)
# Coerce arrays into 2D format and set dtype
dtype = cupy.result_type(x, y, cupy.float64)
x = cupy.asarray(x, dtype=dtype)
y = cupy.asarray(y, dtype=dtype)
assert x.shape == y.shape
if x.ndim < 2:
x = x[None, :]
y = y[None, :]
n_samples, n_obs = x.shape
# Calculate degrees of freedom for each sample pair
ddof = 1
nan_count = (cupy.isnan(x) | cupy.isnan(y)).sum(axis=1, keepdims=True)
fact = n_obs - nan_count - ddof
# Mean normalize
x -= cupy.nanmean(x, axis=1, keepdims=True)
y -= cupy.nanmean(y, axis=1, keepdims=True)
# Calculate covariance matrix
corr = _cov_pairwise(x, y, fact)
if return_pearson:
x_corr = _cov_pairwise(x, x, fact)
y_corr = _cov_pairwise(y, y, fact)
auto_corr = cupy.sqrt(x_corr) * cupy.sqrt(y_corr)
corr = corr / auto_corr
corr = cupy.clip(corr.real, -1, 1, out=corr.real)
return corr
return corr.squeeze()
def select_valid_oof(y, oof):
if isinstance(oof, cupy.ndarray):
if len(oof.shape) == 1:
idx = cupy.argwhere(~cupy.isnan(oof[:])).ravel()
elif len(oof.shape) == 2:
idx = cupy.argwhere(~cupy.isnan(oof[:, 0])).ravel()
elif len(oof.shape) == 3:
idx = cupy.argwhere(~cupy.isnan(oof[:, 0, 0])).ravel()
else:
raise ValueError(f'Unsupported shape:{oof.shape}')
return y.iloc[idx] if hasattr(y, 'iloc') else y[idx], oof[idx]
else:
return ToolBox.select_valid_oof(y, oof)
def gpu_resize(dPhi, dAmp, src_x, src_y, nx, ny):
ratio_x = nx/src_x
ratio_y = ny/src_y
# print(ratio_x , ratio_y)
dPhi[cupy.isnan(dPhi)] = 0
dPhi[cupy.isinf(dPhi)] = 0
dAmp[cupy.isnan(dAmp)] = 1
dAmp[cupy.isinf(dAmp)] = 1
dAmp[cupy.equal(dAmp,0.0)] = 0.01;
dAmp = cupy.absolute(dAmp)
dPhi = cupyx.scipy.ndimage.zoom(dPhi, (ratio_y,ratio_x))
dAmp = cupyx.scipy.ndimage.zoom(dAmp, (ratio_y,ratio_x))
dField = cupy.log(dAmp) + 1j*(dPhi)
return dField
def test_min_max_axis_extremes(sparse_extremes, axis, ignore_nan):
X_sparse_np, X_sparse = sparse_extremes
cu_min, cu_max = cu_min_max_axis(X_sparse, axis=axis,
ignore_nan=ignore_nan)
sk_min, sk_max = sk_min_max_axis(X_sparse_np, axis=axis,
ignore_nan=ignore_nan)
if axis is not None:
assert_allclose(cu_min, sk_min)
assert_allclose(cu_max, sk_max)
else:
assert cu_min == sk_min or (cp.isnan(cu_min) and np.isnan(sk_min))
assert cu_max == sk_max or (cp.isnan(cu_max) and np.isnan(sk_max))
def test_erfcinv_behavior(self, dtype):
a = cupy.empty((1,), dtype=dtype)
a[:] = 2.0 + 1E-6
a = cupyx.scipy.special.erfcinv(a)
assert cupy.isnan(a)
a[:] = 0.0 - 1E-6
a = cupyx.scipy.special.erfcinv(a)
assert cupy.isnan(a)
a[:] = 0.0
a = cupyx.scipy.special.erfcinv(a)
assert numpy.isposinf(cupy.asnumpy(a))
a[:] = 2.0
a = cupyx.scipy.special.erfcinv(a)
assert numpy.isneginf(cupy.asnumpy(a))
def __init__(self, env_arr, seed=300):
"""Initialize environment.
Pad env with NaN in every axis. It will help us to find neighbours of cells even if they are edges.
env should have 3 dimensions (XYZ).
{_agents_positions} is an array of current XYZ position for every agent.
