def main():
parser = argparse.ArgumentParser()
parser.add_argument('-m', '-M', required=True,
help='Message file')
parser.add_argument('-p', '-P', action='store_true')
parser.add_argument('-s', '-S', required=True,
help='filename to store polarity in, no extension needed')
parser.add_argument('-f', '-F', required=True,
help='folder to store the files in, ending with /')
parser.add_argument('-n', '-N', required=False, nargs=2, type=int, default=[0, 2],
help='the neutral threshold, first value is min, second is max')
args = parser.parse_args()
messagefile = args.m
location_to_store = args.f
file_to_store = args.s
separate_sentiment = args.p
neutral_limit = args.n
message_data = hlp.readcsv(messagefile)
message_header = message_data[0]
message_data = message_data[1:]
afinn = afinnsenti(data=message_data, neutral_threshold=neutral_limit)
data = afinn.compilesentiment(separate_sentiment_list=separate_sentiment, field_no=nd.m_content)
if(separate_sentiment):
hlp.dumpvariable(data, file_to_store+'.list', location_to_store)
else:
message_header.append('score')
message_header.append('label')
final_data = [message_header] + data
hlp.writecsv(final_data, location_to_store + file_to_store + '.csv', delimiter_sym=',')
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-m', '-M', type=str, required=True,
help='Message file')
parser.add_argument('-p', '-P', type=str, required=True,
help='pid_dict')
parser.add_argument('-o', '-O', type=str, required=True,
help='output folder')
parser.add_argument('-of', '-OF', type=str, required=True,
help='output file')
args = parser.parse_args()
message_data = hlp.recovervariable(args.m)
pid_dict = hlp.recovervariable(args.p)
output_folder = args.o
output_file = args.of
edge_dict = getedgecount(message_data, pid_dict)
edge_list = converttolist(edge_dict)
hlp.writecsv([['source', 'target', 'pos', 'neu', 'neg']]+edge_list, output_folder+output_file)
hlp.writecsv([['PID', 'Coded ID']]+convertpiddicttolist(pid_dict), output_folder+'pid_dict_list.csv')
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-m', '-M', required=True,
help='Message file')
parser.add_argument('-p', '-P', action='store_true')
parser.add_argument('-s', '-S', required=True,
help='filename to store polarity in, no extension needed')
parser.add_argument('-f', '-F', required=True,
help='folder to store the files in, ending with /')
args = parser.parse_args()
messagefile = args.m
location_to_store = args.f
file_to_store = args.s
separate_sentiment = args.p
message_data = hlp.readcsv(messagefile)
message_header = message_data[0]
message_data = message_data[1:]
vader = vadersenti(data=message_data)
data = vader.compilesentiment(separate_sentiment_list=separate_sentiment)
if separate_sentiment:
hlp.dumpvariable(data, file_to_store+'.list', location_to_store)
else:
message_header.append('pos')
message_header.append('neg')
message_header.append('neu')
message_header.append('compound')
final_data = [message_header] + data
hlp.writecsv(final_data, location_to_store + file_to_store + '.csv', delimiter_sym=',')
def main():
parser = __define_process_parser()
old_dataset_file, new_dataset_mapped, missing_data, \
survey_file, location_to_store = __define_process_parser(True, parser)
old_dataset = hlp.readcsv(old_dataset_file, delimiter_sym=',', remove_first=True)
new_dataset = hlp.readcsv(new_dataset_mapped, delimiter_sym=',', remove_first=True)
old_data_missing = hlp.readcsv(missing_data, delimiter_sym=',', remove_first=True)
old_missing = __dictify(0, old_data_missing)
wi = weeklyinfo()
week_info = wi.getweeklyfo(survey_file)
week_list = week_info.keys()
bullying_positives = __find_positive_survey(survey_file, week_info)
if bullying_positives is None:
print 'Exiting...'
