def run(self, args):
#read inputs
from prime.postrefine.mod_input import process_input, read_pickles
iparams, txt_out_input = process_input(args)
runh = run_handler()
print txt_out_input
#read all integration pickles
frame_files = read_pickles(iparams.data)
n_frames = len(frame_files)
if n_frames == 0:
print "No integration pickle found. Exit program."
exit()
frames = [(i, frame_files[i], iparams) for i in range(n_frames)]
#run command to calculate mean_I
mm_I = 0
if iparams.flag_apply_b_by_frame == False:
inp_pickle = {'iparams':iparams, 'frames':frames}
pickle.dump(inp_pickle, open(iparams.run_no+'/inputs/0.inp',"wb"))
call(["prime._genref_determine_mean_I", iparams.run_no+'/inputs/0.inp'])
runh.check_done(iparams, n_frames)
mm_I = calc_mean_of_mean_I(iparams)
#run command for scaling
frames = [(i, frame_files[i], iparams, mm_I) for i in range(n_frames)]
inp_pickle = {'iparams':iparams, 'frames':frames}
pickle.dump(inp_pickle, open(iparams.run_no+'/inputs/0.inp',"wb"))
call(["prime._genref_scale_frame_by_mean_I", iparams.run_no+'/inputs/0.inp'])
runh.check_done(iparams, n_frames)
#write output to logfile
txt_out = 'Scaling complete. Run prime.merge your_input_phil.phil to merge for a reference set.\n'
print txt_out
f = open(iparams.run_no+'/log.txt', 'w')
f.write(txt_out_input+txt_out)
f.close()
def main(data, only_merohedral):
indambh = indamb_handler()
intFileList = read_pickles([data])
if intFileList:
obsList = {}
for intFileName in intFileList:
intPickle = read_frame(intFileName)
try:
obs = intPickle['observations'][0]
obsList[intFileName] = obs
except Exception as e:
print "Warning:", e
pass
for key, value in obsList.iteritems():
if only_merohedral:
flag_all = False
else:
flag_all = True
ops = indambh.generate_twin_operators(value, flag_all=flag_all)
if ops:
print os.path.basename(
key
), '%6.1f,%6.1f,%6.1f,%6.1f,%6.1f,%6.1f' % value.unit_cell(
).parameters(), ' '.join(
[op.operator.r().as_hkl() for op in ops])
else:
print os.path.basename(
key
), '%6.1f,%6.1f,%6.1f,%6.1f,%6.1f,%6.1f' % value.unit_cell(
).parameters(), 'Twining operators not found'
def run(argv):
comm.Barrier()
start_time = MPI.Wtime()
# broadcast parameters
if rank == 0:
iparams, txt_out_input = process_input(argv)
iparams.flag_volume_correction = False
iparams.flag_hush = True
print(txt_out_input)
frame_files = read_pickles(iparams.data)
else:
iparams = None
frame_files = None
txt_out_input = None
comm.Barrier()
# assign scaling task
if rank == 0:
master(frame_files, iparams, "scale")
result = []
else:
result = client()
result = comm.gather(result, root=0)
comm.Barrier()
_, mdh = merge(result, iparams, txt_out_input, "mean_scaled", "average")
# postrefine task
if rank == 0:
n_postref_cycle = iparams.n_postref_cycle
results = [None] * len(frame_files)
else:
n_postref_cycle = None
results = None
n_postref_cycle = comm.bcast(n_postref_cycle, root=0)
avg_mode = "weighted"
for i_iter in range(n_postref_cycle):
comm.Barrier()
if i_iter == n_postref_cycle - 1:
avg_mode = "final"
if rank == 0:
print("Start post-refinement cycle %d" % (i_iter + 1))
master(
(frame_files, mdh.miller_array_merge, results, avg_mode),
iparams,
"postref",
)
result = []
else:
result = client()
result = comm.gather(result, root=0)
comm.Barrier()
results, mdh = merge(result, iparams, "",
"postref_cycle_%d" % (i_iter + 1), avg_mode)
# collect time profile
comm.Barrier()
end_time = MPI.Wtime()
txt_time = "Elapsed Time (s):%10.2f\n" % (end_time - start_time)
MPI.Finalize()
def run_by_params(self, iparams):
runh = run_handler()
#read all integration pickles
from prime.postrefine.mod_input import read_pickles
frame_files = read_pickles(iparams.data)
n_frames = len(frame_files)
if n_frames == 0:
print "No integration pickle found. Exit program."