{agents_state} is an array of agents states. 1 - live, 0 - dead
{is_available_env} - env-like boolean array, where True indicates free cell
:param env_arr: array of environment, where agents born. move and die.
"""
self._raw_env = env_arr
self.env = cp.pad(cp.array(env_arr).astype(cp.float),
1,
mode='constant',
constant_values=cp.NaN)
self.agents_state = None
self._agents_positions = None
self._agents_positions_all_time = []
self.is_available_env = ~cp.isnan(self.env)
self._rng = np.random.default_rng(seed)
np.random.seed(seed)
cp.random.seed(seed)
def indneutralize(y, X):
# 采用最小二乘法拟合
# 保证二者同维度
if X.shape[0] != y.shape[0]:
X = X.T
# 如果仍然不相等，那就报错
if X.shape[0] != y.shape[0]:
raise ValueError("X和y不同维度")
result = cp.zeros(len(y))
# index = cp.arange(len(y))
bool_y = cp.isnan(y) | cp.isinf(y)
# X中的每一行矩阵加和!=1 的地方
bool_X = ~(cp.abs(cp.sum(X, axis=1) - 1) < 0.000001)
bool_na = bool_y | bool_X
# used_index = index[~bool_na]
used_y = y[~bool_na]
used_X = X[~bool_na]
b = cp.linalg.inv(used_X.T.dot(used_X)).dot(used_X.T).dot(used_y)
pred_used_y = used_X.dot(b)
result[~bool_na] = used_y - pred_used_y
result[bool_na] = cp.nan
return result
def dumptomtrx(self):
amplifyfactor = 5
tilefactor = 0
inputdata = []
outputdata = []
for x in range(len(self.Board2Drops.getBoardslist())):
inputdata.append(self.Board2Drops.getBoardbyIndex(x))
droppoints = self.Board2Drops.getContainbyIndex(x)
windroppoints = droppoints[0]
losedroppoints = droppoints[1]
winboard = np.zeros(64)
loseboard = np.zeros(64)
for droppoint in windroppoints:
winboard[droppoint[0] * 8 + droppoint[1]] += 1
for droppoint in losedroppoints:
loseboard[droppoint[0] * 8 + droppoint[1]] += 1
finalboard = (winboard - loseboard /
(winboard + loseboard)) * amplifyfactor
where_are_NaNs = np.isnan(finalboard)
(finalboard)[where_are_NaNs] = tilefactor
outputdata.append(finalboard.tolist())
InputData = io.RAWWriter()
io.writeAMatrix(np.array(tuple(inputdata)), InputData)
InputData.write('in_policy.mtrx')
OutputData = io.RAWWriter()
io.writeAMatrix(np.array(tuple(outputdata)), OutputData)
OutputData.write('out_policy.mtrx')
def _check_mask(self, mask=None, require_mask=False):
"""Checks that the mask is:
* The same shape as the data
* Is an numpy ndarray (or subtype)
* Does not contain any NaN entrie
Parameters
----------
require_mask : bool (default : False)
"""
# Check that there is a mask if required
_use_mask = mask
if _use_mask is None:
_use_mask = self.mask
if require_mask and _use_mask is None:
raise ValueError("Expected a mask, but got nothing!")
