From cec96a3debb334f991c3e5b41fea5b2a44c1bde7 Mon Sep 17 00:00:00 2001
From: Cosmin SAVEANU <cosmin.saveanu@pasteur.fr>
Date: Wed, 14 Oct 2020 13:59:54 +0200
Subject: [PATCH] Update Get rows py3/Gt_rws_with_list.py
---
Get rows py3/Gt_rws_with_list.py | 279 +++++++++++++++++++++++++++++++
1 file changed, 279 insertions(+)
create mode 100644 Get rows py3/Gt_rws_with_list.py
diff --git a/Get rows py3/Gt_rws_with_list.py b/Get rows py3/Gt_rws_with_list.py
new file mode 100644
index 0000000..f62e667
--- /dev/null
+++ b/Get rows py3/Gt_rws_with_list.py
@@ -0,0 +1,279 @@
+"""
+This script allows the user to obtain
+rows from a tab delimited file in which
+one of the elements in a column matches
+exactly one element from a list of elements
+(get the description of every ORF from
+a list of ORFs for example).
+A line by line filter version should be
+used for very large files; beware.
+
+Usage:
+
+--tabfile, -t = description file (tab delimited large file)
+--tobematched, -i = file with elements to be mathched against
+ description file items
+--help, -h = this help message
+
+"""
+
+import os, sys, getopt
+
+class TabData:
+ """a tab separated data object class"""
+ def __init__(self):
+ self.nmblines = 0
+ self.data = []
+
+ def read_from_file(self, filename):
+ # input data from a tab delimited file
+ self.filename = filename
+ f=open(filename, 'r')
+ for line in f:
+ self.data.append(line.strip('\n\r').split('\t'))
+ f.close()
+ self.nmblines = len(self.data)
+
+ def first_line(self):
+ result = ""
+ for item in self.data[0]:
+ result=result+item+' '
+ return result
+
+ def number_of_columns(self):
+ return len(self.data[0])
+
+ def get_row(self, number):
+ return self.data[number]
+
+ def get_row_by_name(self, row_name):
+ """row by name and error code 0"""
+ r_name = str(row_name)
+ control = 0
+ row_found = []
+ for i in range(self.nmblines):
+ if r_name == self.data[i][0]:
+ for j in range (len(self.data[i])):
+ row_found.append(self.data[i][j])
+ control = 1
+ break
+ return row_found, control
+
+ def get_row_by_colname(self, name, colnmb):
+ """
+ arguments : name - name to be matched, colnmb - position
+ returns a tuple containing the row and 1 if OK or 0 if problem
+ """
+ search_name = name.upper()
+ control = 0
+ row_found = []
+ for i in range(self.nmblines):
+ if (colnmb < len(self.data[i])):
+ if search_name == self.data[i][colnmb]:
+ row_found=self.data[i]
+ control = 1
+ break
+ return row_found, control
+
+ def get_row_withindex(self, name, column):
+ """
+ arguments : name - name to be matched, colum - obtained by get_column
+ returns a tuple containing the row and 1 if OK or 0 if problem
+ """
+ search_name = name.upper()
+ control = 0
+ row_found = []
+ try:
+ idx = column.index(name, 0, len(column))
+ row_found = self.data[idx]
+ control = 1
+ except ValueError:
+ control = 0
+ return row_found, control
+
+ def get_column(self, number):
+ nmb = int(number)
+ col_found = []
+ for i in range(self.nmblines):
+ col_found.append(self.data[i][nmb])
+ return col_found
+
+ def get_column_by_name(self, col_name):
+ c_name = str(col_name)
+ c_nmb = 0
+ control = 0
+ for i in range(len(self.data[0])):
+ if c_name == self.data[0][i]:
+ c_nmb = i
+ control = 1
+ break
+ return self.get_column(c_nmb), control
+
+ def del_row(self, number):
+ del self.data[number]
+
+ def del_column(self, number):
+ """delete column by number"""
+ nmblines = int(self.nmblines)
+ for i in range(nmblines):
+ del self.data[i][number]
+
+ def del_column_by_name(self, column_name):
+ """delete column by name
+
+ accepts a string as the column name
+ if no such column found, returns the original matrix
+
+ """
+ number = 0
+ col_name = str(column_name)
+ for i in range(len(self.data[0])):
+ if col_name == self.data[0][i]:
+ number = i
