# HG changeset patch # User linda.bakker@wur.nl # Date 1430892413 -7200 # Node ID 43902da5d00ee5d8e917825a0c90d3aa83e0a7fa # Parent f70b2c169e3a6f595f65c3fbb9e93d51c922f657 changed match_library location again diff -r f70b2c169e3a -r 43902da5d00e GCMS/library_lookup.xml --- a/GCMS/library_lookup.xml Fri May 01 14:08:26 2015 +0200 +++ b/GCMS/library_lookup.xml Wed May 06 08:06:53 2015 +0200 @@ -61,7 +61,7 @@ - + Performs a lookup of the RI values by matching CAS numbers from the given NIST identifications file to a library. If a direct match is NOT found for the preferred column name, a regression can be done to find diff -r f70b2c169e3a -r 43902da5d00e GCMS/match_library.py --- a/GCMS/match_library.py Fri May 01 14:08:26 2015 +0200 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,133 +0,0 @@ -''' -Containing functions are called from Galaxy to populate lists/checkboxes with selectable items -''' -import csv -import glob -import os - - -__author__ = "Marcel Kempenaar" -__contact__ = "brs@nbic.nl" -__copyright__ = "Copyright, 2012, Netherlands Bioinformatics Centre" -__license__ = "MIT" - -def get_column_type(library_file): - ''' - Returns a Galaxy formatted list of tuples containing all possibilities for the - GC-column types. Used by the library_lookup.xml tool - @param library_file: given library file from which the list of GC-column types is extracted - ''' - if library_file == "": - galaxy_output = [("", "", False)] - else: - (data, header) = read_library(library_file) - - if 'columntype' not in header: - raise IOError('(get_column_type) Missing columns in ', library_file) - - # Filter data on column type - column_type = header.index("columntype") - amounts_in_list_dict = count_occurrence([row[column_type] for row in data]) - galaxy_output = [(str(a) + "(" + str(b) + ")", a, False) for a, b in amounts_in_list_dict.items()] - - return(galaxy_output) - - -def filter_column(library_file, column_type_name): - ''' - Filters the Retention Index database on column type - @param library_file: file containing the database - @param column_type_name: column type to filter on - ''' - if library_file == "": - galaxy_output = [("", "", False)] - else: - (data, header) = read_library(library_file) - - if ('columntype' not in header or - 'columnphasetype' not in header): - raise IOError('(filter_column) Missing columns in ', library_file) - - column_type = header.index("columntype") - statphase = header.index("columnphasetype") - - # Filter data on colunn type name - statphase_list = [line[statphase] for line in data if line[column_type] == column_type_name] - amounts_in_list_dict = count_occurrence(statphase_list) - galaxy_output = [(str(a) + "(" + str(b) + ")", a, False)for a, b in amounts_in_list_dict.items()] - - return(sorted(galaxy_output)) - - -def filter_column2(library_file, column_type_name, statphase): - ''' - Filters the Retention Index database on column type - @param library_file: file containing the database - @param column_type_name: column type to filter on - @param statphase: stationary phase of the column to filter on - ''' - if library_file == "": - galaxy_output = [("", "", False)] - else: - (data, header) = read_library(library_file) - - if ('columntype' not in header or - 'columnphasetype' not in header or - 'columnname' not in header): - raise IOError('(filter_column2) Missing columns in ', library_file) - - column_type_column = header.index("columntype") - statphase_column = header.index("columnphasetype") - column_name_column = header.index("columnname") - - # Filter data on given column type name and stationary phase - statphase_list = [line[column_name_column] for line in data if line[column_type_column] == column_type_name and - line[statphase_column] == statphase] - amounts_in_list_dict = count_occurrence(statphase_list) - galaxy_output = [(str(a) + "(" + str(b) + ")", a, False)for a, b in amounts_in_list_dict.items()] - - return(sorted(galaxy_output)) - - -def read_library(filename): - ''' - Reads a CSV file and returns its contents and a normalized header - @param filename: file to read - ''' - data = list(csv.reader(open(filename, 'rU'), delimiter='\t')) - header_clean = [i.lower().strip().replace(".", "").replace("%", "") for i in data.pop(0)] - return(data, header_clean) - - - -def get_directory_files(dir_name): - ''' - Reads the directory and - returns the list of .txt files found as a dictionary - with file name and full path so that it can - fill a Galaxy drop-down combo box. - - ''' - files = glob.glob(dir_name + "/*.*") - if len(files) == 0: - # Configuration error: no library files found in /" + dir_name : - galaxy_output = [("Configuration error: expected file not found in /" + dir_name, "", False)] - else: - galaxy_output = [(str(get_file_name_no_ext(file_name)), str(os.path.abspath(file_name)), False) for file_name in files] - return(galaxy_output) - -def get_file_name_no_ext(full_name): - ''' - returns just the last part of the name - ''' - simple_name = os.path.basename(full_name) - base, ext = os.path.splitext(simple_name) - return base - - -def count_occurrence(data_list): - ''' - Counts occurrences in a list and returns a dict with item:occurrence - @param data_list: list to count items from - ''' - return dict((key, data_list.count(key)) for key in set(data_list)) diff -r f70b2c169e3a -r 43902da5d00e match_library.