def _scale(self): '''Actually scale all of the data together.''' from xia2.Handlers.Environment import debug_memory_usage debug_memory_usage() Journal.block( 'scaling', self.get_scaler_xcrystal().get_name(), 'XSCALE', {'scaling model':'default (all)'}) epochs = self._sweep_information.keys() epochs.sort() xscale = self.XScale() xscale.set_spacegroup_number(self._xds_spacegroup) xscale.set_cell(self._scalr_cell) Debug.write('Set CELL: %.2f %.2f %.2f %.2f %.2f %.2f' % \ tuple(self._scalr_cell)) Debug.write('Set SPACEGROUP_NUMBER: %d' % \ self._xds_spacegroup) Debug.write('Gathering measurements for scaling') for epoch in epochs: # get the prepared reflections reflections = self._sweep_information[epoch][ 'prepared_reflections'] # and the get wavelength that this belongs to dname = self._sweep_information[epoch]['dname'] sname = self._sweep_information[epoch]['sname'] # and the resolution range for the reflections intgr = self._sweep_information[epoch]['integrater'] Debug.write('Epoch: %d' % epoch) Debug.write('HKL: %s (%s/%s)' % (reflections, dname, sname)) resolution_low = intgr.get_integrater_low_resolution() resolution_high, _ = self._scalr_resolution_limits.get((dname, sname), (0.0, None)) resolution = (resolution_high, resolution_low) xscale.add_reflection_file(reflections, dname, resolution) # set the global properties of the sample xscale.set_crystal(self._scalr_xname) xscale.set_anomalous(self._scalr_anomalous) debug_memory_usage() xscale.run() scale_factor = xscale.get_scale_factor() Debug.write('XSCALE scale factor found to be: %e' % scale_factor) # record the log file pname = self._scalr_pname xname = self._scalr_xname FileHandler.record_log_file('%s %s XSCALE' % \ (pname, xname), os.path.join(self.get_working_directory(), 'XSCALE.LP')) # check for outlier reflections and if a number are found # then iterate (that is, rerun XSCALE, rejecting these outliers) if not PhilIndex.params.dials.fast_mode and not PhilIndex.params.xds.keep_outliers: xscale_remove = xscale.get_remove() if xscale_remove: current_remove = [] final_remove = [] # first ensure that there are no duplicate entries... if os.path.exists(os.path.join( self.get_working_directory(), 'REMOVE.HKL')): for line in open(os.path.join( self.get_working_directory(), 'REMOVE.HKL'), 'r').readlines(): h, k, l = map(int, line.split()[:3]) z = float(line.split()[3]) if not (h, k, l, z) in current_remove: current_remove.append((h, k, l, z)) for c in xscale_remove: if c in current_remove: continue final_remove.append(c) Debug.write( '%d alien reflections are already removed' % \ (len(xscale_remove) - len(final_remove))) else: # we want to remove all of the new dodgy reflections final_remove = xscale_remove remove_hkl = open(os.path.join( self.get_working_directory(), 'REMOVE.HKL'), 'w') z_min = PhilIndex.params.xds.z_min rejected = 0 # write in the old reflections for remove in current_remove: z = remove[3] if z >= z_min: remove_hkl.write('%d %d %d %f\n' % remove) else: rejected += 1 Debug.write('Wrote %d old reflections to REMOVE.HKL' % \ (len(current_remove) - rejected)) Debug.write('Rejected %d as z < %f' % \ (rejected, z_min)) # and the new reflections rejected = 0 used = 0 for remove in final_remove: z = remove[3] if z >= z_min: used += 1 remove_hkl.write('%d %d %d %f\n' % remove) else: rejected += 1 Debug.write('Wrote %d new reflections to REMOVE.HKL' % \ (len(final_remove) - rejected)) Debug.write('Rejected %d as z < %f' % \ (rejected, z_min)) remove_hkl.close() # we want to rerun the finishing step so... # unless we have added no new reflections if used: self.set_scaler_done(False) if not self.get_scaler_done(): Chatter.write('Excluding outlier reflections Z > %.2f' % PhilIndex.params.xds.z_min) return debug_memory_usage() # now get the reflection files out and merge them with aimless output_files = xscale.get_output_reflection_files() wavelength_names = output_files.keys() # these are per wavelength - also allow for user defined resolution # limits a la bug # 3183. No longer... for epoch in self._sweep_information.keys(): input = self._sweep_information[epoch] intgr = input['integrater'] rkey = input['dname'], input['sname'] if intgr.get_integrater_user_resolution(): dmin = intgr.get_integrater_high_resolution() if rkey not in self._user_resolution_limits: self._scalr_resolution_limits[rkey] = (dmin, None) self._user_resolution_limits[rkey] = dmin elif dmin < self._user_resolution_limits[rkey]: self._scalr_resolution_limits[rkey] = (dmin, None) self._user_resolution_limits[rkey] = dmin self._scalr_scaled_refl_files = { } self._scalr_statistics = { } max_batches = 0 mtz_dict = { } project_info = { } for epoch in self._sweep_information.keys(): pname = self._scalr_pname xname = self._scalr_xname dname = self._sweep_information[epoch]['dname'] reflections = os.path.split( self._sweep_information[epoch]['prepared_reflections'])[-1] project_info[reflections] = (pname, xname, dname) for epoch in self._sweep_information.keys(): self._sweep_information[epoch]['scaled_reflections'] = None debug_memory_usage() for wavelength in wavelength_names: hklin = output_files[wavelength] xsh = XDSScalerHelper() xsh.set_working_directory(self.get_working_directory()) ref = xsh.split_and_convert_xscale_output( hklin, 'SCALED_', project_info, 1.0 / scale_factor) for hklout in ref.keys(): for epoch in self._sweep_information.keys(): if os.path.split(self._sweep_information[epoch][ 'prepared_reflections'])[-1] == \ os.path.split(hklout)[-1]: if self._sweep_information[epoch][ 'scaled_reflections'] is not None: raise RuntimeError, 'duplicate entries' self._sweep_information[epoch][ 'scaled_reflections'] = ref[hklout] del(xsh) debug_memory_usage() for epoch in self._sweep_information.keys(): hklin = self._sweep_information[epoch]['scaled_reflections'] dname = self._sweep_information[epoch]['dname'] sname = self._sweep_information[epoch]['sname'] hkl_copy = os.path.join(self.get_working_directory(), 'R_%s' % os.path.split(hklin)[-1]) if not os.path.exists(hkl_copy): shutil.copyfile(hklin, hkl_copy) # let's properly listen to the user's resolution limit needs... if self._user_resolution_limits.get((dname, sname), False): resolution = self._user_resolution_limits[(dname, sname)] else: if PhilIndex.params.xia2.settings.resolution.keep_all_reflections == True: try: resolution = intgr.get_detector().get_max_resolution(intgr.get_beam_obj().get_s0()) Debug.write('keep_all_reflections set, using detector limits') except Exception: resolution = self._estimate_resolution_limit(hklin) else: resolution = self._estimate_resolution_limit(hklin) Chatter.write('Resolution for sweep %s/%s: %.2f' % \ (dname, sname, resolution)) if (dname, sname) not in self._scalr_resolution_limits: self._scalr_resolution_limits[(dname, sname)] = (resolution, None) self.set_scaler_done(False) else: if resolution < self._scalr_resolution_limits[(dname, sname)][0]: self._scalr_resolution_limits[(dname, sname)] = (resolution, None) self.set_scaler_done(False) debug_memory_usage() if not self.get_scaler_done(): Debug.write('Returning as scaling not finished...') return self._sort_together_data_xds() highest_resolution = min(limit for limit, _ in self._scalr_resolution_limits.values()) self._scalr_highest_resolution = highest_resolution Debug.write('Scaler highest resolution set to %5.2f' % \ highest_resolution) if not self.get_scaler_done(): Debug.write('Returning as scaling not finished...') return sdadd_full = 0.0 sdb_full = 0.0 # ---------- FINAL MERGING ---------- sc = self._factory.Aimless() FileHandler.record_log_file('%s %s aimless' % (self._scalr_pname, self._scalr_xname), sc.get_log_file()) sc.set_resolution(highest_resolution) sc.set_hklin(self._prepared_reflections) sc.set_new_scales_file('%s_final.scales' % self._scalr_xname) if sdadd_full == 0.0 and sdb_full == 0.0: pass else: sc.add_sd_correction('both', 