def analyze_distances(self, params, pdb_hierarchy=None, log=sys.stdout):
assert 0 # Not used anywhere?
atoms = None
if params.verbose:
assert pdb_hierarchy is not None
atoms = pdb_hierarchy.atoms()
remove_outliers = params.secondary_structure.protein.remove_outliers
atoms = pdb_hierarchy.atoms()
hist = flex.histogram(self.bond_lengths, 10)
print >> log, " Distribution of hydrogen bond lengths without filtering:"
hist.show(f=log, prefix=" ", format_cutoffs="%.4f")
print >> log, ""
if not remove_outliers:
return False
for i, distance in enumerate(self.bond_lengths):
if distance > distance_max:
self.flag_use_bond[i] = False
if params.verbose:
print >> log, "Excluding H-bond with length %.3fA" % distance
i_seq, j_seq = self.bonds[i]
print >> log, " %s" % atoms[i_seq].fetch_labels().id_str()
print >> log, " %s" % atoms[j_seq].fetch_labels().id_str()
print >> log, " After filtering: %d bonds remaining." % \
self.flag_use_bond.count(True)
print >> log, " Distribution of hydrogen bond lengths after applying cutoff:"
hist = flex.histogram(self.bond_lengths.select(self.flag_use_bond), 10)
hist.show(f=log, prefix=" ", format_cutoffs="%.4f")
print >> log, ""
return True
def analyze_distances (self, params, pdb_hierarchy=None, log=sys.stdout) :
assert 0 # Not used anywhere?
atoms = None
if params.verbose :
assert pdb_hierarchy is not None
atoms = pdb_hierarchy.atoms()
remove_outliers = params.secondary_structure.protein.remove_outliers
atoms = pdb_hierarchy.atoms()
hist = flex.histogram(self.bond_lengths, 10)
print >> log, " Distribution of hydrogen bond lengths without filtering:"
hist.show(f=log, prefix=" ", format_cutoffs="%.4f")
print >> log, ""
if not remove_outliers :
return False
for i, distance in enumerate(self.bond_lengths) :
if distance > distance_max :
self.flag_use_bond[i] = False
if params.verbose :
print >> log, "Excluding H-bond with length %.3fA" % distance
i_seq, j_seq = self.bonds[i]
print >> log, " %s" % atoms[i_seq].fetch_labels().id_str()
print >> log, " %s" % atoms[j_seq].fetch_labels().id_str()
print >> log, " After filtering: %d bonds remaining." % \
self.flag_use_bond.count(True)
print >> log, " Distribution of hydrogen bond lengths after applying cutoff:"
hist = flex.histogram(self.bond_lengths.select(self.flag_use_bond), 10)
hist.show(f=log, prefix=" ", format_cutoffs="%.4f")
print >> log, ""
return True
def process_image(process):
import sys
last_update = start = timeit.default_timer()
i = process
if use_python_counter:
local_hist = Counter()
else:
local_hist = flex.histogram(flex.double(), data_min=0.0, data_max=histmax, n_slots=histbins)
max_images = image_count // nproc
if process >= image_count % nproc:
max_images += 1
while i < image_count:
data = read_cbf_image(image_list[i])
if not use_python_counter:
data = flex.histogram(data.as_double().as_1d(), data_min=0.0, data_max=histmax, n_slots=histbins)
local_hist.update(data)
i = i + nproc
if process == 0:
if timeit.default_timer() > (last_update + 3):
last_update = timeit.default_timer()
if sys.stdout.isatty():
sys.stdout.write('\033[A')
print 'Processed %d%% (%d seconds remain) ' % (100 * i // image_count, round((image_count - i) * (last_update - start) / (i+1)))
return local_hist
def get_map_histograms(data, n_slots=20, data_1=None, data_2=None):
h0, h1, h2 = None, None, None
data_min = None
hmhcc = None
if (data_1 is None):
h0 = flex.histogram(data=data.as_1d(), n_slots=n_slots)
else:
data_min = min(flex.min(data_1), flex.min(data_2))
data_max = max(flex.max(data_1), flex.max(data_2))
h0 = flex.histogram(data=data.as_1d(), n_slots=n_slots)
h1 = flex.histogram(data=data_1.as_1d(),
data_min=data_min,
data_max=data_max,
n_slots=n_slots)
h2 = flex.histogram(data=data_2.as_1d(),
data_min=data_min,
data_max=data_max,
n_slots=n_slots)
hmhcc = flex.linear_correlation(
x=h1.slots().as_double(), y=h2.slots().as_double()).coefficient()
return group_args(h_map=h0,
h_half_map_1=h1,
h_half_map_2=h2,
_data_min=data_min,
half_map_histogram_cc=hmhcc)
def process_image(process):
last_update = start = timeit.default_timer()
i = process
if use_python_counter:
local_hist = Counter()
else:
local_hist = flex.histogram(flex.double(),
data_min=0.0,
data_max=histmax,
n_slots=histbins)
max_images = image_count // nproc
if process >= image_count % nproc:
max_images += 1
while i < image_count:
data = read_cbf_image(image_list[i])
if not use_python_counter:
data = flex.histogram(data.as_double().as_1d(),
data_min=0.0,
data_max=histmax,
n_slots=histbins)
local_hist.update(data)
i = i + nproc
if process == 0:
if timeit.default_timer() > (last_update + 3):
last_update = timeit.default_timer()
if sys.stdout.isatty():
sys.stdout.write('\033[A')
print 'Processed %d%% (%d seconds remain) ' % (
100 * i // image_count,
round((image_count - i) * (last_update - start) /
(i + 1)))
return local_hist
def process_file(file_object, n_slots, data_min, data_max, format_cutoffs):
data = flex.double()
for line in file_object.read().splitlines():
data.append(float(line))
print "total number of data points:", data.size()
if (data_min is None): data_min = flex.min(data)
if (data_max is None): data_max = flex.max(data)
flex.histogram(
data=data, n_slots=n_slots, data_min=data_min, data_max=data_max).show(
format_cutoffs=format_cutoffs)
def process_file(file_object, n_slots, data_min, data_max, format_cutoffs):
data = flex.double()
for line in file_object.read().splitlines():
data.append(float(line))
print("total number of data points:", data.size())
if (data_min is None): data_min = flex.min(data)
if (data_max is None): data_max = flex.max(data)
flex.histogram(
data=data, n_slots=n_slots, data_min=data_min, data_max=data_max).show(
format_cutoffs=format_cutoffs)
def plot_centroid_weights_histograms(reflections, n_slots=50):
from matplotlib import pyplot
from scitbx.array_family import flex
variances = flex.vec3_double([r.centroid_variance for r in reflections])
vx, vy, vz = variances.parts()
idx = (vx > 0).__and__(vy > 0).__and__(vz > 0)
vx = vx.select(idx)
vy = vy.select(idx)
vz = vz.select(idx)
wx = 1 / vx
wy = 1 / vy
wz = 1 / vz
wx = flex.log(wx)
wy = flex.log(wy)
wz = flex.log(wz)
hx = flex.histogram(wx, n_slots=n_slots)
hy = flex.histogram(wy, n_slots=n_slots)
hz = flex.histogram(wz, n_slots=n_slots)
fig = pyplot.figure()
idx2 = flex.max_index(wx)
idx3 = flex.int(range(len(reflections))).select(idx)[idx2]
print(reflections[idx3])
return
# outliers = reflections.select(wx > 50)
# for refl in outliers:
# print refl
for i, h in enumerate([hx, hy, hz]):
ax = fig.add_subplot(311 + i)
slots = h.slots().as_double()
bins, data = hist_outline(h)
log_scale = True
if log_scale:
data.set_selected(
data == 0, 0.1
) # otherwise lines don't get drawn when we have some empty bins
ax.set_yscale("log")
ax.plot(bins, data, "-k", linewidth=2)
# pyplot.suptitle(title)
data_min = min(
[slot.low_cutoff for slot in h.slot_infos() if slot.n > 0])
data_max = max(
[slot.low_cutoff for slot in h.slot_infos() if slot.n > 0])
ax.set_xlim(data_min, data_max + h.slot_width())
pyplot.show()
def build_hist():
from scitbx.array_family import flex
if len(sys.argv) == 2 and sys.argv[1].endswith('.json'):
from dxtbx import datablock
db = datablock.DataBlockFactory.from_json_file(sys.argv[1])[0]
image_list = db.extract_imagesets()[0].paths()
else:
image_list = sys.argv[1:]
image_count = len(image_list)