exit()
ff = filterfields()
old_data_weekly = hlp.divideintoweekly(old_dataset, week_info, ff, date_field=pr.m_time_sent)
new_data_weekly = hlp.divideintoweekly(new_dataset, week_info, ff, date_field=nd.m_timecreated)
bullying_res = [['pid_hash', 'survey_id', 'time_of_survey', 'n_old', 'n_new', 'raw', 'semi', 'ordered', 'other']]
for datum in bullying_positives:
bullying_week = datum[-1]
prev_week = bullying_week - 1 if bullying_week > min(week_list) else min(week_list)
next_week = bullying_week + 1 if bullying_week < max(week_list) else max(week_list)
old_data_pos = old_data_weekly[prev_week] + old_data_weekly[bullying_week] + old_data_weekly[next_week]
new_data_pos = new_data_weekly[prev_week] + new_data_weekly[bullying_week] + new_data_weekly[next_week]
pid_hash = datum[s_i.s_participant]
n_old, n_new, nfr_dict = compare_old_new(old_data_pos, new_data_pos, old_missing, pid_hash, ff)
temp = [pid_hash, datum[s_i.s_id], datum[s_i.s_time], n_old, n_new, nfr_dict['raw'], nfr_dict['semi'],
nfr_dict['ordered'], nfr_dict['other']]
bullying_res.append(temp)
hlp.writecsv(bullying_res, location_to_store+'bullying_res.csv', delimiter_sym=',')
def analyze_polarity(polarity_dict, pid_dict, location_to_store, filename):
final_csv_data = [['source', 'target', 'Pos', 'Neg', 'Neu']]
print '++++ POLARITY INFORMATION ++++'
type_abr = {'participants': 'P', 'nonparticipants':'NP'}
for pid in polarity_dict:
src_new = hlp.getpid(pid_dict, pid)
print '**** For PID: P' + str(src_new) + ' ****'
for (src, trg) in polarity_dict[pid]:
trg_new, trg_type = hlp.getpid(pid_dict, trg, return_p_type=True)
print '(P'+str(src_new)+','+ type_abr[trg_type]+str(trg_new)+')'
temp = ['P'+str(src_new), type_abr[trg_type]+str(trg_new)]
for polarity in polarity_dict[pid][(src, trg)]:
temp.append(polarity)
final_csv_data.append(temp)
hlp.writecsv(final_csv_data, location_to_store+filename, delimiter_sym=',')
def analyze_info(reciprocity_dict, pid_dict, location_to_store, filename):
final_csv_data = []
for pid in reciprocity_dict:
pid_new = hlp.getpid(pid_dict, pid)
print '**** For PID: P' + str(pid_new) + ' ****'
pid_data = reciprocity_dict[pid]
for target_type in pid_data:
target_data = pid_data[target_type]
for target_pid in target_data:
target_pid_new = hlp.getpid(pid_dict, target_pid)
print 'P' + str(pid_new) + '-' + target_type + str(target_pid_new)
temp = get_reci_probability(target_data[target_pid], True)
starting_data = ['P' + str(pid_new), target_type + str(target_pid_new)]
starting_data.extend(temp)
final_csv_data.append(starting_data)
header = ['source', 'target',
'Pr(+|+)', 'Pr(-|+)', 'Pr(U|+)', 'Pr(X|+)',
'Pr(+|U)', 'Pr(-|U)', 'Pr(U|U)', 'Pr(X|U)',
'Pr(+|-)', 'Pr(-|-)', 'Pr(U|-)', 'Pr(X|-)']
toWrite = [header] + final_csv_data
hlp.writecsv(toWrite, location_to_store + filename, delimiter_sym=',')
def generatetablehist(self, input_dictionary, file_path, generate_totals=False, bin_dist=-1):
max_value = float('-inf')
bin_dist = 5 if -1 == bin_dist else bin_dist
for key in input_dictionary.keys():
max_value = max(input_dictionary[key]) if max(input_dictionary[key]) > max_value else max_value
max_value = int(ceil(max_value / bin_dist) * bin_dist)
bins = range(0, max_value + 1, bin_dist)
print 'bins: ', bins, 'max:', max_value
first_line = ['category']
for idx in range(1, len(bins)):
first_line.append(str(bins[idx - 1]) + ' to ' + str(bins[idx]))
if generate_totals:
first_line.append('no. of people')
final_to_write = [first_line]
for key in input_dictionary.keys():
h, be = np.histogram(input_dictionary[key], bins, range=(0, max_value))
