INNER CODE UNIT · Python

CorpusReader

ElizaLo/NLP-Natural-Language-Processing · Shallow Discourse Parsing/PDTB_exploration/pdtb.py:32

class CorpusReader:
    def __init__(self, src_filename):
        self.src_filename = src_filename
   
    def iter_data(self, display_progress=True):
        row_iterator = csv.reader(open(self.src_filename,'rU'))
        next(row_iterator) # Skip past the header.
        i = 1
        for row in row_iterator:
            if display_progress:
                sys.stderr.write("\r") ; sys.stderr.write("row %s" % i) ; sys.stderr.flush()
                i += 1
            yield Datum(row)
        if display_progress: sys.stderr.write("\n")

######################################################################

class Datum:

View source record →