# Faster, yet still less than ideal and wasting a lot of resources.
limit = get_overload(image_list[0])
binfactor = 5 # register up to 500% counts
histmax = (limit * binfactor) + 0.0
histbins = (limit * binfactor) + 1
hist = flex.histogram(flex.double(), data_min=0.0, data_max=histmax, n_slots=histbins)
print "Processing %d images" % image_count
start = timeit.default_timer()
last_update = start
# image_maxima = [None] * image_count
for i in range(image_count):
data = read_cbf_image(image_list[i])
tmp_hist = flex.histogram(data.as_double().as_1d(), data_min=0.0, data_max=histmax, n_slots=histbins)
# image_max = histmax
# for b in reversed(tmp_hist.slots()):
# if b != 0:
# image_maxima[i] = int(image_max)
# break
# image_max -= 1
hist.update(tmp_hist)
if timeit.default_timer() > (last_update + 3):
last_update = timeit.default_timer()
if sys.stdout.isatty():
sys.stdout.write('\033[A')
print 'Processed %d of %d images (%d seconds remain) ' % (i+1, image_count, round((image_count - i) * (last_update - start) / (i+1)))
# print image_maxima
results = { 'scale_factor': 1 / limit,
'bin_count': histbins,
'bins': list(hist.slots()),
'image_files': image_list }
print "Writing results to overload.json"
with open('overload.json', 'w') as fh:
json.dump(results, fh)
def plot_number_of_crystals(experiments):
image_to_expts = {}
for expt in experiments:
img = expt.imageset.get_image_identifier(0)
image_to_expts.setdefault(img, [])
image_to_expts[img].append(expt)
n_crystals_per_image = flex.int(len(expts) for expts in image_to_expts.values())
nmax = flex.max(n_crystals_per_image)
hist = flex.histogram(n_crystals_per_image.as_double(), 0, nmax, n_slots=nmax)
# hist.show()
from matplotlib import pyplot as plt
plt.style.use("ggplot")
plt.bar(
hist.slot_centers(),
hist.slots(),
align="center",
width=hist.slot_width(),
zorder=10,
color="black",
edgecolor=None,
)
plt.savefig("n_crystals_hist.png")
plt.clf()
def filter_histogram_of_key_value(database_dict,
key,
max_reject_fraction,
edge_tolerance_small=1.e-4,
n_slots=3):
values = database_dict[key]
new_values = convert_to_numeric(values=values)
#print flex.min(new_values), flex.max(new_values)
size = new_values.size()
#print size
if (size == 0): return
while True:
values = database_dict[key]
new_values = convert_to_numeric(values=values)
selection = flex.bool(new_values.size(), True)
histogram = flex.histogram(data=new_values, n_slots=n_slots)
l = histogram.data_min()
for i, s in enumerate(histogram.slots()):
r = histogram.data_min() + histogram.slot_width() * (i + 1)
r = r + edge_tolerance_small
l = max(0, l - edge_tolerance_small)
#print "%8.4f %8.4f %d" % (l, r, s)
if (s < size * max_reject_fraction):
selection &= ~((new_values >= l) & (new_values <= r))
l = r
#print
leave, remove = selection.count(True), selection.count(False)
#print leave, remove
if (remove == 0): break
if (size - leave > int(size * max_reject_fraction)): break
database_dict = select_dict(database_dict=database_dict,
selection=selection)
return database_dict
def show(self,
sites_cart,
n_slots_difference_histogram=6,
out=None,
prefix=""):
if (out is None): out = sys.stdout
selection_strings = self.group.selection_strings
for i_op,pair,mx,rms in zip(
count(1),
self.group.selection_pairs,
self.matrices,
self.rms):
print >> out, prefix + "NCS operator %d:" % i_op
print >> out, prefix + " Reference selection:", \
show_string(selection_strings[0])
print >> out, prefix + " Other selection:", \
show_string(selection_strings[i_op])
print >> out, prefix + " Number of atom pairs:", len(pair[0])
print >> out, mx.r.mathematica_form(
label="Rotation", format="%.6g", one_row_per_line=True,
prefix=prefix+" ")
print >> out, mx.t.mathematica_form(
label="Translation", format="%.6g", prefix=prefix+" ")
x = sites_cart.select(pair[0])
y = mx * sites_cart.select(pair[1])
d_sq = (x-y).dot()
if (n_slots_difference_histogram is not None):
print >> out, prefix + " Histogram of differences:"
diff_histogram = flex.histogram(
data=flex.sqrt(d_sq), n_slots=n_slots_difference_histogram)
diff_histogram.show(
f=out, prefix=prefix+" ", format_cutoffs="%8.6f")
print >> out, \
prefix + " RMS difference with respect to the reference: %8.6f" %(rms)
def filter_histogram_of_key_value(database_dict, key, max_reject_fraction,
edge_tolerance_small = 1.e-4, n_slots = 3):
values = database_dict[key]
new_values = convert_to_numeric(values = values)
#print flex.min(new_values), flex.max(new_values)
size = new_values.size()
#print size
if(size == 0): return
while True:
values = database_dict[key]
new_values = convert_to_numeric(values = values)
selection = flex.bool(new_values.size(), True)
histogram = flex.histogram(data = new_values, n_slots = n_slots)
l = histogram.data_min()
for i, s in enumerate(histogram.slots()):
r = histogram.data_min() + histogram.slot_width() * (i+1)
r = r+edge_tolerance_small
l = max(0, l-edge_tolerance_small)
#print "%8.4f %8.4f %d" % (l, r, s)
if(s < size * max_reject_fraction):
selection &= ~((new_values >= l) & (new_values <= r))
l = r
#print
leave, remove = selection.count(True), selection.count(False)
#print leave, remove
if(remove == 0): break
if(size - leave > int(size * max_reject_fraction)): break
database_dict = select_dict(database_dict = database_dict,
selection = selection)
return database_dict
def show(self,
sites_cart,
n_slots_difference_histogram=6,
out=None,
prefix=""):
if (out is None): out = sys.stdout
selection_strings = self.group.selection_strings
for i_op, pair, mx, rms in zip(count(1), self.group.selection_pairs,
self.matrices, self.rms):
print >> out, prefix + "NCS operator %d:" % i_op
print >> out, prefix + " Reference selection:", \
show_string(selection_strings[0])
print >> out, prefix + " Other selection:", \
show_string(selection_strings[i_op])
print >> out, prefix + " Number of atom pairs:", len(pair[0])
print >> out, mx.r.mathematica_form(label="Rotation",
format="%.6g",
one_row_per_line=True,
prefix=prefix + " ")
print >> out, mx.t.mathematica_form(label="Translation",
format="%.6g",
prefix=prefix + " ")
x = sites_cart.select(pair[0])
y = mx * sites_cart.select(pair[1])
d_sq = (x - y).dot()
if (n_slots_difference_histogram is not None):
print >> out, prefix + " Histogram of differences:"
diff_histogram = flex.histogram(
data=flex.sqrt(d_sq), n_slots=n_slots_difference_histogram)
diff_histogram.show(f=out,
prefix=prefix + " ",
format_cutoffs="%8.6f")
print >> out, \
prefix + " RMS difference with respect to the reference: %8.6f" %(rms)
def get_mean_statistic_for_resolution (d_min, stat_type, range=0.2, out=None) :
if (out is None) :
out = sys.stdout
from scitbx.array_family import flex
pkl_file = libtbx.env.find_in_repositories(
relative_path = "chem_data/polygon_data/all_mvd.pickle",
test = os.path.isfile)
db = easy_pickle.load(pkl_file)
all_d_min = db['high_resolution']
stat_values = db[stat_type]
values_for_range = flex.double()
for (d_, v_) in zip(all_d_min, stat_values) :
try :
d = float(d_)
v = float(v_)
except ValueError : continue
else :
if (d > (d_min - range)) and (d < (d_min + range)) :
values_for_range.append(v)
h = flex.histogram(values_for_range, n_slots=10)
print >> out, " %s for d_min = %.3f - %.3f A" % (stat_names[stat_type], d_min-range,
d_min+range)
min = flex.min(values_for_range)
max = flex.max(values_for_range)
mean = flex.mean(values_for_range)
print >> out, " count: %d" % values_for_range.size()
print >> out, " min: %.2f" % min
print >> out, " max: %.2f" % max
print >> out, " mean: %.2f" % mean
print >> out, " histogram of values:"
h.show(prefix=" ")
return mean
def get_mean_statistic_for_resolution(d_min, stat_type, range=0.2, out=None):
if (out is None):
out = sys.stdout
from scitbx.array_family import flex
pkl_file = libtbx.env.find_in_repositories(
relative_path="chem_data/polygon_data/all_mvd.pickle",
test=os.path.isfile)
db = easy_pickle.load(pkl_file)
all_d_min = db['high_resolution']
stat_values = db[stat_type]
values_for_range = flex.double()
for (d_, v_) in zip(all_d_min, stat_values):
try:
d = float(d_)
v = float(v_)
except ValueError:
continue
else:
if (d > (d_min - range)) and (d < (d_min + range)):
values_for_range.append(v)
h = flex.histogram(values_for_range, n_slots=10)
print >> out, " %s for d_min = %.3f - %.3f A" % (
stat_names[stat_type], d_min - range, d_min + range)
min = flex.min(values_for_range)
max = flex.max(values_for_range)
mean = flex.mean(values_for_range)
print >> out, " count: %d" % values_for_range.size()
print >> out, " min: %.2f" % min
print >> out, " max: %.2f" % max
print >> out, " mean: %.2f" % mean
print >> out, " histogram of values:"
h.show(prefix=" ")
return mean
def get_map_histograms(data, n_slots=20, data_1=None, data_2=None):
h0, h1, h2 = None, None, None
data_min = None
if(data_1 is None):
h0 = flex.histogram(data = data.as_1d(), n_slots = n_slots)
else:
data_min = min(flex.min(data), flex.min(data_1), flex.min(data_2))
data_max = max(flex.max(data), flex.max(data_1), flex.max(data_2))
h0 = flex.histogram(data = data.as_1d(), data_min=data_min,
data_max=data_max, n_slots = n_slots)
h1 = flex.histogram(data = data_1.as_1d(), data_min=data_min,
data_max=data_max, n_slots = n_slots)
h2 = flex.histogram(data = data_2.as_1d(), data_min=data_min,
data_max=data_max, n_slots = n_slots)
return group_args(h_map = h0, h_half_map_1 = h1, h_half_map_2 = h2,
_data_min = data_min)
def run():
m = any_reflection_file(sys.argv[1]).file_content()
sg = m.space_group()
mi = m.extract_miller_indices()
mas = m.as_miller_arrays()
absent = flex.bool([sg.is_sys_absent(indx) for indx in mi])
intensities = None
for ma in mas:
if ma.is_xray_intensity_array():
intensities = ma
break
assert intensities, "intensity data not found in %s" % sys.argv[1]
print("Removing %d absent reflections" % absent.count(True))
intensities = intensities.select(~absent)
i_over_sig = intensities.data() / intensities.sigmas()
hist = flex.histogram(i_over_sig, n_slots=50)
print("I/sig(I) N")
for centre, value in zip(hist.slot_centers(), hist.slots()):
print("%5.1f %d" % (centre, value))
def blank_integrated_analysis(reflections, scan, phi_step, fractional_loss):
prf_sel = reflections.get_flags(reflections.flags.integrated_prf)
if prf_sel.count(True) > 0:
reflections = reflections.select(prf_sel)
intensities = reflections["intensity.prf.value"]
variances = reflections["intensity.prf.variance"]
else:
sum_sel = reflections.get_flags(reflections.flags.integrated_sum)
reflections = reflections.select(sum_sel)
intensities = reflections["intensity.sum.value"]
variances = reflections["intensity.sum.variance"]
i_sigi = intensities / flex.sqrt(variances)
xyz_px = reflections["xyzobs.px.value"]
x_px, y_px, z_px = xyz_px.parts()
phi = scan.get_angle_from_array_index(z_px)
osc = scan.get_oscillation()[1]
n_images_per_step = iceil(phi_step / osc)
phi_step = n_images_per_step * osc
phi_min = flex.min(phi)
phi_max = flex.max(phi)
n_steps = iceil((phi_max - phi_min) / phi_step)
hist = flex.histogram(z_px, n_slots=n_steps)
mean_i_sigi = flex.double()
for i, slot_info in enumerate(hist.slot_infos()):
sel = (z_px >= slot_info.low_cutoff) & (z_px < slot_info.high_cutoff)
if sel.count(True) == 0:
mean_i_sigi.append(0)
else:
mean_i_sigi.append(flex.mean(i_sigi.select(sel)))