h = h / sum(h)
if generate_totals:
final_to_write.append([key] + h.tolist() + [len(input_dictionary[key])])
else:
final_to_write.append([key] + h.tolist())
hlp.writecsv(final_to_write, file_path)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-d', '-D', required=True,
help='labelled csv')
parser.add_argument('-f', '-F', required=True,
help='folder to save the data in')
args = parser.parse_args()
data_file = args.d
location_to_store = args.f
all_afinn_data = hlp.readcsv(data_file)
labelled_data = hlp.processafinnsentiment(all_afinn_data)
csv_header = ['pid', 'm_type',
'in_pos', 'in_neg', 'in_neu',
'out_pos', 'out_neg', 'out_neu',
'in_deg_part', 'in_deg_nonpart',
'out_deg_part', 'out_deg_nonpart']
pol_dist, complete_in_out = distribution_polarity(labelled_data)
print '***For Complete Dataset***'
print 'Incoming(P, N, U): ', complete_in_out['in']
print 'Outgoing(P, N, U): ', complete_in_out['out']
hlp.dumpvariable([pol_dist, complete_in_out], 'polarity_in_out.dict', location_to_store)
to_store_csv = [csv_header]
for pid in pol_dist:
pid_data = pol_dist[pid]
for m_type in pid_data:
m_data = pid_data[m_type]
csv_line = __summarize_data(m_data)
final_csv_line = [pid, m_type]
final_csv_line.extend(csv_line)
to_store_csv.append(final_csv_line)
hlp.writecsv(to_store_csv, location_to_store+'polarity_in_out.csv')
def main(sql_path, variable_path):
s_obj = surveys()
data = s_obj.importsqlascsv(sql_path, 'survey')
hlp.dumpvariable(data, 'survey_list.list', variable_path)
hlp.writecsv(data, variable_path+'survey_list.csv')
ndata = s_obj.interpretanswers(data)
hlp.dumpvariable(ndata, 'survey_list_interpret.list', variable_path)
hlp.writecsv(ndata, variable_path+'survey_list_interpret.csv')
ndata_wR = s_obj.interpretanswers(data, True)
hlp.dumpvariable(ndata_wR, 'survey_list_with_response_interpret.list', variable_path)
hlp.writecsv(ndata_wR, variable_path+'survey_list_with_response_interpret.csv')
data_dict = s_obj.datatodict(ndata)
hlp.dumpvariable(data_dict, 'survey_dict_interpret.dict', variable_path)
data_wR_dict = s_obj.datatodict(ndata_wR)
hlp.dumpvariable(data_wR_dict, 'survey_dict_with_response_interpret.dict', variable_path)
def main():
parser = argparse.ArgumentParser('Script to perform sentiment analysis using VADER')
parser.add_argument('-m', '-M', type=str, required=True,
help='Location of the message file')
parser.add_argument('-mt', '-MT', type=str, required=True, nargs='+',
help='types of messages to filter')
parser.add_argument('-f', '-F', type=str, required=True,
help='filename where data is stored, no extension needed')
parser.add_argument('-s', '-S', type=str, required=True,
help='location of folder to store the file, ends with a /')
parser.add_argument('-p', '-P', action='store_true',
help='flag to store polarities separately')
parser.add_argument('-w', '-W', type=str, required=False,
help='conduct weekly analysis, path to the survey data for '
'creating week information')
parser.add_argument('-l', '-L', type=str, nargs='+', required=True,
help='the filters to use, make one or more choices: seenB, wasB, didB')
parser.add_argument('-lf', '-LF', type=str, nargs='+', required=True,
help='location of filtered data, from runSurveyStats.py, in same order as -l/L flag')
args = parser.parse_args()
message_file = args.m
message_types = args.mt
filename_to_store = args.f
location_to_store = args.s
separate_polarity_score = args.p
survey_file = args.w
filters_chosen = args.l
filter_files = args.lf
catch_all_data = hlp.getfilterdata(filters_chosen, filter_files, catch_all=True)