exit()
frames = [(i, frame_files[i], iparams) for i in range(n_frames)]
mm_I = 0
#run command to calculate mean_I
if iparams.flag_apply_b_by_frame == False:
inp_pickle = {'iparams':iparams, 'frames':frames}
pickle.dump(inp_pickle, open(iparams.run_no+'/inputs/0.inp',"wb"))
call(["prime._genref_determine_mean_I", iparams.run_no+'/inputs/0.inp'])
runh.check_done(iparams, n_frames)
mm_I = calc_mean_of_mean_I(iparams)
#run command for scaling
if iparams.queue.mode is None:
#run single node
frames = [(i, frame_files[i], iparams, mm_I) for i in range(n_frames)]
inp_pickle = {'iparams':iparams, 'frames':frames}
pickle.dump(inp_pickle, open(iparams.run_no+'/inputs/0.inp',"wb"))
call(["prime._genref_scale_frame_by_mean_I", iparams.run_no+'/inputs/0.inp'])
else:
#run on n_nodes
n_imgs_per_node = int(round(n_frames/iparams.queue.n_nodes))
for i_node in range(iparams.queue.n_nodes):
start_frame = i_node*n_imgs_per_node
if i_node < iparams.queue.n_nodes - 1:
end_frame = start_frame + n_imgs_per_node
else:
end_frame = n_frames
frames = [(i, frame_files[i], iparams, mm_I) for i in range(start_frame, end_frame)]
inp_pickle = {'iparams':iparams, 'frames':frames}
pickle.dump(inp_pickle, open(iparams.run_no+'/inputs/'+str(i_node)+'.inp',"wb"))
call(["bsub","-q",iparams.queue.qname,"-o",iparams.run_no+"/qout/qout_gr.txt","prime._genref_scale_frame_by_mean_I", iparams.run_no+"/inputs/"+str(i_node)+".inp"])
runh.check_done(iparams, n_frames)
#write output to logfile
txt_out = 'Scaling complete. Run prime.merge your_input_phil.phil to merge for a reference set.\n'
print txt_out
f = open(iparams.run_no+'/log.txt', 'a')
f.write(txt_out)
f.close()
def run(self, args):
#read inputs
from prime.postrefine.mod_input import process_input, read_pickles
iparams, txt_out_input = process_input(args)
print txt_out_input
f = open(iparams.run_no+'/log.txt', 'w')
f.write(txt_out_input)
f.close()
#if solution pickle is given, return the file name
if iparams.indexing_ambiguity.index_basis_in is not None:
if iparams.indexing_ambiguity.index_basis_in.endswith('.pickle'):
return iparams.indexing_ambiguity.index_basis_in, iparams
#read all integration pickles
frame_files = read_pickles(iparams.data)
n_frames = len(frame_files)
if n_frames == 0:
print "No integration pickle found. Exit program."
return None, iparams
#exit if no problem
if self.should_terminate(iparams, frame_files[0]):
print "No indexing ambiguity problem. Set index_ambiguity.mode = Forced and assigned_basis = list of basis formats to solve pseudo-twinning problem."
return None, iparams
#continue with (Auto - alt>1, find solution), (Auto - alt>1, mtz)
#(Forced - assigned_basis, mtz), (Forced - assigned_basis, find solution)
#*************************************************
#if mtz file is given, use it to solve the problem
sol_fname = iparams.run_no+'/index_ambiguity/solution_pickle.pickle'
if iparams.indexing_ambiguity.index_basis_in is not None:
if iparams.indexing_ambiguity.index_basis_in.endswith('.mtz'):
mxh = mx_handler()
flag_ref_found, miller_array_ref = mxh.get_miller_array_from_reflection_file(iparams.indexing_ambiguity.index_basis_in)
if flag_ref_found == False:
print "Reference mtz file not found. Set indexing_ambiguity.index_basis_in = None to enable auto generate the solutions."
return None, iparams
else:
frames = [(i, frame_files[i], iparams, miller_array_ref) for i in range(n_frames)]
cc_results = pool_map(
iterable=frames,
func=solve_with_mtz_mproc,
processes=iparams.n_processors)
sol_pickle = {}
for result in cc_results:
pickle_filename, index_basis = result
sol_pickle[pickle_filename] = index_basis
pickle.dump(sol_pickle, open(sol_fname,"wb"))
return sol_fname, iparams
#*************************************************
#solve with Brehm & Diederichs - sample size n_sample_frames then bootstrap the rest
frames = [(i, frame_files[i], iparams) for i in random.sample(range(n_frames), iparams.indexing_ambiguity.n_sample_frames)]
#get observations list
print "Reading observations"
alt_dict_results = pool_map(
iterable=frames,
func=get_obs_mproc,
processes=iparams.n_processors)
frame_dup_files = []
frame_keys = []
obs_list = []
for result in alt_dict_results:
alt_dict, pickle_filename = result
if alt_dict is not None:
for key in alt_dict.keys():
frame_dup_files.append(pickle_filename)
frame_keys.append(key)
obs_list.append(alt_dict[key])
frames = [(i, frame_dup_files[i], frame_keys[i], obs_list[i], obs_list) for i in range(len(frame_dup_files))]
#calculate r
print "Calculating R"
calc_r_results = pool_map(
iterable=frames,
func=calculate_r_mproc,
processes=iparams.n_processors)
frame_dup_files = []
frame_keys = []
