-
Notifications
You must be signed in to change notification settings - Fork 3
/
banner_parsing.py
1940 lines (1469 loc) · 63.4 KB
/
banner_parsing.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""I am writing some utilities to work with the processing of class
lists and transcripts from Brad Noble's perl code.
Don't forget to use the -a option when generating the classlist:
classlist.sh -a IME 106 FR3 201415 > sec_FR3_classlist.txt
"""
import txt_mixin, csv_to_latex, rwkos
import os, re, glob
import numpy
from numpy import array, arange
from bs4 import BeautifulSoup
from IPython.core.debugger import Pdb
mod_debug = 1#debug print statements for the module
import copy
import pathlib
banner_id_pat = re.compile('(800[0-9]+)')
gnum_pat = re.compile('G[0-9]+')
def semester_str_to_pretty_str(semester_in):
"""Convert strings like '201435' to something pretty and easy to
read like Fall_2014."""
year_str = semester_in[0:4]
sem_key = semester_in[-2:]
sem_dict = {'15':'Spring', \
'25':'Summer', \
'35':'Fall'}
pretty_str = '%s_%s' % (sem_dict[sem_key], year_str)
return pretty_str
def parse_one_name(string_in):
#last, rest = string_in.split(' ',1)
name_list = string_in.split(' ')
last = name_list.pop(-1).strip()
first = name_list.pop(0).strip()
middle = ''
if name_list:
middle = ' '.join(name_list)
if middle:
middle = middle.strip()
return last, first, middle
email_pat = re.compile('<(.*)>')
def parse_one_email_string(string_in):
q = email_pat.search(string_in)
return q.group(1)
letter_to_gpa_dict = {'A':4.0, \
'A-':3.6666667, \
'B+':3.3333333, \
'B':3.0, \
'B-':2.6666667, \
'C+':2.3333333, \
'C':2.0, \
'C-':1.6666667, \
'D+':1.3333333, \
'D':1.0, \
'D-':0.6666667, \
'F':0}
def letter_grade_to_gpa(letter):
return letter_to_gpa_dict[letter]
def letter_grade_list_to_gpa_list(listin):
listout = [letter_grade_to_gpa(item) for item in listin]
return listout
class classlist_puller(object):
"""Class to support pulling a classlist using Brad Noble's perl
script. semester needs to be one of '15' (spring), '25' (summer),
or '35' (fall). I am trying to make this function also accept
'spring', 'summer', or 'fall'. Ultimately, we need a string like
this one:
cmd = 'classlist.sh -a ME 482 001 201415 > ' + pathout
"""
def __init__(self, course_num, section, year, semester, \
folder='', subject='ME'):
if type(semester) == int:
semester = '%i' % semester
elif semester not in ['15','25','35']:
key = semester[0:3].lower()
sem_dict = {'spr':15,'sum':25,'fal':'35'}
semester = sem_dict[key]
year = str(year)
if type(course_num) == int:
course_num = '%0.3i' % course_num
else:
course_num = str(course_num)
if type(section) == int:
section = '%0.3i' % section
self.course_num = course_num
self.section = section
self.year = year
self.semester = semester
self.folder = folder
self.subject = subject
def build_filename(self):
fn = '%s%s_%s_%s%s_classlist.txt' % (self.subject, \
self.course_num, \
self.section, \
self.year, \
self.semester)
self.filename = fn
self.pathout = os.path.join(self.folder, self.filename)
return self.pathout
def _build_cmd(self):
cmd = 'classlist.sh -a %s %s %s %s%s > %s' % (self.subject, \
self.course_num, \
self.section, \
self.year, \
self.semester, \
self.pathout)
self.cmd = cmd
return self.cmd
def pull(self):
if not hasattr(self, 'pathout'):
self.build_filename()
self._build_cmd()
os.system(self.cmd)
def exists(self):
if not hasattr(self, 'pathout'):
self.build_filename()
return os.path.exists(self.pathout)
class name_replacer(object):
"""Class to replace first names in a class list with a preferred
alternate name. I am going to require that the last name and
given first name both match before a replacment is done so that I
don't require everyone named Smith to change their first name."""