if separate_polarity_score and survey_file is not None:
print 'Cannot have separate polarity scores and weekly analysis together, ' \
'please remove the -p/-P flag'
return
if survey_file is not None:
wi = weeklyinfo()
week_dates = wi.getweeklyfo(survey_file)
gh = ghelper()
ff = filterfields(message_file)
data = []
for message_type in message_types:
data.extend(ff.filterbyequality(pr.m_type, message_type))
pid_dict = hlp.getuniqueparticipants(data, 'all' if len(message_types) > 1 else message_types[0])
sentiment_analyzer = vadersenti(data[1:])
returned_data = sentiment_analyzer.compilesentiment(pr.m_content, separate_sentiment_list=separate_polarity_score)
if separate_polarity_score:
hlp.dumpvariable(returned_data, filename_to_store + '.data', location_to_store)
else:
header = pr.message_header + ['pos', 'neg', 'neu', 'compound']
final_data = [header] + returned_data
hlp.writecsv(final_data, location_to_store + filename_to_store + '.csv')
weekly_data = gh.filterweeklydata(pid_dict, returned_data, week_dates,
'all' if len(message_types) > 1 else message_types[0])
hlp.dumpvariable(weekly_data, 'weekly_data.dict', location_to_store)
summarized_sentiment = {}
for pid in weekly_data:
summarized_sentiment[pid] = {}
participant_data = weekly_data[pid]
for week_no in participant_data:
summarized_sentiment[pid][week_no] = sentiment_analyzer.summarizesentiment(participant_data[week_no],
separate_in_out=True,
message_type=message_type)
hlp.dumpvariable(summarized_sentiment, 'weekly_summarized_sentiment.dict', location_to_store)
plt = plots()
overlay_data = gh.createbullyingoverlay(catch_all_data, week_dates, ff)
plt.plotweeklyprogression(summarized_sentiment, location_to_store, 'Sentiment Progress', 'Week',
'Sentiment Value', sentiment_legend=['Positive', 'Negative', 'Neutral'],
overlay_data=overlay_data)
print 'done'
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-o', '-O', help='Old Dataset', required=True)
parser.add_argument('-n', '-N', help='New Dataset', required=True)
parser.add_argument('-f', '-F', help='Folder to store results in, ending with /', required=True)
parser.add_argument('-p', '-P', help='text file with list of people who were ordered to be removed', required=True)
parser.add_argument('-s', '-S', help='text file with list of people who were semi-consented', required=True)
args = parser.parse_args()
old_dataset_file = args.o
new_dataset_file = args.n
location_to_store = args.f
ordered_removed_file = args.p
semi_consented_file = args.s
print '***Reading data from arguments...'
old_dataset = hlp.readcsv(old_dataset_file, delimiter_sym=',', remove_first=True)
new_dataset = hlp.readcsv(new_dataset_file, delimiter_sym=',')
new_dataset_dictionary = generate_new_dataset_dictionary(new_dataset[1:])
new_dataset_msg_id_dictionary = generate_new_dataset_dictionary(new_dataset[1:], use_m_id=True)
with open(ordered_removed_file, 'r') as f:
ordered_removed = eval(f.read())
with open(semi_consented_file, 'r') as f:
semi_consented = eval(f.read())
print '***Filtering old data within dates of study...'
ff = filterfields()
old_dataset_within_dates = ff.filterbetweendates(ff.converttodate(pr.start_datetime),
ff.converttodate(pr.end_datetime), data_to_work=old_dataset,
right_equality=True, date_field=pr.m_time_sent)
old_dataset = old_dataset_within_dates
old_dataset_counts = {}
for datum in old_dataset:
m_type = datum[pr.m_type]
if m_type not in old_dataset_counts:
old_dataset_counts[m_type] = 0
old_dataset_counts[m_type] += 1
print '*** OLD DATASET COUNTS***', old_dataset_counts
print '***Finding mapping...'
