def main(args):
argsmap = parseargs(args)
# print(args_dict)
files = argsmap.get('files')
if (not files):
sys.exit(0)
no_files_with_ratings = read_all_files(files)
print("\nNumber of files with ratings = %d" % no_files_with_ratings)
def main(args):
argsmap = parseargs(args)
mapfile = argsmap.get("map")
modelfile = argsmap.get("savemodel")
if (not mapfile or not modelfile):
print('Both map and savemodel must be specified...')
sys.exit(1)
mapfile = mapfile[0]
modelfile = modelfile[0]
alg = argsmap.get("alg")
if (not alg):
alg = 'svc'
else:
alg = alg[0]
mapper = SubtopicMapper(mapfile, modelfile, alg)
def main(args):
argsmap = parseargs(args)
files = argsmap.get('files')
if (not files):
sys.exit(0)
topic = argsmap.get("topic")
if (not topic):
topic = "IT Assessment"
else:
topic = topic[0]
summaryfile = argsmap.get("summary")
if (not summaryfile):
print("Summary file must be specified...")
sys.exit(1)
summaryfile = summaryfile[0]
summary_map = find_topics.get_summary_map(summaryfile)
tmodelfile = argsmap.get("tmodel")
if (not tmodelfile):
print('Topic Model must be specified. using --tmmodel ..')
sys.exit(1)
tmodelfile = tmodelfile[0]
(origmap, sorted_y, vectorizer, le,
grid_search) = read_model_file(tmodelfile)
topics = find_topics.toc_entries(origmap)
# print(topics)
mapper = Mapper(origmap, sorted_y, vectorizer, le, grid_search)
subtopicReader = SubtopicReader(topic, mapper, summary_map)
smodelfile = argsmap.get("smodel")
if (not smodelfile):
print('Subtopic Model must be specified using --smodel ...')
sys.exit(1)
smodelfile = smodelfile[0]
subtopicPredictor = SubtopicPredictor(smodelfile)
for filename in files:
subtopic_dict = subtopicReader.mapped_subtopics(
filename, subtopicPredictor)
subtopic_columns = subtopicReader.get_column_names(subtopicPredictor)
print(json.dumps(subtopic_dict, indent=2))
print('---------------------------------------')
print(subtopic_columns)
def main(args):
argsmap = parseargs(args)
# print(args_dict)
files = argsmap.get('files')
if (not files):
sys.exit(0)
reveal = argsmap.get('reveal')
if (reveal == []):
read_all_files(files, True)
else:
outfile = argsmap.get('out')
if (outfile):
outfile = outfile[0]
distinctfile = argsmap.get('distinct')
if (distinctfile):
distinctfile = distinctfile[0]
ratings = Ratings()
ratings.read_all_files(files, False, outfile, distinctfile)
def main(args):
argsmap = parseargs(args)
files = argsmap.get('files')
if (not files):
sys.exit(0)
ratings_mapper_file = argsmap.get("rmap")
if ratings_mapper_file:
ratings_mapper_file = ratings_mapper_file[0]
if not ratings_mapper_file:
print(
"Ratings Mapper File file name must be entered using the --rmap option..."
)
sys.exit(1)
ratings = Ratings(ratings_mapper_file)
for filename in files:
print("Processing file: " + filename)
print("============================")
process_ratings_for_file(ratings, filename)
def main(args):
argsmap = parseargs(args)
# print(args_dict)
files = argsmap.get('files')
if (not files):
sys.exit(0)
topic = argsmap.get("topic")
if (not topic):
topic = "IT Assessment"
else:
topic = topic[0]
summaryfile = argsmap.get("summary")
if (not summaryfile):
print("Summary file must be specified...")
sys.exit(1)
summaryfile = summaryfile[0]
summary_map = find_topics.get_summary_map(summaryfile)
# print(summary_map)
modelfile = argsmap.get("model")
if (not modelfile):
print('Model must be specified...')
