def make_basemap(basemap):
try:
set_status('getting document list', model=basemap)
with ManagedSession() as session:
filtered_query = create_query_for_model(session, basemap, dirty=False)
extracted_terms = extract_terms(filtered_query, basemap.term_type)
if not extracted_terms:
raise Exception('No documents found matching query!')
map_dict, graph_terms, phrase_frequencies, unnormed_dict, phrase_scores = map_representation(extracted_terms,
ranking_algorithm=basemap.ranking_algorithm,
similarity_algorithm=basemap.similarity_algorithm,
filtering_algorithm=basemap.filtering_algorithm,
number_of_terms=basemap.number_of_terms,
model=basemap)
# map_string will be a graphviz-processable string
# map_string = write_dot.output_pairs_dict(map_dict, True, phrase_frequencies=phrase_frequencies, true_scaling=True).decode('ascii', 'ignore')
map_string = write_dot.output_pairs_dict(map_dict, True, phrase_frequencies=phrase_frequencies, true_scaling=True, similarities=unnormed_dict, phrase_scores=phrase_scores).decode('ascii', 'ignore')
# save to database
basemap.dot_rep = map_string
# basemap.phrase_frequencies = json.dumps(jsonize_phrase_dict(phrase_frequencies), indent=4).decode('ascii', 'ignore')
# get phrases as a list of lists of strings (one list of words per term)
basemap.phrases_in_map = json.dumps(jsonize_phrase_set(graph_terms, None)).decode('ascii', 'ignore')
basemap.save()
svg_str, width, height = strip_dimensions(call_graphviz(map_string, file_format='svg', model=basemap))
basemap.svg_rep = svg_str
basemap.width = width
basemap.height = height
basemap.finished = True
basemap.save()
set_status('basemap complete', model=basemap)
print 'basemap complete'
return map_dict, graph_terms
except ZeroDivisionError as e:
set_status('Error: too few documents to produce a map. Try a broader search', model=basemap)
def make_heatmap(heatmap, graph_terms):
try:
set_status('getting document list', model=heatmap)
with ManagedSession() as session:
filtered_query = create_query_for_model(session, heatmap, dirty=False)
extracted_terms = extract_terms(filtered_query, heatmap.term_type)
heatmap_terms = flatten(extracted_terms)
heatmap_vals = calculate_heatmap_values(heatmap_terms, graph_terms)
heatmap.terms = json.dumps(jsonize_phrase_dict(heatmap_vals, 'intensity'))
set_status('heatmap complete', model=heatmap)
heatmap.finished = True
heatmap.save()
return heatmap_vals
except Exception as e:
set_status('Error: %s' % e, model=heatmap)
raise e