mapping_dict = {}
inverted_mapping_dict = {}
missed_dict = {}
no_reason = []
counts_no_match = {'ord': {'sms': 0, 'fb_message': 0, 'twitter_status': 0, 'twitter_message': 0,
'fb_activity': 0, 'fb_like': 0, 'fb_comment': 0},
'semi': {'sms': 0, 'fb_message': 0, 'twitter_status': 0, 'twitter_message': 0, 'fb_activity': 0,
'fb_like': 0, 'fb_comment': 0},
'no': {'sms': 0, 'fb_message': 0, 'twitter_status': 0, 'twitter_message': 0, 'fb_activity': 0,
'fb_like': 0, 'fb_comment': 0}}
counts_match = {'sms': 0, 'fb_message': 0, 'twitter_status': 0, 'twitter_message': 0, 'fb_activity': 0,
'fb_like': 0, 'fb_comment': 0}
no_reason_counts = {}
for datum in old_dataset:
m_result, msg_val = message_exists(datum, new_dataset_dictionary, ff)
if m_result:
mapping_dict[datum[pr.msg_id]] = msg_val
if msg_val[1] not in inverted_mapping_dict:
inverted_mapping_dict[msg_val[1]] = []
inverted_mapping_dict[msg_val[1]].append(datum[pr.msg_id])
m_type = datum[pr.m_type]
if m_type in counts_match:
counts_match[m_type] += 1
else:
src = datum[pr.m_source]
trg = datum[pr.m_target]
m_type = datum[pr.m_type]
if src in ordered_removed or trg in ordered_removed:
reason = 'ordered removed'
if m_type in counts_no_match['ord']:
counts_no_match['ord'][m_type] += 1
elif src in semi_consented or trg in semi_consented:
reason = 'semi consented'
if m_type in counts_no_match['semi']:
counts_no_match['semi'][m_type] += 1
else:
reason = ''
temp = datum
temp.append(msg_val)
no_reason.append(temp)
if m_type in counts_no_match['no']:
counts_no_match['no'][m_type] += 1
if m_type not in no_reason_counts.keys():
no_reason_counts[m_type] = {}
if msg_val not in no_reason_counts[m_type].keys():
no_reason_counts[m_type][msg_val] = 0
no_reason_counts[m_type][msg_val] += 1
missed_dict[datum[pr.msg_id]] = [msg_val, datum[pr.m_type], reason]
print '\n\n**NOT FOUND**'
for key_v in counts_no_match.keys():
print key_v
print counts_no_match[key_v]
print '\n\n**NO REASON**'
for key_v in no_reason_counts.keys():
print key_v
print no_reason_counts[key_v]
print '\n\n**FOUND**', counts_match
print '***Creating new dataset with mappings...'
new_dataset_header = new_dataset[0]
new_dataset_header.extend(['Old Message IDs'])
final_dataset = [new_dataset_header]
for new_msg_id in new_dataset_msg_id_dictionary.keys():
datum = new_dataset_msg_id_dictionary[new_msg_id]
old_msg_id = [''] if new_msg_id not in inverted_mapping_dict else inverted_mapping_dict[new_msg_id]
datum.extend(old_msg_id)
final_dataset.append(datum)
print '***Writing data...'
hlp.writecsv(final_dataset, location_to_store + 'new_old_mapped_hashed_dataset.csv', delimiter_sym=',')
mapping_dict_list = [[x, mapping_dict[x][0], mapping_dict[x][1]] for x in mapping_dict]
mapping_header = [['old_id', 'cosine_val', 'new_id']]
mapping_header.extend(mapping_dict_list)
hlp.writecsv(mapping_header, location_to_store + 'old_to_new_mapping.csv', delimiter_sym=',')
missed_dict_list = [[x, missed_dict[x][0], missed_dict[x][1], missed_dict[x][2]] for x in missed_dict]
missed_header = [['old_id', 'Reason', 'm_type', 'Explanation']]
missed_header.extend(missed_dict_list)
hlp.writecsv(missed_header, location_to_store + 'old_not_found.csv', delimiter_sym=',')
hlp.writecsv(no_reason, location_to_store + 'old_not_found_no_reason.csv', delimiter_sym=',')
print 'TADAA!!!'