def __init__(self, arrayin):
"""arrayin must have 3 columns: last name, given first name,
preferred name"""
nr, nc = arrayin.shape
assert nc == 3, "arrayin for name_replacer class must have 3 colums"
self.array = arrayin
self.lastnames = arrayin[:,0].tolist()
self.given_firsts = arrayin[:,1].tolist()
self.alt_firsts = arrayin[:,2].tolist()
def search_one_name(self, lastname, firstname):
if lastname in self.lastnames:
ind = self.lastnames.index(lastname)
fn_check = self.given_firsts[ind]
if fn_check == firstname:
#we have a match
return self.alt_firsts[ind]
class classlist_parser(txt_mixin.txt_file_with_list):
def get_row(self, index):
"""output a clean row list that contains
[lastname, firstname, studentid, grade]"""
attrs = ['lastnames','firstnames','studentid','grade']
rowout = []
for attr in attrs:
vector = getattr(self, attr)
val = vector[index]
rowout.append(val)
return rowout
def get_data_from_list_of_rows(self, index_list):
listout = []
for index in index_list:
row = self.get_row(index)
listout.append(row)
return listout
def filter_by_grades(self, good_grades=['A','B','C']):
"""Search through the Grades column and find all grades not in
A-C."""
keep_inds = []
grades_col = self.col_labels.index('Grade')
for i, row in enumerate(self.array):
grade = row[grades_col]
if grade not in good_grades:
keep_inds.append(i)
#self.grades = self.get_col(grades_col)
listout = self.get_data_from_list_of_rows(keep_inds)
return listout
def find_inds(self):
"""Find the indices for the start of each column after the
first one."""
labels = self.col_labels[1:]
inds = []
label_row = self.list[0]
for item in labels:
ind = label_row.find(item)
inds.append(ind)
self.col_inds = inds
def break_rows(self):
"""Break each row string into columns based on the column
widths/inds found using self.find_inds"""
listout = []
for row in self.list[1:]:
prev_ind = 0
row_list = []
for ind in self.col_inds:
chunk = row[prev_ind:ind]
row_list.append(chunk)
prev_ind = ind
last_chunk = row[prev_ind:]
row_list.append(last_chunk)
listout.append(row_list)
self.raw_nested_list = listout
def strip_items(self):
listout = []
for row in self.raw_nested_list:
row_list = []
for item in row:
item2 = item.strip()
row_list.append(item2)
listout.append(row_list)
self.nested_list = listout
def get_col(self, ind):
col = self.array[:,ind]
return col
def get_banner_ids(self):
self.banner_ids = self.get_col(2)
return self.banner_ids
def get_levels(self):
self.levels = self.get_col(4)
return self.levels
def get_email_strings(self):
return self.get_col(-1)
def parse_emails(self):
email_strings = self.get_email_strings()
test_email = email_strings[0]
assert test_email.find('@siue.edu') > -1, "problem with email string check : %s" % test_email
clean_emails = [parse_one_email_string(item) for item in email_strings]
self.emails = clean_emails
def parse(self):
"""Assuming self.list already exists, determine the width of
the fixed with columns and break each line into columns.
This will be hard coded a bit to the known format of the fixed
width files Brad's code generates. The first row contains the
labels. The first label is not needed."""
self.find_inds()
self.break_rows()
self.strip_items()
self.array = array(self.nested_list)
def assign_cols_to_attrs(self):
from txt_database import label_to_attr_name
for i, label in enumerate(self.col_labels):
if label == '#':
attr = 'num'
else:
attr = label_to_attr_name(label)
attr = attr.lower()
col = self.get_col(i)
setattr(self, attr, col)
def __init__(self, *args, **kwargs):
txt_mixin.txt_file_with_list.__init__(self, *args, **kwargs)
self.col_labels = ['#','Name','StudentID','Stat','Lvl','Grade','e-Mail Address']
self.parse()
self.assign_cols_to_attrs()
self.parse_names()
self.parse_emails()
def replace_names(self, replacer):
"""Replace first names if students strongly prefer to be
called something else and make this known before class starts."""
