def get_svg_file_url(node_id, isMap):
c = Centrality()
node_path = c.create_svg_url(node_id, isMap)
try:
file = urlopen(node_path)
svg = file.read()
except (IOError):
print('File was not found:')
print(node_path)
return svg
def get_svg_file(node_id):
c = Centrality()
node_path = c.get_svg_path(node_id)
try:
with application.open_resource(node_path) as file:
svg = file.read()
except (IOError):
print('File was not found:')
print(node_path)
return svg
def get_loc_sim_matrix(graph, graph1):
centra = Centrality()
aifsim = Aifsim()
g_copy = graph.copy()
g1_copy = graph1.copy()
g_lnodes = centra.get_l_node_list(g_copy)
g1_lnodes = centra.get_l_node_list(g1_copy)
relsl, valsl, switched = aifsim.text_sim_matrix(g_lnodes, g1_lnodes)
rels_dict = aifsim.rels_to_dict(relsl, switched)
return rels_dict
def get_prop_sim_matrix(graph, graph1):
centra = Centrality()
aifsim = Aifsim()
g_copy = graph.copy()
g1_copy = graph1.copy()
g_inodes = centra.get_i_node_list(g_copy)
g1_inodes = centra.get_i_node_list(g1_copy)
relsi, valsi, switched = aifsim.text_sim_matrix(g_inodes, g1_inodes)
#if switched the relations have been switched order so they need reversed when creating the dictionary
rels_dict = aifsim.rels_to_dict(relsi, switched)
return rels_dict
def get_ordered_nodes(node_id):
centra = Centrality()
node_path = centra.get_nodeset_path(node_id)
graph = centra.get_graph(node_path)
n_graph = centra.remove_redundant_nodes(graph)
i_nodes = centra.get_eigen_centrality(n_graph)
ordered_nodes = centra.sort_by_centrality(i_nodes)
return ordered_nodes
def get_graph_sim(aif_id1, aif_id2):
centra = Centrality()
aifsim = Aifsim()
graph, json = aifsim.get_graph(aif_id1, centra)
graph1, json1 = aifsim.get_graph(aif_id2, centra)
graph = centra.remove_iso_analyst_nodes(graph)
graph1 = centra.remove_iso_analyst_nodes(graph1)
rep_form = aifsim.is_iat(graph, graph1, centra)
g_copy = graph.copy()
g1_copy = graph1.copy()
graph_mean = 0
text_mean = 0
overall_mean = 0
if rep_form == 'diff':
return 'Error'
else:
graph_mean = aifsim.call_diagram_parts_and_sum(
g_copy, g1_copy, rep_form)
if rep_form == 'aif':
g_inodes = centra.get_i_node_list(g_copy)
g1_inodes = centra.get_i_node_list(g1_copy)
relsi, valsi, switched = aifsim.text_sim_matrix(
g_inodes, g1_inodes)
i_mean = aifsim.get_mean_of_list(valsi)
text_mean = i_mean
else:
g_inodes = centra.get_i_node_list(g_copy)
g1_inodes = centra.get_i_node_list(g1_copy)
g_lnodes = centra.get_l_node_list(g_copy)
g1_lnodes = centra.get_l_node_list(g1_copy)
relsi, valsi, switched = aifsim.text_sim_matrix(
g_inodes, g1_inodes)
relsl, valsl, switched = aifsim.text_sim_matrix(
g_lnodes, g1_lnodes)
i_mean = aifsim.get_mean_of_list(valsi)
l_mean = aifsim.get_mean_of_list(valsl)
text_mean = aifsim.get_l_i_mean(l_mean, i_mean)
overall_score = aifsim.get_l_i_mean(text_mean, graph_mean)
return overall_score, text_mean, graph_mean
def get_arg_schemes(nodeset):
cent = Centrality()
j_url = cent.create_json_url(str(nodeset), True)
graph = cent.get_graph_url(j_url)
json_data = get_json_string(j_url)
ras = cent.get_ras(graph)
ras_i_list = cent.get_ra_i_nodes(graph, ras)
ra_changes = []
for ns in ras_i_list:
ra_id = ns[0]
s_id = ns[1]
e_id = ns[2]
schemes = identifyScheme(e_id, s_id)
if len(schemes) < 1:
continue
else:
ra_tup = (ra_id, schemes[0])
ra_changes.append(ra_tup)
#get json string and replace text at ID then upload
print(ra_changes)
if len(ra_changes) < 1:
