def story_words_csv(topics_id, stories_id):
query = add_to_user_query('stories_id:'+stories_id)
ngram_size = request.args['ngram_size'] if 'ngram_size' in request.args else 1 # default to word count
word_counts = topic_ngram_counts(user_mediacloud_key(), topics_id, ngram_size, q=query,
num_words=WORD_COUNT_DOWNLOAD_NUM_WORDS)
return csv.stream_response(word_counts, WORD_COUNT_DOWNLOAD_COLUMNS,
'topic-{}-story-{}-sampled-ngrams-{}-word'.format(topics_id, stories_id, ngram_size))
def topic_provider_words_csv(topics_id):
optional_args = _parse_words_optional_arguments()
results = apicache.topic_ngram_counts(user_mediacloud_key(), topics_id,
**optional_args)
file_name = 'topic-{}-sampled-ngrams-{}-word'.format(
topics_id, optional_args['ngram_size'])
return csv.stream_response(results, apicache.WORD_COUNT_DOWNLOAD_COLUMNS,
file_name)
def media_words_csv(topics_id, media_id):
query = apicache.add_to_user_query('media_id:'+media_id)
ngram_size = request.args['ngram_size'] if 'ngram_size' in request.args else 1 # default to word count
word_counts = apicache.topic_ngram_counts(user_mediacloud_key(), topics_id, ngram_size=ngram_size, q=query,
num_words=WORD_COUNT_DOWNLOAD_NUM_WORDS,
sample_size=WORD_COUNT_DOWNLOAD_SAMPLE_SIZE)
return csv.stream_response(word_counts, apicache.WORD_COUNT_DOWNLOAD_COLUMNS,
'topic-{}-media-{}-sampled-ngrams-{}-word'.format(topics_id, media_id, ngram_size))
def topic_words_csv(topics_id):
query = apicache.add_to_user_query(None)
sample_size = request.args['sample_size'] if 'sample_size' in request.args else WORD_COUNT_SAMPLE_SIZE
ngram_size = request.args['ngram_size'] if 'ngram_size' in request.args else 1 # default to word count
word_counts = apicache.topic_ngram_counts(user_mediacloud_key(), topics_id, ngram_size=ngram_size, q=query,
num_words=WORD_COUNT_DOWNLOAD_NUM_WORDS, sample_size=sample_size)
return csv.stream_response(word_counts, apicache.WORD_COUNT_DOWNLOAD_COLUMNS,
'topic-{}-sampled-ngrams-{}-word'.format(topics_id, ngram_size))
def topic_provider_words(topics_id):
optional_args = _parse_words_optional_arguments()
word_counts = apicache.topic_ngram_counts(user_mediacloud_key(), topics_id, **optional_args)
results = {
'words': word_counts[:WORD_COUNT_UI_NUM_WORDS],
**optional_args
}
return jsonify(results)
def topic_word_associated_words_csv(topics_id, word):
query = apicache.add_to_user_query(word)
ngram_size = request.args[
'ngram_size'] if 'ngram_size' in request.args else 1 # default to word count
word_counts = apicache.topic_ngram_counts(user_mediacloud_key(),
topics_id,
ngram_size=ngram_size,
q=query)
return csv.stream_response(
word_counts, apicache.WORD_COUNT_DOWNLOAD_COLUMNS,
'topic-{}-{}-sampled-ngrams-{}-word'.format(topics_id, word,
ngram_size))