N = len(self.name_strs)
n_list = arange(N)
for i, last, first in zip(n_list, self.lastnames, self.firstnames):
alt_name = replacer.search_one_name(last, first)
if alt_name:
self.firstnames[i] = alt_name
def parse_names(self, force=False):
if hasattr(self,'lastnames') and not force:
#do nothing
return
self.name_strs = self.get_col(1)
lastnames = []
firstnames = []
for item in self.name_strs:
last, first = parse_one_name(item)
lastnames.append(last)
firstnames.append(first)
self.lastnames = lastnames
self.firstnames = firstnames
def append_file(self, filename):
"""Append a second classlist. This would be used for example
with robotics where there are two classlists (ME 454 and ECE
467) that need to be combined into one effective classlist."""
newlist = classlist_parser(filename)
new_array = numpy.row_stack([self.array, newlist.array])
big_list = new_array.tolist()
name_col = self.col_labels.index('Name')
#sort by Name
big_list.sort(key=lambda item: item[name_col])
self.array = array(big_list)
self.assign_cols_to_attrs()
self.parse_names(force=True)
self.parse_emails()
def build_csv_classlist(self):
#Last Name,First Name,ID,Please Call Me,Email Address
#Bailey,Adam,800512776,,
#Burley,Keith,800486675,,
#Dickinson,Alexander,800508999,,
self.parse_names()
self.banner_ids = self.get_banner_ids()
nested_out = []
for last, first, banner_id in zip(self.lastnames, self.firstnames, self.banner_ids):
rowout = [last, first, banner_id, '', '']
nested_out.append(rowout)
return nested_out
def build_data(self, attrlist):
"""Return an array whose columns are the items in attrlist"""
data = []
for attr in attrlist:
vect = getattr(self, attr)
data.append(vect)
array_out = numpy.column_stack(data)
return array_out
def make_latex_list(self, pathout, extra_col_labels=None, **kwargs):
"""Create a classlist that is ready for pdflatex for use on
the first day of class for getting preferred emails or nicknames."""
names_array = self.build_data(['lastnames','firstnames'])
names_list = names_array.tolist()
hrule = None
if extra_col_labels is not None:
hrule='\\rule{2.0in}{0pt}'
latex_out = csv_to_latex.csv_to_latex_table(names_list, labels=['Lastname','Firstname'], \
extra_col_labels=extra_col_labels, \
hrule=hrule, **kwargs)
txt_mixin.dump(pathout, latex_out)
def build_email_csv_list_for_import(self):
if not hasattr(self, 'lastnames'):
self.parse_names()
self.parse_emails()
nested_out = []
for last, first, email in zip(self.lastnames, self.firstnames, self.emails):
rowout = [last, first, email]
nested_out.append(rowout)
return nested_out
def save_email_csv_classlist(self, pathout=None):
if pathout is None:
fno, ext = os.path.splitext(self.pathin)
pathout = fno + '_email_list.csv'
mylist = self.build_email_csv_list_for_import()
labels = ['Last Name','First Name', 'Email']
txt_mixin.dump_delimited(pathout, mylist, delim=',', labels=labels)
def save_csv_classlist(self, pathout=None):
if pathout is None:
fno, ext = os.path.splitext(self.pathin)
pathout = fno + '_out.csv'
mylist = self.build_csv_classlist()
labels = ['Last Name','First Name', 'ID', 'Please Call Me','Email Address']
txt_mixin.dump_delimited(pathout, mylist, delim=',', labels=labels)
def process_one_table_row(row_list, delim='|'):
rowstr = ''
def rowstr_append(rowstr, text):
rowstr += text + delim
return rowstr
for td in row_list:
text = None
if td.find(text=True):
text = ''.join(td.find(text=True))
text = text.replace(' ',' ')
text = text.replace(u'\xa0', u' ')
text = text.strip()
rowstr = rowstr_append(rowstr, text)
test = td.select('a[href^=mailto]')
if test:
link = test[0].attrs['href'].strip()
assert link.find('mailto:') == 0, "Problem with href str: %s" % link
junk, email_str = link.split(':',1)
rowstr = rowstr_append(rowstr, email_str)
return rowstr
def transcript_html_to_txt_list(filename, delim='|'):
#soup = BeautifulSoup(open(filename))
soup = BeautifulSoup(open(filename), "html.parser")
#markup_type=markup_type))
body = soup.body
rows = body.findAll('tr')
listout = []
for tr in rows:
headers = tr.findAll('th')
header_str = ''
if headers:
header_str = process_one_table_row(headers, delim=delim)
cols = tr.findAll('td')
cols_str = ''
if cols:
cols_str = process_one_table_row(cols, delim=delim)
rowstr = header_str + cols_str
if rowstr and rowstr[-1] == delim:
rowstr = rowstr[0:-1]
listout.append(rowstr.encode())
return listout
class transcript_html_parser(object):
