def fix_student_names(csvin):
"""CATME csv files use 'Student Name' as the label and 'Last,
First' as the name column. This function breaks that into seperate last and
first columns and rewrites the csv file."""
#Last Name First Name
mydb = txt_database.db_from_file(csvin)
lower_labels = [item.lower() for item in mydb.labels]
mylist = ['last name', 'lastname', 'lname']
for label in mylist:
if label in lower_labels:
#exit now
return
#keep going only if we didn't find a last name column
if "Student Name" not in mydb.labels:
#problem, bail
raise(KeyError, "did not find 'Student Name' in column labels")
student_names = mydb.Student_Name
last_names = []
first_names = []
for name in student_names:
last, first = name.split(',',1)
last = last.strip()
first = first.strip()
last_names.append(last)
first_names.append(first)
new_data = column_stack([last_names, first_names, mydb.data])
new_labels = numpy.append(["Last Name", "First Name"], mydb.labels)
mydb.data = new_data
mydb.labels = new_labels
mydb.save(csvin, delim=',')
def fix_student_names(csvin):
"""CATME csv files use 'Student Name' as the label and 'Last,
First' as the name column. This function breaks that into seperate last and
first columns and rewrites the csv file."""
#Last Name First Name
mydb = txt_database.db_from_file(csvin)
lower_labels = [item.lower() for item in mydb.labels]
mylist = ['last name', 'lastname', 'lname']
for label in mylist:
if label in lower_labels:
#exit now
return
#keep going only if we didn't find a last name column
if "Student Name" not in mydb.labels:
#problem, bail
raise(KeyError, "did not find 'Student Name' in column labels")
student_names = mydb.Student_Name
last_names = []
first_names = []
for name in student_names:
last, first = name.split(',',1)
last = last.strip()
first = first.strip()
last_names.append(last)
first_names.append(first)
new_data = column_stack([last_names, first_names, mydb.data])
new_labels = numpy.append(["Last Name", "First Name"], mydb.labels)
mydb.data = new_data
mydb.labels = new_labels
mydb.save(csvin, delim=',')
def validate_spreadsheet(self, path, debug=1):
db = txt_database.db_from_file(path)
mylist = txt_mixin.txt_list(db.labels)
def get_db_attr_by_pat(pat):
inds = mylist.findallre(pat)
assert len(inds) > 0, "did not find a match for %s in labels" % pat
assert len(inds) == 1, "found more than one match for %s" %s
ind = inds[0]
fn_label = db.labels[ind]
attr = db.attr_label_dict[fn_label]
vect = getattr(db, attr)
return vect
fn_pat = '[Ff]irst[ _][Nn]ame'
try:
self.first_names = get_db_attr_by_pat(fn_pat)
except:
print('delimited text file must have a column label that matches %s' % \
fn_pat)
self.emails = get_db_attr_by_pat('[Ee]mail')
if debug:
print('first_names:' + str(self.first_names))
print('emails:' + str(self.emails))
check_for_blanks(self.first_names)
check_for_blanks(self.emails)
assert len(self.first_names) == len(self.emails), \
"lengthes of first names and emails do not match"
def get_banner_ids(filename):
if type(filename) == list:
filename = filename[0]
# mysheet = spreadsheet.TabDelimSpreadSheet(filename)
# mysheet.ReadData()
# ids = mysheet.get_col(2)
mydb = txt_database.db_from_file(filename)
ids = mydb.ID
if ids[0].lower() == "id":
ids.pop(0)
return ids
def __init__(self, filename):
self.filename = filename
listin = load_bb_csv(filename)
fno, ext = os.path.splitext(filename)
outname = fno + '_clean' + ext
clean_list = clean_bb_csv_list(listin)
txt_mixin.dump(outname, clean_list)
self.db = txt_database.db_from_file(outname)
def get_banner_ids(filename):
if type(filename) == list:
filename = filename[0]
#mysheet = spreadsheet.TabDelimSpreadSheet(filename)
#mysheet.ReadData()
#ids = mysheet.get_col(2)
mydb = txt_database.db_from_file(filename)
ids = mydb.ID
if ids[0].lower() == 'id':
ids.pop(0)
return ids
def __init__(self, filename):
self.filename = filename
listin = load_bb_csv(filename)
fno, ext = os.path.splitext(filename)
outname = fno + '_clean' + ext
clean_list = clean_bb_csv_list(listin)
txt_mixin.dump(outname, clean_list)
self.db = txt_database.db_from_file(outname)
def __init__(self, csvpathin, folderout='out', \
basename_pat='report_%0.2i.rst',
title_pat='My Title %i', \
ignorecols=[]):
self.csvpathin = csvpathin
self.folderout = folderout
self.basename_pat = basename_pat
self.title_pat = title_pat
self.ignorecols = ignorecols
self.db = txt_database.db_from_file(csvpathin)
self.N = len(self.db.data)
self.filt_labels = [item for item in self.db.labels if item not in ignorecols]
def get_names_from_Banner_txt(filename):
# this approach assumes labels are in the top row (1 row of labels
# only) and that the column label for the student names is "Student Name"
mydb = txt_database.db_from_file(filename)
names = mydb.Student_Name
return names
def get_names_from_Banner_txt(filename):
#this approach assumes labels are in the top row (1 row of labels
#only) and that the column label for the student names is "Student Name"
mydb = txt_database.db_from_file(filename)
names = mydb.Student_Name
return names
