made some simple fixes in sripts

scripts/chunker_scripts/chunk_eval/chunk_eval.py

@@ -20,7 +20,7 @@ Created on 01-08-2012
 from optparse import OptionParser
 import corpus2
 import sys, os
-from chunker_scripts2.csv_table import CSVTable
+from chunker_scripts.csv_table.CSVTable import CSVTable
 import codecs
 
 descr = """%prog [options] CHUNKED REF
@@ -92,7 +92,7 @@ def get_annots(sent, chan_name):
         ann_vec = chan.make_annotation_vector()
         for ann in ann_vec:
             assert ann.head_index in ann.indices
-            annots.appendCell(ann)
+            annots.append(ann)
     return annots
 
 def go():

scripts/chunker_scripts/csv_table/CSVColumn.py

@@ -30,7 +30,7 @@ class CSVColumn:
     def addSubColumn(self, name, type = ''):
         assert len(self.content) == 0 or self.hasSubColumns()
         self.type = 'dict'
-        self.content.appendCell(CSVColumn(self, name, self.separator, type))
+        self.content.append(CSVColumn(self, name, self.separator, type))
         self.recountWidths()
         
     def insertValue(self, row, data, subColumn =''):
@@ -96,7 +96,7 @@ class CSVColumn:
             
             if len(self.content) == 0:
                 self.type = type(data).__name__
-            self.content.appendCell(data)
+            self.content.append(data)
             if len(str(data)) > self.width and self.isSubColumn():
                 self.parent.recountWidths(self.parent.content.index(self))
             elif len(str(data) + self.separator) > self.width:
@@ -171,10 +171,10 @@ class CSVColumn:
         else:
             for i in range(0, rows):
                 if self.type == "float":
-                    self.content.appendCell(0.0)
+                    self.content.append(0.0)
                 elif self.type == "int":
-                    self.content.appendCell(0)
+                    self.content.append(0)
                 else:
-                    self.content.appendCell('')
+                    self.content.append('')
     
     
\ No newline at end of file

scripts/chunker_scripts/csv_table/CSVTable.py

@@ -35,7 +35,7 @@ class CSVTable:
         for column in self.content:
             assert column.name != name, 'Column with name: '+ name+ ' already exists'
         column = CSVColumn(self, name, self.separator, type)
-        self.content.appendCell(column)
+        self.content.append(column)
         
         if self.rows > 0 and type != 'dict':
             column.fillZeros(self.rows)

scripts/chunker_scripts/experiments/oracle.py

@@ -10,7 +10,7 @@ import sys, os
 import corpus2
 from chunker_scripts import tools
 
-descr = """%prog [options] [in_dir] [out_dir]
+descr = """%prog [options] [in_dir] [ref_dir] [out_dir]
 in_dir has to contain subdirs with folds chunked by individual chunkers. 
 Subdir should be named as chunker which chunked files in it.
 """

scripts/chunker_scripts/stats/count_not_cont.py

@@ -7,9 +7,7 @@ Created on Mar 25, 2013
 '''
 from optparse import OptionParser
 import sys, os
-
-from csv_table2.csv_table import CsvTable
-
+from chunker_scripts import tools
 import corpus2
 descr="""%prog [options] in_dir out_dir
 
@@ -22,12 +20,6 @@ def go():
     parser.add_option('-i', '--input-format', type='string', action='store',
         dest='input_format', default='ccl',
         help='set the input format; default: ccl')
-    parser.add_option('-o', '--output-format', type='string', action='store',
-        dest='output_format', default='ccl',
-        help='set the output format; default: ccl')
-    parser.add_option('-O', '--output-file', type='string', action='store',
-        dest='out_path', default='',
-        help='set output filename (do not write to stdout)')
     parser.add_option('-c', '--chunk-names', type='string', action='store',
         dest='chunk_names', default='chunk_np,chunk_vp,chunk_adjp,chunk_agp',
         help='set chunk_names to count')
@@ -69,26 +61,6 @@ def get_input_paths(in_path, folds, input_format):
             
     return input_paths
     
-def get_writer(out_path, output_format, tagset):
-    if out_path:
-        return corpus2.TokenWriter.create_path_writer(output_format, out_path,
-            tagset)
-    else:
-        return corpus2.TokenWriter.create_stdout_writer(output_format, tagset)
-
-def get_reader(in_path, input_format, tagset):
-    if in_path:
-        return corpus2.TokenReader.create_path_reader(
-            input_format, tagset, in_path)
-    else:
-        return corpus2.TokenReader.create_stdin_reader(input_format, tagset)
-
-def get_output_path(out_path, basename = None):
-    if basename == None:
-        return out_path
-    else:
-        return os.path.join(out_path, basename)
-    
 def main(in_path, input_format, output_format, chunk_names, folds, tagset):
     tagset = corpus2.get_named_tagset(tagset)
     chunk_names = chunk_names.split(",")
@@ -99,7 +71,7 @@ def main(in_path, input_format, output_format, chunk_names, folds, tagset):
 
     i=0
     for input_path in input_paths:
-        reader = get_reader(input_path, input_format, tagset)
+        reader = tools.get_reader(input_path, input_format, tagset)
         print input_path
         fold_results = {'all':0, 'n_c':0, '%':0}