return ''
else:
n_json_data = replace_node(json_data, ra_changes)
url_aif = 'http://www.aifdb.org/json/'
jsn_data = json.dumps(n_json_data)
map_response = aif_upload(url_aif, jsn_data)
map_data = json.loads(map_response)
fin_map_id = map_data['nodeSetID']
return fin_map_id
def ca_anchor(graph1, graph2):
conf_matrix = [[0, 0],[0, 0]]
aifsim = Aifsim()
cent = Centrality()
cas1 = cent.get_cas(graph1)
cas2 = cent.get_cas(graph2)
ca1_len = len(cas1)
ca2_len = len(cas2)
if ca1_len > 0 and ca2_len > 0:
if ca1_len > ca2_len:
for ca_i, ca in enumerate(cas1):
cas2_id = ''
yas1 = aifsim.get_ya_nodes_from_prop(ca, graph1)
try:
cas2_id = cas2[ca_i]
except:
cas2_id = ''
if cas2_id == '':
#conf_matrix[index][len(all_ya_text) + 1] = conf_matrix[index][len(all_ya_text) + 1] + 1
conf_matrix[1][0] = conf_matrix[1][0] + 1
else:
yas2 = aifsim.get_ya_nodes(cas2_id, graph2)
if yas1 == yas2:
conf_matrix[0][0] = conf_matrix[0][0] + 1
else:
conf_matrix[1][0] = conf_matrix[1][0] + 1
elif ca2_len > ca1_len:
for ca_i, ca in enumerate(cas2):
cas1_id = ''
yas2 = aifsim.get_ya_nodes_from_prop(ca, graph2)
try:
cas1_id = cas1[ca_i]
except:
cas1_id = ''
if cas1_id == '':
#conf_matrix[index][len(all_ya_text) + 1] = conf_matrix[index][len(all_ya_text) + 1] + 1
conf_matrix[0][1] = conf_matrix[0][1] + 1
else:
yas1 = aifsim.get_ya_nodes(cas1_id, graph1)
if yas1 == yas2:
conf_matrix[0][0] = conf_matrix[0][0] + 1
else:
conf_matrix[0][1] = conf_matrix[0][1] + 1
else:
for ca_i, ca in enumerate(cas1):
ya1 = aifsim.get_ya_nodes_from_prop(ca, graph1)
ya2 = aifsim.get_ya_nodes_from_prop(cas2[ca_i], graph2)
if ya1 == ya2:
conf_matrix[0][0] = conf_matrix[0][0] + 1
else:
conf_matrix[1][0] = conf_matrix[1][0] + 1
elif ca1_len == 0 and ca2_len == 0:
conf_matrix[1][1] = conf_matrix[1][1] + 1
elif ca1_len == 0:
conf_matrix[0][1] = conf_matrix[0][1] + ca2_len
elif ca2_len == 0:
conf_matrix[1][0] = conf_matrix[1][0] + ca1_len
return conf_matrix
def ra_anchor(graph1, graph2):
conf_matrix = [[0, 0],[0, 0]]
aifsim = Aifsim()
cent = Centrality()
ras1 = cent.get_ras(graph1)
ras2 = cent.get_ras(graph2)
ra1_len = len(ras1)
ra2_len = len(ras2)
if ra1_len > 0 and ra2_len > 0:
if ra1_len > ra2_len:
for ra_i, ra in enumerate(ras1):
ras2_id = ''
yas1 = aifsim.get_ya_nodes_from_prop(ra, graph1)
try:
ras2_id = ras2[ra_i]
except:
ras2_id = ''
if ras2_id == '':
#conf_matrix[index][len(all_ya_text) + 1] = conf_matrix[index][len(all_ya_text) + 1] + 1
conf_matrix[1][0] = conf_matrix[1][0] + 1
else:
yas2 = get_ya_nodes(ras2_id, graph2)
if yas1 == yas2:
conf_matrix[0][0] = conf_matrix[0][0] + 1
else:
conf_matrix[1][0] = conf_matrix[1][0] + 1
elif ra2_len > ra1_len:
for ra_i, ra in enumerate(ras2):
ras1_id = ''
yas2 = aifsim.get_ya_nodes_from_prop(ra, graph2)
try:
ras1_id = ras1[ra_i]
except:
ras1_id = ''
if ras1_id == '':
#conf_matrix[index][len(all_ya_text) + 1] = conf_matrix[index][len(all_ya_text) + 1] + 1
conf_matrix[0][1] = conf_matrix[0][1] + 1
else:
yas1 = aifsim.get_ya_nodes(ras1_id, graph1)
if yas1 == yas2:
conf_matrix[0][0] = conf_matrix[0][0] + 1
else:
conf_matrix[0][1] = conf_matrix[0][1] + 1
else:
for ra_i, ra in enumerate(ras1):
ya1 = aifsim.get_ya_nodes_from_prop(ra, graph1)
ya2 = aifsim.get_ya_nodes_from_prop(ras2[ra_i], graph2)
if ya1 == ya2:
conf_matrix[0][0] = conf_matrix[0][0] + 1
else:
conf_matrix[1][0] = conf_matrix[1][0] + 1
elif ra1_len == 0 and ra2_len == 0:
conf_matrix[1][1] = conf_matrix[1][1] + 1
