def makeGrid(batchPath, settingName=None, settings=None, read_only=False, interactive=False, install_reqs_at=None, install_reqs_force=None): print("Generating grid...") batchPath = os.path.abspath(batchPath) + os.sep if not settings: if not settingName: raise NotImplementedError( "Re-using previous batch is work in progress...") # if not pathIsGrid(batchPath): # raise Exception('Need to give name of setting file if batchPath/config ' # 'does not exist') # read_only = True # sys.path.insert(0, batchPath + 'config') # settings = __import__(IniFile(batchPath + 'config/config.ini').params['setting_file'].replace('.py', '')) elif os.path.splitext(settingName)[-1].lower() in _yaml_extensions: settings = yaml_load_file(settingName) else: raise NotImplementedError( "Using a python script is work in progress...") # In this case, info-as-dict would be passed # settings = __import__(settingName, fromlist=['dummy']) batch = batchjob.BatchJob(batchPath) # batch.skip = settings.get("skip", False) batch.makeItems(settings, messages=not read_only) if read_only: for jobItem in [b for b in batch.jobItems]: if not jobItem.chainExists(): batch.jobItems.remove(jobItem) batch.save() print('OK, configured grid with %u existing chains' % (len(batch.jobItems))) return batch else: batch.makeDirectories(setting_file=None) batch.save() infos = {} components_used = {} # Default info defaults = copy.deepcopy(settings) grid_definition = defaults.pop("grid") models_definitions = grid_definition["models"] datasets_definitions = grid_definition["datasets"] for jobItem in batch.items(wantSubItems=False): # Model info jobItem.makeChainPath() try: model_info = copy.deepcopy(models_definitions[jobItem.param_set] or {}) except KeyError: raise ValueError("Model '%s' must be defined." % jobItem.param_set) model_info = merge_info(defaults, model_info) # Dataset info try: dataset_info = copy.deepcopy( datasets_definitions[jobItem.data_set.tag]) except KeyError: raise ValueError("Data set '%s' must be defined." % jobItem.data_set.tag) # Combined info combined_info = merge_info(defaults, model_info, dataset_info) if "preset" in combined_info: preset = combined_info.pop("preset") combined_info = merge_info(create_input(**preset), combined_info) combined_info[_output_prefix] = jobItem.chainRoot # Requisites components_used = get_used_components(components_used, combined_info) if install_reqs_at: combined_info[_packages_path] = os.path.abspath(install_reqs_at) # Save the info (we will write it after installation: # we need to install to add auto covmats if jobItem.param_set not in infos: infos[jobItem.param_set] = {} infos[jobItem.param_set][jobItem.data_set.tag] = combined_info # Installing requisites if install_reqs_at: print("Installing required code and data for the grid.") from cobaya.log import logger_setup logger_setup() install_reqs(components_used, path=install_reqs_at, force=install_reqs_force) print("Adding covmats (if necessary) and writing input files") for jobItem in batch.items(wantSubItems=False): info = infos[jobItem.param_set][jobItem.data_set.tag] # Covariance matrices # We try to find them now, instead of at run time, to check if correctly selected try: sampler = list(info[kinds.sampler])[0] except KeyError: raise ValueError("No sampler has been chosen") if sampler == "mcmc" and info[kinds.sampler][sampler].get( "covmat", "auto"): packages_path = install_reqs_at or info.get(_packages_path, None) if not packages_path: raise ValueError( "Cannot assign automatic covariance matrices because no " "external packages path has been defined.") # Need updated info for covmats: includes renames updated_info = update_info(info) # Ideally, we use slow+sampled parameters to look for the covariance matrix # but since for that we'd need to initialise a model, we approximate that set # as theory+sampled from itertools import chain like_params = set( chain(*[ list(like[_params]) for like in updated_info[kinds.likelihood].values() ])) params_info = { p: v for p, v in updated_info[_params].items() if is_sampled_param(v) and p not in like_params } best_covmat = _get_best_covmat(os.path.abspath(packages_path), params_info, updated_info[kinds.likelihood]) info[kinds.sampler][sampler]["covmat"] = os.path.join( best_covmat["folder"], best_covmat["name"]) # Write the info for this job # Allow overwrite since often will want to regenerate grid with tweaks yaml_dump_file(jobItem.iniFile(), sort_cosmetic(info), error_if_exists=False) # Non-translated old code # if not start_at_bestfit: # setMinimize(jobItem, ini) # variant = '_minimize' # ini.saveFile(jobItem.iniFile(variant)) ## NOT IMPLEMENTED: start at best fit ## ini.params['start_at_bestfit'] = start_at_bestfit # --- # for deffile in settings.defaults: # ini.defaults.append(batch.commonPath + deffile) # if hasattr(settings, 'override_defaults'): # ini.defaults = [batch.commonPath + deffile for deffile in settings.override_defaults] + ini.defaults # --- # # add ini files for importance sampling runs # for imp in jobItem.importanceJobs(): # if getattr(imp, 'importanceFilter', None): continue # if batch.hasName(imp.name.replace('_post', '')): # raise Exception('importance sampling something you already have?') # for minimize in (False, True): # if minimize and not getattr(imp, 'want_minimize', True): continue # ini = IniFile() # updateIniParams(ini, imp.importanceSettings, batch.commonPath) # if cosmomcAction == 0 and not minimize: # for deffile in settings.importanceDefaults: # ini.defaults.append(batch.commonPath + deffile) # ini.params['redo_outroot'] = imp.chainRoot # ini.params['action'] = 1 # else: # ini.params['file_root'] = imp.chainRoot # if minimize: # setMinimize(jobItem, ini) # variant = '_minimize' # else: # variant = '' # ini.defaults.append(jobItem.iniFile()) # ini.saveFile(imp.iniFile(variant)) # if cosmomcAction != 0: break if not interactive: return batch print('Done... to run do: cobaya-grid-run %s' % batchPath)
def makeGrid(batchPath, settingName=None, settings=None, read_only=False, interactive=False, install_reqs_at=None, install_reqs_force=None): batchPath = os.path.abspath(batchPath) + os.sep # # 0: chains, 1: importance sampling, 2: best-fit, 3: best-fit and Hessian # cosmomcAction = 0 if not settings: if not settingName: raise NotImplementedError( "Re-using previous batch is work in progress...") # if not pathIsGrid(batchPath): # raise Exception('Need to give name of setting file if batchPath/config ' # 'does not exist') # read_only = True # sys.path.insert(0, batchPath + 'config') # sys.modules['batchJob'] = batchjob # old name # settings = __import__(IniFile(batchPath + 'config/config.ini').params['setting_file'].replace('.py', '')) elif os.path.splitext(settingName)[-1].lower() in (".yml", ".yaml"): settings = yaml_load_file(settingName) else: # ACTUALLY, in the scripted case a DICT or a YAML FILE NAME should be passed raise NotImplementedError( "Using a python script is work in progress...") # settings = __import__(settingName, fromlist=['dummy']) from cobaya.grid_tools import batchjob batch = batchjob.batchJob(batchPath, settings.get("yaml_dir", None)) ### batch.skip = settings.get("skip", False) if "skip" in settings: raise NotImplementedError("Skipping not implemented yet.") batch.makeItems(settings, messages=not read_only) if read_only: for jobItem in [b for b in batch.jobItems]: if not jobItem.chainExists(): batch.jobItems.remove(jobItem) batch.save() print('OK, configured grid with %u existing chains' % (len(batch.jobItems))) return batch else: # WAS batch.makeDirectories(settings.__file__) # WHY THE DIR OF settings AND NOT THE GRID DIR GIVEN??? batch.makeDirectories(setting_file=None) batch.save() # NOT IMPLEMENTED YET: start at best fit!!! # start_at_bestfit = getattr(settings, 'start_at_bestfit', False) defaults = copy.deepcopy(settings) modules_used = {} grid_definition = defaults.pop("grid") models_definitions = grid_definition["models"] datasets_definitions = grid_definition["datasets"] for jobItem in batch.items(wantSubItems=False): jobItem.makeChainPath() base_info = copy.deepcopy(defaults) try: model_info = models_definitions[jobItem.param_set] or {} except KeyError: raise ValueError("Model '%s' must be defined." % jobItem.param_set) # COVMATS NOT IMPLEMENTED YET!!! # cov_dir_name = getattr(settings, 'cov_dir', 'planck_covmats') # covdir = os.path.join(batch.basePath, cov_dir_name) # covmat = os.path.join(covdir, jobItem.name + '.covmat') # if not os.path.exists(covmat): # covNameMappings = getattr(settings, 'covNameMappings', None) # mapped_name_norm = jobItem.makeNormedName(covNameMappings)[0] # covmat_normed = os.path.join(covdir, mapped_name_norm + '.covmat') # covmat = covmat_normed # if not os.path.exists(covmat) and hasattr(jobItem.data_set, # 'covmat'): covmat = batch.basePath + jobItem.data_set.covmat # if not os.path.exists(covmat) and hasattr(settings, 'covmat'): covmat = batch.basePath + settings.covmat # else: # covNameMappings = None # if os.path.exists(covmat): # ini.params['propose_matrix'] = covmat # if getattr(settings, 'newCovmats', True): ini.params['MPI_Max_R_ProposeUpdate'] = 20 # else: # hasCov = False # ini.params['MPI_Max_R_ProposeUpdate'] = 20 # covmat_try = [] # if 'covRenamer' in dir(settings): # covmat_try += settings.covRenamer(jobItem.name) # covmat_try += settings.covRenamer(mapped_name_norm) # if hasattr(settings, 'covrenames'): # for aname in [jobItem.name, mapped_name_norm]: # covmat_try += [aname.replace(old, new, 1) for old, new in settings.covrenames if old in aname] # for new1, old1 in settings.covrenames: # if old1 in aname: # name = aname.replace(old1, new1, 1) # covmat_try += [name.replace(old, new, 1) for old, new in settings.covrenames if old in name] # if 'covWithoutNameOrder' in dir(settings): # if covNameMappings: # removes = copy.deepcopy(covNameMappings) # else: # removes = dict() # for name in settings.covWithoutNameOrder: # if name in jobItem.data_set.names: # removes[name] = '' # covmat_try += [jobItem.makeNormedName(removes)[0]] # covdir2 = os.path.join(batch.basePath, getattr(settings, 'cov_dir_fallback', cov_dir_name)) # for name in covmat_try: # covmat = os.path.join(batch.basePath, covdir2, name + '.covmat') # if os.path.exists(covmat): # ini.params['propose_matrix'] = covmat # print('covmat ' + jobItem.name + ' -> ' + name) # hasCov = True # break # if not hasCov: print('WARNING: no matching specific covmat for ' + jobItem.name) ## NOT IMPLEMENTED: start at best fit ## ini.params['start_at_bestfit'] = start_at_bestfit try: dataset_info = datasets_definitions[jobItem.data_set.tag] except KeyError: raise ValueError("Data set '%s' must be defined." % jobItem.data_set.tag) combined_info = merge_info(base_info, model_info, dataset_info) combined_info[_output_prefix] = jobItem.chainRoot # ??? # for deffile in settings.defaults: # ini.defaults.append(batch.commonPath + deffile) # if hasattr(settings, 'override_defaults'): # ini.defaults = [batch.commonPath + deffile for deffile in settings.override_defaults] + ini.defaults # requisites modules_used = get_modules(modules_used, combined_info) if install_reqs_at: combined_info[_path_install] = os.path.abspath(install_reqs_at) # Write the info for this job yaml_dump_file(combined_info, jobItem.iniFile()) # if not start_at_bestfit: # setMinimize(jobItem, ini) # variant = '_minimize' # ini.saveFile(jobItem.iniFile(variant)) # # add ini files for importance sampling runs # for imp in jobItem.importanceJobs(): # if getattr(imp, 'importanceFilter', None): continue # if batch.hasName(imp.name.replace('_post', '')): # raise Exception('importance sampling something you already have?') # for minimize in (False, True): # if minimize and not getattr(imp, 'want_minimize', True): continue # ini = IniFile() # updateIniParams(ini, imp.importanceSettings, batch.commonPath) # if cosmomcAction == 0 and not minimize: # for deffile in settings.importanceDefaults: # ini.defaults.append(batch.commonPath + deffile) # ini.params['redo_outroot'] = imp.chainRoot # ini.params['action'] = 1 # else: # ini.params['file_root'] = imp.chainRoot # if minimize: # setMinimize(jobItem, ini) # variant = '_minimize' # else: # variant = '' # ini.defaults.append(jobItem.iniFile()) # ini.saveFile(imp.iniFile(variant)) # if cosmomcAction != 0: break # Installing requisites print("Installing required code and data for the grid.") if install_reqs_at: install_reqs(modules_used, path=install_reqs_at, force=install_reqs_force) if not interactive: return batch print('Done... to run do: cobaya-grid-run %s' % batchPath)