fractional_mean_i_sigi = mean_i_sigi / flex.max(mean_i_sigi)
potential_blank_sel = mean_i_sigi <= (fractional_loss * flex.max(mean_i_sigi))
xmin, xmax = zip(*[(slot_info.low_cutoff, slot_info.high_cutoff) for slot_info in hist.slot_infos()])
d = {
"data": [
{
"x": list(hist.slot_centers()),
"y": list(mean_i_sigi),
"xlow": xmin,
"xhigh": xmax,
"blank": list(potential_blank_sel),
"type": "bar",
"name": "blank_counts_analysis",
}
],
"layout": {"xaxis": {"title": "z observed (images)"}, "yaxis": {"title": "Number of reflections"}, "bargap": 0},
}
blank_regions = blank_regions_from_sel(d["data"][0])
d["blank_regions"] = blank_regions
return d
def blank_counts_analysis(reflections, scan, phi_step, fractional_loss):
if not len(reflections):
raise Sorry("Input contains no reflections")
xyz_px = reflections["xyzobs.px.value"]
x_px, y_px, z_px = xyz_px.parts()
phi = scan.get_angle_from_array_index(z_px)
osc = scan.get_oscillation()[1]
n_images_per_step = iceil(phi_step / osc)
phi_step = n_images_per_step * osc
array_range = scan.get_array_range()
phi_min = scan.get_angle_from_array_index(array_range[0])
phi_max = scan.get_angle_from_array_index(array_range[1])
assert phi_min <= flex.min(phi)
assert phi_max >= flex.max(phi)
n_steps = int(round((phi_max - phi_min) / phi_step))
hist = flex.histogram(
z_px, data_min=array_range[0], data_max=array_range[1], n_slots=n_steps
)
logger.debug("Histogram:")
logger.debug(hist.as_str())
counts = hist.slots()
fractional_counts = counts.as_double() / flex.max(counts)
potential_blank_sel = fractional_counts <= fractional_loss
xmin, xmax = zip(
*[
(slot_info.low_cutoff, slot_info.high_cutoff)
for slot_info in hist.slot_infos()
]
)
d = {
"data": [
{
"x": list(hist.slot_centers()),
"y": list(hist.slots()),
"xlow": xmin,
"xhigh": xmax,
"blank": list(potential_blank_sel),
"type": "bar",
"name": "blank_counts_analysis",
}
],
"layout": {
"xaxis": {"title": "z observed (images)"},
"yaxis": {"title": "Number of reflections"},
"bargap": 0,
},
}
blank_regions = blank_regions_from_sel(d["data"][0])
d["blank_regions"] = blank_regions
return d
def plot_uc_vs_detector_distance(
uc_params,
panel_distances,
outliers,
steps_per_angstrom=20,
filename="uc_vs_distance.png",
):
from matplotlib import pyplot as plt
plt.style.use("ggplot")
f = plt.figure(figsize=(12, 8))
ax1 = plt.subplot2grid((2, 3), (0, 0))
ax2 = plt.subplot2grid((2, 3), (0, 1), sharey=ax1)
ax3 = plt.subplot2grid((2, 3), (0, 2), sharey=ax1)
ax4 = plt.subplot2grid((2, 3), (1, 0), colspan=3)
a, b, c = uc_params[:3]
def hist2d(p1, p2, ax):
nbins = 100
H, xedges, yedges = np.histogram2d(p1, p2, bins=nbins)
H = np.rot90(H)
H = np.flipud(H)
Hmasked = np.ma.masked_where(H == 0, H)
ax.pcolormesh(xedges, yedges, Hmasked)
hist2d(a, panel_distances[0], ax1)
hist2d(b, panel_distances[0], ax2)
hist2d(c, panel_distances[0], ax3)
mmm = flex.min_max_mean_double(panel_distances[0])
steps_per_mm = 20
Amin = math.floor(mmm.min * steps_per_mm) / steps_per_mm
Amax = math.floor(mmm.max * steps_per_mm) / steps_per_mm
n_slots = max(1, int((Amax - Amin) * steps_per_mm))
if Amin == Amax:
eps = 0.05
Amin -= eps
Amax += eps
hist = flex.histogram(panel_distances[0], Amin, Amax, n_slots=n_slots)
ax4.bar(
hist.slot_centers(),
hist.slots(),
align="center",
width=hist.slot_width(),
zorder=10,
color="red",
edgecolor=None,
linewidth=0,
)
ax1.set_ylabel("Detector distance (mm)")
ax1.set_xlabel(r"a ($\AA$)")
ax2.set_xlabel(r"b ($\AA$)")
ax3.set_xlabel(r"c ($\AA$)")
ax4.set_xlabel("Detector distance (mm)")
f.savefig(filename)
plt.tight_layout()
f.clf()
def __init__(self, map_1, map_2, sites_cart, unit_cell, radius, n_slots):
assert_same_gridding(map_1, map_2)
self.ccs = from_map_map_atoms_per_atom(map_1=map_1,
map_2=map_2,
sites_cart=sites_cart,
unit_cell=unit_cell,
radius=radius)
self.hist = flex.histogram(data=self.ccs, n_slots=n_slots)
def __init__(self, map_1, map_2, sites_cart, unit_cell, radius, n_slots):
assert_same_gridding(map_1, map_2)
self.ccs = from_map_map_atoms_per_atom(
map_1 = map_1,
map_2 = map_2,
sites_cart = sites_cart,
unit_cell = unit_cell,
radius = radius)
self.hist = flex.histogram(data = self.ccs, n_slots = n_slots)
def plot_centroid_weights_histograms(reflections, n_slots=50):
from matplotlib import pyplot
from scitbx.array_family import flex
variances = flex.vec3_double([r.centroid_variance for r in reflections])
vx, vy, vz = variances.parts()
idx = (vx > 0).__and__(vy > 0).__and__(vz > 0)
vx = vx.select(idx)
vy = vy.select(idx)
vz = vz.select(idx)
wx = 1/vx
wy = 1/vy
wz = 1/vz
wx = flex.log(wx)
wy = flex.log(wy)
wz = flex.log(wz)
hx = flex.histogram(wx, n_slots=n_slots)
hy = flex.histogram(wy, n_slots=n_slots)
hz = flex.histogram(wz, n_slots=n_slots)
fig = pyplot.figure()
idx2 = flex.max_index(wx)
idx3 = flex.int(range(len(reflections))).select(idx)[idx2]
print reflections[idx3]
return
#outliers = reflections.select(wx > 50)
#for refl in outliers:
#print refl
for i, h in enumerate([hx, hy, hz]):
ax = fig.add_subplot(311+i)
slots = h.slots().as_double()
bins, data = hist_outline(h)
log_scale = True
if log_scale:
data.set_selected(data == 0, 0.1) # otherwise lines don't get drawn when we have some empty bins
ax.set_yscale("log")
ax.plot(bins, data, '-k', linewidth=2)
#pyplot.suptitle(title)
data_min = min([slot.low_cutoff for slot in h.slot_infos() if slot.n > 0])
data_max = max([slot.low_cutoff for slot in h.slot_infos() if slot.n > 0])
ax.set_xlim(data_min, data_max+h.slot_width())
pyplot.show()
def normal_probability_plot(self, data, rankits_sel=None, plot=False):
""" Use normal probability analysis to determine if a set of data is normally distributed
See https://en.wikipedia.org/wiki/Normal_probability_plot.
Rankits are computed in the same way as qqnorm does in R.
@param data flex array
@param rankits_sel only use the rankits in a certain range. Useful for outlier rejection. Should be
a tuple such as (-0.5,0.5).
@param plot whether to show the normal probabilty plot
"""
from scitbx.math import distributions
import numpy as np
norm = distributions.normal_distribution()
n = len(data)
if n <= 10:
a = 3/8
else:
a = 0.5
sorted_data = flex.sorted(data)
rankits = flex.double([norm.quantile((i+1-a)/(n+1-(2*a))) for i in range(n)])
if rankits_sel is None:
corr, slope, offset = self.get_overall_correlation_flex(sorted_data, rankits)
else:
sel = (rankits >= rankits_sel[0]) & (rankits <= rankits_sel[1])
corr, slope, offset = self.get_overall_correlation_flex(sorted_data.select(sel), rankits.select(sel))
if plot:
from matplotlib import pyplot as plt
f = plt.figure(0)
lim = -5, 5
x = np.linspace(lim[0],lim[1],100) # 100 linearly spaced numbers
y = slope * x + offset
plt.plot(sorted_data, rankits, '-')
#plt.plot(x,y)
plt.title("CC: %.3f Slope: %.3f Offset: %.3f"%(corr, slope, offset))
plt.xlabel("Sorted data")
plt.ylabel("Rankits")
plt.xlim(lim); plt.ylim(lim)
plt.axes().set_aspect('equal')
f = plt.figure(1)
h = flex.histogram(sorted_data, n_slots=100, data_min = lim[0], data_max = lim[1])
stats = flex.mean_and_variance(sorted_data)
plt.plot(h.slot_centers().as_numpy_array(), h.slots().as_numpy_array(), '-')
plt.xlim(lim)
plt.xlabel("Sorted data")
plt.ylabel("Count")
plt.title("Normalized data mean: %.3f +/- %.3f"%(stats.mean(), stats.unweighted_sample_standard_deviation()))
if self.scaler.params.raw_data.error_models.sdfac_refine.plot_refinement_steps:
plt.ion()
plt.pause(0.05)
return corr, slope, offset
def show_histogram(data=None, n_slots=None, data_min=None, data_max=None,
log=None):
from cctbx.array_family import flex
hm = flex.histogram(data = data, n_slots = n_slots, data_min = data_min,
data_max = data_max)
lc_1 = hm.data_min()
s_1 = enumerate(hm.slots())
for (i_1,n_1) in s_1:
hc_1 = hm.data_min() + hm.slot_width() * (i_1+1)
print >> log, "%10.4f - %-10.4f : %d" % (lc_1, hc_1, n_1)
lc_1 = hc_1
def blank_counts_analysis(reflections, scan, phi_step, fractional_loss):
if not len(reflections):
raise Sorry('Input contains no reflections')
xyz_px = reflections['xyzobs.px.value']
x_px, y_px, z_px = xyz_px.parts()
phi = scan.get_angle_from_array_index(z_px)
osc = scan.get_oscillation()[1]
n_images_per_step = iceil(phi_step / osc)
phi_step = n_images_per_step * osc
array_range = scan.get_array_range()
phi_min = scan.get_angle_from_array_index(array_range[0])
phi_max = scan.get_angle_from_array_index(array_range[1])
assert phi_min <= flex.min(phi)
assert phi_max >= flex.max(phi)
n_steps = iceil((phi_max - phi_min) / phi_step)
hist = flex.histogram(z_px, n_slots=n_steps)
counts = hist.slots()
fractional_counts = counts.as_double() / flex.max(counts)
potential_blank_sel = fractional_counts <= fractional_loss
xmin, xmax = zip(*[(slot_info.low_cutoff, slot_info.high_cutoff)
for slot_info in hist.slot_infos()])
d = {
'data': [{
'x': list(hist.slot_centers()),
'y': list(hist.slots()),
'xlow': xmin,
'xhigh': xmax,
'blank': list(potential_blank_sel),
'type': 'bar',
'name': 'blank_counts_analysis'
}],
'layout': {
'xaxis': {
'title': 'z observed (images)'
},
'yaxis': {
'title': 'Number of reflections'
},
'bargap': 0,
},
}
blank_regions = blank_regions_from_sel(d['data'][0])
d['blank_regions'] = blank_regions
return d
def show_histogram(data, n_slots):
hm = flex.histogram(data = data, n_slots = n_slots)
lc_1 = hm.data_min()
s_1 = enumerate(hm.slots())
tmp = None
for (i_1,n_1) in s_1:
hc_1 = hm.data_min() + hm.slot_width() * (i_1+1)
#print "%10.3f - %-10.3f : %d" % (lc_1, hc_1, n_1)
lc_1 = hc_1
if(tmp is None): tmp = hc_1
return tmp
def show_histogram(data=None, n_slots=None, data_min=None, data_max=None,
log=None):
from cctbx.array_family import flex
hm = flex.histogram(data = data, n_slots = n_slots, data_min = data_min,
data_max = data_max)
lc_1 = hm.data_min()
s_1 = enumerate(hm.slots())
for (i_1,n_1) in s_1:
hc_1 = hm.data_min() + hm.slot_width() * (i_1+1)
print >> log, "%10.4f - %-10.4f : %d" % (lc_1, hc_1, n_1)
lc_1 = hc_1
def __init__(self, rs_vectors, percentile=0.05):
from scitbx.array_family import flex
NEAR = 10
self.NNBIN = 5 # target number of neighbors per histogram bin
# nearest neighbor analysis
from annlib_ext import AnnAdaptor
query = flex.double()
for spot in rs_vectors: # spots, in reciprocal space xyz
query.append(spot[0])
query.append(spot[1])
query.append(spot[2])
assert len(
rs_vectors) > NEAR # Can't do nearest neighbor with too few spots
IS_adapt = AnnAdaptor(data=query, dim=3, k=1)
IS_adapt.query(query)
direct = flex.double()
for i in range(len(rs_vectors)):
direct.append(1.0 / math.sqrt(IS_adapt.distances[i]))
# determine the most probable nearest neighbor distance (direct space)
hst = flex.histogram(direct, n_slots=int(len(rs_vectors) / self.NNBIN))
centers = hst.slot_centers()
islot = hst.slots()
highest_bin_height = flex.max(islot)
most_probable_neighbor = centers[list(islot).index(highest_bin_height)]
if False: # to print out the histogramming analysis
smin, smax = flex.min(direct), flex.max(direct)
stats = flex.mean_and_variance(direct)
import sys
out = sys.stdout
print(" range: %6.2f - %.2f" % (smin, smax), file=out)
print(" mean: %6.2f +/- %6.2f on N = %d" %
(stats.mean(), stats.unweighted_sample_standard_deviation(),
direct.size()),
file=out)
hst.show(f=out, prefix=" ", format_cutoffs="%6.2f")
print("", file=out)