def save(self, txt_path=None, folder=''):
if txt_path is None:
txt_path = os.path.join(folder, self.txt_filename)
txt_mixin.dump(txt_path, self.txt_list)
def __init__(self, filename):
self.html_path = filename
self.folder, self.html_filename = os.path.split(self.html_path)
fno, ext = os.path.splitext(self.html_filename)
self.txt_filename = fno + '.txt'
self.txt_list = transcript_html_to_txt_list(self.html_path)
if type(self.txt_list[0]) == bytes:
str_list = [item.decode('utf-8') for item in self.txt_list]
self.txt_list = str_list
self.txt_list = txt_mixin.txt_list(self.txt_list)
def find_student_name(self):
inds = self.txt_list.findall("Name :")
assert len(inds) == 1, "Problem with search for Name :, inds = " + str(inds)
name_row = self.txt_list[inds[0]]
junk, name = name_row.split('|',1)
name = name.strip()
self.student_name = name
def get_filename_from_student_name(self):
if not hasattr(self, 'student_name'):
self.find_student_name()
filename = rwkos.clean_filename(self.student_name + '.txt')
return filename
class class_schedule_parser(txt_mixin.txt_file_with_list):
"""The first step in my undergraduate committee work of finding
out who should be on probation is generating a list of all ME
courses taught in a given semester. This was done manually in the
past. In Dec. 2014 I am deciding to manually do a search for ME
courses and save the results to an html file. I will then use
this class to extract all course names, CRNs, and sections from
that html file."""
def __init__(self, pathin, **kwargs):
txt_mixin.txt_file_with_list.__init__(self, pathin, **kwargs)
self.title_line_pat = re.compile('(<TH.*?>)<A (.*?)>(.*)</A></TH>')
self.build_pathout()
def build_pathout(self):
pne, ext = os.path.splitext(self.pathin)
pathout = pne + '_parsed.csv'
self.pathout = pathout
return self.pathout
def find_title_inds(self):
title_inds = self.list.findall('<TH CLASS="ddtitle"', forcestart=1)
self.title_inds = title_inds
def get_raw_title_lines(self):
raw_title_lines = []
for ind in self.title_inds:
raw_title_lines.append(self.list[ind])
self.raw_title_lines = raw_title_lines
def parse_one_title_line(self, linein):
q = self.title_line_pat.search(linein)
assert q, "problem with regexp match for line: %s" % linein
return q.group(3)
def extract_titles_from_raw_lines(self):
self.course_titles = []
for line in self.raw_title_lines:
title = self.parse_one_title_line(line)
self.course_titles.append(title)
def break_one_title(self, title_in):
"""The course titles appear to be hyphen delimited with spaces
around the hyphens. There also appears to be four elements to
the title, the course name, the CRN, the course number, and
the section number."""
row_list = title_in.split('-')
assert len(row_list) == 4, "problem with number of items in hyphen delimited row: %s" % title_in
clean_row = [item.strip() for item in row_list]
return clean_row
def break_titles(self):
data = []
for title in self.course_titles:
cur_row = self.break_one_title(title)
data.append(cur_row)
self.data = data
def parse(self):
self.find_title_inds()
self.get_raw_title_lines()
self.extract_titles_from_raw_lines()
self.break_titles()
def save(self):
mylabels = ['course name','CRN','course number','section']
txt_mixin.dump_delimited(self.pathout, self.data, \
delim=',', labels=mylabels)
def append_delim_to_pat(pat_in, delim):
"""the pipe delim that I like right now needs to be escaped in
regexp patterns."""
pat = pat_in
if delim == '|':
pat += '\\' + delim
else:
pat += delim
return pat
def pop_empty_from_end(listin):
while not listin[-1]:
listin.pop(-1)
return listin
name_pat = re.compile('^([A-z]+) ([A-Z])\. ([A-z ]+)$')
name_pat_no_mi = re.compile('^([A-z]+) ([A-z ]+)$')
other_subjects = ['AD','POLS','ENG','PHIL','SOC','THEA', \
'PSYC','ECON','SPC',]
class transcript_txt_parser(txt_mixin.txt_file_with_list):
def break_name(self):
name = self.get_name()
q = name_pat.match(name)
if q:
self.first_name = q.group(1)
self.mi = q.group(2)
self.last_name = q.group(3)
else:
q = name_pat_no_mi.match(name)
self.first_name = q.group(1)
self.mi = ''
self.last_name = q.group(2)
def _get_one_line(self, pat, match=False):
inds = self.list.findallre(pat, match=match)
assert len(inds) == 1, "did not find exactly one match for " + pat
return self.list[inds[0]]
def _get_first_line(self, pat, match=False):
"""College:delim may match many times; I just want the first
one, which should be the current one."""