r_matrix = []
for result in calc_r_results:
if result is not None:
pickle_filename, index_basis, r_set = result
frame_dup_files.append(pickle_filename)
frame_keys.append(index_basis)
if len(r_matrix) == 0:
r_matrix = r_set
else:
r_matrix = np.append(r_matrix, r_set, axis=0)
#choose groups with best CC
print "Selecting frames with best R"
i_mean_r = np.argsort(np.mean(r_matrix, axis=1))[::-1]
r_matrix_sorted = r_matrix[i_mean_r]
frame_dup_files_sorted = np.array(frame_dup_files)[i_mean_r]
frame_keys_sorted = np.array(frame_keys)[i_mean_r]
frame_dup_files_sel = []
for frame_file, frame_key, r_set in zip(frame_dup_files_sorted, frame_keys_sorted, r_matrix_sorted):
if frame_file not in frame_dup_files_sel:
frame_dup_files_sel.append(frame_file)
print frame_file, frame_key, np.mean(r_set)
if len(frame_dup_files_sel) >= iparams.indexing_ambiguity.n_selected_frames:
print 'Found all %6.0f good frames'%(len(frame_dup_files_sel))
break
##
#rebuild observations and r_matrix
frames = [(i, frame_dup_files_sel[i], iparams) for i in range(len(frame_dup_files_sel))]
#get observations list
print "Re-reading observations"
alt_dict_results = pool_map(
iterable=frames,
func=get_obs_mproc,
processes=iparams.n_processors)
frame_dup_files = []
frame_keys = []
obs_list = []
for result in alt_dict_results:
alt_dict, pickle_filename = result
if alt_dict is not None:
for key in alt_dict.keys():
frame_dup_files.append(pickle_filename)
frame_keys.append(key)
obs_list.append(alt_dict[key])
frames = [(i, frame_dup_files[i], frame_keys[i], obs_list[i], obs_list) for i in range(len(frame_dup_files))]
#calculate r
print "Re-calculating R"
calc_r_results = pool_map(
iterable=frames,
func=calculate_r_mproc,
processes=iparams.n_processors)
frame_dup_files = []
frame_keys = []
r_matrix = []
for result in calc_r_results:
if result is not None:
pickle_filename, index_basis, r_set = result
frame_dup_files.append(pickle_filename)
frame_keys.append(index_basis)
if len(r_matrix) == 0:
r_matrix = r_set
else:
r_matrix = np.append(r_matrix, r_set, axis=0)
print "Minimizing frame distance"
idah = indamb_handler()
x_set = idah.optimize(r_matrix, flag_plot=iparams.flag_plot)
x_pickle = {'frame_dup_files':frame_dup_files, 'frame_keys':frame_keys, \
'r_matrix':r_matrix, 'x_set':x_set}
pickle.dump(x_pickle, open(iparams.run_no+'/index_ambiguity/x.out',"wb"))
print "Clustering results"
kmh = kmeans_handler()
k = 2**(len(idah.get_observations(frame_dup_files[0], iparams))-1)
centroids, labels = kmh.run(x_set, k, flag_plot=iparams.flag_plot)
print "Get solution pickle"
sample_fname = iparams.run_no+'/index_ambiguity/sample.lst'
sol_pickle = idah.assign_basis(frame_dup_files, frame_keys, labels, k, sample_fname)
pickle.dump(sol_pickle, open(sol_fname,"wb"))
#if more frames found, merge the sample frames to get a reference set
#that can be used for breaking the ambiguity.
if n_frames > iparams.indexing_ambiguity.n_selected_frames:
print "Breaking the indexing ambiguity for the remaining images."
old_iparams_data = iparams.data[:]
iparams.data = [sample_fname]
iparams.indexing_ambiguity.index_basis_in = sol_fname
grh = genref_handler()
grh.run_by_params(iparams)
mh = merge_handler()
mh.run_by_params(iparams)
DIR = iparams.run_no+'/mtz/'
file_no_list = [int(fname.split('.')[0]) for fname in os.listdir(DIR)]
if len(file_no_list) > 0:
hklref_indamb = DIR + str(max(file_no_list)) + '.mtz'
print "Bootstrap reference reflection set:", hklref_indamb
#setup a list of remaining frames
frame_files_remain = []
for frame in frame_files:
if frame not in sol_pickle:
frame_files_remain.append(frame)
#determine index basis
mxh = mx_handler()
flag_ref_found, miller_array_ref = mxh.get_miller_array_from_reflection_file(hklref_indamb)
frames = [(i, frame_files_remain[i], iparams, miller_array_ref) for i in range(len(frame_files_remain))]
cc_results = pool_map(
iterable=frames,
func=solve_with_mtz_mproc,
processes=iparams.n_processors)
for result in cc_results:
pickle_filename, index_basis = result
sol_pickle[pickle_filename] = index_basis
iparams.data = old_iparams_data[:]
#write out solution pickle
pickle.dump(sol_pickle, open(sol_fname,"wb"))
#write out text output
txt_out = "Solving indexing ambiguity complete. Solution file saved to "+sol_fname+"\n"
f = open(iparams.run_no+'/log.txt', 'a')
f.write(txt_out)
f.close()
return sol_fname, iparams
def run_by_params(self, iparams):
runh = run_handler()
#read all integration pickles
from prime.postrefine.mod_input import read_pickles
frame_files = read_pickles(iparams.data)
n_frames = len(frame_files)
if n_frames == 0:
print "No integration pickle found. Exit program."