+ if number == 0:
+ return self.data
+ else:
+ return self.del_column(number)
+
+ def del_row_by_name(self, row_name):
+ """delete row by name
+
+ accepts a string as the row name
+ if no such row found, returns the original matrix
+
+ """
+ number = 0
+ r_name = str(row_name)
+ for i in range(self.nmblines):
+ if r_name == self.data[i][0]:
+ number = i
+ if number == 0:
+ return self.data
+ else:
+ return self.del_row(number)
+
+ def numb_of_lines(self):
+ return len(self.data)
+
+ def __str__(self):
+ return self.data
+
+ def extract_column(self, column_name):
+ """returns a list corresponding to column"""
+ result_list = []
+ for i in range(len(self.data)):
+ for j in range (len(self.data[i])):
+ if self.data[0][j]==column_name:
+ result_list.append(self.data[i][j])
+ return result_list
+
+ def transpose(self):
+ """transpose matrix"""
+ transposed = []
+ for i in range(len(self.data[0])):
+ int_list = []
+ for j in range(len(self.data)):
+ int_list.append(self.data[j][i])
+ transposed.append(int_list)
+ return transposed
+
+
+ def transpose_z(self):
+ """transpose matrix using zip"""
+ return list(zip(*self))
+#_________________________________
+#main
+
+def write_matrix(matrix, file_handle):
+ for line in matrix:
+ for item in line:
+ file_handle.write(item)
+ file_handle.write('\t')
+ file_handle.write('\n')
+#__________________________________
+
+class Usage(Exception):
+ def __init__(self, msg):
+ self.msg = msg
+
+def main(argv=None):
+ global tabfile_fname, tobematched_fname
+ tabfile_fname, tobematched_fname = "", ""
+ if argv is None:
+ argv = sys.argv
+ try:
+
+ try:
+ opts, args = getopt.getopt(argv[1:], "ht:i:", ["help", "tabfile=", "tobematched="])
+ except getopt.error as msg:
+ raise Usage(msg)
+ # option processing
+ for option, value in opts:
+ if option in ("-h", "--help"):
+ raise Usage(__doc__)
+ if option in ("-t", "--tabfile"):
+ tabfile_fname= value
+ if option in ("-i", "--tobematched"):
+ tobematched_fname = value
+
+ if (tabfile_fname == "" or tobematched_fname == ""):
+ raise Usage("no input filenames!")
+ sys.exit(2)
+ else:
+ try:
+ #read data from tab file in TabData object
+ file_info = os.stat(tabfile_fname)
+ print("Reading ", tabfile_fname, ' of ' , (file_info[6]/1024), ' kBytes .......... \n')
+ print("The results will be written to a file called matchedrows.out")
+
+ properties = TabData()
+ properties.read_from_file(tabfile_fname)
+
+ #read data from list of items in a list
+ file = open(tobematched_fname, 'r')
+ item_list = []
+ for line in file:
+ item_list.append(line.strip('\r\n'))
+ file.close()
+
+ print('Your description file has', properties.number_of_columns(), 'columns')
+ print('The first line of the file says:')
+ print(properties.first_line())
+ print('Enter the number of the column used for match, (1 to '+str(properties.number_of_columns())+'):\n')
+ match_colnumber = int(input())
+
+ #output file path
+ path_toht = os.path.split(tobematched_fname)
+ path_to = path_toht[0]
+ output_filename = os.path.join(path_to,"matchedrows.out")
+
+ result_data = []
+ visual_counter = 0
+ indexed_column = properties.get_column(match_colnumber -1)
+ for item in item_list:
+ int_result = properties.get_row_withindex(item,
+ indexed_column)
+ if int_result[1]==1: #check for return
+ result_data.append(int_result[0])
+ else:
+ result_data.append([item,""])
+ print("Item", item, "not found")
+ visual_counter+=1
+ print(visual_counter, item)
+ out_file = open(output_filename, "w")
+ write_matrix(result_data, out_file)
+ out_file.close()
+ finally:
+ pass
+
+ except Usage as err:
+ print(sys.argv[0].split("/")[-1] + ": " + str(err.msg), file=sys.stderr)
+ print("\t for help use --help", file=sys.stderr)
+ return 2
+
+if __name__ == "__main__":
+ sys.exit(main())
+
+
+
+
--
GitLab