def readPagesByTerm(term):
pages = Pages()
# getting the top similar pages for the searched term
main_term_id = str(pages.get_id(term))
sim_pages = pages.query_page(main_term_id)
top_similar_pages = sorted(sim_pages, key=lambda x: x[1], reverse=True)[1:21]
possible_page_ids = set()
possible_page_ids.add(main_term_id)
value_of_list_item = main_term_id +',' + main_term_id + ',0.0'
# add the possible page to the set
page_page_set = set()
page_page_set.add(value_of_list_item)
# Save the page-page similarity values in dict
pages_pages_association_dict = dict()
pages_pages_association_dict[main_term_id] = dict()
for page_vals in sim_pages:
pages_pages_association_dict[main_term_id][str(page_vals[0])] = page_vals[1]
pages_pages_association_dict[page_vals[0]] = { str(page_vals[0]): page_vals[1]}
print ("main term", main_term_id)
# for the pages that are similar to the search term(first layer similar pages), get the top similar page
for page in top_similar_pages:
possible_page_ids.add(str(page[0]))
if str(page[0]) not in pages_pages_association_dict:
pages_pages_association_dict[str(page[0])] = dict()
second_layer_pages = pages.query_page(page[0])
second_layer_pages_top = sorted(second_layer_pages, key=lambda x: x[1], reverse=True)[1:21]
for associated_page in second_layer_pages_top:
possible_page_ids.add(str(associated_page[0]))
for associated_page in second_layer_pages:
if str(associated_page[0]) not in pages_pages_association_dict:
pages_pages_association_dict[str(associated_page[0])] = dict()
pages_pages_association_dict[str(page[0])][str(associated_page[0])] = associated_page[1]
pages_pages_association_dict[str(associated_page[0])][str(page[0])] = associated_page[1]
# form all the page-page similarity values
for page1 in possible_page_ids:
for page2 in possible_page_ids:
if page1 == page2:
# if page1 and page2 doesn't have any similarty value, the similarity values is assigned to 0
value = page1 + ',' + page2 +',' + '0.0'
page_page_set.add(value)
else:
if page1 in pages_pages_association_dict and page2 in pages_pages_association_dict[page1]:
value = str(page1) + ',' + str(page2) +',' + str(pages_pages_association_dict[str(page1)][str(page2)])
else:
value = str(page1) + ',' + str(page2) +',0.0'
page_page_set.add(value)
if page2 in pages_pages_association_dict and page1 in pages_pages_association_dict[page2]:
value = str(page2) + ',' + str(page1) + ','+ str(pages_pages_association_dict[str(page2)][str(page1)])
else:
value = str(page2) + ',' + str(page1) + ',0.0'
page_page_set.add(value)
# printing out the pages in similarity matrx
print (possible_page_ids)
print (len(pages_pages_association_dict))
print (pages_pages_association_dict.keys())
# Return the page-page similarity matrx
return list( page_page_set)
def graph(term):
#make network graph with depth = 2 for term
pages = Pages()
id = pages.get_id(term)
sim_pages = pages.query_page(id)
#make networkx graph object
G = nx.Graph()
node_dict = {}
title = pages.get_title(int(id))
G.add_node(title)
#original term is red
node_dict[title] = ('red', 0.0)
#add top 10 pages similar to term
short_sim_pages = sorted(sim_pages, key=lambda x: x[1], reverse=True)[1:11]
for page in short_sim_pages:
page_name = pages.get_title(int(page[0]))
G.add_node(page_name)
#depth = 1 terms are blue
node_dict[page_name] = ('blue', float(page[1]))
G.add_edge(title,page_name)
addl_nodes = add_x_nodes(pages, G, page[0], 10)
#add next depth of pages
for node in addl_nodes:
if node not in node_dict:
#depth = 2 terms are green
node_dict[node] = ('green', float(page[1]))
node_list = []
node_color = []
node_size = []
#make node size proportional to similarity score of each node to original term
for node in node_dict:
node_list.append(node)
node_color.append(node_dict[node][0])
node_size.append(node_dict[node][1])
node_size = [x*300/max(node_size) for x in node_size]
node_size[node_size.index(0.0)]=300
#draw and save network figure
nx.draw_networkx(G=G,with_labels=True,nodelist=node_list,node_size=node_size,node_color=node_color,font_size=8)
fig_name = "%s.png" %(term)
plt.savefig(fig_name)
def getDifferenceWikiPageRankLists(search_term, rank_list):
pages = Pages()
page_id = pages.get_id(search_term)
wiki_page_links = set(pages.getPageLinksList(int(page_id)))
rank_name_list = [pages.get_title(int(ranked_page[0])).lower() for ranked_page in rank_list]
rank_set = set(rank_name_list)
# get the links in both ranked list and wikipedea links
print ("Intersection", rank_set.intersection(wiki_page_links))
# get the links that exist only in ranked list
print ("Difference", rank_set.difference(wiki_page_links))
page_summary, page_content = pages.getPageSummaryContent(page_id)
# get ranked pages that exist in summary and content of page
links_in_summary_only = set()
links_in_content_only = set()
links_in_both = set()
for rank_page in rank_name_list:
in_summary = False
in_content = False
if re.search(r'\b%s\b' % rank_page, page_summary):
in_summary = True
if re.search(r'\b%s\b' % rank_page, page_content):
in_content = True
if in_summary and in_content:
links_in_both.add(rank_page)
elif in_summary:
links_in_summary_only.add(rank_page)
elif in_content:
links_in_content_only.add(rank_page)
# print out the summary for the comparison between the wikilinks, content and the ranked list
print ("inks_in_both", links_in_both)
print ("links_in_summary_only", links_in_summary_only)
print ("links_in_content_only", links_in_content_only)
PAGES_IN_WIKI_LINKS_AND_CONTENT = links_in_both.union(rank_set.intersection(wiki_page_links))
print ("pages in both links and the content", PAGES_IN_WIKI_LINKS_AND_CONTENT)
top_ranked_50 = set(rank_name_list[0:50])
print ("print intersection with top ranks 50 and wiki", top_ranked_50.intersection(PAGES_IN_WIKI_LINKS_AND_CONTENT))
print ("pages in top 50 and not in common set", top_ranked_50.difference(PAGES_IN_WIKI_LINKS_AND_CONTENT))