inds = self.list.findallre(pat, match=match)
return self.list[inds[0]]
def _get_last_line(self, pat, match=False):
"""Get last match, which should hopefully be the most current
major (for example)."""
inds = self.list.findallre(pat, match=match)
return self.list[inds[-1]]
def get_regexp_matches(self, pat, match=False):
listout = []
inds = self.list.findallre(pat, match=match)
for ind in inds:
line = self.list[ind]
listout.append(line)
return listout
def get_major_and_dept(self):
pat = append_delim_to_pat('^Major and Department:', self.delim)
line = self._get_one_line(pat)
junk, m_and_d_str = line.split(self.delim, 1)
major, dept = m_and_d_str.split(',',1)
self.major = major.strip()
self.dept = dept.strip()
return self.major, self.dept
def get_major(self):
pat = append_delim_to_pat('^Major:', self.delim)
line = self._get_last_line(pat)
junk, major = line.split(self.delim, 1)
self.major = major.strip()
return self.major
def get_college(self):
pat = append_delim_to_pat('^College:', self.delim)
line = self._get_first_line(pat)
junk, college = line.split(self.delim, 1)
self.college = college.strip()
return self.college
def get_and_print_regexp(self, pat, **kwargs):
listout = self.get_regexp_matches(pat, **kwargs)
for line in listout:
print(line)
def get_name(self):
pat = append_delim_to_pat('^Name *:', self.delim)
inds = self.list.findallre(pat)
assert len(inds) == 1, "did not find exactly one match for " + pat
ind = inds[0]
name_row = self.list[ind]
junk, name = name_row.split(self.delim, 1)
return name
def get_subject_lines(self, subject):
pat = '^' + subject
pat = append_delim_to_pat(pat, self.delim)
linesout = self.get_regexp_matches(pat)
return linesout
def split_row_to_list(self, rowstr):
"""split row using self.delim and pop empty elements from the
end"""
course_list = rowstr.split(self.delim)
while not course_list[-1]:
course_list.pop(-1)
return course_list
def get_grade_form_line(self, line):
"""split a line into a list and grab the -3 element"""
line_list = self.split_row_to_list(line)
grade = line_list[-3]
#all_grades = ['A','B','C','D','F','S','NS','W','WP','WF','UW','WR','I']
#assert grade in all_grades, "Invalid grade: %s" % grade
return grade
def gpa_from_list_of_lines(self, lines):
credit_hours = []
quality_points = []
valid_grades = ['A','B','C','D','F']#not sure what to do with
#W right now
for course_row in lines:
course_list = self.split_row_to_list(course_row)
skip = False
if not skip:
assert len(course_list) == 8, "bad grade row: " + course_row
qp = float(course_list[-1])
ch = float(course_list[-2])
letter_grade = course_list[-3]
if letter_grade in valid_grades:
credit_hours.append(ch)
quality_points.append(qp)
else:
error_str = self.delim.join(course_list[0:2] + \
course_list[-3:])
print('skipping: ' + error_str)
num = numpy.sum(quality_points)
den = numpy.sum(credit_hours)
if den == 0.0:
gpa = None
else:
gpa = float(num)/float(den)
return gpa
def modify_lines_ending_in_E_and_I(self, lines):
"""Lines ending in E or I are tricky and may not affect term
GPA, but I am pretty sure they still count for how many times
a course has been dropped. So, this method will be used with
find_repeated_failures_and_withdraws to make the lines ending
in E and I look like regular lines (by dropping the last two
elements in the in)."""