elif ra1_len == 0:
conf_matrix[0][1] = conf_matrix[0][1] + ra2_len
elif ra2_len == 0:
conf_matrix[1][0] = conf_matrix[1][0] + ra1_len
return conf_matrix
def get_svg_file_path(node_id):
c = Centrality()
node_path = c.get_svg_path(node_id)
return node_path
def render_text():
source_text = session.get('s_text', None)
external_text = session.get('e_text', None)
aif_mode = session.get('aif', None)
han_mode = session.get('han', None)
ex_aif_mode = session.get('e_aif', None)
source_date = session.get('s_date', None)
centra = Centrality()
s_map_numbers = []
ex_map_numbers = []
ma_thresh = 0.85
ra_thresh = 0.55
s_l_i_nodes = []
ex_l_i_nodes = []
s_l_nodes = []
ex_l_nodes = []
h_l_i_nodes = []
h_l_nodes = []
if aif_mode == "true" and han_mode == "true" and ex_aif_mode == "false":
# Source Map and Hansard
sources = source_text.split(',')
s_map_numbers = [int(i) for i in sources]
central_nodes, s_l_i_nodes, s_l_nodes = centra.get_top_nodes_combined(
s_map_numbers)
source_topic_text = get_topic_text(central_nodes)
txt_df = sent_to_df(source_topic_text)
result = predict_topic(txt_df)
hansard_fp = get_hansard_file_path(source_date, result,
'HansardDataAMF')
hansard_map_num = check_hansard_path(hansard_fp)
if hansard_map_num[0] == '':
hansard_text = get_hansard_text(hansard_fp)
hansard_text = hansard_text.decode("utf-8")
ex_map_numbers = do_amf_calls(hansard_text, True)
write_to_csv(ex_map_numbers, hansard_fp)
else:
ex_map_numbers = hansard_map_num
ex_map_numbers = ast.literal_eval(ex_map_numbers)
h_i_nodes, h_l_i_nodes, h_l_nodes = centra.get_top_nodes_combined(
ex_map_numbers)
relations = itc_matrix(central_nodes, h_i_nodes, ma_thresh, ra_thresh)
if len(relations) > 0:
#Build itc map
map_id = build_itc_map(relations, s_l_i_nodes, h_l_i_nodes,
s_l_nodes, h_l_nodes)
elif aif_mode == "true" and han_mode == "false" and ex_aif_mode == "true":
# Source Map and External Maps
sources = source_text.split(',')
s_map_numbers = [int(i) for i in sources]
external = external_text.split(',')
ex_map_numbers = [int(i) for i in external]
central_nodes, s_l_i_nodes, s_l_nodes = centra.get_top_nodes_combined(
s_map_numbers)
ex_i_nodes, ex_l_i_nodes, ex_l_nodes = centra.get_all_nodes_combined(
ex_map_numbers)
relations = itc_matrix(central_nodes, ex_i_nodes, ma_thresh, ra_thresh)
if len(relations) > 0:
#Build itc map
map_id = build_itc_map(relations, s_l_i_nodes, ex_l_i_nodes,
s_l_nodes, ex_l_nodes)
elif aif_mode == "false" and han_mode == "true" and ex_aif_mode == "false":
# Source Text and Hansard
s_map_numbers = do_amf_calls(source_text, False)
central_nodes, s_l_i_nodes, s_l_nodes = centra.get_top_nodes_combined(
s_map_numbers)
source_topic_text = get_topic_text(central_nodes)
txt_df = sent_to_df(source_topic_text)
result = predict_topic(txt_df)
hansard_fp = get_hansard_file_path(source_date, result,
'HansardDataAMF')
hansard_map_num = check_hansard_path(hansard_fp)
if hansard_map_num[0] == '':
hansard_text = get_hansard_text(hansard_fp)
hansard_text = hansard_text.decode("utf-8")
ex_map_numbers = do_amf_calls(hansard_text, True)
write_to_csv(ex_map_numbers, hansard_fp)
else:
ex_map_numbers = hansard_map_num
ex_map_numbers = ast.literal_eval(ex_map_numbers)
h_i_nodes, h_l_i_nodes, h_l_nodes = centra.get_top_nodes_combined(
ex_map_numbers)
#print(central_nodes, h_i_nodes)
relations = itc_matrix(central_nodes, h_i_nodes, ma_thresh, ra_thresh)
