def find_similar(sent, lst): dist = {} lst = lst + split_and_add(lst) for item in lst: item = util.normalize(item) sent = util.normalize(sent) d = jarow(item, sent) #print item , d if d > 0.75: dist[item] = d #print dist max_arr = util.get_max(dist) return max_arr
def correct_right(lc, rc, index, llc=None): lc = util.normalize(rc) dist = {} try: right_ctx = index[rc]["right"] for item in right_ctx: d = jarow(item, rc) #print item , (d * 1.0)/len(item) if d > 0.75: dist[item] = d max_arr = util.get_max(dist) #print dist return max_arr except: return None
def correct_left(rc, lc, index, rrc=None): rc = util.normalize(rc) dist = {} try: left_ctx = index[rc]["left"] for item in left_ctx: d = jarow(item, lc) #print item , (d * 1.0)/len(item) #print d if d > 0.75: dist[item] = d max_arr = util.get_max(dist) #print dist return max_arr except: return None