def inspect_labelled_output(p):
f = get_raw_csv_filename(p)
# open csv
gen_in = yield_csv_rows(f)
# produce new rows
headline_dict, support_dict = load_spec(p)
print_rows_with_labels(gen_in, headline_dict, support_dict)
def yield_labelled_rows(p):
f = get_raw_csv_filename(p)
# open csv
gen_in = yield_csv_rows(f)
# produce new rows
headline_dict, support_dict = load_spec(p)
return yield_row_with_labels(gen_in, headline_dict, support_dict)
def inspect_labelled_output(p):
f = get_raw_csv_filename(p)
# open csv
gen_in = yield_csv_rows(f)
# produce new rows
headline_dict, support_dict = load_spec(p)
print_rows_with_labels(gen_in, headline_dict, support_dict)
def yield_labelled_rows(p):
f = get_raw_csv_filename(p)
# open csv
gen_in = yield_csv_rows(f)
# produce new rows
headline_dict, support_dict = load_spec(p)
return yield_row_with_labels(gen_in, headline_dict, support_dict)
def dump_doc_files_to_csv(file_list, csv=None):
"""Write tables from .doc in *file_list* into *csv* file. """
if csv is None:
csv = get_raw_csv_filename(file_list[0])
folder_iter = yield_rows_from_many_files(file_list)
dump_iter_to_csv(folder_iter, csv)
return csv
def dump_doc_files_to_csv(file_list, csv=None):
"""Write tables from .doc in *file_list* into *csv* file. """
if csv is None:
csv = get_raw_csv_filename(file_list[0])
folder_iter = yield_rows_from_many_files(file_list)
dump_iter_to_csv(folder_iter, csv)
return csv
def check_vars_not_in_labelled_csv(p):
"""Returns varnames not written to labelled csv file. Prints explaination."""
infile = get_raw_csv_filename(p)
headline_dict, support_dict = load_spec(p)
gen_in = yield_csv_rows(infile)
gen_out = yield_row_with_labels(gen_in, headline_dict, support_dict)
z2 = list(v[0] for k, v in headline_dict.items())
print("\nVars in spec:")
print(list_as_string(z2))
z1 = list(set(row[0] for row in gen_out))
print("Vars in labelled csv:")
print(list_as_string(z1))
not_in_file = [x for x in z2 if x not in z1]
if not_in_file:
print("Not loaded to labelled csv:")
print(list_as_string(not_in_file))
else:
print("Variables in spec and in labelled csv file match.\n")
return not_in_file
def check_vars_not_in_labelled_csv(p):
"""Returns varnames not written to labelled csv file. Prints explaination."""
infile = get_raw_csv_filename(p)
headline_dict, support_dict = load_spec(p)
gen_in = yield_csv_rows(infile)
gen_out = yield_row_with_labels(gen_in, headline_dict, support_dict)
z2 = list(v[0] for k,v in headline_dict.items())
print ("\nVars in spec:")
print(list_as_string(z2))
z1 = list(set(row[0] for row in gen_out))
print ("Vars in labelled csv:")
print(list_as_string(z1))
not_in_file = [x for x in z2 if x not in z1]
if not_in_file:
print ("Not loaded to labelled csv:")
print (list_as_string(not_in_file))
else:
print ("Variables in spec and in labelled csv file match.\n")
return not_in_file
# ______________________________________________________________________________
doc = """1.10. Внешнеторговый оборот – всего1), млрд.долларов США / Foreign trade turnover – total1), bln US dollars
1999 115,1 24,4 27,2 28,4 35,1 7,2 7,9 9,3 9,8 8,0 9,3 9,5 9,3 9,6 10,4 11,1 13,7"""
def test_iter():
for row in [x.split("\t") for x in doc.split("\n")]:
yield row
if __name__ == "__main__":
# import os
# p = os.path.abspath("../data/1-07/1-07.txt")
# gen = yield_labelled_rows(p)
# for x in gen:
# print(x)
#
# inspect_labelled_output(p)
import os
p = os.path.abspath("../data/minitab/minitab.csv")
f = get_raw_csv_filename(p)
# open csv
gen_in = test_iter()
# produce new rows
headline_dict, support_dict = load_spec(p)
print_rows_with_labels(gen_in, headline_dict, support_dict)
if is_label_found_func(text, pat):
return label_dict[pat]
# False will not cause change in labels
return False
#______________________________________________________________________________
doc = """1.10. Внешнеторговый оборот – всего1), млрд.долларов США / Foreign trade turnover – total1), bln US dollars
1999 115,1 24,4 27,2 28,4 35,1 7,2 7,9 9,3 9,8 8,0 9,3 9,5 9,3 9,6 10,4 11,1 13,7"""
def test_iter():
for row in [x.split("\t") for x in doc.split("\n")]:
yield row
if __name__ == "__main__":
# import os
# p = os.path.abspath("../data/1-07/1-07.txt")
# gen = yield_labelled_rows(p)
# for x in gen:
# print(x)
#
# inspect_labelled_output(p)
import os
p = os.path.abspath("../data/minitab/minitab.csv")
f = get_raw_csv_filename(p)
# open csv
gen_in = test_iter()
# produce new rows
headline_dict, support_dict = load_spec(p)
print_rows_with_labels(gen_in, headline_dict, support_dict)
def dump_doc_to_single_csv_file(p):
csv_filename = get_raw_csv_filename(p)
many_rows_iter = yield_continious_rows(p)
dump_iter_to_csv(many_rows_iter, csv_filename)
return csv_filename
def dump_doc_to_single_csv_file(p):
csv_filename = get_raw_csv_filename(p)
many_rows_iter = yield_continious_rows(p)
dump_iter_to_csv(many_rows_iter, csv_filename)
return csv_filename