# If we have a mask, check it
if _use_mask is not None:
# Check the mask inherets from an ndarray
if not isinstance(_use_mask, np.ndarray):
raise TypeError("mask is of type %s, " % type(_use_mask) +
"must be numpy.ndarray")
# Check if there is an nan-value in the mask
if np.isnan(np.sum(_use_mask)):
raise ValueError("NaNs in the data mask")
# Check the mask and the values have the same shape
if self.values.shape != _use_mask.shape:
raise ValueError("shape mismatch: dataframe.values.shape = %s"
% str(self.values.shape) + \
" but mask.shape = %s,"
% str(_use_mask.shape)) + \
"must identical"
def HaversineLocal(busMatrix, lineMatrix, haversine=True):
MatrizOnibus = cp.copy(busMatrix)
MatrizLinhas = cp.copy(lineMatrix)
MatrizLinhas = cp.dsplit(MatrizLinhas, 2)
MatrizOnibus = cp.dsplit(MatrizOnibus, 2)
infVector = cp.squeeze(cp.sum(cp.isnan(MatrizLinhas[0]), axis=1), axis=-1)
MatrizLinhas[0] = cp.expand_dims(MatrizLinhas[0], axis=-1)
MatrizLinhas[1] = cp.expand_dims(MatrizLinhas[1], axis=-1)
MatrizOnibus[0] = cp.expand_dims(MatrizOnibus[0], axis=-1)
MatrizOnibus[1] = cp.expand_dims(MatrizOnibus[1], axis=-1)
MatrizOnibus[0] *= cp.pi / 180
MatrizOnibus[1] *= cp.pi / 180
MatrizLinhas[1] = cp.transpose(MatrizLinhas[1], [2, 3, 0, 1]) * cp.pi / 180
MatrizLinhas[0] = cp.transpose(MatrizLinhas[0], [2, 3, 0, 1]) * cp.pi / 180
# Haversine or euclidian, based on <haversine>
if haversine:
results = 1000*2*6371.0088*cp.arcsin(
cp.sqrt(
(cp.sin((MatrizOnibus[0] - MatrizLinhas[0])*0.5)**2 + \
cp.cos(MatrizOnibus[0])* cp.cos(MatrizLinhas[0]) * cp.sin((MatrizOnibus[1] - MatrizLinhas[1])*0.5)**2)
))
else:
results = cp.sqrt((MatrizOnibus[0] - MatrizLinhas[0])**2 +
(MatrizOnibus[1] - MatrizLinhas[1])**2)
return results, infVector
def _index_or_values_interpolation(column, index=None):
"""
Interpolate over a float column. assumes a linear interpolation
strategy using the index of the data to denote spacing of the x
values. For example the data and index [1.0, NaN, 4.0], [1, 3, 4]
would result in [1.0, 3.0, 4.0]
"""
# figure out where the nans are
mask = cp.isnan(column)
# trivial cases, all nan or no nans
num_nan = mask.sum()
if num_nan == 0 or num_nan == len(column):
return column
to_interp = Frame(data={None: column}, index=index)
known_x_and_y = to_interp._apply_boolean_mask(as_column(~mask))
known_x = known_x_and_y._index._column.values
known_y = known_x_and_y._data.columns[0].values
result = cp.interp(to_interp._index.values, known_x, known_y)
# find the first nan
first_nan_idx = (mask == 0).argmax().item()
result[:first_nan_idx] = np.nan
return result
def test_percentile_memory_access(self, dtype):
# Create an allocator that guarantees array allocated in
# cupy.percentile call will be followed by a NaN
original_allocator = cuda.get_allocator()
def controlled_allocator(size):
memptr = original_allocator(size)
base_size = memptr.mem.size
assert base_size % 512 == 0
item_size = dtype().itemsize
shape = (base_size // item_size, )
x = cupy.ndarray(memptr=memptr, shape=shape, dtype=dtype)
x.fill(cupy.nan)
return memptr
# Check that percentile still returns non-NaN results
a = testing.shaped_random((5, ), cupy, dtype)
q = cupy.array((0, 100), dtype=dtype)
cuda.set_allocator(controlled_allocator)
try:
percentiles = cupy.percentile(a, q, axis=None, method='linear')
finally:
cuda.set_allocator(original_allocator)
assert not cupy.any(cupy.isnan(percentiles))
def sinhm(arr):
"""Hyperbolic Sine calculation for a given nXn matrix
Args:
arr(cupy.ndarray) :
Square matrix with dimension nXn.
Returns:
(cupy.ndarray):
Hyperbolic sine of given square matrix as input.
