def pseudotime_analysis(self, vlm, figsize=(9,9), dpi=100):
nn = NearestNeighbors(50)
nn.fit(ind4.pcs[:,:4])
knn_pca = nn.kneighbors_graph(mode='distance')
knn_pca = knn_pca.tocoo()
G = igraph.Graph(list(zip(knn_pca.row, knn_pca.col)), directed=False, edge_attrs={'weight': knn_pca.data})
VxCl = G.community_multilevel(return_levels=False, weights="weight")
labels = np.array(VxCl.membership)
pc_obj = principal_curve(ind4.pcs[:,:4], False)
pc_obj.arclength = np.max(pc_obj.arclength) - pc_obj.arclength
labels = np.argsort(np.argsort(aggregate_np(labels, pc_obj.arclength, func=np.median)))[labels]
manual_annotation = {str(i):[i] for i in labels}
annotation_dict = {v:k for k, values in manual_annotation.items() for v in values }
clusters = np.array([annotation_dict[i] for i in labels])
colors20 = np.vstack((plt.cm.tab20b(np.linspace(0., 1, 20))[::2], plt.cm.tab20c(np.linspace(0, 1, 20))[1::2]))
vlm.set_clusters(clusters, cluster_colors_dict={k:colors20[v[0] % 20,:] for k,v in manual_annotation.items()})
k = 550
vlm.knn_imputation(n_pca_dims=n_comps,k=k, balanced=True,
b_sight=np.minimum(k*8, vlm.S.shape[1]-1),
b_maxl=np.minimum(k*4, vlm.S.shape[1]-1))
vlm.normalize_median()
vlm.fit_gammas(maxmin_perc=[2,95], limit_gamma=True)
vlm.normalize(which="imputed", size=False, log=True)
vlm.Pcs = np.array(vlm.pcs[:,:2], order="C")
vlm.predict_U()
vlm.calculate_velocity()
vlm.calculate_shift()
vlm.extrapolate_cell_at_t(delta_t=1)
vlm.estimate_transition_prob(hidim="Sx_sz", embed="Pcs", transform="log", psc=1,
n_neighbors=150, knn_random=True, sampled_fraction=1)
vlm.calculate_grid_arrows(smooth=0.9, steps=(25, 25), n_neighbors=200)
vlm.set_clusters(ind4.ca["ClusterName"])
plt.figure(None,figsize=figsize, dpi=dpi)
vlm.plot_grid_arrows(scatter_kwargs_dict={"alpha":0.7, "lw":0.7, "edgecolor":"0.4", "s":70, "rasterized":True},
min_mass=2.9, angles='xy', scale_units='xy',
headaxislength=2.75, headlength=5, headwidth=4.8, quiver_scale=0.35, scale_type="absolute")
plt.plot(pc_obj.projections[pc_obj.ixsort,0], pc_obj.projections[pc_obj.ixsort,1], c="w", lw=6, zorder=1000000)
plt.plot(pc_obj.projections[pc_obj.ixsort,0], pc_obj.projections[pc_obj.ixsort,1], c="k", lw=3, zorder=2000000)
plt.gca().invert_xaxis()
plt.axis("off")
plt.axis("equal");
def build_histogram(x_hist,
data_mat,
N_x_bins,
N_y_bins,
weighting_vec=1,
min_resp=None,
max_resp=None,
func=None,
debug=False,
*args,
**kwargs):
"""
Creates histogram for a single block of pixels
Parameters
----------
x_hist : 1D numpy array
bins for x-axis of 2d histogram
data_mat : numpy array
data to be binned for y-axis of 2d histogram
weighting_vec : 1D numpy array or float
weights. If setting all to one value, can be a scalar
N_x_bins : integer
number of bins in the x-direction
N_y_bins : integer
number of bins in the y-direction
min_resp : float
minimum value for y binning
max_resp : float
maximum value for y binning
func : function
function to be used to bin data_vec. All functions should take as input data_vec.