exit()
frames = [(i, frame_files[i], iparams) for i in range(n_frames)]
mm_I = 0
#run command to calculate mean_I
if iparams.flag_apply_b_by_frame == False:
inp_pickle = {'iparams': iparams, 'frames': frames}
pickle.dump(inp_pickle, open(iparams.run_no + '/inputs/0.inp',
"wb"))
call([
"prime._genref_determine_mean_I",
iparams.run_no + '/inputs/0.inp'
])
runh.check_done(iparams, n_frames)
mm_I = calc_mean_of_mean_I(iparams)
#run command for scaling
if iparams.queue.mode is None:
#run single node
frames = [(i, frame_files[i], iparams, mm_I)
for i in range(n_frames)]
inp_pickle = {'iparams': iparams, 'frames': frames}
pickle.dump(inp_pickle, open(iparams.run_no + '/inputs/0.inp',
"wb"))
call([
"prime._genref_scale_frame_by_mean_I",
iparams.run_no + '/inputs/0.inp'
])
else:
#run on n_nodes
n_imgs_per_node = int(round(n_frames / iparams.queue.n_nodes))
for i_node in range(iparams.queue.n_nodes):
start_frame = i_node * n_imgs_per_node
if i_node < iparams.queue.n_nodes - 1:
end_frame = start_frame + n_imgs_per_node
else:
end_frame = n_frames
frames = [(i, frame_files[i], iparams, mm_I)
for i in range(start_frame, end_frame)]
inp_pickle = {'iparams': iparams, 'frames': frames}
pickle.dump(
inp_pickle,
open(iparams.run_no + '/inputs/' + str(i_node) + '.inp',
"wb"))
call([
"bsub", "-q", iparams.queue.qname, "-o",
iparams.run_no + "/qout/qout_gr.txt",
"prime._genref_scale_frame_by_mean_I",
iparams.run_no + "/inputs/" + str(i_node) + ".inp"
])
runh.check_done(iparams, n_frames)
#write output to logfile
txt_out = 'Scaling complete. Run prime.merge your_input_phil.phil to merge for a reference set.\n'
print txt_out
f = open(iparams.run_no + '/log.txt', 'a')
f.write(txt_out)
f.close()
def run(argv):
comm.Barrier()
start_time = MPI.Wtime()
# broadcast parameters
if rank == 0:
iparams, txt_out_input = process_input(argv)
iparams.flag_volume_correction = False
iparams.flag_hush = True
print(txt_out_input)
frame_files = read_pickles(iparams.data)
else:
iparams = None
frame_files = None
comm.Barrier()
# assign scaling task
if rank == 0:
master(frame_files, iparams, "scale")
result = []
else:
result = client()
result = comm.gather(result, root=0)
comm.Barrier()
# pre-merge task
if rank == 0:
results = sum(result, [])
print("Scaling is done on %d cores for %d frames" %
(size, len(results)))
master(results, iparams, "pre_merge")
result = []
else:
result = client()
result = comm.gather(result, root=0)
comm.Barrier()
# merge task
if rank == 0:
print("Pre-merge is done on %d cores" % (len(result)))
master(result, iparams, "merge")
result = []
else:
result = client()
# finalize merge
result = comm.gather(result, root=0)
comm.Barrier()
if rank == 0:
print("Merge completed on %d cores" % (len(result)))
results = sum(result, [])
mdh = merge_data_handler()
txt_out_rejection = ""
for _mdh, _txt_out_rejection in results:
mdh.extend(_mdh)
txt_out_rejection += _txt_out_rejection
# selet only indices with non-Inf non-Nan stats
selections = flex.bool([
False if (math.isnan(r0) or math.isinf(r0) or math.isnan(r1)
or math.isinf(r1)) else True
for r0, r1 in zip(mdh.r_meas_div, mdh.r_meas_divisor)
])
mdh.reduce_by_selection(selections)
its = intensities_scaler()
mdh, txt_merge_mean_table = its.write_output(mdh, iparams, "test",
"average")
print(txt_merge_mean_table)
# collect time profile
comm.Barrier()
end_time = MPI.Wtime()
txt_time = "Elapsed Time (s):%10.2f\n" % (end_time - start_time)
# write log output
if rank == 0:
print(txt_time)
with open(os.path.join(iparams.run_no, "log.txt"), "w") as f:
f.write(txt_out_input + txt_merge_mean_table + txt_time)
with open(os.path.join(iparams.run_no, "rejections.txt"), "w") as f:
f.write(txt_out_rejection)
MPI.Finalize()
def run(self, args):
#read inputs
from prime.postrefine.mod_input import process_input, read_pickles
iparams, txt_out_input = process_input(args)
print txt_out_input
f = open(iparams.run_no+'/log.txt', 'w')
f.write(txt_out_input)
f.close()
#if solution pickle is given, return the file name
if iparams.indexing_ambiguity.index_basis_in is not None:
if iparams.indexing_ambiguity.index_basis_in.endswith('.pickle'):
return iparams.indexing_ambiguity.index_basis_in, iparams
#read all integration pickles
frame_files = read_pickles(iparams.data)
n_frames = len(frame_files)
if n_frames == 0:
print "No integration pickle found. Exit program."
return None, iparams
#exit if no problem
if self.should_terminate(iparams, frame_files[0]):
print "No indexing ambiguity problem. Set index_ambiguity.mode = Forced and assigned_basis = list of basis formats to solve pseudo-twinning problem."