sys.exit(1)
modelfile = modelfile[0]
(origmap, sorted_y, vectorizer, le, grid_search) = read_model_file(modelfile)
topics = find_topics.toc_entries(origmap)
# print(topics)
mapper = Mapper(origmap, sorted_y, vectorizer, le, grid_search)
subtopicReader = SubtopicReader(topic, mapper, summary_map)
all_subtopics = subtopicReader.read_all_files(files, 'print_detail' in argsmap.keys())
if 'print_summary' in argsmap.keys():
subtopicReader.print_summary()
def main(args):
argsmap = parseargs(args)
# print(args_dict)
files = argsmap.get('files')
if (not files):
sys.exit(0)
summaryfile = argsmap.get("summary")[0]
summary_map = get_summary_map(summaryfile)
# print(summary_map)
modelfile = argsmap.get("model")
if (not modelfile):
print('Model must be specified...')
sys.exit(1)
modelfile = modelfile[0]
(origmap, sorted_y, vectorizer, le,
grid_search) = read_model_file(modelfile)
topics = toc_entries(origmap)
# print(topics)
mapper = Mapper(origmap, sorted_y, vectorizer, le, grid_search)
read_all_files(files, mapper, summary_map)
print("Overall Prediction")
print("==================")
for case in test_cases():
prediction, score, type = predictor.get_subtopic(case)
print("%-50s: %30s - (%d, %s)" % (case, prediction, score, type))
print("==================")
print("")
def run_guess_tests(predictor):
print("Guess Prediction")
print("==================")
for case in test_cases():
prediction, score, type = predictor.get_subtopic_guess(case)
print("%-50s: %30s - (%0.3f, %s)" % (case, prediction, score, type))
print("==================")
print("")
if __name__ == '__main__':
import sys
args = sys.argv[1:]
argsmap = parseargs(args)
modelfile = argsmap.get("model")
if (not modelfile):
print('Model must be specified...')
sys.exit(1)
modelfile = modelfile[0]
predictor = SubtopicPredictor(modelfile)
run_tests(predictor)
run_guess_tests(predictor)
def main(args):
global NEWLINE_WITHIN_COLUMN
argsmap = parseargs(args)
files = argsmap.get('files')
if (not files):
sys.exit(0)
summaryfile = argsmap.get("summary")
if (not summaryfile or len(summaryfile) == 0):
print('Summary file must be specified...')
sys.exit(1)
summary_map = get_summary_map(summaryfile[0])
# print(summary_map)
modelfile = argsmap.get("model")
if (not modelfile):
print('Model must be specified...')
sys.exit(1)
modelfile = modelfile[0]
(origmap, sorted_y, vectorizer, le, grid_search) = read_model_file(modelfile)
topics = toc_entries(origmap)
mapper = Mapper(origmap, sorted_y, vectorizer, le, grid_search)
nosplit = argsmap.get('nosplit')
if nosplit == []:
nosplit = True
else:
nosplit = False
if not nosplit:
topic_split_times = argsmap.get('split')
if (not topic_split_times):
topic_split_times = 4
else:
topic_split_times = int(topic_split_times[0])
else:
topic_split_times = 0
NL = argsmap.get('NL') ## Set newline character for multiline columns
if (NL):
NL = NL[0]
if (NL):
NEWLINE_WITHIN_COLUMN = NL
outfile = argsmap.get("out")
if (outfile):
outfile = outfile[0]
exfile = argsmap.get("err")
if exfile:
exfile = exfile[0]
if not exfile:
print("Exception file name must be entered using the --err option...")
sys.exit(1)
ratings_mapper_file = argsmap.get("rmap")
if ratings_mapper_file:
ratings_mapper_file = ratings_mapper_file[0]
if not ratings_mapper_file:
print("Ratings Mapper File file name must be entered using the --rmap option...")
sys.exit(1)
ratings = Ratings(ratings_mapper_file)
global CSV_FIELD_DELIMITER
field_delim = argsmap.get('fd')
if field_delim:
field_delim = field_delim[0]
if field_delim:
CSV_FIELD_DELIMITER = field_delim
global FD_REPLACED
fd_replaced = argsmap.get('fdr')
if fd_replaced:
fd_replaced = fd_replaced[0]
if fd_replaced:
FD_REPLACED = fd_replaced
smodels = argsmap.get("smodels")
stopics = argsmap.get("stopics")
get_headers_for_files(files, topics, mapper, summary_map, outfile, exfile, nosplit, topic_split_times, ratings, smodels, stopics)