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-m', '-M', type=str, required=True,
help='Message list file')
parser.add_argument('-r', '-R', type=str, required=True,
help='survey file')
parser.add_argument('-p', '-P', type=str, required=True,
help='PID dict inverted')
parser.add_argument('-b', '-B', type=str, required=True,
help='bullying dictionary')
parser.add_argument('-o', '-O', type=str, required=True,
help='Output folder')
parser.add_argument('-l', '-L', type=str, nargs='+',
help='Filters chosen')
parser.add_argument('-f', '-f', type=str, nargs='+',
help='Filter files')
args = parser.parse_args()
output_folder = args.o
message_data = hlp.recovervariable(args.m)
pid_dict = hlp.recovervariable(args.p)
filters_chosen = args.l
filter_files = args.f
catch_all_data = hlp.getfilterdata(filters_chosen, filter_files, catch_all=True)
wi = weeklyinfo()
weekly_info = wi.getweeklyfo(args.r)
ff = filterfields()
gh = ghelper()
bullying_overlay = gh.createbullyingoverlay(catch_all_data, weekly_info, ff)
bullying_overlay = flip_bullying_overlay(bullying_overlay, weekly_info.keys())
pid_list = pid_dict.keys()
pid_list.sort()
for pid in pid_list:
training_set_final = []
testing_set_final = []
pid_list_training = deepcopy(pid_list)
pid_list_training.remove(pid)
ff.setdata(message_data)
testing_raw_data = ff.filterbyequality(pr.m_source, pid_dict[pid]) + \
ff.filterbyequality(pr.m_target, pid_dict[pid])
ff.removebyequality(pr.m_source, pid_dict[pid])
ff.removebyequality(pr.m_target, pid_dict[pid])
training_raw_data = ff.getdata()
fe = raw_features(data=None)
_, _ = fe.get_scoring_factors(training_raw_data)
training_weekly_data = {}
for training_pid in pid_list_training:
training_weekly_data[training_pid] = {}
data_to_use = ff.filterbyequality(pr.m_source, pid_dict[training_pid]) + \
ff.filterbyequality(pr.m_target, pid_dict[training_pid])
if 0 == len(data_to_use):
print 'no data found, probably filtered into the testing set, Training PID: '+\
training_pid+', Testing PID: '+pid
continue
pid_weekly_w_bullying, global_in_degree, global_out_degree, global_in_ew, global_out_ew, incoming_ss, \
outgoing_ss = get_pid_level_features(data_to_use, weekly_info, ff,
bullying_overlay, pid_dict,
training_pid, fe)
for week_no in pid_weekly_w_bullying:
fr_in_degree, fr_out_degree, fr_in_ew, \
fr_out_ew, fr_in_senti, fr_out_senti, \
current_in_ss, current_out_ss = get_week_features(pid_weekly_w_bullying, week_no, fe,
global_in_degree, global_out_degree,
global_in_ew, global_out_ew,
incoming_ss, outgoing_ss,
pid_dict[training_pid])
training_set_final.append(
[training_pid, week_no,
fr_in_senti[0], fr_in_senti[1], fr_in_senti[2],
fr_out_senti[0], fr_out_senti[1], fr_out_senti[2],
fr_in_degree, fr_out_degree,
fr_in_ew, fr_out_ew,
current_in_ss, current_out_ss,
pid_weekly_w_bullying[week_no]['label']])
# testing pid
pid_weekly_w_bullying, global_in_degree, global_out_degree, \
global_in_ew, global_out_ew, incoming_ss, outgoing_ss = get_pid_level_features(testing_raw_data, weekly_info,
ff, bullying_overlay, pid_dict,
pid, fe)
for week_no in pid_weekly_w_bullying:
fr_in_degree, fr_out_degree, fr_in_ew, \
fr_out_ew, fr_in_senti, fr_out_senti, \
current_in_ss, current_out_ss = get_week_features(pid_weekly_w_bullying, week_no, fe,
global_in_degree, global_out_degree,
global_in_ew, global_out_ew,
incoming_ss, outgoing_ss,
pid_dict[pid])
testing_set_final.append(
[pid, week_no,
fr_in_senti[0], fr_in_senti[1], fr_in_senti[2],