# determine the 5th-percentile direct-space distance
perm = flex.sort_permutation(direct, reverse=True)
percentile = direct[perm[int(percentile * len(rs_vectors))]]
MAXTOL = 1.5 # Margin of error for max unit cell estimate
self.max_cell = max(MAXTOL * most_probable_neighbor,
MAXTOL * percentile)
if False:
self.plot(direct)
def multihist(unmerged_mtz):
from iotbx.reflection_file_reader import any_reflection_file
reader = any_reflection_file(unmerged_mtz)
assert reader.file_type() == "ccp4_mtz"
mtz_object = reader.file_content()
arrays = reader.as_miller_arrays(merge_equivalents=False)
for ma in arrays:
if ma.info().labels == ["I", "SIGI"]:
intensities = ma
elif ma.info().labels == ["I(+)", "SIGI(+)", "I(-)", "SIGI(-)"]:
intensities = ma
indices = mtz_object.extract_original_index_miller_indices()
intensities = intensities.customized_copy(indices=indices,
info=intensities.info())
intensities = intensities.resolution_filter(d_min=2.0)
merging = intensities.merge_equivalents()
multiplicities = merging.redundancies().complete_array(new_data_value=0)
mult_acentric = multiplicities.select_acentric().data()
mult_centric = multiplicities.select_centric().data()
from scitbx.array_family import flex
max_mult = max(flex.max(mult_acentric), flex.max(mult_centric))
hist_acentric = flex.histogram(mult_acentric.as_double(),
data_min=0,
data_max=max_mult,
n_slots=max_mult)
hist_centric = flex.histogram(mult_centric.as_double(),
data_min=0,
data_max=max_mult,
n_slots=max_mult)
for s, a, c in zip(hist_acentric.slot_centers(), hist_acentric.slots(),
hist_centric.slots()):
print(s, a, c)
def __init__(self, rs_vectors, percentile=0.05):
from scitbx.array_family import flex
NEAR = 10
self.NNBIN = 5 # target number of neighbors per histogram bin
# nearest neighbor analysis
from annlib_ext import AnnAdaptor
query = flex.double()
for spot in rs_vectors: # spots, in reciprocal space xyz
query.append(spot[0])
query.append(spot[1])
query.append(spot[2])
assert len(rs_vectors)>NEAR # Can't do nearest neighbor with too few spots
IS_adapt = AnnAdaptor(data=query,dim=3,k=1)
IS_adapt.query(query)
direct = flex.double()
for i in xrange(len(rs_vectors)):
direct.append(1.0/math.sqrt(IS_adapt.distances[i]))
# determine the most probable nearest neighbor distance (direct space)
hst = flex.histogram(direct, n_slots=int(len(rs_vectors)/self.NNBIN))
centers = hst.slot_centers()
islot = hst.slots()
highest_bin_height = flex.max(islot)
most_probable_neighbor = centers[list(islot).index(highest_bin_height)]
if False: # to print out the histogramming analysis
smin, smax = flex.min(direct), flex.max(direct)
stats = flex.mean_and_variance(direct)
import sys
out = sys.stdout
print >> out, " range: %6.2f - %.2f" % (smin, smax)
print >> out, " mean: %6.2f +/- %6.2f on N = %d" % (
stats.mean(), stats.unweighted_sample_standard_deviation(), direct.size())
hst.show(f=out, prefix=" ", format_cutoffs="%6.2f")
print >> out, ""
# determine the 5th-percentile direct-space distance
perm = flex.sort_permutation(direct, reverse=True)
percentile = direct[perm[int(percentile * len(rs_vectors))]]
MAXTOL = 1.5 # Margin of error for max unit cell estimate
self.max_cell = max( MAXTOL * most_probable_neighbor,
MAXTOL * percentile)
if False:
self.plot(direct)
def show_histogram(data, n_slots, data_min, data_max, log=sys.stdout):
from cctbx.array_family import flex
h_data = flex.double()
hm = flex.histogram(
data=data, n_slots=n_slots, data_min=data_min, data_max=data_max)
lc_1 = hm.data_min()
s_1 = enumerate(hm.slots())
for (i_1,n_1) in s_1:
hc_1 = hm.data_min() + hm.slot_width() * (i_1+1)
#print >> log, "%10.5f - %-10.5f : %d" % (lc_1, hc_1, n_1)
#print >> log, "%10.2f : %d" % ((lc_1+hc_1)/2, n_1)
print ("%10.2f : %10.4f" % ((lc_1+hc_1)/2, n_1*100./data.size()), file=log)
lc_1 = hc_1
return h_data
def blank_counts_analysis(reflections, scan, phi_step, fractional_loss):
if not len(reflections):
raise Sorry("Input contains no reflections")
xyz_px = reflections["xyzobs.px.value"]
x_px, y_px, z_px = xyz_px.parts()
phi = scan.get_angle_from_array_index(z_px)
osc = scan.get_oscillation()[1]
n_images_per_step = iceil(phi_step / osc)
phi_step = n_images_per_step * osc
array_range = scan.get_array_range()
phi_min = scan.get_angle_from_array_index(array_range[0])
phi_max = scan.get_angle_from_array_index(array_range[1])
assert phi_min <= flex.min(phi)
assert phi_max >= flex.max(phi)
n_steps = iceil((phi_max - phi_min) / phi_step)
hist = flex.histogram(z_px, n_slots=n_steps)
counts = hist.slots()
fractional_counts = counts.as_double() / flex.max(counts)
potential_blank_sel = fractional_counts <= fractional_loss
xmin, xmax = zip(*[(slot_info.low_cutoff, slot_info.high_cutoff) for slot_info in hist.slot_infos()])
d = {
"data": [
{
"x": list(hist.slot_centers()),
"y": list(hist.slots()),
"xlow": xmin,
"xhigh": xmax,
"blank": list(potential_blank_sel),
"type": "bar",
"name": "blank_counts_analysis",
}
],
"layout": {"xaxis": {"title": "z observed (images)"}, "yaxis": {"title": "Number of reflections"}, "bargap": 0},
}
blank_regions = blank_regions_from_sel(d["data"][0])
d["blank_regions"] = blank_regions
return d
def compare_data_with_model(cif_file, mtz_file):
from iotbx import cif, mtz
from scitbx.array_family import flex
import math
import random
# read model, compute Fc, square to F^2
model = cif.reader(file_path=cif_file).build_crystal_structures()["1"]
ic = (
model.structure_factors(anomalous_flag=True, d_min=0.55, algorithm="direct")
.f_calc()
.as_intensity_array()
)
# read experimental measurements
m = mtz.object(mtz_file)
mad = m.as_miller_arrays_dict(merge_equivalents=False)
idata = mad[("HKL_base", "HKL_base", "I")].as_anomalous_array()
match = idata.match_indices(ic)
# pair up, extract to vanilla arrays for easier handling
pairs = match.pairs()
icalc = flex.double()
iobs = flex.double()
sobs = flex.double()
for p in pairs:
iobs.append(idata.data()[p[0]])
sobs.append(idata.sigmas()[p[0]])
icalc.append(ic.data()[p[1]])
# estimate conversion scale - apply F^2
icalc *= flex.sum(iobs) / flex.sum(icalc)
d = (iobs - icalc) / sobs
dh = flex.histogram(d, data_min=-6, data_max=6, n_slots=120)
m = flex.sum(d) / d.size()
s = math.sqrt(flex.sum(d * d) / d.size() - m * m)
# mean and standard deviation -
print(m, s)
def plot_rij_histogram(rij_matrix, key="cosym_rij_histogram"):
"""Plot a histogram of the rij values.
Args:
plot_name (str): The file name to save the plot to.
If this is not defined then the plot is displayed in interactive mode.
"""
rij = rij_matrix.as_1d()
rij = rij.select(rij != 0)
hist = flex.histogram(
rij,
data_min=min(-1, flex.min(rij)),
data_max=max(1, flex.max(rij)),
n_slots=100,
)
d = {
key: {
"data": [{
"x": list(hist.slot_centers()),
"y": list(hist.slots()),
"type": "bar",
"name": "Rij histogram",
}],
"layout": {
"title": "Distribution of values in the Rij matrix",
"xaxis": {
"title": "r<sub>ij</sub>"
},
"yaxis": {
"title": "Frequency"
},
"bargap": 0,
},
"help":
"""\
A histogram of the values of the Rij matrix of pairwise correlation coefficients. A
unimodal distribution of values may suggest that no indexing ambiguity is evident,
whereas a bimodal distribution can be indicative of the presence of an indexing
ambiguity.
""",
}
}
return d
def recalculate(self):
from scitbx.array_family import flex
measurable_only = self.meas_box.GetValue()
obs_type = self.obs_type.GetStringSelection()
n_bins = self.n_bins.GetValue()
d_ano_rel = self._array.bijvoet_ratios(obs_type=obs_type,
measurable_only=measurable_only)
hist = flex.histogram(d_ano_rel, n_slots=n_bins)
hist.show(f=sys.stdout)
if (obs_type == "intensities"):
x_label = "D_anom(I[hkl]) / I_mean[hkl]"
else:
x_label = "D_anom(F[hkl]) / F_mean[hkl]"
self.show_histogram(data=list(d_ano_rel),
n_bins=n_bins,
x_label=x_label,
y_label="# hkl",
title="Bijvoet ratios for %s" % self._array_name,
log_scale=self.log_box.GetValue())
def event(self, evt, env):
"""The event() function is called for every L1Accept transition.
Once self.nshots shots are accumulated, this function turns into
a nop.
@param evt Event data object, a configure object
@param env Environment object
"""
super(pixel_histograms, self).event(evt, env)
if (evt.get("skip_event")):
return
if self.sigma_scaling:
flex_cspad_img = self.cspad_img.as_double()
flex_cspad_img_sel = flex_cspad_img.as_1d().select(
self.dark_mask.as_1d())
flex_dark_stddev = self.dark_stddev.select(
self.dark_mask.as_1d()).as_double()
assert flex_dark_stddev.count(0) == 0
flex_cspad_img_sel /= flex_dark_stddev
flex_cspad_img.as_1d().set_selected(
self.dark_mask.as_1d().iselection(), flex_cspad_img_sel)
self.cspad_img = flex_cspad_img.iround()
pixels = self.cspad_img.deep_copy()
dimensions = pixels.all()
if self.roi is None:
self.roi = (0, dimensions[1], 0, dimensions[0])
for i in range(self.roi[2], self.roi[3]):
for j in range(self.roi[0], self.roi[1]):
if (i, j) not in self.histograms:
self.histograms[(i, j)] = flex.histogram(
flex.double(), self.hist_min, self.hist_max,
self.n_slots)
self.histograms[(i, j)].update(pixels[i, j])
self.nmemb += 1
if 0 and math.log(self.nmemb, 2) % 1 == 0:
self.endjob(env)
print self.nmemb
def show_histogram(data, n_slots, smooth=True):
triplets = []
histogram = flex.histogram(data=data, n_slots=n_slots)
l = histogram.data_min()
for i, s in enumerate(histogram.slots()):
r = histogram.data_min() + histogram.slot_width() * (i + 1)
triplets.append([l, r, s])
print "%8.4f %8.4f %d" % (l, r, s)
l = r
if (smooth):
print "... smooth histogram"
triplets_smooth = []
for i, t in enumerate(triplets):
values = flex.double()
for j in [-1, 0, 1]:
if (i + j >= 0 and i + j < len(triplets)):
values.append(float(triplets[i + j][2]))
triplets_smooth.append((t[0], t[1], flex.mean(values)))
for t in triplets_smooth:
print "%8.4f %8.4f %d" % (t[0], t[1], int("%.0f" % t[2]))
return histogram
def recalculate (self) :
from scitbx.array_family import flex
measurable_only = self.meas_box.GetValue()
obs_type = self.obs_type.GetStringSelection()
n_bins = self.n_bins.GetValue()
d_ano_rel = self._array.bijvoet_ratios(
obs_type=obs_type,
measurable_only=measurable_only)
hist = flex.histogram(d_ano_rel, n_slots=n_bins)
hist.show(f=sys.stdout)
if (obs_type == "intensities") :
x_label = "D_anom(I[hkl]) / I_mean[hkl]"
else :
x_label = "D_anom(F[hkl]) / F_mean[hkl]"
self.show_histogram(
data=list(d_ano_rel),
n_bins=n_bins,
x_label=x_label,
y_label="# hkl",
title="Bijvoet ratios for %s" % self._array_name,
log_scale=self.log_box.GetValue())
def show_histogram(data, n_slots, smooth = True):
triplets = []
histogram = flex.histogram(data = data, n_slots = n_slots)
l = histogram.data_min()
for i, s in enumerate(histogram.slots()):
r = histogram.data_min() + histogram.slot_width() * (i+1)
triplets.append( [l, r, s] )
print "%8.4f %8.4f %d" % (l, r, s)
l = r
if(smooth):
print "... smooth histogram"
triplets_smooth = []
for i, t in enumerate(triplets):
values = flex.double()
for j in [-1,0,1]:
if(i+j >=0 and i+j < len(triplets)):
values.append(float(triplets[i+j][2]))
triplets_smooth.append((t[0],t[1],flex.mean(values)))
for t in triplets_smooth:
print "%8.4f %8.4f %d" % (t[0], t[1], int("%.0f"%t[2]))
return histogram
def event(self, evt, env):
"""The event() function is called for every L1Accept transition.
