def main():
baseDir = "/Users/francis/Documents/cpe480_texts/basicmaterials/chemicals"
os.chdir(baseDir)
articles = glob.glob('*.txt')
graph = nx.Graph()
print "Let's get to work!"
for index in range(0, len(articles)):
start = time.time()
article = articles[index]
print article, "- (",index + 1,"of", len(articles),")"
significant = blib.filterWords(article)
blib.handleDocumentNouns(significant["NN"], graph)
print article, "done."
print "Time Elapsed:", time.time() - start, "seconds"
print
print
# sentiment = determineSemtiment(significant[0])
# Export graph data to a file
edgeListFile = "chemicals.graph"
print "Writing graph to file...."
nx.write_gml(graph, edgeListFile)
print "done"
def reinforce(graph, path, posReinforce): significant = blib.filterWords(path) for noun in significant["NN"]: try: node = graph.node[noun] if posReinforce: node["value"] += 1 else: node["value"] -= 1 except: continue
def main():
# List all the avaliable graphs and their names
baseDir = "/Users/francis/Documents/cpe480_texts/"
graphs = {
"Basic Materials : Oil And Gas": baseDir + "basicmaterials/oilngasdrilling/oilngasdrilling.graph",
"Basic Materials : Chemicals": baseDir + "basicmaterials/chemicals/chemicals.graph",
}
matchRate = {}
currentArticleLoc = "/Users/francis/Documents/cpe480_texts/unmatched/" + sys.argv[1]
articleWords = blib.filterWords(currentArticleLoc)
# For each graph in graphs
begin = time.time()
print "Begin Matching..."
for name, graphLoc in graphs.iteritems():
print "Matching", name, "graph..."
# load the graph
graph = nx.read_gml(graphLoc)
# find the match rate
rate = findMatchRate(graph, articleWords["NN"])
# add match rate to the match rate dictionary
matchRate[name] = rate
# Find highest and print Match Rate
highest = ("", 0)
for name, rate in matchRate.iteritems():
if rate > highest[1]:
highest = (name, rate)
print name, ":", rate
print sys.argv[1], "..."
print "Matched to", highest[0], ": Match Rate", highest[1]
print "Time Elapsed:", (time.time() - begin) / 60, "mins"