fr_out_senti[0], fr_out_senti[1], fr_out_senti[2],
fr_in_degree, fr_out_degree,
fr_in_ew, fr_out_ew,
current_in_ss, current_out_ss,
pid_weekly_w_bullying[week_no]['label']])
header = ['pid', 'wkno',
'frWInSenPos', 'frWInSenNeu', 'frWInSenNeg',
'frWOutSenPos', 'frWOutSenNeu', 'frWOutSenNeg',
'frInDegO', 'frOutDegO',
'frInEdgeO', 'frOutEdgeO',
'inSenSc', 'outSenSc',
'label']
training_set_final = [header] + training_set_final
testing_set_final = [header] + testing_set_final
hlp.writecsv(training_set_final, output_folder+pid+'_tr.csv')
hlp.writecsv(testing_set_final, output_folder+pid+'_ts.csv')
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-m', '-M', required=True,
help='Sentiment Message file')
parser.add_argument('-t', '-T', action='store_true',
help='Sentiment type flag, if used then vader, else afinn')
parser.add_argument('-f', '-F', required=True,
help='Folder to store checkpoints, and final result')
parser.add_argument('-w', '-W', required=False,
help='Per week/month analysis')
args = parser.parse_args()
message_file = args.m
sentiment_type = args.t
location_to_store = args.f
survey_file = args.w
# get message data, only sms and fb_message
ff = filterfields(message_file)
ff.setdata(ff.getdata()[1:])
sms_data = ff.filterbyequality(pr.m_type, 'sms')
pid_dict_sms = hlp.getuniqueparticipants2(sms_data)
fb_message_data = ff.filterbyequality(pr.m_type, 'fb_message')
pid_dict_fb = hlp.getuniqueparticipants2(fb_message_data)
message_data = sms_data + fb_message_data
# put the labels on
labelled_data = hlp.processvadersentiment(message_data, label_only=False) if sentiment_type else \
hlp.processafinnsentiment(message_data, label_only=False)
if survey_file is not None:
wi = weeklyinfo()
weekly_info = wi.getweeklyfo(survey_file)
weekly_data = hlp.divideintoweekly(labelled_data, weekly_info, ff)
#__temp_testing_for_discrepancy(labelled_data, weekly_data)
# get the pid_dict for easier handling
pid_dict = hlp.getuniqueparticipants2(labelled_data)
if survey_file is not None:
over_sent, in_sent, out_sent, xtick, ytick = per_participant_sentiment(weekly_data, pid_dict['participants'])
__plot_imshow(over_sent, 'Participant', 'Week #', xtick, ytick, location_to_store+'sent_imshow_over.pdf')
__plot_imshow(in_sent, 'Participant', 'Week #', xtick, ytick, location_to_store+'sent_imshow_in.pdf')
__plot_imshow(out_sent, 'Participant', 'Week #', xtick, ytick, location_to_store+'sent_imshow_out.pdf')
print '***SMS***'
print 'P: ', len(pid_dict_sms['participants'].values()), ' NP: ', len(pid_dict_sms['nonparticipants'].values())
print '***FB***'
print 'P: ', len(pid_dict_fb['participants'].values()), 'NP: ', len(pid_dict_fb['nonparticipants'].values())
print '***OVERALL***'
print 'P: ', len(pid_dict['participants'].values()), 'NP: ', len(pid_dict['nonparticipants'].values())
summary_src_trg = summarize_message_by_src_trg(labelled_data)
print '***Message Distribution***'
for m_type_1 in summary_src_trg:
print m_type_1, summary_src_trg[m_type_1]
if survey_file is not None:
week_list = weekly_data.keys()
week_list.sort()
# this is not good, as there aren't enough triads
months = [[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]]
# this has at least 8 triads, always, use this
months2 = [[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]]
month_idx = 1
for month in months2:
labelled_data = []
for week in month:
labelled_data.extend(weekly_data[week])
general_graph, random_graph = conduct_triad_analysis(labelled_data, pid_dict)
