def canopy(n):
df = fl_data()
df2 = oge_data()
x = ngram_index(df, 'nname', n=n)
for s in shingle(df2.nname[0],k=n):
print(len(x[s]))
def ngram_index(df, name_field, n=4):
index = defaultdict(set)
for idx, row in df.iterrows():
for s in shingle(row[name_field], k=n):
index[s].add(idx)
return index
