files = ["transcripts/" + f for f in listdir(mypath) if isfile(join(mypath, f))]
f = open("scores","w")
f.write("Scores:\n")
f.close()
for file in files:
print "Now processing " + file
slash = file.find('/')
end_docket = file.find('_')
if file.find('q') != -1:
docket_number = file.find('q')
docket_number = file[slash+1:end_docket]
print "Checking database for docket #%s" % docket_number
print "Winner identified: %s" % scdb.get_winning_party(docket_number)
raw_input()
the_transcript = transcript.get_transcript_from_PDF(file)
petitioners, respondents = transcript.get_petitioners_and_respondents(the_transcript)
argument = transcript.get_argument(the_transcript)
arguments_by_advocate = transcript.get_arguments_by_advocate(petitioners, respondents, argument)
for petitioner, argument in arguments_by_advocate["petitioner"].iteritems():
statements = transcript.get_statements_in_argument(argument, petitioner)
#scores.get_statistics_from_statements(statements)
number_of_words_per_speaker = scores.get_number_of_words_per_speaker(statements)
features = scores.get_features_from_statements(statements)
flat_features = scores.flatten_features(features)
#import matplotlib.pyplot as plt
slash = file.find('/')
end_docket = file.find('_')
if end_docket == -1:
end_docket = file.find(".pdf")
questionnumber = re.search(r"q\d", file)
if questionnumber:
end_docket = questionnumber.start()
docket_number = file[slash+1:end_docket]
print "Checking database for docket #%s" % docket_number
info = scdb.get_case_info(docket_number)
if not info:
print "Couldn't find case in SCDB. Will skip."
continue
print "Now processing transcript for ", info["caseName"]
winner = scdb.get_winning_party(docket_number)
if winner == "unclear":
print "The winner of this case is unclear. Will skip."
continue
print "Winner identified: %s" % winner
print "Decision direction: %s" % info["decisionDirection"]
the_transcript = transcript.get_transcript_from_PDF(file)
petitioners, respondents = transcript.get_petitioners_and_respondents(the_transcript)
argument = transcript.get_argument(the_transcript)
arguments_by_advocate = transcript.get_arguments_by_advocate(petitioners, respondents, argument)
inputs = []
for petitioner, argument in arguments_by_advocate["petitioner"].iteritems():