Once self.nshots shots are accumulated, this function turns into
a nop.
@param evt Event data object, a configure object
@param env Environment object
"""
super(pixel_histograms, self).event(evt, env)
if (evt.get("skip_event")):
return
if self.sigma_scaling:
flex_cspad_img = self.cspad_img.as_double()
flex_cspad_img_sel = flex_cspad_img.as_1d().select(self.dark_mask.as_1d())
flex_dark_stddev = self.dark_stddev.select(self.dark_mask.as_1d()).as_double()
assert flex_dark_stddev.count(0) == 0
flex_cspad_img_sel /= flex_dark_stddev
flex_cspad_img.as_1d().set_selected(self.dark_mask.as_1d().iselection(), flex_cspad_img_sel)
self.cspad_img = flex_cspad_img.iround()
pixels = self.cspad_img.deep_copy()
dimensions = pixels.all()
if self.roi is None:
self.roi = (0, dimensions[1], 0, dimensions[0])
for i in range(self.roi[2], self.roi[3]):
for j in range(self.roi[0], self.roi[1]):
if (i,j) not in self.histograms:
self.histograms[(i,j)] = flex.histogram(flex.double(), self.hist_min, self.hist_max, self.n_slots)
self.histograms[(i,j)].update(pixels[i,j])
self.nmemb += 1
if 0 and math.log(self.nmemb, 2) % 1 == 0:
self.endjob(env)
print self.nmemb
def plot_rij_histogram(rij_matrix, key="cosym_rij_histogram"):
"""Plot a histogram of the rij values.
Args:
plot_name (str): The file name to save the plot to.
If this is not defined then the plot is displayed in interactive mode.
"""
rij = rij_matrix.as_1d()
rij = rij.select(rij != 0)
hist = flex.histogram(
rij,
data_min=min(-1, flex.min(rij)),
data_max=max(1, flex.max(rij)),
n_slots=100,
)
d = {
key: {
"data": [{
"x": list(hist.slot_centers()),
"y": list(hist.slots()),
"type": "bar",
"name": "Rij histogram",
}],
"layout": {
"title": "Distribution of values in the Rij matrix",
"xaxis": {
"title": "r<sub>ij</sub>"
},
"yaxis": {
"title": "Frequency"
},
"bargap": 0,
},
}
}
return d
def centroidify(width, shift, count):
g = variate(normal_distribution(mean=shift, sigma=width))
values = flex.double([next(g) for c in range(count)])
hist = flex.histogram(data=values, n_slots=20, data_min=-10, data_max=10)
true_mean = flex.sum(values) / values.size()
true_variance = sum([(v - true_mean)**2
for v in values]) / (values.size() - 1)
total = 1.0 * flex.sum(hist.slots())
hist_mean = sum([c * v for c, v in zip(hist.slot_centers(), hist.slots())
]) / total
# equation 6
hist_var = sum([(v / total)**2 * (1.0 / 12.0) for v in hist.slots()])
# print input setings
print("%8.5f %4.1f %4d" % (width**2 / count, shift, count), end=" ")
# true variance / mean of distribution
print("%6.3f %8.5f" % (true_mean, true_variance / values.size()), end=" ")
# putative values of same derived from histogram
print("%6.3f %8.5f" % (hist_mean, hist_var))
def __init__(self,
cmd_list,
nprocs=1,
out=sys.stdout,
log=None,
verbosity=DEFAULT_VERBOSITY,
max_time=180):
if (log is None): log = null_out()
self.out = multi_out()
self.log = log
self.out.register("stdout", out)
self.out.register("log", log)
self.verbosity = verbosity
self.quiet = (verbosity == 0)
self.results = []
self.pool = None
# Filter cmd list for duplicates.
self.cmd_list = []
for cmd in cmd_list:
if (not cmd in self.cmd_list):
self.cmd_list.append(cmd)
else:
print >> self.out, "Test %s repeated, skipping" % cmd
# Set number of processors.
if (nprocs is Auto):
nprocs = cpu_count()
nprocs = min(nprocs, len(self.cmd_list))
# Starting summary.
if (self.verbosity > 0):
print >> self.out, "Running %d tests on %s processors:" % (len(
self.cmd_list), nprocs)
for cmd in self.cmd_list:
print >> self.out, " %s" % cmd
print >> self.out, ""
# Either run tests in parallel or run parallel tests, but
# can't run parallel tests in parallel (cctbx#95)
os.environ['OPENBLAS_NUM_THREADS'] = "1"
t_start = time.time()
if nprocs > 1:
# Run the tests with multiprocessing pool.
self.pool = Pool(processes=nprocs)
for command in self.cmd_list:
self.pool.apply_async(run_command, [command, verbosity, out],
callback=self.save_result)
try:
self.pool.close()
except KeyboardInterrupt:
print >> self.out, "Caught KeyboardInterrupt, terminating"
self.pool.terminate()
finally:
try:
self.pool.join()
except KeyboardInterrupt:
pass
else:
# Run tests serially.
for command in self.cmd_list:
rc = run_command(command, verbosity=verbosity, out=out)
if self.save_result(rc) == False:
break
# Print ending summary.
t_end = time.time()
print >> self.out, "=" * 80
print >> self.out, ""
print >> self.out, "Tests finished. Elapsed time: %.2fs" % (t_end -
t_start)
print >> self.out, ""
# Process results for errors and warnings.
extra_stderr = len(
[result for result in self.results if result.stderr_lines])
longjobs = [
result for result in self.results if result.wall_time > max_time
]
warnings = [
result for result in self.results
if result.alert_status == Status.WARNING
]
failures = [
result for result in self.results
if result.alert_status == Status.FAIL
]
self.finished = len(self.results)
self.failure = len(failures)
self.warning = len(warnings)
# Try writing the XML result file
write_JUnit_XML(self.results, "output.xml")
# Run time distribution.
if (libtbx.env.has_module("scitbx")):
from scitbx.array_family import flex
print >> self.out, "Distribution of test runtimes:"
hist = flex.histogram(flex.double(
[result.wall_time for result in self.results]),
n_slots=10)
hist.show(f=self.out, prefix=" ", format_cutoffs="%.1fs")
print >> self.out, ""
# Long job warning.
if longjobs:
print >> self.out, ""
print >> self.out, "Warning: the following jobs took at least %d seconds:" % max_time
for result in sorted(longjobs,
key=lambda result: result.wall_time):
print >> self.out, " %s: %.1fs" % (result.command,
result.wall_time)
else:
# Just print 5 worst offenders to encourage developers to check them out
print >> self.out, ""
print >> self.out, "Warning: the following are 5 longest jobs:"
for result in sorted(self.results,
key=lambda result: -result.wall_time)[:5]:
print >> self.out, " %s: %.1fs" % (result.command,
result.wall_time)
print >> self.out, "Please try to reduce overall runtime - consider splitting up these tests."
print >> self.out, ""
# Failures.
if failures:
print >> self.out, ""
print >> self.out, "Error: the following jobs returned non-zero exit codes or suspicious stderr output:"
print >> self.out, ""
for result in warnings:
self.display_result(result,
alert=Status.WARNING,
out=self.out,
log_return=self.out,
log_stderr=self.out)
for result in failures:
self.display_result(result,
alert=Status.FAIL,
out=self.out,
log_return=self.out,
log_stderr=self.out)
print >> self.out, ""
print >> self.out, "Please verify these tests manually."
print >> self.out, ""
# Summary
print >> self.out, "Summary:"
print >> self.out, " Tests run :", self.finished
print >> self.out, " Failures :", self.failure
print >> self.out, " Warnings (possible failures) :", self.warning
print >> self.out, " Stderr output (discouraged) :", extra_stderr
if (self.finished != len(self.cmd_list)):
print >> self.out, "*" * 80
print >> self.out, " WARNING: NOT ALL TESTS FINISHED!"
print >> self.out, "*" * 80
class run_command_list(object):
def __init__(self,
cmd_list,
nprocs=1,
out=sys.stdout,
log=None,
verbosity=DEFAULT_VERBOSITY,
max_time=180):
if (log is None): log = null_out()
self.out = multi_out()
self.log = log
self.out.register("stdout", out)
self.out.register("log", log)
self.verbosity = verbosity
self.quiet = (verbosity == 0)
self.results = []
# Filter cmd list for duplicates.
self.cmd_list = []
for cmd in cmd_list:
if (not cmd in self.cmd_list):
self.cmd_list.append(cmd)
else:
print >> self.out, "Test %s repeated, skipping" % cmd
# Set number of processors.
if (nprocs is Auto):
nprocs = cpu_count()
nprocs = min(nprocs, len(self.cmd_list))
# Starting summary.
if (self.verbosity > 0):
print >> self.out, "Running %d tests on %s processors:" % (len(
self.cmd_list), nprocs)
for cmd in self.cmd_list:
print >> self.out, " %s" % cmd
print >> self.out, ""
t_start = time.time()
if nprocs > 1:
# Run the tests with multiprocessing pool.
pool = Pool(processes=nprocs)
for command in self.cmd_list:
pool.apply_async(run_command, [command, verbosity, out],
callback=self.save_result)
try:
pool.close()
except KeyboardInterrupt:
print >> self.out, "Caught KeyboardInterrupt, terminating"
pool.terminate()
finally:
pool.join()
else:
# Run tests serially.
for command in self.cmd_list:
rc = run_command(command, verbosity=verbosity, out=out)
self.save_result(rc)
# Print ending summary.
t_end = time.time()
print >> self.out, "=" * 80
print >> self.out, ""
print >> self.out, "Tests finished. Elapsed time: %.2fs" % (t_end -
t_start)
print >> self.out, ""
test_cases = []
# Process results for errors and warnings.
extra_stderr = len(
[result for result in self.results if result.stderr_lines])
longjobs = [
result for result in self.results if result.wall_time > max_time
]
warnings = [
result for result in self.results if self.check_alert(result) == 1
]
failures = [
result for result in self.results if self.check_alert(result) == 2
]
self.finished = len(self.results)
self.failure = len(failures)
self.warning = len(warnings)
# Output JUnit XML if possible
try:
from junit_xml import TestSuite, TestCase
import re
def decode_string(string):
try:
return string.encode('ascii', 'xmlcharrefreplace')
except Exception: # intentional
return unicode(string, errors='ignore').encode(
'ascii', 'xmlcharrefreplace')
for result in self.results:
test_name = reconstruct_test_name(result.command)
plain_stdout = map(decode_string, result.stdout_lines)
plain_stderr = map(decode_string, result.stderr_lines)
output = '\n'.join(plain_stdout + plain_stderr)
tc = TestCase(classname=test_name[0],
name=test_name[1],
elapsed_sec=result.wall_time,
stdout='\n'.join(plain_stdout),
stderr='\n'.join(plain_stderr))
if result.return_code == 0:
# Identify skipped tests
if re.search('skip', output, re.IGNORECASE):
# find first line including word 'skip' and use it as message
skipline = re.search('^((.*)skip(.*))$', output,
re.IGNORECASE
| re.MULTILINE).group(1)
tc.add_skipped_info(skipline)
else:
# Test failed. Extract error message and stack trace if possible
error_message = 'exit code %d' % result.return_code
error_output = '\n'.join(plain_stderr)
if plain_stderr:
error_message = plain_stderr[-1]
if len(plain_stderr) > 20:
error_output = '\n'.join(plain_stderr[-20:])
tc.add_failure_info(message=error_message,
output=error_output)
test_cases.append(tc)
ts = TestSuite("libtbx.run_tests_parallel", test_cases=test_cases)
with open('output.xml', 'wb') as f:
print >> f, TestSuite.to_xml_string([ts], prettyprint=True)
except ImportError, e:
pass
# Run time distribution.
if (libtbx.env.has_module("scitbx")):
from scitbx.array_family import flex
print >> self.out, "Distribution of test runtimes:"
hist = flex.histogram(flex.double(
[result.wall_time for result in self.results]),
n_slots=10)
hist.show(f=self.out, prefix=" ", format_cutoffs="%.1fs")
print >> self.out, ""
# Long job warning.
if longjobs:
print >> self.out, ""
print >> self.out, "Warning: the following jobs took at least %d seconds:" % max_time
for result in sorted(longjobs,
key=lambda result: result.wall_time):
print >> self.out, " %s: %.1fs" % (result.command,
result.wall_time)
print >> self.out, "Please try to reduce overall runtime - consider splitting up these tests."