..seealso:: :func: 'scipy.linalg.sinhm'
"""
arr = cupy.array(arr)
# Checking whether the input is a 2D matrix or not
if (len(arr.shape) != 2):
raise ValueError("Dimensions of matrix should be 2")
# Checking whether the input matrix is square matrix or not
if (arr.shape[0] != arr.shape[1]):
raise ValueError("Input matrix should be a square matrix")
# Checking whether the input matrix elements are nan or not
if (cupy.isnan(cupy.cumsum(arr)[2 * arr.shape[0] - 1])):
raise ValueError("Input matrix elements cannot be nan")
# Checking whether the input matrix elements are infinity or not
if (cupy.isinf(cupy.cumsum(arr)[2 * arr.shape[0] - 1])):
raise ValueError("Input matrix elements cannot be infinity")
return 0.5 * (cupy.exp(arr) - cupy.exp(-1 * arr))
def jitter(raster, window):
ntrials, nbins = raster.shape
# if needed, pad to be divisible by window
if nbins % window:
pad = cp.zeros((ntrials, -nbins % window))
raster = cp.concatenate([raster, pad], axis=1)
nbins_rounded = raster.shape[1]
n_jitter_bins = nbins_rounded // window
# get psth
psth = raster.mean(axis=0)
# bin over window and sum
raster_binned = cp.reshape(raster, (ntrials, window, n_jitter_bins)).sum(axis=1)
psth_binned = cp.reshape(psth, (window, n_jitter_bins)).sum(axis=0)
# determine correction
correction = raster_binned / cp.expand_dims(psth_binned, 0)
correction = cp.tile(cp.expand_dims(correction, 1), [1, window, 1])
correction = cp.reshape(correction, (ntrials, nbins_rounded))
# apply correction
raster_jittered = cp.expand_dims(psth, 0) * correction
# trim off padding
raster_jittered = raster_jittered[:, :nbins]
raster_jittered[cp.isnan(raster_jittered)] = 0
return raster_jittered
def _min_or_max_axis(X, axis, min_or_max):
N = X.shape[axis]
if N == 0:
raise ValueError("zero-size array to reduction operation")
M = X.shape[1 - axis]
mat = X.tocsc() if axis == 0 else X.tocsr()
mat.sum_duplicates()
major_index, value = _minor_reduce(mat, min_or_max)
not_full = np.diff(mat.indptr)[major_index] < N
if 'min' in min_or_max:
fminmax = np.fmin
else:
fminmax = np.fmax
is_nan = np.isnan(value)
value[not_full] = fminmax(value[not_full], 0)
if 'nan' not in min_or_max:
value[is_nan] = np.nan
mask = value != 0
major_index = np.compress(mask, major_index)
value = np.compress(mask, value)
if axis == 0:
res = gpu_sp.coo_matrix((value, (np.zeros(len(value)), major_index)),
dtype=X.dtype,
shape=(1, M))
else:
res = gpu_sp.coo_matrix((value, (major_index, np.zeros(len(value)))),
dtype=X.dtype,
shape=(M, 1))
return res.A.ravel()
def weighted_avg_and_std(values, axis, weights):
"""Returns the weighted average and standard deviation.
Parameters
---------
values : array
Data array of shape (time, variables).
axis : int
Axis to average/std about
weights : array
Weight array of shape (time, variables).
Returns
-------
(average, std) : tuple of arrays
Tuple of weighted average and standard deviation along axis.
"""
values[np.isnan(values)] = 0.
average = np.ma.average(values, axis=axis, weights=weights)
variance = np.sum(weights * (values - np.expand_dims(average, axis))**2,
axis=axis) / weights.sum(axis=axis)
return (average, np.sqrt(variance))
def calc_cc(vol1, vol2, intrad, num_bins, mask=None):
'''Calculate CC as a function of binned radius'''
v1v2 = np.zeros(num_bins)
v1v1 = np.zeros(num_bins)
v2v2 = np.zeros(num_bins)
if mask is None:
mask = ~(np.isnan(vol1) | np.isnan(vol2))
scatter_add(v1v2, intrad[mask], vol1[mask] * vol2[mask])
scatter_add(v1v1, intrad[mask], vol1[mask]**2)
scatter_add(v2v2, intrad[mask], vol2[mask]**2)
denr = v1v1 * v2v2
sel = (denr > 0)
v1v2[sel] /= np.sqrt(denr[sel])
return v1v2
def transform(self, X):
"""[summary].
Args:
X (cupy.ndarray): [description].
Returns:
cupy.ndarray: [description].
