def topic_compare_subtopic_top_words(topics_id):
snapshots_id, timespans_id, foci_id, q = filters_from_args(request.args)
selected_focal_sets_id = request.args['focal_sets_id']
word_count = request.args['word_count'] if 'word_count' in request.args else 20
# first we need to figure out which timespan they are working on
selected_snapshot_timespans = apicache.cached_topic_timespan_list(user_mediacloud_key(), topics_id,
snapshots_id=snapshots_id)
selected_timespan = None
for t in selected_snapshot_timespans:
if t['timespans_id'] == int(timespans_id):
selected_timespan = t
try:
focal_set = apicache.topic_focal_set(user_mediacloud_key(), topics_id, snapshots_id, selected_focal_sets_id)
except ValueError:
return json_error_response('Invalid Focal Set Id')
timespans = apicache.matching_timespans_in_foci(topics_id, selected_timespan, focal_set['foci'])
for idx in range(0, len(timespans)):
data = apicache.topic_word_counts(user_mediacloud_key(), topics_id,
timespans_id=timespans[idx]['timespans_id'])
focal_set['foci'][idx]['top_words'] = data
# stitch together the counts to download now
data = []
headers = [f['name'] for f in focal_set['foci']]
for idx in range(0, word_count):
row = {f['name']: "{} ({})".format(f['top_words'][idx]['term'], f['top_words'][idx]['count'])
for f in focal_set['foci']}
data.append(row)
return csv.stream_response(data, headers,
'topic-{}-subtopic-{}-{}-top-words-comparison'.format(
topics_id, focal_set['name'], selected_focal_sets_id))
def topic_compare_subtopic_top_words(topics_id):
snapshots_id, timespans_id, foci_id, q = filters_from_args(request.args)
selected_focal_sets_id = request.args['focal_sets_id']
word_count = request.args['word_count'] if 'word_count' in request.args else 20
# first we need to figure out which timespan they are working on
selected_snapshot_timespans = apicache.cached_topic_timespan_list(user_mediacloud_key(), topics_id, snapshots_id=snapshots_id)
selected_timespan = None
for t in selected_snapshot_timespans:
if t['timespans_id'] == int(timespans_id):
selected_timespan = t
focal_set = apicache.topic_focal_set(user_mediacloud_key(), topics_id, snapshots_id, selected_focal_sets_id)
timespans = apicache.matching_timespans_in_foci(topics_id, selected_timespan, focal_set['foci'])
for idx in range(0, len(timespans)):
data = apicache.topic_word_counts(user_mediacloud_key(), topics_id,
timespans_id=timespans[idx]['timespans_id'])
focal_set['foci'][idx]['top_words'] = data
# stitch together the counts to download now
data = []
headers = [f['name'] for f in focal_set['foci']]
for idx in range(0, word_count):
row = {f['name']: u"{} ({})".format(f['top_words'][idx]['term'], f['top_words'][idx]['count'])
for f in focal_set['foci']}
data.append(row)
return csv.stream_response(data, headers,
'topic-{}-subtopic-{}-{}-top-words-comparison'.format(
topics_id, focal_set['name'], selected_focal_sets_id))
def topic_focal_set_split_stories_compare(topics_id, focal_sets_id):
snapshots_id, timespans_id, foci_id, q = filters_from_args(request.args)
# need the timespan info, to find the appropriate timespan with each focus
try:
base_timespan = base_snapshot_timespan(topics_id)
focal_set = apicache.topic_focal_set(user_mediacloud_key(), topics_id, snapshots_id, focal_sets_id)
except ValueError as e:
return json_error_response(e.message)
# collect the story split counts for each foci
timespans = apicache.matching_timespans_in_foci(topics_id, base_timespan, focal_set['foci'])
for idx in range(0, len(timespans)):
data = apicache.topic_split_story_counts(user_mediacloud_key(), topics_id, snapshots_id=snapshots_id,
timespans_id=timespans[idx]['timespans_id'])
focal_set['foci'][idx]['split_story_counts'] = data
return jsonify(focal_set)
def topic_focal_set_split_stories_compare(topics_id, focal_sets_id):
snapshots_id, timespans_id, foci_id, q = filters_from_args(request.args)
# need the timespan info, to find the appropriate timespan with each focus
base_snapshot_timespans = apicache.cached_topic_timespan_list(
user_mediacloud_key(), topics_id, snapshots_id=snapshots_id)
# if they have a focus selected, we need to find the appropriate overall timespan
if foci_id is not None:
timespan = apicache.topic_timespan(topics_id, snapshots_id, foci_id,
timespans_id)
for t in base_snapshot_timespans:
if apicache.is_timespans_match(timespan, t):
base_timespan = t
else:
base_timespan = None
for t in base_snapshot_timespans:
if t['timespans_id'] == int(timespans_id):
base_timespan = t
logger.info('base timespan = %s', timespans_id)
if base_timespan is None:
return json_error_response("Couldn't find the timespan you specified")
# iterate through to find the one of interest
focal_set = apicache.topic_focal_set(user_mediacloud_key(), topics_id,
snapshots_id, focal_sets_id)
if focal_set is None:
return json_error_response('Invalid Focal Set Id')
# collect the story split counts for each foci
timespans = apicache.matching_timespans_in_foci(topics_id, base_timespan,
focal_set['foci'])
for idx in range(0, len(timespans)):
data = apicache.topic_split_story_counts(
user_mediacloud_key(),
topics_id,
snapshots_id=snapshots_id,
timespans_id=timespans[idx]['timespans_id'])
focal_set['foci'][idx]['split_story_counts'] = data
return jsonify(focal_set)