frac_triad = general_graph[3]
summary_triad = general_graph[2]
frac_triad_rand = random_graph[3]
summary_triad_rand = random_graph[2]
print '** Months ', 2*month_idx-1, 2*month_idx, ': ', month,' ***'
print 'len(LD): ', len(labelled_data)
for summary in frac_triad:
print summary, 'Study: ', frac_triad[summary], '(', len(summary_triad[summary]), ')', ' Random: ', \
frac_triad_rand[summary], '(', len(summary_triad_rand[summary]), ')'
words_list, short_list = word_count(labelled_data)
toWrite_wl_csv = create_word_count_csv(words_list)
hlp.writecsv(toWrite_wl_csv, location_to_store+'word_list_'+str(2*month_idx-1)+'-'+str(2*month_idx)+'.csv',
delimiter_sym=',')
for mtype in words_list:
counted_words = Counter(words_list[mtype])
counted_short = Counter(short_list[mtype])
print '***For '+mtype+' ***'
print 'Top 20 words: ', __get_top_word_sentiment(counted_words.most_common(20))
print 'Top 20 short: ', counted_short.most_common(20)
print '\n\n'
hlp.dumpvariable([general_graph, random_graph, labelled_data, pid_dict], 'month_'+str(month_idx)+'.list', location_to_store)
month_idx += 1
else:
print 'len(LD): ', len(labelled_data)
words_list, short_list = word_count(labelled_data)
toWrite_wl_csv = create_word_count_csv(words_list)
hlp.writecsv(toWrite_wl_csv, location_to_store+'word_list.csv', delimiter_sym=',')
for mtype in words_list:
counted_words = Counter(words_list[mtype])
counted_short = Counter(short_list[mtype])
print '***For '+mtype+' ***'
print 'Top 20 words: ', __get_top_word_sentiment(counted_words.most_common(20))
print 'Top 20 short: ', counted_short.most_common(20)
print '\n\n'
general_graph, random_graph = conduct_triad_analysis(labelled_data, pid_dict)
frac_triad = general_graph[3]
summary_triad = general_graph[2]
frac_triad_rand = random_graph[3]
summary_triad_rand = random_graph[2]
for summary in frac_triad:
print summary, 'Study: ', frac_triad[summary], '(', len(summary_triad[summary]), ')', ' Random: ', \
frac_triad_rand[summary], '(', len(summary_triad_rand[summary]), ')'
hlp.dumpvariable([general_graph, random_graph, labelled_data, pid_dict], 'Overall.list', location_to_store)
# plot_degree_dist(general_graph[4], 'Degree(d)', '# of Participants with Degree d')
pos, neg, neu = get_polarity_directionality(labelled_data)
print '***Polarity Distribution***'
print 'Positive: \n', pos
print 'Negative: \n', neg
print 'Neutral: \n', neu
in_m, out_m, in_d, out_d = get_count_degrees_messages_directed(labelled_data, pid_dict['participants'])
print '***Incoming Messages***'
print 'Total: ', sum(in_m), 'Mean: ', np.mean(in_m), 'Std. dev.: ', np.std(in_m)
print '***Outgoing Messages***'
print 'Total: ', sum(out_m), 'Mean: ', np.mean(out_m), 'Std. dev.: ', np.std(out_m)
print '***In Degree***'
print 'Total: ', sum(in_d), 'Mean: ', np.mean(in_d), 'Std. dev.: ', np.std(in_d)
print '***Out Degree***'
print 'Total: ', sum(out_d), 'Mean: ', np.mean(out_d), 'Std. dev.: ', np.std(out_d)
print '***COUNTS***'
plot_messages_degree([in_m, out_m], '# of Messages', 'Cumulative Participant Prob.',
location_to_store+'in_out_messages.pdf')
# plot_messages_degree(out_m, '# of Outgoing Messages', 'Cumulative Participant Prob.',
# location_to_store+'out_messages.pdf')
plot_messages_degree([in_d, out_d], 'Degree', 'Cumulative Participant Prob.',
location_to_store+'in_out_degree.pdf', True)
# plot_messages_degree(out_d, 'Out Degree', 'Cumulative Participant Prob.',
# location_to_store+'out_degree.pdf', True)
print 'TADAA!!'