1.0, sdadd_full, sdb_full) for epoch in epochs: input = self._sweep_information[epoch] start, end = (min(input['batches']), max(input['batches'])) rkey = input['dname'], input['sname'] run_resolution_limit, _ = self._scalr_resolution_limits[rkey] sc.add_run(start, end, exclude = False, resolution = run_resolution_limit, name = input['sname']) sc.set_hklout(os.path.join(self.get_working_directory(), '%s_%s_scaled.mtz' % \ (self._scalr_pname, self._scalr_xname))) if self.get_scaler_anomalous(): sc.set_anomalous() sc.multi_merge() FileHandler.record_xml_file('%s %s aimless xml' % (self._scalr_pname, self._scalr_xname), sc.get_xmlout()) data = sc.get_summary() loggraph = sc.parse_ccp4_loggraph() standard_deviation_info = { } for key in loggraph.keys(): if 'standard deviation v. Intensity' in key: dataset = key.split(',')[-1].strip() standard_deviation_info[dataset] = transpose_loggraph( loggraph[key]) resolution_info = { } for key in loggraph.keys(): if 'Analysis against resolution' in key: dataset = key.split(',')[-1].strip() resolution_info[dataset] = transpose_loggraph( loggraph[key]) # and also radiation damage stuff... batch_info = { } for key in loggraph.keys(): if 'Analysis against Batch' in key: dataset = key.split(',')[-1].strip() batch_info[dataset] = transpose_loggraph( loggraph[key]) # finally put all of the results "somewhere useful" self._scalr_statistics = data self._scalr_scaled_refl_files = copy.deepcopy( sc.get_scaled_reflection_files()) self._scalr_scaled_reflection_files = { } # also output the unmerged scalepack format files... sc = self._factory.Aimless() sc.set_resolution(highest_resolution) sc.set_hklin(self._prepared_reflections) sc.set_scalepack() for epoch in epochs: input = self._sweep_information[epoch] start, end = (min(input['batches']), max(input['batches'])) rkey = input['dname'], input['sname'] run_resolution_limit, _ = self._scalr_resolution_limits[rkey] sc.add_run(start, end, exclude = False, resolution = run_resolution_limit, name = input['sname']) sc.set_hklout(os.path.join(self.get_working_directory(), '%s_%s_scaled.mtz' % \ (self._scalr_pname, self._scalr_xname))) if self.get_scaler_anomalous(): sc.set_anomalous() sc.multi_merge() self._scalr_scaled_reflection_files['sca_unmerged'] = { } self._scalr_scaled_reflection_files['mtz_unmerged'] = { } for dataset in sc.get_scaled_reflection_files().keys(): hklout = sc.get_scaled_reflection_files()[dataset] # then mark the scalepack files for copying... scalepack = os.path.join(os.path.split(hklout)[0], os.path.split(hklout)[1].replace( '_scaled', '_scaled_unmerged').replace('.mtz', '.sca')) self._scalr_scaled_reflection_files['sca_unmerged'][ dataset] = scalepack FileHandler.record_data_file(scalepack) mtz_unmerged = os.path.splitext(scalepack)[0] + '.mtz' self._scalr_scaled_reflection_files['mtz_unmerged'][dataset] = mtz_unmerged FileHandler.record_data_file(mtz_unmerged) if PhilIndex.params.xia2.settings.merging_statistics.source == 'cctbx': for key in self._scalr_scaled_refl_files: stats = self._compute_scaler_statistics( self._scalr_scaled_reflection_files['mtz_unmerged'][key], wave=key) self._scalr_statistics[ (self._scalr_pname, self._scalr_xname, key)] = stats # convert reflection files to .sca format - use mtz2various for this self._scalr_scaled_reflection_files['sca'] = { } self._scalr_scaled_reflection_files['hkl'] = { } for key in self._scalr_scaled_refl_files: f = self._scalr_scaled_refl_files[key] scaout = '%s.sca' % f[:-4] m2v = self._factory.Mtz2various() m2v.set_hklin(f) m2v.set_hklout(scaout) m2v.convert() self._scalr_scaled_reflection_files['sca'][key] = scaout FileHandler.record_data_file(scaout) if PhilIndex.params.xia2.settings.small_molecule == True: hklout = '%s.hkl' % f[:-4] m2v = self._factory.Mtz2various() m2v.set_hklin(f) m2v.set_hklout(hklout) m2v.convert_shelx() self._scalr_scaled_reflection_files['hkl'][key] = hklout FileHandler.record_data_file(hklout)