"""
check_is_fitted(self, "class_means_")
# TODO(smly):
# X = column_or_1d(X, warn=True)
# Label encoding if necessary
if self._label_encoding_uniques is not None:
X = self._label_encoding_uniques.get_indexer(X.to_pandas())
X = cupy.asarray(X)
missing_mask = cupy.isnan(X)
encode_mask = cupy.invert(missing_mask)
unseen_mask = cupy.bitwise_xor(
cupy.isin(X, self.classes_, invert=True), missing_mask)
X = X.copy()
X[unseen_mask] = cupy.max(self.classes_)
indices = _get_index_cupy(self.classes_, X[encode_mask])
_classes_index_list = cupy.searchsorted(self.lut_[:, 0], self.classes_)
encoded_values = cupy.zeros(X.shape[0], dtype=cupy.float32)
encoded_values[encode_mask] = cupy.take(
self.lut_[:, 1], cupy.take(_classes_index_list, indices))
encoded_values[unseen_mask] = self.default_unseen_
return encoded_values
def calc_stc(cum, gpu=False):
"""
Calculate STC (spatio-temporal consistensy; Hanssen et al., 2008,
Terrafirma) of time series of displacement.
Note that isolated pixels (which have no surrounding pixel) have nan of STC.
Input:
cum : Cumulative displacement (n_im, length, width)
gpu : GPU flag
Return:
stc : STC (length, width)
"""
if gpu:
import cupy as xp
cum = xp.asarray(cum)
else:
xp = np
n_im, length, width = cum.shape
### Add 1 pixel margin to cum data filled with nan
cum1 = xp.ones((n_im, length + 2, width + 2), dtype=xp.float32) * xp.nan
cum1[:, 1:length + 1, 1:width + 1] = cum
### Calc STC for surrounding 8 pixels
_stc = xp.ones((length, width, 8), dtype=xp.float32) * xp.nan
pixels = [[0, 0], [0, 1], [0, 2], [1, 0], [1, 2], [2, 0], [2, 1], [2, 2]]
## Left Top = [0, 0], Rigth Bottmon = [2, 2], Center = [1, 1]
for i, pixel in enumerate(pixels):
### Spatial difference (surrounding pixel-center)
d_cum = cum1[:, pixel[0]:length + pixel[0], pixel[1]:width +
pixel[1]] - cum1[:, 1:length + 1, 1:width + 1]
### Temporal difference (double difference)
dd_cum = d_cum[:-1, :, :] - d_cum[1:, :, :]
### STC (i.e., RMS of DD)
sumsq_dd_cum = xp.nansum(dd_cum**2, axis=0)
n_dd_cum = (xp.sum(~xp.isnan(dd_cum),
axis=0)).astype(xp.float32) #nof non-nan
n_dd_cum[n_dd_cum == 0] = xp.nan #to avoid 0 division
_stc[:, :, i] = xp.sqrt(sumsq_dd_cum / n_dd_cum)
### Strange but some adjacent pixels can have identical time series,
### resulting in 0 of stc. To avoid this, replace 0 with nan.
_stc[_stc == 0] = xp.nan
### Identify minimum value as final STC
with warnings.catch_warnings(): ## To silence warning by All-Nan slice
warnings.simplefilter('ignore', RuntimeWarning)
stc = xp.nanmin(_stc, axis=2)
if gpu:
stc = xp.asnumpy(stc)
del cum, cum1, _stc, d_cum, dd_cum, sumsq_dd_cum, n_dd_cum
return stc
def test_niblack_sauvola_pathological_image():
# For certain values, floating point error can cause
# E(X^2) - (E(X))^2 to be negative, and taking the square root of this
# resulted in NaNs. Here we check that these are safely caught.
# see https://github.com/scikit-image/scikit-image/issues/3007
value = 0.03082192 + 2.19178082e-09
src_img = cp.full((4, 4), value).astype(cp.float64)
assert not cp.any(cp.isnan(threshold_niblack(src_img)))
def check_not_all_nans(series):
"""
Description:
return True if length of series without NaN is greater than 0
"""
if series.dtype not in CUDF_DATETIME_TYPES:
return not all(cp.isnan(series))
return True
def eval_pdf_multi(self, x_kj, systs=None, kernel_2d=False, get=True):
'''
Evaluates the signal's normalized PDF at a list-like series of points.