return None, iparams
#continue with (Auto - alt>1, find solution), (Auto - alt>1, mtz)
#(Forced - assigned_basis, mtz), (Forced - assigned_basis, find solution)
#*************************************************
#if mtz file is given, use it to solve the problem
sol_fname = iparams.run_no+'/index_ambiguity/solution_pickle.pickle'
if iparams.indexing_ambiguity.index_basis_in is not None:
if iparams.indexing_ambiguity.index_basis_in.endswith('.mtz'):
mxh = mx_handler()
flag_ref_found, miller_array_ref = mxh.get_miller_array_from_reflection_file(iparams.indexing_ambiguity.index_basis_in)
if flag_ref_found == False:
print "Reference mtz file not found. Set indexing_ambiguity.index_basis_in = None to enable auto generate the solutions."
return None, iparams
else:
frames = [(i, frame_files[i], iparams, miller_array_ref) for i in range(n_frames)]
cc_results = pool_map(
iterable=frames,
func=solve_with_mtz_mproc,
processes=iparams.n_processors)
sol_pickle = {}
for result in cc_results:
pickle_filename, index_basis = result
sol_pickle[pickle_filename] = index_basis
pickle.dump(sol_pickle, open(sol_fname,"wb"))
return sol_fname, iparams
#*************************************************
#solve with Brehm & Diederichs - sample size n_sample_frames then bootstrap the rest
frames = [(i, frame_files[i], iparams) for i in random.sample(range(n_frames), iparams.indexing_ambiguity.n_sample_frames)]
#get observations list
print "Reading observations"
alt_dict_results = pool_map(
iterable=frames,
func=get_obs_mproc,
processes=iparams.n_processors)
frame_dup_files = []
frame_keys = []
obs_list = []
for result in alt_dict_results:
alt_dict, pickle_filename = result
if alt_dict is not None:
for key in alt_dict.keys():
frame_dup_files.append(pickle_filename)
frame_keys.append(key)
obs_list.append(alt_dict[key])
frames = [(i, frame_dup_files[i], frame_keys[i], obs_list[i], obs_list) for i in range(len(frame_dup_files))]
#calculate r
print "Calculating R"
calc_r_results = pool_map(
iterable=frames,
func=calculate_r_mproc,
processes=iparams.n_processors)
frame_dup_files = []
frame_keys = []
r_matrix = []
for result in calc_r_results:
if result is not None:
pickle_filename, index_basis, r_set = result
frame_dup_files.append(pickle_filename)
frame_keys.append(index_basis)
if len(r_matrix) == 0:
r_matrix = r_set
else:
r_matrix = np.append(r_matrix, r_set, axis=0)
#choose groups with best CC
print "Selecting frames with best R"
i_mean_r = np.argsort(np.mean(r_matrix, axis=1))[::-1]
r_matrix_sorted = r_matrix[i_mean_r]
frame_dup_files_sorted = np.array(frame_dup_files)[i_mean_r]
frame_keys_sorted = np.array(frame_keys)[i_mean_r]
frame_dup_files_sel = []
for frame_file, frame_key, r_set in zip(frame_dup_files_sorted, frame_keys_sorted, r_matrix_sorted):
if frame_file not in frame_dup_files_sel:
frame_dup_files_sel.append(frame_file)
print frame_file, frame_key, np.mean(r_set)
if len(frame_dup_files_sel) >= iparams.indexing_ambiguity.n_selected_frames:
print 'Found all %6.0f good frames'%(len(frame_dup_files_sel))
break
##
#rebuild observations and r_matrix
frames = [(i, frame_dup_files_sel[i], iparams) for i in range(len(frame_dup_files_sel))]
#get observations list
print "Re-reading observations"
alt_dict_results = pool_map(
iterable=frames,
func=get_obs_mproc,
processes=iparams.n_processors)
frame_dup_files = []
frame_keys = []
obs_list = []
for result in alt_dict_results:
alt_dict, pickle_filename = result
if alt_dict is not None:
for key in alt_dict.keys():
frame_dup_files.append(pickle_filename)
frame_keys.append(key)
obs_list.append(alt_dict[key])
frames = [(i, frame_dup_files[i], frame_keys[i], obs_list[i], obs_list) for i in range(len(frame_dup_files))]
#calculate r
print "Re-calculating R"
calc_r_results = pool_map(
iterable=frames,
func=calculate_r_mproc,
processes=iparams.n_processors)
frame_dup_files = []
frame_keys = []
r_matrix = []
for result in calc_r_results:
if result is not None:
pickle_filename, index_basis, r_set = result
frame_dup_files.append(pickle_filename)
frame_keys.append(index_basis)
if len(r_matrix) == 0:
r_matrix = r_set
else:
r_matrix = np.append(r_matrix, r_set, axis=0)
print "Minimizing frame distance"
idah = indamb_handler()
x_set = idah.optimize(r_matrix, flag_plot=iparams.flag_plot)
x_pickle = {'frame_dup_files':frame_dup_files, 'frame_keys':frame_keys, \
'r_matrix':r_matrix, 'x_set':x_set}
pickle.dump(x_pickle, open(iparams.run_no+'/index_ambiguity/x.out',"wb"))
print "Clustering results"
kmh = kmeans_handler()
k = 2**(len(idah.get_observations(frame_dup_files[0], iparams))-1)
centroids, labels = kmh.run(x_set, k, flag_plot=iparams.flag_plot)
print "Get solution pickle"
sample_fname = iparams.run_no+'/index_ambiguity/sample.lst'
sol_pickle = idah.assign_basis(frame_dup_files, frame_keys, labels, k, sample_fname)
pickle.dump(sol_pickle, open(sol_fname,"wb"))
#if more frames found, merge the sample frames to get a reference set
#that can be used for breaking the ambiguity.