# - find lines with 10 elements where the last element is E or I
# - keep only elements [0:8]
# - rebuild the list into a string
# - return the newlist with regular lines unmodified
listout = []
for line in lines:
cur_list = self.split_row_to_list(line)
if len(cur_list) == 8:
#do nothing, pass it through
listout.append(line)
elif len(cur_list) == 10:
last_item = cur_list.pop(-1)
assert last_item in ['E','I'], "Invalid last item in row of length 10: %s" % last_item
empty_item = cur_list.pop(-1).strip()
assert empty_item == '', "This item should have been empty in row of length 10: %s" % empty_item
new_line = self.delim.join(cur_list)
listout.append(new_line)
return listout
def handle_lines_ending_in_E_and_I(self, lines):
"""If a grade row ends in E, it seems not to count in the term
GPA, so I am assuming it is a special case and I am dropping
those rows. A row ending in I appears to be an incomplete
that is latter filled in."""
lineouts = []
for course_row in lines:
course_list = self.split_row_to_list(course_row)
skip = False
if course_list[-1] == 'E':
#I guess these are skipped
skip = True
elif course_list[-1] == 'I':
#I don't think these are skipped
course_list.pop(-1)
course_list = pop_empty_from_end(course_list)
course_row = self.delim.join(course_list)
if not skip:
lineouts.append(course_row)
return lineouts
def filter_passing_grades(self, lines):
"""Given a list of transcript lines, filter out the ones with
passing grades. This is done to try to find instances where a
student has failed or withdrawn from a course more than twice."""
linesout = []
passing_grades = ['A','B','C','D','S']
for line in lines:
cur_grade = self.get_grade_form_line(line)
if cur_grade not in passing_grades:
linesout.append(line)
return linesout
def filter_inprogress_courses(self, lines):
"""After scrubbing off empty elements from the end of the
list, completed courses should have 8 elements per row, while
inprogress coures have 6."""
linesout = []
for course_row in lines:
course_list = self.split_row_to_list(course_row)
if len(course_list) > 6:
linesout.append(course_row)
#elif len(course_list) != 6:
# raise(ValueError, "problem with this course_list: " + \
# str(course_list))
return linesout
def get_filtered_non_passing_lines(self, subject):
"""Get the lines for ^subject that were not passed, filtering
out inprogress courses."""
subject_lines = self.get_subject_lines(subject)
subject_lines_modified = self.modify_lines_ending_in_E_and_I(subject_lines)
subject_lines_filt = self.filter_inprogress_courses(subject_lines_modified)
non_passing_subject_lines = self.filter_passing_grades(subject_lines_filt)
return non_passing_subject_lines
def key_from_line(self, line):
"""Make a dictionary key from a transcript line. This will be
used in a dictionary to count withdraws and failures"""
line_list = self.split_row_to_list(line)
subject = line_list[0]
course = line_list[1]
key = subject+course
return key
def nonpassing_lines_to_dict(self, lines):
"""take a list of lines composed of nonpassing courses and
convert them to a dictionary so that we can count how many
times each course has been dropped or failed."""
mydict = {}
for line in lines:
key = self.key_from_line(line)
cur_grade = self.get_grade_form_line(line)
if mydict.has_key(key):
mydict[key].append(cur_grade)
else:
mydict[key] = [cur_grade]
return mydict
def check_dict_for_too_many_non_passing_grades(self, mydict):
bad_dict = {}
for key, value in mydict.iteritems():
if len(value) > 2:
bad_dict[key] = value
return bad_dict
def find_repeated_failures_and_withdraws(self):
"""Find all courses with repeated failures or withdraws
following these steps:
- find all ME courses
- find all grades that are not A-D
- count the number of instances of each course
- verify that any course failed or withdrawn from multiple times is not an elective
"""
subject_list = ['ME']#the UG catalog says required courses in
#the major, I don't know if that just
#means ME or all courses required for the degree,
#assuming just ME for now
non_passing_lines = []
for subject in subject_list:
cur_lines = self.get_filtered_non_passing_lines(subject)
non_passing_lines.extend(cur_lines)
mydict = self.nonpassing_lines_to_dict(non_passing_lines)
bad_dict = self.check_dict_for_too_many_non_passing_grades(mydict)
self.non_passing_dict = mydict
self.too_many_dict = bad_dict
return mydict, bad_dict
def filt_subject_lines_below_300(self, lines):
linesout = []
for course_row in lines:
keep = False
course_list = course_row.split(self.delim)
num_str = course_list[1].strip()
try:
course_num = int(num_str)
if course_num > 299:
keep = True
except ValueError:
if num_str[-1] == 'L':
course_num = int(num_str[0:-1])#drop the L
if course_list > 299:
keep = True
if keep:
linesout.append(course_row)
return linesout