If CuPy is present on the system, a CUDA kernel will be used to run this
calculation on the default GPU. (See: KernelDensityPDF._kdpdf1_multi)
'''
if systs is None:
t_ij, h_ij, w_i = self.t_ij, self.h_ij, self.w_i
else:
t_ij, h_ij, w_i = systs
x_kj = cp.asarray(x_kj)
norm = cp.asarray(self._normalization(t_ij=t_ij, h_ij=h_ij, w_i=w_i))
if np == cp:
return np.asarray([
KernelDensityPDF._kdpdf1(x_j, t_ij, h_ij, w_i) for x_j in x_kj
]) / norm
else:
if kernel_2d: # faster for fewer points, i*k memory requirements
pdf_ki = cp.empty((x_kj.shape[0], t_ij.shape[0]))
block_size = 32
k_grid_size = pdf_ki.shape[0] // block_size + 1
i_grid_size = pdf_ki.shape[1] // block_size + 1
KernelDensityPDF._kdpdf1_ki(
(k_grid_size, i_grid_size), (block_size, block_size),
(x_kj, t_ij, h_ij, w_i, t_ij.shape[0], t_ij.shape[1],
x_kj.shape[0], pdf_ki))
pdf_k = cp.sum(pdf_ki, axis=1)
pdf_k = pdf_k / cp.sum(self.w_i) / norm
return pdf_k.get() if get else pdf_k
else:
pdf_k = cp.empty(x_kj.shape[0])
block_size = 64
grid_size = x_kj.shape[0] // block_size + 1
KernelDensityPDF._kdpdf1_k(
(grid_size, ), (block_size, ),
(x_kj, t_ij, h_ij, w_i, t_ij.shape[0], t_ij.shape[1],
x_kj.shape[0], pdf_k))
pdf_k = pdf_k / cp.sum(self.w_i) / norm
if cp.any(cp.isnan(pdf_k)):
print('w_i sum:', cp.sum(self.w_i), 'norm:', norm)
print('t_ij nan:', t_ij[cp.isnan(t_ij)])
print('h_ij nan:', h_ij[cp.isnan(h_ij)])
print('h_ij zero:', h_ij[h_ij == 0])
raise Exception('NaN value probability in ' + self.name)
return pdf_k.get() if get else pdf_k
def test_min_max_axis(failure_logger, sparse_random_dataset, axis, ignore_nan):
_, X, X_sparse_np, X_sparse = sparse_random_dataset
X_sparse[0, 0] = np.nan
X_sparse_np[0, 0] = np.nan
cu_min, cu_max = cu_min_max_axis(X_sparse, axis=axis,
ignore_nan=ignore_nan)
sk_min, sk_max = sk_min_max_axis(X_sparse_np, axis=axis,
ignore_nan=ignore_nan)
if axis is not None:
assert_allclose(cu_min, sk_min)
assert_allclose(cu_max, sk_max)
else:
assert cu_min == sk_min or (cp.isnan(cu_min) and np.isnan(sk_min))
assert cu_max == sk_max or (cp.isnan(cu_max) and np.isnan(sk_max))
with pytest.raises(Exception):
cu_min_max_axis(X, axis=axis, ignore_nan=ignore_nan)
def __lioness_loop(self):
"""
Description:
Initialize instance of Lioness class and load data.
Outputs:
self.total_lioness_network: An edge-by-sample matrix containing sample-specific networks.
"""
for i in self.indexes:
print("Running LIONESS for sample %d:" % (i+1))
idx = [x for x in range(self.n_conditions) if x != i] # all samples except i
with Timer("Computing coexpression network:"):
if self.computing=='gpu':
import cupy as cp
correlation_matrix = cp.corrcoef(self.expression_matrix[:, idx])
if cp.isnan(correlation_matrix).any():
cp.fill_diagonal(correlation_matrix, 1)
correlation_matrix = cp.nan_to_num(correlation_matrix)
correlation_matrix=cp.asnumpy(correlation_matrix)
else:
correlation_matrix = np.corrcoef(self.expression_matrix[:, idx])
if np.isnan(correlation_matrix).any():
np.fill_diagonal(correlation_matrix, 1)
correlation_matrix = np.nan_to_num(correlation_matrix)
with Timer("Normalizing networks:"):
correlation_matrix_orig = correlation_matrix # save matrix before normalization
correlation_matrix = self._normalize_network(correlation_matrix)
with Timer("Inferring LIONESS network:"):
if self.motif_matrix is not None:
del correlation_matrix_orig
subset_panda_network = self.panda_loop(correlation_matrix, np.copy(self.motif_matrix), np.copy(self.ppi_matrix),self.computing)
else:
del correlation_matrix
subset_panda_network = correlation_matrix_orig
lioness_network = self.n_conditions * (self.network - subset_panda_network) + subset_panda_network
with Timer("Saving LIONESS network %d to %s using %s format:" % (i+1, self.save_dir, self.save_fmt)):
path = os.path.join(self.save_dir, "lioness.%d.%s" % (i+1, self.save_fmt))
if self.save_fmt == 'txt':
np.savetxt(path, lioness_network)
elif self.save_fmt == 'npy':
np.save(path, lioness_network)
elif self.save_fmt == 'mat':
from scipy.io import savemat
savemat(path, {'PredNet': lioness_network})
else:
print("Unknown format %s! Use npy format instead." % self.save_fmt)
np.save(path, lioness_network)
if i == 0:
self.total_lioness_network = np.fromstring(np.transpose(lioness_network).tostring(),dtype=lioness_network.dtype)
else:
self.total_lioness_network=np.column_stack((self.total_lioness_network ,np.fromstring(np.transpose(lioness_network).tostring(),dtype=lioness_network.dtype)))
return self.total_lioness_network
def isnan(x: Array, /) -> Array:
"""
Array API compatible wrapper for :py:func:`np.isnan <numpy.isnan>`.