Arguments should be passed properly to func. This has not been heavily tested.
debug : bool, optional
If True, extra debugging statements are printed. Default False
Returns
-------
pixel_hist : 2D numpy array
contains the histogram of the input data
Apply func to input data, convert to 1D array, and normalize
"""
if func is not None:
y_hist = func(data_mat, *args, **kwargs)
else:
y_hist = data_mat
'''
Get the min_resp and max_resp from y_hist if they are none
'''
if min_resp is None:
min_resp = np.min(y_hist)
if max_resp is None:
max_resp = np.max(y_hist)
if debug:
print('min_resp', min_resp, 'max_resp', max_resp)
y_hist = __scale_and_discretize(y_hist, N_y_bins, max_resp, min_resp,
debug)
'''
Combine x_hist and y_hist into one matrix
'''
if debug:
print(np.shape(x_hist))
print(np.shape(y_hist))
try:
group_idx = np.zeros((2, x_hist.size), dtype=np.int32)
group_idx[0, :] = x_hist
group_idx[1, :] = y_hist
except:
raise
'''
Aggregate matrix for histogram of current chunk
'''
if debug:
print(np.shape(group_idx))
print(np.shape(weighting_vec))
print(N_x_bins, N_y_bins)
try:
if not disable_histogram:
pixel_hist = aggregate_np(group_idx,
weighting_vec,
func='sum',
size=(N_x_bins, N_y_bins),
dtype=np.int32)
else:
pixel_hist = None
except:
raise
return pixel_hist
def buildHistogram(x_hist,
data_mat,
N_x_bins,
N_y_bins,
weighting_vec=1,
min_resp=None,
max_resp=None,
func=None,
debug=False,
*args,
**kwargs):
'''
Creates histogram for a single block of pixels
Parameters:
-------------
x_hist : 1D numpy array
bins for x-axis of 2d histogram
data_mat : numpy array
data to be binned for y-axis of 2d histogram
weighting_vec : 1D numpy array or float
weights. If setting all to one value, can be a scalar
N_x_bins : integer
number of bins in the x-direction
N_y_bins : integer
number of bins in the y-direction
min_resp : float
minimum value for y binning
max_resp : float
maximum value for y binning
func : function
function to be used to bin data_vec. All functions should take as input data_vec.
Arguments should be passed properly to func. This has not been heavily tested.
Output:
--------------
pixel_hist : 2D numpy array
contains the histogram of the input data
Apply func to input data, convert to 1D array, and normalize
'''
if debug: print 'min_resp', min_resp, 'max_resp', max_resp
y_hist = data_mat
if func is not None:
y_hist = func(y_hist, *args, **kwargs)
y_hist = np.squeeze(np.reshape(y_hist, (data_mat.size, 1)))
y_hist = np.clip(y_hist, min_resp, max_resp, y_hist)
y_hist = y_hist - min_resp
y_hist = y_hist / (max_resp - min_resp)
'''
Descritize y_hist
'''
y_hist = np.rint(y_hist * (N_y_bins - 1))
if debug: print 'ymin', min(y_hist), 'ymax', max(y_hist)
'''
Combine x_hist and y_hist into one matrix
'''
if debug:
print np.shape(x_hist)
print np.shape(y_hist)
try:
group_idx = np.zeros((2, x_hist.size), dtype=np.int32)
group_idx[0, :] = x_hist
group_idx[1, :] = y_hist
except:
raise
'''
Aggregate matrix for histogram of current chunk
'''
if debug:
print np.shape(group_idx)
print np.shape(weighting_vec)
print N_x_bins, N_y_bins
try:
pixel_hist = npg.aggregate_np(group_idx,
weighting_vec,
func='sum',
size=(N_x_bins, N_y_bins),
dtype=np.int32)
except:
raise
return pixel_hist
def aggregate_group_loop(*args, **kwargs):
"""wraps func in lambda which prevents aggregate_numpy from
recognising and optimising it. Instead it groups and loops."""
func = kwargs['func']
del kwargs['func']
return aggregate_np(*args, func=lambda x: func(x), **kwargs)
"""wraps func in lambda which prevents aggregate_numpy from
recognising and optimising it. Instead it groups and loops."""
func = kwargs['func']
del kwargs['func']
return aggregate_np(*args, func=lambda x: func(x), **kwargs)
print("TODO: use more extensive tests")
print("")
print("-----simple examples----------")
test_a = np.array([12.0, 3.2, -15, 88, 12.9])
test_group_idx = np.array([1, 0, 1, 4, 1 ])
print("test_a: ", test_a)
print("test_group_idx: ", test_group_idx)
print("aggregate(test_group_idx, test_a):")
