annotate dml-cla/python/csvutils.py @ 0:718306e29690 tip

commiting public release
author Daniel Wolff
date Tue, 09 Feb 2016 21:05:06 +0100
parents
children
rev   line source
Daniel@0 1 # Part of DML (Digital Music Laboratory)
Daniel@0 2 # Copyright 2014-2015 Samer Abdallah, University College London
Daniel@0 3
Daniel@0 4 # This program is free software; you can redistribute it and/or
Daniel@0 5 # modify it under the terms of the GNU General Public License
Daniel@0 6 # as published by the Free Software Foundation; either version 2
Daniel@0 7 # of the License, or (at your option) any later version.
Daniel@0 8 #
Daniel@0 9 # This program is distributed in the hope that it will be useful,
Daniel@0 10 # but WITHOUT ANY WARRANTY; without even the implied warranty of
Daniel@0 11 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
Daniel@0 12 # GNU General Public License for more details.
Daniel@0 13 #
Daniel@0 14 # You should have received a copy of the GNU General Public
Daniel@0 15 # License along with this library; if not, write to the Free Software
Daniel@0 16 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Daniel@0 17
Daniel@0 18 # -*- coding: utf-8 -*-
Daniel@0 19 __author__="samer"
Daniel@0 20
Daniel@0 21 import csv
Daniel@0 22 from warnings import warn
Daniel@0 23
Daniel@0 24 import sys
Daniel@0 25 import time
Daniel@0 26 def print_status(msg): sys.stderr.write(msg+'\n')
Daniel@0 27
Daniel@0 28 # call function for each row of a CSV that has ncols columns.
Daniel@0 29 # A warning is printed if any rows have the wrong number of columns.
Daniel@0 30 #
Daniel@0 31 # csv_for_each : string, integer, (list(string) -> void) -> void
Daniel@0 32 def csv_for_each(filename,ncols,f):
Daniel@0 33 badcount=0
Daniel@0 34 with open(filename,'rb') as csvfile:
Daniel@0 35 contents=csv.reader(csvfile, delimiter=',',quotechar='"')
Daniel@0 36 for row in contents:
Daniel@0 37 if len(row)==ncols: f(row)
Daniel@0 38 else: badcount += 1
Daniel@0 39 # if badcount>0: warn("Ignoring %d malformed rows in CSV file %s" % (badcount,filename))
Daniel@0 40
Daniel@0 41 # map f over list of rows from CSV to list of values
Daniel@0 42 #
Daniel@0 43 # csv_map_rows : string, integer, (list(string) -> A) -> list(A)
Daniel@0 44 def csv_map_rows(filename,ncols,f):
Daniel@0 45 good=[]
Daniel@0 46 def append_row(row): good.append(f(row))
Daniel@0 47 csv_for_each(filename,ncols,append_row)
Daniel@0 48 return good
Daniel@0 49
Daniel@0 50 def id(x): return x
Daniel@0 51
Daniel@0 52
Daniel@0 53 # returns selected columns of CSV, one list per column
Daniel@0 54 #
Daniel@0 55 # csv_columns : string, integer, list(integer) -> list(list(string))
Daniel@0 56 def csv_columns(filename,ncols,columns):
Daniel@0 57 def getter(i): return lambda r:r[i]
Daniel@0 58 return csv_map_columns(filename,ncols,map(getter,columns))
Daniel@0 59
Daniel@0 60 # returns selected columns of CSV, one list per column, with
Daniel@0 61 # a function supplied for converting one row of strings to a row of data
Daniel@0 62 #
Daniel@0 63 # csv_map_columns : string, integer, list(list(string)->A) -> list(list(A))
Daniel@0 64 def csv_map_columns(filename,ncols,sels):
Daniel@0 65 ii=range(0,len(sels))
Daniel@0 66 data=[[] for i in ii]
Daniel@0 67 def append_columns(row):
Daniel@0 68 for i in ii: data[i].append(sels[i](row))
Daniel@0 69 csv_for_each(filename,ncols,append_columns)
Daniel@0 70
Daniel@0 71 return data