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/match_library.py Wed May 06 08:06:53 2015 +0200 @@ -0,0 +1,133 @@ +''' +Containing functions are called from Galaxy to populate lists/checkboxes with selectable items +''' +import csv +import glob +import os + + +__author__ = "Marcel Kempenaar" +__contact__ = "brs@nbic.nl" +__copyright__ = "Copyright, 2012, Netherlands Bioinformatics Centre" +__license__ = "MIT" + +def get_column_type(library_file): + ''' + Returns a Galaxy formatted list of tuples containing all possibilities for the + GC-column types. Used by the library_lookup.xml tool + @param library_file: given library file from which the list of GC-column types is extracted + ''' + if library_file == "": + galaxy_output = [("", "", False)] + else: + (data, header) = read_library(library_file) + + if 'columntype' not in header: + raise IOError('(get_column_type) Missing columns in ', library_file) + + # Filter data on column type + column_type = header.index("columntype") + amounts_in_list_dict = count_occurrence([row[column_type] for row in data]) + galaxy_output = [(str(a) + "(" + str(b) + ")", a, False) for a, b in amounts_in_list_dict.items()] + + return(galaxy_output) + + +def filter_column(library_file, column_type_name): + ''' + Filters the Retention Index database on column type + @param library_file: file containing the database + @param column_type_name: column type to filter on + ''' + if library_file == "": + galaxy_output = [("", "", False)] + else: + (data, header) = read_library(library_file) + + if ('columntype' not in header or + 'columnphasetype' not in header): + raise IOError('(filter_column) Missing columns in ', library_file) + + column_type = header.index("columntype") + statphase = header.index("columnphasetype") + + # Filter data on colunn type name + statphase_list = [line[statphase] for line in data if line[column_type] == column_type_name] + amounts_in_list_dict = count_occurrence(statphase_list) + galaxy_output = [(str(a) + "(" + str(b) + ")", a, False)for a, b in amounts_in_list_dict.items()] + + return(sorted(galaxy_output)) + + +def filter_column2(library_file, column_type_name, statphase): + ''' + Filters the Retention Index database on column type + @param library_file: file containing the database + @param column_type_name: column type to filter on + @param statphase: stationary phase of the column to filter on + ''' + if library_file == "": + galaxy_output = [("", "", False)] + else: + (data, header) = read_library(library_file) + + if ('columntype' not in header or + 'columnphasetype' not in header or + 'columnname' not in header): + raise IOError('(filter_column2) Missing columns in ', library_file) + + column_type_column = header.index("columntype") + statphase_column = header.index("columnphasetype") + column_name_column = header.index("columnname") + + # Filter data on given column type name and stationary phase + statphase_list = [line[column_name_column] for line in data if line[column_type_column] == column_type_name and + line[statphase_column] == statphase] + amounts_in_list_dict = count_occurrence(statphase_list) + galaxy_output = [(str(a) + "(" + str(b) + ")", a, False)for a, b in amounts_in_list_dict.items()] + + return(sorted(galaxy_output)) + + +def read_library(filename): + ''' + Reads a CSV file and returns its contents and a normalized header + @param filename: file to read + ''' + data = list(csv.reader(open(filename, 'rU'), delimiter='\t')) + header_clean = [i.lower().strip().replace(".", "").replace("%", "") for i in data.pop(0)] + return(data, header_clean) + + + +def get_directory_files(dir_name): + ''' + Reads the directory and + returns the list of .txt files found as a dictionary + with file name and full path so that it can + fill a Galaxy drop-down combo box. + + ''' + files = glob.glob(dir_name + "/*.*") + if len(files) == 0: + # Configuration error: no library files found in /" + dir_name : + galaxy_output = [("Configuration error: expected file not found in /" + dir_name, "", False)] + else: + galaxy_output = [(str(get_file_name_no_ext(file_name)), str(os.path.abspath(file_name)), False) for file_name in files] + return(galaxy_output) + +def get_file_name_no_ext(full_name): + ''' + returns just the last part of the name + ''' + simple_name = os.path.basename(full_name) + base, ext = os.path.splitext(simple_name) + return base + + +def count_occurrence(data_list): + ''' + Counts occurrences in a list and returns a dict with item:occurrence + @param data_list: list to count items from + ''' + return dict((key, data_list.count(key)) for key in set(data_list))