# Failures.
if failures:
print >> self.out, ""
print >> self.out, "Error: the following jobs returned non-zero exit codes or suspicious stderr output:"
print >> self.out, ""
for result in warnings:
self.display_result(result,
alert=1,
out=self.out,
log_return=self.out,
log_stderr=self.out)
for result in failures:
self.display_result(result,
alert=2,
out=self.out,
log_return=self.out,
log_stderr=self.out)
print >> self.out, ""
print >> self.out, "Please verify these tests manually."
print >> self.out, ""
# Summary
print >> self.out, "Summary:"
print >> self.out, " Tests run :", self.finished
print >> self.out, " Failures :", self.failure
print >> self.out, " Warnings (possible failures) :", self.warning
print >> self.out, " Stderr output (discouraged) :", extra_stderr
if (self.finished != len(self.cmd_list)):
print >> self.out, "*" * 80
print >> self.out, " WARNING: NOT ALL TESTS FINISHED!"
print >> self.out, "*" * 80
def del_anom_normal_plot(intensities, strong_cutoff=0.0):
"""Make a normal probability plot of the normalised anomalous differences."""
diff_array = intensities.anomalous_differences()
if not diff_array.data().size():
return {}
delta = diff_array.data() / diff_array.sigmas()
n = delta.size()
y = np.sort(flumpy.to_numpy(delta))
d = 0.5 / n
v = np.linspace(start=d, stop=1.0 - d, endpoint=True, num=n)
x = norm.ppf(v)
H, xedges, yedges = np.histogram2d(x, y, bins=(200, 200))
nonzeros = np.nonzero(H)
z = np.empty(H.shape)
z[:] = np.NAN
z[nonzeros] = H[nonzeros]
# also make a histogram
histy = flex.histogram(flumpy.from_numpy(y), n_slots=100)
# make a gaussian for reference also
n = y.size
width = histy.slot_centers()[1] - histy.slot_centers()[0]
gaussian = []
from math import exp, pi
for x in histy.slot_centers():
gaussian.append(n * width * exp(-(x**2) / 2.0) / ((2.0 * pi) ** 0.5))
title = "Normal probability plot of anomalous differences"
plotname = "normal_distribution_plot"
if strong_cutoff > 0.0:
title += f" (d > {strong_cutoff:.2f})"
plotname += "_lowres"
else:
title += " (all data)"
plotname += "_highres"
return {
plotname: {
"data": [
{
"x": xedges.tolist(),
"y": yedges.tolist(),
"z": z.transpose().tolist(),
"type": "heatmap",
"name": "normalised deviations",
"colorbar": {
"title": "Number of reflections",
"titleside": "right",
},
"colorscale": "Viridis",
},
{
"x": [-5, 5],
"y": [-5, 5],
"type": "scatter",
"mode": "lines",
"name": "z = m",
"color": "rgb(0,0,0)",
},
],
"layout": {
"title": title,
"xaxis": {
"anchor": "y",
"title": "expected delta",
"range": [-4, 4],
},
"yaxis": {
"anchor": "x",
"title": "observed delta",
"range": [-5, 5],
},
},
"help": """\
This plot shows the normalised anomalous differences, sorted in order and
plotted against the expected order based on a normal distribution model.
A true normal distribution of deviations would give the straight line indicated.
[1] P. L. Howell and G. D. Smith, J. Appl. Cryst. (1992). 25, 81-86
https://doi.org/10.1107/S0021889891010385
[2] P. Evans, Acta Cryst. (2006). D62, 72-82
https://doi.org/10.1107/S0907444905036693
""",
}
}
def eval_logs(file_names, out=None):
if (out is None): out = sys.stdout
from scitbx.array_family import flex
from libtbx.str_utils import format_value
min_secs_epoch = None
max_secs_epoch = None
n_refinements_initialized = 0
gaps = flex.double()
infos = flex.std_string()
n_stale = 0
n_unfinished = 0
n_exception = 0
n_traceback = 0
n_abort = 0
seconds = []
space_groups_by_cod_id = {}
for file_name in file_names:
have_time_end = False
cod_id = None
n_scatt = None
iso = None
file_str = open(file_name).read()
if (file_str.find(chr(0)) >= 0):
n_stale += 1
continue
for line in file_str.splitlines():
if (line.startswith("cod_id: ")):
cod_id = line[10:]
iso = None
elif (line.startswith("Space group: ")):
assert cod_id is not None
space_group = line.split(None, 2)[2]
tabulated = space_groups_by_cod_id.setdefault(cod_id, space_group)
assert tabulated == space_group
elif (line.startswith("Number of scatterers: ")):
assert cod_id is not None
n_scatt = int(line.split(": ",1)[1])
elif (line.startswith("Number of refinable parameters: ")):
assert cod_id is not None
n_refinements_initialized += 1
elif (line.startswith("iso cc, r1: ")):
assert cod_id is not None
assert iso is None
iso = line.split(": ",1)[1]
elif ( line.startswith("dev cc, r1: ")
or line.startswith("ls_simple cc, r1: ")
or line.startswith("ls_lm cc, r1: ")
or line.startswith("shelxl_fm cc, r1: ")
or line.startswith("shelxl_cg cc, r1: ")
or line.startswith("shelx76 cc, r1: ")):
assert iso is not None
ref = line.split(": ",1)[1]
gap = float(ref.split()[1]) - float(iso.split()[1])
gaps.append(gap)
infos.append(" : ".join([
cod_id, iso, ref, "%.3f" % gap, str(n_scatt),
space_groups_by_cod_id[cod_id]]))
cod_id = None
n_scatt = None
iso = None
else:
def get_secs_epoch():
return float(line.split()[-2][1:])
if (line.find("EXCEPTION") >= 0):
n_exception += 1
if (line.startswith("Traceback")):
n_traceback += 1
if (line.find("Abort") >= 0):
n_abort += 1
if (line.startswith("wall clock time: ")):
if (line.endswith(" seconds")):
secs = float(line.split()[-2])
else:
_, fld = line.split("(", 1)
assert fld.endswith(" seconds total)")
secs = float(fld.split()[0])
seconds.append(secs)
elif (line.startswith("TIME BEGIN cod_refine: ")):
s = get_secs_epoch()
if (min_secs_epoch is None or s < min_secs_epoch): min_secs_epoch = s
elif (line.startswith("TIME END cod_refine: ")):
s = get_secs_epoch()
if (max_secs_epoch is None or s > max_secs_epoch): max_secs_epoch = s
have_time_end = True
if (not have_time_end):
n_unfinished += 1
perm = flex.sort_permutation(gaps)
gaps = gaps.select(perm)
n_missing = n_refinements_initialized - gaps.size()
print >> out, "Number of results: %d (%d missing)" % (gaps.size(), n_missing)
assert n_missing >= 0
print >> out, "Stale, Unfinished, Exceptions, Tracebacks, Abort:", \
n_stale, n_unfinished, n_exception, n_traceback, n_abort
if (n_exception + n_abort < n_missing):
print "WARNING: more missing results than expected."
if (len(seconds) != 0):
if (min_secs_epoch is not None and max_secs_epoch is not None):
g = max_secs_epoch - min_secs_epoch
else:
g = None
print >> out, "min, max, global seconds: %.2f %.2f %s" % (
min(seconds), max(seconds), format_value("%.2f", g))
print >> out
def stats(f):
n = f.count(True)
return "%6d = %5.2f %%" % (n, 100 * n / max(1,n_refinements_initialized))
print >> out, "gaps below -0.05:", stats(gaps < -0.05)
print >> out, "gaps below -0.01:", stats(gaps < -0.01)
print >> out, "gaps below 0.01:", stats(gaps < 0.01)
print >> out, "gaps above 0.01:", stats(gaps > 0.01)
print >> out, "gaps above 0.05:", stats(gaps > 0.05)
print >> out
print >> out, "Histogram of gaps:"
flex.histogram(gaps, n_slots=10).show(f=out)
print >> out
infos = infos.select(perm)
for info in infos:
print >> out, info
return (len(file_names), n_unfinished, min_secs_epoch, max_secs_epoch)
def __init__(self, reflections, step_size=45, tolerance=1.5,
max_height_fraction=0.25, percentile=0.05,
histogram_binning='linear'):
self.tolerance = tolerance # Margin of error for max unit cell estimate
from scitbx.array_family import flex
NEAR = 10
self.NNBIN = 5 # target number of neighbors per histogram bin
self.histogram_binning = histogram_binning
direct = flex.double()
if 'entering' in reflections:
entering_flags = reflections['entering']
else:
entering_flags = flex.bool(reflections.size(), True)
rs_vectors = reflections['rlp']
phi_deg = reflections['xyzobs.mm.value'].parts()[2] * (180/math.pi)
d_spacings = flex.double()
# nearest neighbor analysis
from annlib_ext import AnnAdaptor
for imageset_id in range(flex.max(reflections['imageset_id'])+1):
sel = reflections['imageset_id'] == imageset_id
if sel.count(True) == 0:
continue
phi_min = flex.min(phi_deg.select(sel))
phi_max = flex.max(phi_deg.select(sel))
d_phi = phi_max - phi_min
n_steps = max(int(math.ceil(d_phi / step_size)), 1)
for n in range(n_steps):
sel &= (phi_deg >= (phi_min+n*step_size)) & (phi_deg < (phi_min+(n+1)*step_size))
for entering in (True, False):
sel &= entering_flags == entering
if sel.count(True) == 0:
continue
query = flex.double()
query.extend(rs_vectors.select(sel).as_double())
if query.size() == 0:
continue
IS_adapt = AnnAdaptor(data=query,dim=3,k=1)
IS_adapt.query(query)
direct.extend(1/flex.sqrt(IS_adapt.distances))
d_spacings.extend(1/rs_vectors.norms())
assert len(direct)>NEAR, (
"Too few spots (%d) for nearest neighbour analysis." %len(direct))
perm = flex.sort_permutation(direct)
direct = direct.select(perm)
d_spacings = d_spacings.select(perm)
# reject top 1% of longest distances to hopefully get rid of any outliers
n = int(math.floor(0.99*len(direct)))
direct = direct[:n]
d_spacings = d_spacings[:n]
# determine the most probable nearest neighbor distance (direct space)
if self.histogram_binning == 'log':
hst = flex.histogram(
flex.log10(direct), n_slots=int(len(direct)/self.NNBIN))
else:
hst = flex.histogram(direct, n_slots=int(len(direct)/self.NNBIN))
centers = hst.slot_centers()
if self.histogram_binning == 'log':
self.slot_start = flex.double(
[10**s for s in hst.slot_centers() - 0.5 * hst.slot_width()])
self.slot_end = flex.double(
[10**s for s in hst.slot_centers() + 0.5 * hst.slot_width()])
self.slot_width = self.slot_end - self.slot_start
else:
self.slot_start = hst.slot_centers() - 0.5 * hst.slot_width()
self.slot_end = hst.slot_centers() + 0.5 * hst.slot_width()
self.slot_width = hst.slot_width()
self.relative_frequency = hst.slots().as_double()/self.slot_width
highest_bin_height = flex.max(self.relative_frequency)
if False: # to print out the histogramming analysis
smin, smax = flex.min(direct), flex.max(direct)
stats = flex.mean_and_variance(direct)
import sys
out = sys.stdout
print >> out, " range: %6.2f - %.2f" % (smin, smax)
print >> out, " mean: %6.2f +/- %6.2f on N = %d" % (
stats.mean(), stats.unweighted_sample_standard_deviation(), direct.size())
hst.show(f=out, prefix=" ", format_cutoffs="%6.2f")
print >> out, ""
# choose a max cell based on bins above a given fraction of the highest bin height
# given multiple
isel = (self.relative_frequency.as_double() > (
max_height_fraction * highest_bin_height)).iselection()
self.max_cell = (
self.tolerance * self.slot_end[int(flex.max(isel.as_double()))])
# determine the 5th-percentile direct-space distance
perm = flex.sort_permutation(direct, reverse=True)
self.percentile = direct[perm[int(percentile * len(direct))]]
self.reciprocal_lattice_vectors = rs_vectors
self.d_spacings = d_spacings
self.direct = direct
self.histogram = hst
def common_mode(self, img, stddev, mask):
"""The common_mode() function returns the mode of image stored in
the array pointed to by @p img. @p mask must be such that the @p
stddev at the selected pixels is greater than zero.
