def wikigoogle(w, k, p):
'''
Input:
- w: a word
- k: number of results
- p: pagerank eigenvector
Output:
- the list of the names of the kth heighest-pagerank Wikipedia
articles containing the word w
'''
related = pagerank.find_word(w)
related.sort(key=lambda x: p[x], reverse=True)
return related[:k]
def power_method_biased(A1, i, r):
'''
Input:
- A1: a matrix, as in power_method
- i: number of iterations
- r: bias label
Output:
- Approximate eigenvector of .55A_1 + 0.15A_2 + 0.3A_r
'''
biased_articles = pagerank.find_word(r)
A_r = Mat(A1.D, {(r,c): 1 for c in biased_articles for r in A1.D[0] if A1[r,c] > 0})
A = .55 * A1 + .15 * Mat(A1.D, {(r,c): 1/len(A1.D[0]) for r in A1.D[0] for c in A1.D[1]}) + .30 * A_r
return power_method(A, i)
def power_method_biased(A1, i, r):
'''
Input:
- A1: a matrix, as in power_method
- i: number of iterations
- r: bias label
Output:
- Approximate eigenvector of .55A_1 + 0.15A_2 + 0.3A_r
'''
list_r = pagerank.find_word(r)
list_links2r = [c for r in list_r for c in A1.D[0] if A1[r,c] > 0]
A_r = make_Markov(Mat(A1.D,{(r,c): 1 for r in list_r for c in list_links2r}))
A = 0.55*A1 + 0.15A2 + 0.3*A_r
return power_method(A,i)
for _ in range(i):
v1 = (A1 * v)
v2 = (Vec(A1.D[1], {c: 1.0 / len(A1.D[1])
for c in A1.D[1]}) * v) * Vec(
v.D, {c: 1
for c in v.D})
v = 0.85 * v1 + 0.15 * v2
v = normalized(v)
print("Power_method, v['sport']: ", v['sport'])
return v
## 4: (Task 12.12.4) Jordan
reload(pagerank)
A1 = pagerank.read_data()
number_of_docs_with_jordan = len(pagerank.find_word('jordan'))
print("Num jordan docs: ", number_of_docs_with_jordan)
## 5: (Task 12.12.5) Wikigoogle
def wikigoogle(w, k, p):
'''
Input:
- w: a word
- k: number of results
- p: pagerank eigenvector
Output:
- the list of the names of the kth heighest-pagerank Wikipedia
articles containing the word w
'''
related = pagerank.find_word(w)
def wikigoogle(w, k, p): related = pagerank.find_word(w) related.sort(key=lambda x:p[x], reverse=True) return related[:k]