if n_frames > iparams.indexing_ambiguity.n_selected_frames:
print "Breaking the indexing ambiguity for the remaining images."
old_iparams_data = iparams.data[:]
iparams.data = [sample_fname]
iparams.indexing_ambiguity.index_basis_in = sol_fname
grh = genref_handler()
grh.run_by_params(iparams)
mh = merge_handler()
mh.run_by_params(iparams)
DIR = iparams.run_no+'/mtz/'
file_no_list = [int(fname.split('.')[0]) for fname in os.listdir(DIR)]
if len(file_no_list) > 0:
hklref_indamb = DIR + str(max(file_no_list)) + '.mtz'
print "Bootstrap reference reflection set:", hklref_indamb
#setup a list of remaining frames
frame_files_remain = []
for frame in frame_files:
if frame not in sol_pickle:
frame_files_remain.append(frame)
#determine index basis
mxh = mx_handler()
flag_ref_found, miller_array_ref = mxh.get_miller_array_from_reflection_file(hklref_indamb)
frames = [(i, frame_files_remain[i], iparams, miller_array_ref) for i in range(len(frame_files_remain))]
cc_results = pool_map(
iterable=frames,
func=solve_with_mtz_mproc,
processes=iparams.n_processors)
for result in cc_results:
pickle_filename, index_basis = result
sol_pickle[pickle_filename] = index_basis
iparams.data = old_iparams_data[:]
#write out solution pickle
pickle.dump(sol_pickle, open(sol_fname,"wb"))
#write out text output
txt_out = "Solving indexing ambiguity complete. Solution file saved to "+sol_fname+"\n"
f = open(iparams.run_no+'/log.txt', 'a')
f.write(txt_out)
f.close()
return sol_fname, iparams
def run(argv):
#capture starting time
time_global_start = datetime.now()
import logging
logging.captureWarnings(True)
formatter = logging.Formatter('%(asctime)s\t%(levelname)s\t%(message)s')
console_handler = logging.StreamHandler()
console_handler.setLevel(logging.ERROR)
console_handler.setFormatter(formatter)
logging.getLogger().addHandler(console_handler)
logging.getLogger('py.warnings').addHandler(console_handler)
logging.basicConfig(format='%(asctime)s\t%(levelname)s\t%(message)s',
level=logging.DEBUG)
#0.1 determine indexing ambiguity and setup iparams
txt_indexing_ambiguity = "Determine if there is an indexing ambiguity on the dataset"
print txt_indexing_ambiguity
idah = indexing_ambiguity_handler()
sol_fname, iparams = idah.run(argv)
if sol_fname is None:
print "No ambiguity."
txt_indexing_ambiguity += "\nNo ambiguity."
else:
print "Ambiguity is solved. Solution file was saved to :" + str(
sol_fname)
txt_indexing_ambiguity += "Ambiguity is solved. Solution file was saved to :" + str(
sol_fname)
iparams.indexing_ambiguity.index_basis_in = sol_fname
#0.2 setup parameters
iparams.flag_volume_correction = False
if iparams.partiality_model == "Lognormal":
iparams.voigt_nu = 0.008 #use voigt_nu as lognpdf zero parameter
#0.3 read frames
frame_files = read_pickles(iparams.data)
frames = range(len(frame_files))
#1. prepare reference miller array
txt_merge_mean = 'Generating a reference set (will not be used if hklrefin is set)'
print txt_merge_mean
#Always generate the mean-intensity scaled set.
scaled_pres_set = scale_frames(frames, frame_files, iparams)
mdh, _txt_merge_mean = merge_frames(scaled_pres_set, iparams)
miller_array_ref = mdh.miller_array_merge
txt_merge_mean += '\n' + _txt_merge_mean
if not iparams.n_postref_cycle:
with open(iparams.run_no + '/log.txt', 'a') as f:
f.write(txt_indexing_ambiguity + txt_merge_mean)
raise Usage(
"No. of post-refinement cycle was set to 0. Exit without post-refinement."
)
if iparams.hklrefin is not None:
mxh = mx_handler()
_, miller_array_ref = mxh.get_miller_array_from_reflection_file(
iparams.hklrefin)
if miller_array_ref is None:
raise Usage(
"Problem with the assigned reference set. Try setting hklrefin=None and rerun the program."