@param img 2D integer array of the image
@param stddev 2D integer array of the standard deviation of each
pixel in @p img
@param mask 2D Boolean array, @c True if the pixel is to be
included, @c False otherwise
@return Mode of the image, as a real number
"""
# Flatten the image and take out inactive pixels XXX because we
# cannot take means and medians of 2D arrays?
img_1d = img.as_1d().select(mask.as_1d()).as_double()
assert img_1d.size() > 0
if (self.common_mode_correction == "mean"):
# The common mode is approximated by the mean of the pixels with
# signal-to-noise ratio less than a given threshold. XXX Breaks
# if the selection is empty!
THRESHOLD_SNR = 2
img_snr = img_1d / stddev.as_double().as_1d().select(mask.as_1d())
return (flex.mean(img_1d.select(img_snr < THRESHOLD_SNR)))
elif (self.common_mode_correction == "median"):
return (flex.median(img_1d))
# Identify the common-mode correction as the peak histogram of the
# histogram of pixel values (the "standard" common-mode correction, as
# previously implemented in this class).
hist_min = -40
hist_max = 40
n_slots = 100
hist = flex.histogram(img_1d, hist_min, hist_max, n_slots=n_slots)
slots = hist.slots()
i = flex.max_index(slots)
common_mode = list(hist.slot_infos())[i].center()
if (self.common_mode_correction == "mode"):
return (common_mode)
# Determine the common-mode correction from the peak of a single
# Gaussian function fitted to the histogram.
from scitbx.math.curve_fitting import single_gaussian_fit
x = hist.slot_centers()
y = slots.as_double()
fit = single_gaussian_fit(x, y)
scale, mu, sigma = fit.a, fit.b, fit.c
self.logger.debug("fitted gaussian: mu=%.3f, sigma=%.3f" %(mu, sigma))
mode = common_mode
common_mode = mu
if abs(mode-common_mode) > 1000: common_mode = mode # XXX
self.logger.debug("delta common mode corrections: %.3f" %(mode-common_mode))
if 0 and abs(mode-common_mode) > 0:
#if 0 and skew > 0.5:
# view histogram and fitted gaussian
from numpy import exp
from matplotlib import pyplot
x_all = x
n, bins, patches = pyplot.hist(section_img.as_1d().as_numpy_array(), bins=n_slots, range=(hist_min, hist_max))
y_all = scale * flex.exp(-flex.pow2(x_all-mu) / (2 * sigma**2))
scale = slots[flex.max_index(slots)]
y_all *= scale/flex.max(y_all)
pyplot.plot(x_all, y_all)
pyplot.show()
return (common_mode)
def run(args):
from dials.util.options import OptionParser
from dials.util.options import flatten_experiments
from dials.util.options import flatten_reflections
import libtbx.load_env
usage = "%s [options] datablock.json" %(
libtbx.env.dispatcher_name)
parser = OptionParser(
usage=usage,
phil=phil_scope,
read_experiments=True,
read_reflections=True,
check_format=True,
epilog=help_message)
params, options = parser.parse_args(show_diff_phil=True)
experiments = flatten_experiments(params.input.experiments)
reflections = flatten_reflections(params.input.reflections)
if len(experiments) == 0 or len(reflections) == 0:
parser.print_help()
exit(0)
imagesets = experiments.imagesets()
reflections = reflections[0]
shadowed = filter_shadowed_reflections(experiments, reflections)
print "# shadowed reflections: %i/%i (%.2f%%)" %(
shadowed.count(True), shadowed.size(),
shadowed.count(True)/shadowed.size() * 100)
expt = experiments[0]
x,y,z = reflections['xyzcal.px'].parts()
z_ = z * expt.scan.get_oscillation()[1]
zmin, zmax = expt.scan.get_oscillation_range()
hist_scan_angle = flex.histogram(z_.select(shadowed), n_slots=int(zmax-zmin))
#hist_scan_angle.show()
uc = experiments[0].crystal.get_unit_cell()
d_spacings = uc.d(reflections['miller_index'])
ds2 = uc.d_star_sq(reflections['miller_index'])
hist_res = flex.histogram(ds2.select(shadowed), flex.min(ds2), flex.max(ds2), n_slots=20, )
#hist_res.show()
import matplotlib
matplotlib.use('Agg')
from matplotlib import pyplot as plt
plt.hist2d(z_.select(shadowed).as_numpy_array(),
ds2.select(shadowed).as_numpy_array(), bins=(40,40),
range=((flex.min(z_), flex.max(z_)),(flex.min(ds2), flex.max(ds2))))
yticks_dsq = flex.double(plt.yticks()[0])
from cctbx import uctbx
yticks_d = uctbx.d_star_sq_as_d(yticks_dsq)
plt.axes().set_yticklabels(['%.2f' %y for y in yticks_d])
plt.xlabel('Scan angle (degrees)')
plt.ylabel('Resolution (A^-1)')
cbar = plt.colorbar()
cbar.set_label('# shadowed reflections')
plt.savefig('n_shadowed_hist2d.png')
plt.clf()
plt.scatter(hist_scan_angle.slot_centers().as_numpy_array(), hist_scan_angle.slots().as_numpy_array())
plt.xlabel('Scan angle (degrees)')
plt.ylabel('# shadowed reflections')
plt.savefig("n_shadowed_vs_scan_angle.png")
plt.clf()
plt.scatter(hist_res.slot_centers().as_numpy_array(), hist_res.slots().as_numpy_array())
plt.xlabel('d_star_sq')
plt.savefig("n_shadowed_vs_resolution.png")
plt.clf()
if False:
# have an I/sigma selection of > 1
i_over_sigi = pkl.data() / pkl.sigmas()
pkl = pkl.select(i_over_sigi > 1)
c, n = compare(reference1, pkl, sgtype)
print '%5d %s %6.3f %5d' % (i, pkl_file.strip(), c, n),
ccs[0].append(c)
for j, reference in enumerate(references):
c, n = compare(reference, pkl, sgtype)
print '%6.3f %5d' % (c, n),
ccs[j + 1].append(c)
print ''
from matplotlib import pyplot
for j in sorted(ccs):
pyplot.scatter(range(len(ccs[j])), ccs[j])
pyplot.savefig('ccs.png')
pyplot.close()
from scitbx.array_family import flex
for j in sorted(ccs):
hist = flex.histogram(flex.double(ccs[j]), n_slots=50)
pyplot.plot(hist.slot_centers(), hist.slots())
pyplot.savefig('cc_hist_%d.png' % j)
pyplot.close()
def convert_to_histogram(data, n_slots) : histogram = flex.histogram(data=data, n_slots=n_slots) return histogram
def set_ensemble_b_factors_to_xyz_displacement(
pdb_hierarchy,
include_hydrogens=False,
include_waters=False,
use_c_alpha_values=False,
method="rmsf",
selection=None,
substitute_b_value=-1.0,
logarithmic=False,
log=None,
):
"""
Given an ensemble (multi-MODEL PDB hierarchy), calculate the deviation
between copies of each atom (defined here as either the root-mean-square
fluctuation, or the radius of the minimum covering sphere) and set the
isotropic B-factors to this value.
