mps_list_evts Namespace Reference

Functions
def	get_mille_lines ()
def	get_num_evts_per_dataset (mille_lines)
def	get_num_evts_per_merged_dataset (merged_datasets, num_evts_per_dataset)
def	merge_datasets (num_evts_per_dataset)
def	print_merging_scheme (merged_datasets)
def	print_num_evts_per_dataset (num_evts_per_dataset)

Variables
	merged_datasets = merge_datasets(num_evts_per_dataset)
	mille_lines = get_mille_lines()
string	mps_db = "mps.db"
	num_evts_per_dataset = get_num_evts_per_dataset(mille_lines)
	num_evts_per_merged_dataset = get_num_evts_per_merged_dataset(merged_datasets,num_evts_per_dataset)

Detailed Description

Print the total number of events processed by the mille jobs per dataset

The information is taken from the `mps.db' file. Will group entries of the
same dataset and also datasets the script *thinks* belong to the same
data type, e.g. 0T cosmics. This is implemented very simple and should 
always be checked by the user.

Usage:

 `python mps_list_evts.py <mps.db file name>' or, after `scram b'
 `mps_list_evts.py <mps.db file name>'

M. Schroeder, DESY Hamburg      26-May-2014

Function Documentation

def mps_list_evts.get_mille_lines

(

)

Return list of mps.db lines that correspond to a mille job 

Definition at line 24 of file mps_list_evts.py.

def get_mille_lines():
    """ Return list of mps.db lines that correspond to a mille job """
    mille_lines = []
    with open(mps_db,"r") as db:
        for line in db:
            line = line.rstrip('\n')
            # mille and pede job lines have 13 `:' separated fields
            parts = line.split(":")
            if len(parts) == 13:
                # mille lines start with `<123>:job<123>'
                if parts[1] == "job"+parts[0]:
                    mille_lines.append(parts)

    return mille_lines

def mps_list_evts.get_num_evts_per_dataset

(

mille_lines

)

Return number of events per dataset

Returns a dict `<dataset>:<num_evts>', where <dataset> is the label
in the last field of the mille line.

Definition at line 41 of file mps_list_evts.py.

References createfilelist.int.

def get_num_evts_per_dataset(mille_lines):
    """ Return number of events per dataset

    Returns a dict `<dataset>:<num_evts>', where <dataset> is the label
    in the last field of the mille line.
    """
    num_evts_per_dataset = {}
    for line in mille_lines:
        dataset = line[12]
        num_evts = int(line[6])
        if dataset in num_evts_per_dataset:
            num_evts_per_dataset[dataset] = num_evts_per_dataset[dataset] + num_evts
        else:
            num_evts_per_dataset[dataset] = num_evts

    return num_evts_per_dataset

def mps_list_evts.get_num_evts_per_merged_dataset	(		merged_datasets,
			num_evts_per_dataset
	)

Return number of events per merged dataset

Returns a dict `<merged_dataset>:<num_evts>'; see comments to function
`merge_datasets' for an explanation of <merged_dataset>.

Definition at line 60 of file mps_list_evts.py.

def get_num_evts_per_merged_dataset(merged_datasets,num_evts_per_dataset):
    """ Return number of events per merged dataset

    Returns a dict `<merged_dataset>:<num_evts>'; see comments to function
    `merge_datasets' for an explanation of <merged_dataset>.
    """
    num_evts_per_merged_dataset = {}
    for merged_dataset,datasets in merged_datasets.iteritems():
        num_evts = 0
        for dataset in datasets:
            num_evts = num_evts + num_evts_per_dataset[dataset]
        num_evts_per_merged_dataset[merged_dataset] = num_evts

    return num_evts_per_merged_dataset

def mps_list_evts.merge_datasets

(

num_evts_per_dataset

)

Return dict `<merged_dataset> : list of <dataset>'

Associates all datasets in `num_evts_per_dataset' that belong by their
name to the same PD but to a different run era. For example:

isolated_mu_runa_v1, isolated_mu_runb_v1, isolated_mu_runc_v2 --> isolated_mu

The returned dict has as value a list of the merged datasets.

Definition at line 77 of file mps_list_evts.py.

References mps_alisetup.append.

def merge_datasets(num_evts_per_dataset):
    """ Return dict `<merged_dataset> : list of <dataset>'

    Associates all datasets in `num_evts_per_dataset' that belong by their
    name to the same PD but to a different run era. For example:
    
    isolated_mu_runa_v1, isolated_mu_runb_v1, isolated_mu_runc_v2 --> isolated_mu

    The returned dict has as value a list of the merged datasets.
    """
    datasets = num_evts_per_dataset.keys()
    merged_datasets = {}
    for dataset in datasets:
        bare_name = dataset[0:dataset.find("run")].rstrip("_")
        if bare_name in merged_datasets:
            merged_datasets[bare_name].append(dataset)
        else:
            merged_datasets[bare_name] = [dataset]

    return merged_datasets

def mps_list_evts.print_merging_scheme

(

merged_datasets

)

Print number of events per merged dataset

See comments to function `merge_datasets' for an explanation
of what is meant by merged dataset.

Definition at line 100 of file mps_list_evts.py.

def print_merging_scheme(merged_datasets):
    """ Print number of events per merged dataset

    See comments to function `merge_datasets' for an explanation
    of what is meant by merged dataset.
    """
    print "Defining the following merged datasets:"
    for merged_dataset,datasets in merged_datasets.iteritems():
        print "\n  `"+merged_dataset+"' from:"
        for dataset in datasets:
            print "    `"+dataset+"'"

def mps_list_evts.print_num_evts_per_dataset

(

num_evts_per_dataset

)

Print number of events per dataset

See comments to function `get_num_evts_per_dataset' for an
explanation of what is meant by dataset.

Definition at line 114 of file mps_list_evts.py.

References harvestTrackValidationPlots.str.

def print_num_evts_per_dataset(num_evts_per_dataset):
    """ Print number of events per dataset

    See comments to function `get_num_evts_per_dataset' for an
    explanation of what is meant by dataset.
    """
    print "The following number of events per dataset have been processed:"
    datasets = sorted(num_evts_per_dataset.keys())
    max_name = 0
    max_num = 0
    for dataset in datasets:
        if len(dataset) > max_name:
            max_name = len(dataset)
        if len(str(num_evts_per_dataset[dataset])) > max_num:
            max_num = len(str(num_evts_per_dataset[dataset]))
    expr_name = " {0: <"+str(max_name)+"}"
    expr_num = " {0: >"+str(max_num)+"}"
    for dataset in datasets:
        print expr_name.format(dataset)+" : "+expr_num.format(str(num_evts_per_dataset[dataset]))

Variable Documentation

mps_list_evts.merged_datasets = merge_datasets(num_evts_per_dataset)

Definition at line 150 of file mps_list_evts.py.

mps_list_evts.mille_lines = get_mille_lines()

Definition at line 148 of file mps_list_evts.py.

mps_list_evts.mps_db = "mps.db"

Definition at line 21 of file mps_list_evts.py.

mps_list_evts.num_evts_per_dataset = get_num_evts_per_dataset(mille_lines)

Definition at line 149 of file mps_list_evts.py.

mps_list_evts.num_evts_per_merged_dataset = get_num_evts_per_merged_dataset(merged_datasets,num_evts_per_dataset)

Definition at line 151 of file mps_list_evts.py.