if len(relations) > 0:
#Build itc map
map_id = build_itc_map(relations, s_l_i_nodes, h_l_i_nodes,
s_l_nodes, h_l_nodes)
elif aif_mode == "false" and han_mode == "false" and ex_aif_mode == "false":
# Source Text and External Text
s_map_numbers = do_amf_calls(source_text, False)
central_nodes, s_l_i_nodes, s_l_nodes = centra.get_top_nodes_combined(
s_map_numbers)
ex_map_numbers = do_amf_calls(external_text, False)
ex_i_nodes, ex_l_i_nodes, ex_l_nodes = centra.get_all_nodes_combined(
ex_map_numbers)
relations = itc_matrix(central_nodes, ex_i_nodes, ma_thresh, ra_thresh)
if len(relations) > 0:
#Build itc map
map_id = build_itc_map(relations, s_l_i_nodes, ex_l_i_nodes,
s_l_nodes, ex_l_nodes)
elif aif_mode == "true" and han_mode == "false" and ex_aif_mode == "false":
# Source Text and External Text
sources = source_text.split(',')
s_map_numbers = [int(i) for i in sources]
central_nodes, s_l_i_nodes, s_l_nodes = centra.get_top_nodes_combined(
s_map_numbers)
ex_map_numbers = do_amf_calls(external_text, False)
ex_i_nodes, ex_l_i_nodes, ex_l_nodes = centra.get_all_nodes_combined(
ex_map_numbers)
relations = itc_matrix(central_nodes, ex_i_nodes, ma_thresh, ra_thresh)
if len(relations) > 0:
#Build itc map
map_id = build_itc_map(relations, s_l_i_nodes, ex_l_i_nodes,
s_l_nodes, ex_l_nodes)
elif aif_mode == "false" and han_mode == "false" and ex_aif_mode == "true":
# Source Text and External Map
s_map_numbers = do_amf_calls(source_text, False)
central_nodes, s_l_i_nodes, s_l_nodes = centra.get_top_nodes_combined(
s_map_numbers)
external = external_text.split(',')
ex_map_numbers = [int(i) for i in external]
ex_i_nodes, ex_l_i_nodes, ex_l_nodes = centra.get_all_nodes_combined(
ex_map_numbers)
relations = itc_matrix(central_nodes, ex_i_nodes, ma_thresh, ra_thresh)
if len(relations) > 0:
#Build itc map
map_id = build_itc_map(relations, s_l_i_nodes, ex_l_i_nodes,
s_l_nodes, ex_l_nodes)
new_map_numbers = get_new_map_nums(s_map_numbers)
if len(relations) > 0:
itc_map_number = get_new_itc_map(map_id)
itc_map_list = [itc_map_number]
itc_map_view_list = create_argview_links(itc_map_list)
itc_number = str(itc_map_view_list[0])
itc_relations = [(rels[1], rels[3], rels[4]) for rels in relations]
else:
itc_number = 'No ITC relations found'
itc_relations = ['No ITC relations found']
source_map_numbers_links = create_argview_links(new_map_numbers)
ex_map_number_links = create_argview_links(ex_map_numbers)
return render_template('results.html',
source_text=source_text,
source_maps_links=source_map_numbers_links,
ex_map_links=ex_map_number_links,
itc_number=itc_number,
itc_relations=itc_relations)
def get_ordered_nodes(node_id, isMap):
centra = Centrality()
#node_path = centra.get_nodeset_path(node_id)
#Add extension for L-nodes here
node_path = centra.create_json_url(node_id, isMap)
graph = centra.get_graph_url(node_path)
graph = centra.remove_iso_nodes(graph)
l_nodes = centra.get_l_node_list(graph)
l_node_i_node = centra.get_loc_prop_pair(graph)
n_graph = centra.remove_redundant_nodes(graph)
list_of_nodes = centra.list_nodes(graph)
divergent_nodes = centra.get_divergent_nodes(n_graph)
s_nodes = centra.get_s_node_list(n_graph)
i_nodes = centra.get_eigen_centrality(n_graph)
ordered_nodes = centra.sort_by_centrality(i_nodes)
children, edges = centra.get_child_edges(n_graph)
return ordered_nodes, list_of_nodes, divergent_nodes, children, edges, s_nodes, l_nodes, l_node_i_node
