Mercurial > repos > pieterlukasse > prims_metabolomics2

comparison metaMS/match_library.py @ 7:a1e3324dc244

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
added match_library.py to each project
author pieter.lukasse@wur.nl
date Thu, 19 Mar 2015 12:32:51 +0100
parents
children
comparison
equal deleted inserted replaced
6:4393f982d18f 7:a1e3324dc244
1 '''
2 Containing functions are called from Galaxy to populate lists/checkboxes with selectable items
3 '''
4 import csv
5 import glob
6 import os
7
8
9 __author__ = "Marcel Kempenaar"
10 __contact__ = "brs@nbic.nl"
11 __copyright__ = "Copyright, 2012, Netherlands Bioinformatics Centre"
12 __license__ = "MIT"
13
14 def get_column_type(library_file):
15 '''
16 Returns a Galaxy formatted list of tuples containing all possibilities for the
17 GC-column types. Used by the library_lookup.xml tool
18 @param library_file: given library file from which the list of GC-column types is extracted
19 '''
20 if library_file == "":
21 galaxy_output = [("", "", False)]
22 else:
23 (data, header) = read_library(library_file)
24
25 if 'columntype' not in header:
26 raise IOError('Missing columns in ', library_file)
27
28 # Filter data on column type
29 column_type = header.index("columntype")
30 amounts_in_list_dict = count_occurrence([row[column_type] for row in data])
31 galaxy_output = [(str(a) + "(" + str(b) + ")", a, False) for a, b in amounts_in_list_dict.items()]
32
33 return(galaxy_output)
34
35
36 def filter_column(library_file, column_type_name):
37 '''
38 Filters the Retention Index database on column type
39 @param library_file: file containing the database
40 @param column_type_name: column type to filter on
41 '''
42 if library_file == "":
43 galaxy_output = [("", "", False)]
44 else:
45 (data, header) = read_library(library_file)
46
47 if ('columntype' not in header or
48 'columnphasetype' not in header):
49 raise IOError('Missing columns in ', library_file)
50
51 column_type = header.index("columntype")
52 statphase = header.index("columnphasetype")
53
54 # Filter data on colunn type name
55 statphase_list = [line[statphase] for line in data if line[column_type] == column_type_name]
56 amounts_in_list_dict = count_occurrence(statphase_list)
57 galaxy_output = [(str(a) + "(" + str(b) + ")", a, False)for a, b in amounts_in_list_dict.items()]
58
59 return(sorted(galaxy_output))
60
61
62 def filter_column2(library_file, column_type_name, statphase):
63 '''
64 Filters the Retention Index database on column type
65 @param library_file: file containing the database
66 @param column_type_name: column type to filter on
67 @param statphase: stationary phase of the column to filter on
68 '''
69 if library_file == "":
70 galaxy_output = [("", "", False)]
71 else:
72 (data, header) = read_library(library_file)
73
74 if ('columntype' not in header or
75 'columnphasetype' not in header or
76 'columnname' not in header):
77 raise IOError('Missing columns in ', library_file)
78
79 column_type_column = header.index("columntype")
80 statphase_column = header.index("columnphasetype")
81 column_name_column = header.index("columnname")
82
83 # Filter data on given column type name and stationary phase
84 statphase_list = [line[column_name_column] for line in data if line[column_type_column] == column_type_name and
85 line[statphase_column] == statphase]
86 amounts_in_list_dict = count_occurrence(statphase_list)
87 galaxy_output = [(str(a) + "(" + str(b) + ")", a, False)for a, b in amounts_in_list_dict.items()]
88
89 return(sorted(galaxy_output))
90
91
92 def read_library(filename):
93 '''
94 Reads a CSV file and returns its contents and a normalized header
95 @param filename: file to read
96 '''
97 data = list(csv.reader(open(filename, 'rU'), delimiter='\t'))
98 header_clean = [i.lower().strip().replace(".", "").replace("%", "") for i in data.pop(0)]
99 return(data, header_clean)
100
101
102
103 def get_directory_files(dir_name):
104 '''
105 Reads the directory and
106 returns the list of .txt files found as a dictionary
107 with file name and full path so that it can
108 fill a Galaxy drop-down combo box.
109
110 '''
111 files = glob.glob(dir_name + "/*.*")
112 if len(files) == 0:
113 # Configuration error: no library files found in <galaxy-home-dir>/" + dir_name :
114 galaxy_output = [("Configuration error: expected file not found in <galaxy-home-dir>/" + dir_name, "", False)]
115 else:
116 galaxy_output = [(str(get_file_name_no_ext(file_name)), str(os.path.abspath(file_name)), False) for file_name in files]
117 return(galaxy_output)
118
119 def get_file_name_no_ext(full_name):
120 '''
121 returns just the last part of the name
122 '''
123 simple_name = os.path.basename(full_name)
124 base, ext = os.path.splitext(simple_name)
125 return base
126
127
128 def count_occurrence(data_list):
129 '''
130 Counts occurrences in a list and returns a dict with item:occurrence
131 @param data_list: list to count items from
132 '''
133 return dict((key, data_list.count(key)) for key in set(data_list))