See its docstring for more information.
"""
if x.dtype not in _numeric_dtypes:
raise TypeError("Only numeric dtypes are allowed in isnan")
return Array._new(np.isnan(x._array))
def _cholesky(B):
"""
Wrapper around `cupy.linalg.cholesky` that raises LinAlgError if there are
NaNs in the output
"""
R = cupy.linalg.cholesky(B)
if cupy.any(cupy.isnan(R)):
raise numpy.linalg.LinAlgError
return R
def main():
'''CLI entry point. Also shows usage pattern'''
parser = argparse.ArgumentParser(description='CC vs radius/q calculator')
parser.add_argument('volume1', help='Path to first volume ccp4 map')
parser.add_argument('volume2', help='Path to second volume ccp4 map')
parser.add_argument('-r',
'--res_edge',
help='Resolution at center-edge in A',
type=float,
default=-1.)
parser.add_argument('-b',
'--bin_size',
help='Radial bin size in voxels. Default: 1',
type=int,
default=1)
parser.add_argument('-o',
'--out_fname',
help='Path to output file. Default: cc.dat',
default='cc.dat')
args = parser.parse_args()
with h5py.File(args.volume1, 'r') as fptr:
vol1 = np.array(fptr['diff_intens'][:])
with h5py.File(args.volume2, 'r') as fptr:
vol2 = np.array(fptr['diff_intens'][:])
mask = ~(np.isnan(vol1) | np.isnan(vol2))
assert vol1.shape == vol2.shape
size = vol1.shape[-1]
rbin = calc_rad(size, args.bin_size)
num_bins = int(rbin.max() + 1)
subtract_radavg(vol1, rbin, num_bins, mask)
subtract_radavg(vol2, rbin, num_bins, mask)
cc = calc_cc(vol1, vol2, rbin, num_bins, mask)
if args.res_edge > 0.:
cen = size // 2
q = np.arange(num_bins) * args.bin_size / cen / args.res_edge
else:
q = None
save_to_file(args.out_fname, cc, q)
def _masked_column_mean(arr, masked_value):
"""Compute the mean of each column in the 2D array arr, ignoring any
instances of masked_value"""
mask = _get_mask(arr, masked_value)
count_missing_values = mask.sum(axis=0)
n_elems = arr.shape[0] - count_missing_values
mean = cp.nansum(arr, axis=0)
if not cp.isnan(masked_value):
mean -= (count_missing_values * masked_value)
mean /= n_elems
return mean
def step(self, model, step_num):
# expected signal
self.y_expected = signal.get_signal_gpu(model.solution,
model.detector_geometry)
# multiplication
self.mult = cp.divide(self.w_det, self.y_expected)
self.mult = cp.where(cp.isnan(self.mult), 0, self.mult)
self.mult = cp.sum(self.mult, axis=-1)
self.mult /= self.wi
# find delta
model.solution = model.solution * self.mult
def _zdivide(x, y):
"""Patched version of :func:`sporco.linalg.zdivide`."""
div = x / y
div[cp.logical_or(cp.isnan(div), cp.isinf(div))] = 0
return div