"""
if log is None:
log = null_out()
assert method in ["rmsf", "mcs"]
from scitbx.math import minimum_covering_sphere
from scitbx.array_family import flex
pdb_atoms = pdb_hierarchy.atoms()
pdb_atoms.reset_i_seq()
xyz_by_atom = {}
def get_key(atom):
labels = atom.fetch_labels()
return (labels.chain_id, labels.resid(), labels.altloc, atom.name)
def get_c_alpha(atom):
if (atom.name.strip() == "CA") and (atom.element.strip() == "C"):
return atom
for other in atom.parent().atoms():
if (other.name.strip() == "CA") and (other.element.strip() == "C"):
return other
return None
for model in pdb_hierarchy.models():
for atom in model.atoms():
if selection is not None:
if not selection[atom.i_seq]:
continue
elif (not include_hydrogens) and (atom.element.strip() in ["H", "D"]):
continue
elif (not include_waters) and (atom.parent().resname in ["HOH"]):
continue
if (use_c_alpha_values) and (atom.name.strip() != "CA"):
continue
atom_key = get_key(atom)
if atom_key in xyz_by_atom:
xyz_by_atom[atom_key].append(atom.xyz)
else:
xyz_by_atom[atom_key] = flex.vec3_double([atom.xyz])
dev_by_atom = {}
for atom_key, xyz in xyz_by_atom.iteritems():
if method == "mcs":
mcs = minimum_covering_sphere(points=xyz, epsilon=0.1)
radius = mcs.radius()
if logarithmic:
radius = math.log(radius + 1.0)
dev_by_atom[atom_key] = radius
else:
mean_array = flex.vec3_double(xyz.size(), xyz.mean())
rmsf = xyz.rms_difference(mean_array)
dev_by_atom[atom_key] = rmsf
all_dev = flex.double(dev_by_atom.values())
if method == "mcs":
print >> log, "Distribution of sphere radii:"
else:
print >> log, "Distribution of root-mean-square fluctuation values:"
flex.histogram(all_dev, n_slots=20).show(f=log, prefix=" ", format_cutoffs="%.2f")
for model in pdb_hierarchy.models():
for atom in model.atoms():
if use_c_alpha_values:
c_alpha = get_c_alpha(atom)
if c_alpha is None:
atom.b = substitute_b_value
else:
atom_key = get_key(c_alpha)
atom.b = dev_by_atom.get(atom_key, substitute_b_value)
else:
atom_key = get_key(atom)
atom.b = dev_by_atom.get(atom_key, substitute_b_value)
def __init__ (self,
cmd_list,
nprocs=1,
out=sys.stdout,
log=None,
quiet=False,
output_junit_xml=False) :
if (log is None) : log = null_out()
self.out = multi_out()
self.log = log
self.out.register("stdout", out)
self.out.register("log", log)
self.quiet = quiet
self.cmd_list = []
for cmd in cmd_list :
if (not cmd in self.cmd_list) :
self.cmd_list.append(cmd)
else :
print >> self.out, " test %s repeated, skipping" % cmd
nprocs = min(nprocs, len(self.cmd_list))
print >> self.out, "\n Starting command list"
print >> self.out, " NProcs :",nprocs
print >> self.out, " Cmds :",len(self.cmd_list)
t_start = time.time()
if nprocs>1:
pool = Pool(processes=nprocs)
self.results = []
for command in self.cmd_list:
if nprocs>1:
pool.apply_async(
run_command,
[command, (not quiet), out],
callback=self.save_result)
else:
rc = run_command(command, verbose=(not quiet), out=out)
self.save_result(rc)
if nprocs>1:
try :
try :
pool.close()
except KeyboardInterrupt :
print >> self.out, "Caught KeyboardInterrupt, terminating"
pool.terminate()
finally :
pool.join()
print >> self.out, '\nProcesses have joined : %d\n' % len(self.results)
t_end = time.time()
print >> self.out, ""
print >> self.out, "Elapsed time: %.2fs" %(t_end-t_start)
print >> self.out, ""
finished = 0
warning = 0
extra_stderr = 0
failure = 0
failures = []
long_jobs = []
long_runtimes = []
runtimes = []
if output_junit_xml:
from junit_xml import TestSuite, TestCase
test_cases = []
for result in self.results :
finished += 1
runtimes.append(result.wall_time)
if (result.return_code != 0) :
failure += 1
failures.append(result)
else :
if (len(result.error_lines) != 0) :
warning += 1
failures.append(result)
if (len(result.stderr_lines) != 0):
extra_stderr += 1
if (result.wall_time > max_time) :
long_jobs.append(result.command)
long_runtimes.append(result.wall_time)
if output_junit_xml:
tc = TestCase(name=result.command,
classname=result.command,
elapsed_sec=result.wall_time,
stdout='\n'.join(result.stdout_lines),
stderr='\n'.join(result.stderr_lines))
if result.return_code != 0:
tc.add_failure_info(message='exit code %d' %result.return_code)
#if len(result.stderr_lines):
#tc.add_error_info(output='\n'.join(result.stderr_lines))
test_cases.append(tc)
if output_junit_xml:
ts = TestSuite("libtbx.run_tests_parallel", test_cases=test_cases)
with open('output.xml', 'wb') as f:
print >> f, TestSuite.to_xml_string([ts], prettyprint=True)
if (libtbx.env.has_module("scitbx")) :
from scitbx.array_family import flex
print >> self.out, "Distribution of test runtimes:"
hist = flex.histogram(flex.double(runtimes), n_slots=20)
hist.show(f=self.out, prefix=" ", format_cutoffs="%.1fs")
print >> self.out, ""
if (len(long_jobs) > 0) :
print >> self.out, ""
print >> self.out, "WARNING: the following jobs took at least %d seconds:" % \
max_time
jobs_and_timings = list(zip(long_jobs, long_runtimes))
jobs_and_timings.sort(lambda x,y: cmp(x[1], y[1]))
for cmd, runtime in jobs_and_timings :
print >> self.out, " " + cmd + " : %.1fs" % runtime
print >> self.out, "Please try to reduce overall runtime - consider splitting up these tests."
if (len(failures) > 0) :
print >> self.out, ""
print >> self.out, "ERROR: the following jobs returned non-zero exit codes or suspicious stderr output:"
for result in failures :
print >> self.out, ""
print >> self.out, result.command + "(exit code %d):" % result.return_code
for line in result.stderr_lines :
print >> self.out, " " + line
for line in result.error_lines :
print >> self.out, " " + line
print >> self.out, ""
print >> self.out, "Please verify these tests manually."
print >> self.out, ""
print >> self.out, "Summary:"
print >> self.out, " Tests run :",finished
print >> self.out, " Failures :",failure
print >> self.out, " Warnings (possible failures) :",warning
print >> self.out, " Stderr output (discouraged) :",extra_stderr
if (finished != len(self.cmd_list)) :
print >> self.out, "*" * 80
print >> self.out, " WARNING: NOT ALL TESTS FINISHED!"
print >> self.out, "*" * 80
def run(self, flags, sweep=None, observations=None, **kwargs):
obs_x, obs_y = observations.centroids().px_position_xy().parts()
import numpy as np
H, xedges, yedges = np.histogram2d(
obs_x.as_numpy_array(), obs_y.as_numpy_array(),bins=self.nbins)
from scitbx.array_family import flex
H_flex = flex.double(H.flatten().astype(np.float64))
n_slots = min(int(flex.max(H_flex)), 30)
hist = flex.histogram(H_flex, n_slots=n_slots)
slots = hist.slots()
cumulative_hist = flex.long(len(slots))
for i in range(len(slots)):
cumulative_hist[i] = slots[i]
if i > 0:
cumulative_hist[i] += cumulative_hist[i-1]
cumulative_hist = cumulative_hist.as_double()/flex.max(
cumulative_hist.as_double())
cutoff = None
gradients = flex.double()
for i in range(len(slots)-1):
x1 = cumulative_hist[i]
x2 = cumulative_hist[i+1]
g = (x2 - x1)/hist.slot_width()
gradients.append(g)
if (cutoff is None and i > 0 and
g < self.gradient_cutoff and gradients[i-1] < self.gradient_cutoff):
cutoff = hist.slot_centers()[i-1]-0.5*hist.slot_width()
H_flex = flex.double(np.ascontiguousarray(H))
isel = (H_flex > cutoff).iselection()
sel = np.column_stack(np.where(H > cutoff))
for (ix, iy) in sel:
flags.set_selected(
((obs_x > xedges[ix]) & (obs_x < xedges[ix+1]) &
(obs_y > yedges[iy]) & (obs_y < yedges[iy+1])), False)
if 0:
from matplotlib import pyplot
fig, ax1 = pyplot.subplots()
extent = [yedges[0], yedges[-1], xedges[0], xedges[-1]]
plot1 = ax1.imshow(H, extent=extent, interpolation="nearest")
pyplot.xlim((0, pyplot.xlim()[1]))
pyplot.ylim((0, pyplot.ylim()[1]))
pyplot.gca().invert_yaxis()
cbar1 = pyplot.colorbar(plot1)
pyplot.axes().set_aspect('equal')
pyplot.show()
fig, ax1 = pyplot.subplots()
ax2 = ax1.twinx()
ax1.scatter(hist.slot_centers()-0.5*hist.slot_width(), cumulative_hist)
ax1.set_ylim(0, 1)
ax2.plot(hist.slot_centers()[:-1]-0.5*hist.slot_width(), gradients)
ymin, ymax = pyplot.ylim()
pyplot.vlines(cutoff, ymin, ymax, color='r')
pyplot.show()
H2 = H.copy()
if cutoff is not None:
H2[np.where(H2 >= cutoff)] = 0
fig, ax1 = pyplot.subplots()
plot1 = ax1.pcolormesh(xedges, yedges, H2)
pyplot.xlim((0, pyplot.xlim()[1]))
pyplot.ylim((0, pyplot.ylim()[1]))
pyplot.gca().invert_yaxis()
cbar1 = pyplot.colorbar(plot1)
pyplot.axes().set_aspect('equal')
pyplot.show()
return flags
def __init__ (self,
cmd_list,
nprocs=1,
out=sys.stdout,
log=None,
verbosity=DEFAULT_VERBOSITY,
output_junit_xml=False) :
if (log is None) : log = null_out()
self.out = multi_out()
self.log = log
self.out.register("stdout", out)
self.out.register("log", log)
self.verbosity = verbosity
self.quiet = (verbosity == 0)
self.results = []
# Filter cmd list for duplicates.
self.cmd_list = []
for cmd in cmd_list :
if (not cmd in self.cmd_list) :
self.cmd_list.append(cmd)
else :
print >> self.out, "Test %s repeated, skipping"%cmd
# Set number of processors.
if (nprocs is Auto) :
nprocs = cpu_count()
nprocs = min(nprocs, len(self.cmd_list))
# Starting summary.
if (self.verbosity > 0) :
print >> self.out, "Running %d tests on %s processors:"%(len(self.cmd_list), nprocs)
for cmd in self.cmd_list:
print >> self.out, " %s"%cmd
print >> self.out, ""
t_start = time.time()
if nprocs > 1:
# Run the tests with multiprocessing pool.
pool = Pool(processes=nprocs)
for command in self.cmd_list:
pool.apply_async(
run_command,
[command, verbosity, out],
callback=self.save_result)
try:
pool.close()
except KeyboardInterrupt:
print >> self.out, "Caught KeyboardInterrupt, terminating"
pool.terminate()
finally:
pool.join()
else:
# Run tests serially.
for command in self.cmd_list:
rc = run_command(command, verbosity=verbosity, out=out)
self.save_result(rc)
# Print ending summary.
t_end = time.time()
print >> self.out, "="*80
print >> self.out, ""
print >> self.out, "Tests finished. Elapsed time: %.2fs" %(t_end-t_start)
print >> self.out, ""
extra_stderr = 0
test_cases = []
# Process results for errors and warnings.
extra_stderr = len([result for result in self.results if result.stderr_lines])
longjobs = [result for result in self.results if result.wall_time > MAX_TIME]
warnings = [result for result in self.results if self.check_alert(result) == 1]
failures = [result for result in self.results if self.check_alert(result) == 2]
self.finished = len(self.results)
self.failure = len(failures)
self.warning = len(warnings)
# Output JUnit XML
if output_junit_xml:
from junit_xml import TestSuite, TestCase
for result in self.results:
tc = TestCase(name=result.command,
classname=result.command,
elapsed_sec=result.wall_time,
stdout='\n'.join(result.stdout_lines),
stderr='\n'.join(result.stderr_lines))
if result.return_code != 0:
tc.add_failure_info(message='exit code %d' %result.return_code)
#if len(result.stderr_lines):
#tc.add_error_info(output='\n'.join(result.stderr_lines))
test_cases.append(tc)
ts = TestSuite("libtbx.run_tests_parallel", test_cases=test_cases)
with open('output.xml', 'wb') as f:
print >> f, TestSuite.to_xml_string([ts], prettyprint=True)
# Run time distribution.
if (libtbx.env.has_module("scitbx")) :
from scitbx.array_family import flex
print >> self.out, "Distribution of test runtimes:"
hist = flex.histogram(flex.double([result.wall_time for result in self.results]), n_slots=10)
hist.show(f=self.out, prefix=" ", format_cutoffs="%.1fs")
print >> self.out, ""
# Long job warning.
if longjobs:
print >> self.out, ""
print >> self.out, "Warning: the following jobs took at least %d seconds:"%MAX_TIME
for result in sorted(longjobs, key=lambda result:result.wall_time):
print >> self.out, " %s: %.1fs"%(result.command, result.wall_time)
print >> self.out, "Please try to reduce overall runtime - consider splitting up these tests."
# Failures.
if failures:
print >> self.out, ""
print >> self.out, "Error: the following jobs returned non-zero exit codes or suspicious stderr output:"
print >> self.out, ""
for result in warnings:
self.display_result(result, alert=1, out=self.out, log_return=self.out, log_stderr=self.out)
for result in failures:
self.display_result(result, alert=2, out=self.out, log_return=self.out, log_stderr=self.out)
print >> self.out, ""
print >> self.out, "Please verify these tests manually."
print >> self.out, ""
# Summary
print >> self.out, "Summary:"
print >> self.out, " Tests run :",self.finished
print >> self.out, " Failures :",self.failure
print >> self.out, " Warnings (possible failures) :",self.warning
print >> self.out, " Stderr output (discouraged) :",extra_stderr
if (self.finished != len(self.cmd_list)) :
print >> self.out, "*" * 80
print >> self.out, " WARNING: NOT ALL TESTS FINISHED!"
print >> self.out, "*" * 80