def find_path_astar(start, stop):
visited = []
unvisited = [start]
parent = {start: "None"}
gscore = {start: 0}
#fscore = {start:1/links_in_common(start,stop)}
fscore = MinHeap()
fscore.insert((start, distance_heuristic(start, stop)))
#print(fscore)
global article_data
while len(unvisited) > 0:
curr = fscore.extract()[0]
print(ancestor_chain(parent, curr))
if curr == stop:
unwrap_path(parent, start, stop)
break
try:
unvisited.remove(curr)
visited.append(curr)
curr_links = get_page_links(curr)["parse"]["links"]
for l in curr_links:
try:
if l["exists"] == "":
link = l["*"]
if (is_article(link)) and (link not in visited):
tentative_gscore = gscore[curr] + 1
if link not in unvisited:
unvisited.append(link)
elif tentative_gscore >= gscore[link]:
continue
parent[link] = curr
gscore[link] = tentative_gscore
#fscore[link] = gscore[link] + (1/links_in_common(link,stop))
f = gscore[link] + distance_heuristic(link, stop)
fscore.insert((link, f))
except:
continue
#print(fscore.array)
#print("{0} of {1}".format(fscore.size,fscore.capacity))
except:
continue
del article_data[curr]
from minheap import MinHeap
import sys
#get the count for every job and state
count = Counting(sys.argv[1])
job_count, state_count, sum_count = count.count()
#find the top_10 jobs
job_heap = MinHeap(10)
job_fhandle = open(sys.argv[2],'w')
for key,value in job_count.items():
job_heap.add(key,value)
job_fhandle.write('TOP_OCCUPATIONS;NUMBER_CERTIFIED_APPLICATIONS;PERCENTAGE\n')
result = dict()
for i in range(min(10,len(job_count))):
key,value = job_heap.extract()
result[key.lstrip('""').rstrip('""')] = value
result = sorted(result.items(), key = lambda item:item[0])
result.sort(key = lambda x:x[1], reverse = True)
for item in result:
key = item[0]
value = item[1]
p = round(value / sum_count * 100.0, 1)
s = key + ';' + str(value) + ';' + str(p) + '%' + '\n'
job_fhandle.write(s)
#find the top_10 states
state_heap = MinHeap(10)
state_fhandle = open(sys.argv[3],'w')
for key,value in state_count.items():
state_heap.add(key,value)