print(aggregate_np(test_group_idx, test_a)) # group vals by idx and sum
# array([3.2, 9.9, 0., 0., 88.])
print("aggregate(test_group_idx, test_a, sz=8, func='min', fill_value=np.nan):")
print(aggregate_np(test_group_idx, test_a, size=8, func='min', fill_value=np.nan))
# array([3.2, -15., nan, 88., nan, nan, nan, nan])
print("aggregate(test_group_idx, test_a, sz=5, func=lambda x: ' + '.join(str(xx) for xx in x),fill_value='')")
print(aggregate_np(test_group_idx, test_a, size=5, func=lambda x: ' + '.join(str(xx) for xx in x), fill_value=''))
print("")
print("---------testing--------------")
print("compare against group-and-loop with numpy")
testable_funcs = {aliasing[f]: f for f in (np.sum, np.prod, np.any, np.all, np.min, np.max, np.std, np.var, np.mean)}
test_group_idx = np.random.randint(0, int(1e3), int(1e5))
test_a = np.random.rand(int(1e5)) * 100 - 50
test_a[test_a > 25] = 0 # for use with bool functions
if pca:
results.PCs = np.array(xr) #only the used components
return results
nn = NearestNeighbors(50)
nn.fit(ind_pseudotime.pcs[:,:4])
knn_pca = nn.kneighbors_graph(mode='distance')
knn_pca = knn_pca.tocoo()
G = igraph.Graph(list(zip(knn_pca.row, knn_pca.col)), directed=False, edge_attrs={'weight': knn_pca.data})
VxCl = G.community_multilevel(return_levels=False, weights="weight")
labels = np.array(VxCl.membership)
pc_obj = principal_curve(ind_pseudotime.pcs[:,:4], False)
pc_obj.arclength = np.max(pc_obj.arclength) - pc_obj.arclength
labels = np.argsort(np.argsort(aggregate_np(labels, pc_obj.arclength, func=np.median)))[labels]
manual_annotation = {str(i):[i] for i in labels}
annotation_dict = {v:k for k, values in manual_annotation.items() for v in values }
clusters = np.array([annotation_dict[i] for i in labels])
colors20 = np.vstack((plt.cm.tab20b(np.linspace(0., 1, 20))[::2], plt.cm.tab20c(np.linspace(0, 1, 20))[1::2]))
#ind_pseudotime.set_clusters(clusters, cluster_colors_dict={k:colors20[v[0] % 20,:] for k,v in manual_annotation.items()})
ind_pseudotime.set_clusters(ind_pseudotime.ca["ClusterName"])
k = 550
ind_pseudotime.knn_imputation(n_pca_dims=n_comps,k=k, balanced=True,
b_sight=np.minimum(k*8, ind_pseudotime.S.shape[1]-1),
b_maxl=np.minimum(k*4, ind_pseudotime.S.shape[1]-1))
ind_pseudotime.normalize_median()
ind_pseudotime.fit_gammas(maxmin_perc=[2,95], limit_gamma=True)
def build_histogram(x_hist, data_mat, N_x_bins, N_y_bins, weighting_vec=1, min_resp=None, max_resp=None, func=None,
debug=False, *args, **kwargs):
"""
Creates histogram for a single block of pixels
Parameters
----------
x_hist : 1D numpy array
bins for x-axis of 2d histogram
data_mat : numpy array
data to be binned for y-axis of 2d histogram
weighting_vec : 1D numpy array or float
weights. If setting all to one value, can be a scalar
N_x_bins : integer
number of bins in the x-direction
N_y_bins : integer
number of bins in the y-direction
min_resp : float
minimum value for y binning
max_resp : float
maximum value for y binning
func : function
function to be used to bin data_vec. All functions should take as input data_vec.
Arguments should be passed properly to func. This has not been heavily tested.
debug : bool, optional
If True, extra debugging statements are printed. Default False
Returns
-------
pixel_hist : 2D numpy array
contains the histogram of the input data
Apply func to input data, convert to 1D array, and normalize
"""
if func is not None:
y_hist = func(data_mat, *args, **kwargs)
else:
y_hist = data_mat
'''
Get the min_resp and max_resp from y_hist if they are none
'''
if min_resp is None:
min_resp = np.min(y_hist)
if max_resp is None:
max_resp = np.max(y_hist)
if debug:
print('min_resp', min_resp, 'max_resp', max_resp)
y_hist = __scale_and_discretize(y_hist, N_y_bins, max_resp, min_resp, debug)
'''
Combine x_hist and y_hist into one matrix
'''
if debug:
print(np.shape(x_hist))
print(np.shape(y_hist))
try:
group_idx = np.zeros((2, x_hist.size), dtype=np.int32)
group_idx[0, :] = x_hist
group_idx[1, :] = y_hist
except:
raise
'''
Aggregate matrix for histogram of current chunk
'''
if debug:
print(np.shape(group_idx))
print(np.shape(weighting_vec))
print(N_x_bins, N_y_bins)
try:
if not disable_histogram:
pixel_hist = aggregate_np(group_idx, weighting_vec, func='sum', size=(N_x_bins, N_y_bins), dtype=np.int32)
else:
pixel_hist = None
except:
raise
return pixel_hist