)
#2. Post-refinement
txt_merge_postref = ''
postref_pres_set = [None] * len(frames)
avg_mode = 'weighted'
for i_iter in xrange(iparams.n_postref_cycle):
if i_iter == (iparams.n_postref_cycle - 1): avg_mode = 'final'
postref_good_pres_set, postref_pres_set, _txt_merge_postref = postrefine_frames(
i_iter, frames, frame_files, iparams, postref_pres_set,
miller_array_ref, avg_mode)
if postref_good_pres_set:
mdh, _txt_merge_postref = merge_frames(
postref_good_pres_set,
iparams,
avg_mode=avg_mode,
mtz_out_prefix='postref_cycle_' + str(i_iter + 1))
miller_array_ref = mdh.miller_array_merge
txt_merge_postref += _txt_merge_postref
else:
raise Usage(
"Problem with post-refinement. No images refined. Please check your input file."
)
#3. collect caculating time
time_global_end = datetime.now()
time_global_spent = time_global_end - time_global_start
txt_out_time_spent = 'Total calculation time: '+'{0:.2f}'.format(time_global_spent.seconds)+ \
' seconds\nFinished: '+time_global_end.strftime("%A %d. %B %Y %H:%M:%S")+'\n'
print txt_out_time_spent
txt_out = txt_indexing_ambiguity + txt_merge_mean + txt_merge_postref + txt_out_time_spent
with open(os.path.join(iparams.run_no, 'log.txt'), 'a') as f:
f.write(txt_out)
with open(os.path.join(iparams.run_no, '.done'), 'w') as f:
f.write('Done')
return mdh
exit()
if pixel_size_mm is None:
print "Please specify pixel size (eg. pixel_size_mm=0.079346)"
exit()
return data, hklrefin, pixel_size_mm, target_unit_cell, d_min, d_max
if (__name__ == "__main__"):
uc_tol = 3
ry, rz, re, rotx, roty = (0, 0, 0.008, 0, 0)
flag_beam_divergence = False
lambda_template = flex.double(range(-50, 50, 1)) / 1000
#0 .read input parameters and frames (pickle files)
data, hklrefin, pixel_size_mm, target_unit_cell, \
d_min, d_max = read_input(args = sys.argv[1:])
frame_files = read_pickles(data)
for pickle_filename in frame_files:
observations_pickle = read_frame(pickle_filename)
pickle_filename_arr = pickle_filename.split('/')
pickle_filename_only = pickle_filename_arr[len(pickle_filename_arr) -
1]
mxh = mx_handler()
flag_hklisoin_found, miller_array_iso = mxh.get_miller_array_from_reflection_file(
hklrefin)
observations = observations_pickle["observations"][0]
#check if the uc is good
flag_good_unit_cell = good_unit_cell(
observations.unit_cell().parameters(),
None,
uc_tol,
target_unit_cell=target_unit_cell)
def run(self, args):
#read inputs
from prime.postrefine.mod_input import process_input, read_pickles
iparams, txt_out_input = process_input(args)
print txt_out_input
with open(os.path.join(iparams.run_no, self.module_name, 'log.txt'),
'w') as f:
f.write(txt_out_input)
#read all integration pickles
frame_files = read_pickles(iparams.data)
n_frames = len(frame_files)
if n_frames == 0:
print "No integration pickle found. Exit program."
return None, iparams
#start
if iparams.isoform_cluster.isorefin:
#get collection of iso. ref. reflection set.
mxh = mx_handler()
miller_array_ref_set = []
for isorefin in iparams.isoform_cluster.isorefin:
flag_ref_found, miller_array_ref = mxh.get_miller_array_from_reflection_file(
isorefin)
if flag_ref_found:
miller_array_ref_set.append(miller_array_ref)
#get observation list
frame_files_sel, obs_list = self.get_observation_set(
iparams, frame_files, n_frames)
if miller_array_ref_set:
frames = [(i, frame_files_sel[i], obs_list[i], iparams,
miller_array_ref_set) for i in range(len(obs_list))]
cc_results = pool_map(iterable=frames,
func=solve_with_mtz_mproc,
processes=iparams.n_processors)
sol_pickle = {}
for result in cc_results:
pickle_filename, cluster_id = result
sol_pickle[pickle_filename] = cluster_id
write_out_solutions(iparams, sol_pickle)
txt_out = "Cluster images with given " + str(
len(miller_array_ref_set)
) + " mtz files completed. Use cluster_0.lst - cluster_k.lst (for k clusters) for merging.\n"
print txt_out
with open(
os.path.join(iparams.run_no, self.module_name,
'log.txt'), 'a') as f:
f.write(txt_out)
return
#*************************************************
#solve with Brehm & Diederichs - sample size n_sample_frames then bootstrap the rest
txt_out = "Cluster images with B&D algorithms.\n"
frame_files_sel, obs_list = self.get_observation_set(
iparams, frame_files, iparams.isoform_cluster.n_sample_frames)
frames = [(i, frame_files_sel[i], obs_list[i], obs_list)
for i in range(len(frame_files_sel))]
#calculate r
print "Calculating R"
calc_r_results = pool_map(iterable=frames,
func=calculate_r_mproc,
processes=iparams.n_processors)
frame_files_sel = []
r_matrix = []
obs_list = []
for result in calc_r_results:
if result:
pickle_filename, r_set, obs = result
frame_files_sel.append(pickle_filename)
obs_list.append(obs)
if len(r_matrix) == 0:
r_matrix = r_set
else:
r_matrix = np.append(r_matrix, r_set, axis=0)
#choose groups with best R
print "Selecting frames with best R"
i_mean_r = np.argsort(np.mean(r_matrix, axis=1))[::-1]
r_matrix_sorted = r_matrix[i_mean_r]
frame_files_sorted = np.array(frame_files_sel)[i_mean_r]
obs_list_sorted = np.array(obs_list)[i_mean_r]
frame_files_sel = []
obs_sel = []
for frame_file, r_set, obs in zip(frame_files_sorted, r_matrix_sorted,
obs_list_sorted):
if frame_file not in frame_files_sel:
frame_files_sel.append(frame_file)
obs_sel.append(obs)
print frame_file, np.mean(r_set)
if len(frame_files_sel
) >= iparams.isoform_cluster.n_selected_frames:
print 'Found all %6.0f good frames' % (
len(frame_files_sel))
break
#Recalculate r for the new selected list
frames = [(i, frame_files_sel[i], obs_sel[i], obs_sel)
for i in range(len(frame_files_sel))]
print "Re-calculating R"
calc_r_results = pool_map(iterable=frames,
func=calculate_r_mproc,
processes=iparams.n_processors)
frame_files_sel = []
r_matrix = []
obs_list = []
for result in calc_r_results:
if result:
pickle_filename, r_set, obs = result
frame_files_sel.append(pickle_filename)
obs_list.append(obs)
if len(r_matrix) == 0:
r_matrix = r_set
else:
r_matrix = np.append(r_matrix, r_set, axis=0)
print "Minimizing frame distance"
isoch = isoform_cluster_handler()
x_set = isoch.optimize(r_matrix, flag_plot=iparams.flag_plot)
print "Clustering results"
kmh = kmeans_handler()
k = iparams.isoform_cluster.n_clusters
centroids, labels = kmh.run(x_set, k, flag_plot=iparams.flag_plot)
print "Get solution pickle and cluster files list"
sol_pickle, cluster_files = isoch.assign_cluster(frame_files_sel, labels, k, \
os.path.join(iparams.run_no,self.module_name))
#if more frames found, merge the sample frames to get a reference set
#that can be used for breaking the ambiguity.
if n_frames > iparams.isoform_cluster.n_selected_frames:
print "Assign cluster_id for the remaining images."
old_iparams_data = iparams.data[:]
miller_array_ref_set = []
from prime.command_line.postrefine import scale_frames, merge_frames
for i in range(k):
#generate a reference set from solved frames
with open(cluster_files[i]) as f:
frame_files_processed = f.read().split('\n')[:-1]
scaled_pres_set = scale_frames(
range(len(frame_files_processed)), frame_files_processed,
iparams)
mdh, txt_merge_out = merge_frames(scaled_pres_set, iparams, \
mtz_out_prefix=os.path.join(self.module_name,'cluster_'+str(i)))
miller_array_ref_set.append(mdh.miller_array_merge)
txt_out += txt_merge_out
#setup a list of remaining frames
frame_files_remain = [
frame for frame in frame_files if frame not in sol_pickle
]
frame_files_remain_sel, obs_remain_sel_list = self.get_observation_set(iparams, \
frame_files_remain, len(frame_files_remain))
frames = [(i, frame_files_remain_sel[i], obs_remain_sel_list[i],
iparams, miller_array_ref_set)
for i in range(len(obs_remain_sel_list))]
cc_results = pool_map(iterable=frames,
func=solve_with_mtz_mproc,
processes=iparams.n_processors)
for result in cc_results:
if result:
pickle_filename, cluster_id = result
sol_pickle[pickle_filename] = cluster_id
iparams.data = old_iparams_data[:]
#write out solution pickle
write_out_solutions(iparams, sol_pickle)
#write out text output
txt = "Cluster images completed. Use cluster_0.lst - cluster_k.lst (for k clusters) for merging.\n"
txt_out += txt
print txt
with open(os.path.join(iparams.run_no, self.module_name, 'log.txt'),
'a') as f:
f.write(txt_out)
if pair[0] == "data":
data.append(pair[1])
elif pair[0] == "data_sweep":
data_sweep = pair[1]
if len(data) == 0:
print("Please input all parameters")
exit()
return data, data_sweep
if __name__ == "__main__":
# Read input parameters and frames (pickle files)
data_fine, data_sweep = read_input(args=sys.argv[1:])
pixel_size_mm = 0.079346
# read all the pickle files from fine-slice data
frames_fine = read_pickles(data_fine)
# get a sample reflections
sample_no = 0
obs_fine_sample = None
for i in range(2000):
frame = frames_fine[i]
pickle_fine = read_frame(frame)
obs_fine = pickle_fine["observations"][0]
obs_fine = obs_fine.select(obs_fine.data() > 0)
if len(obs_fine.data()) > 5:
print(frame)
for index, d, I, sigI in zip(
obs_fine.indices(),
obs_fine.d_spacings().data(),
obs_fine.data(),
obs_fine.sigmas(),
def __init__(self, iparams): self.iparams = iparams self.frame_files = read_pickles(iparams.data) self.idv_range = len(self.frame_files)
