B_test = graph.construct_bi_graph_buyer_product(test)
testBuyers, testProducts = nx.bipartite.sets(B_test)
timer = MeasureTimer()
def predict_random_buyers(testProducts, k):
for product in testProducts:
by = np.random.choice(list(buyers),
int(all_c * k / 100),
replace=False)
yield (product, by)
results = {}
for k in map(int, np.linspace(100, 0, K)):
dprint("Running for k: ", k)
with timer:
predicted = predict_random_buyers(testProducts, k)
scores = validate_buyers_for_products(B_test, predicted, all_c)
#results[k] = tuple(np.average(list(scores), axis=0))
results[k] = list(scores)
if saveto:
with open(saveto, 'wb') as f:
pickle.dump(Result(results, timer), f)
printResults(results)
print("Average time %s" % timer.getAverage())
KNeighborsRegressor, LogisticRegression
]):
with timer:
all_predicted = predict_buyers_mining(testProducts,
list(np.linspace(0, 1, K)), m)
predicted = defaultdict(list)
for p in all_predicted:
predicted[p[0]].append(p[1:])
for k, p in predicted.items():
scores = validate_buyers_for_products(B_test, p, all_c)
#results[idx][k] = tuple(np.average(list(scores), axis=0))
results[idx][k] = list(scores)
if saveto:
with open(saveto, 'wb') as f:
pickle.dump(Result(results, timer), f)
print("LINEAR REGRESSION")
printResults(results[0])
print("RANDOM FOREST")
printResults(results[1])
print("KNN")
printResults(results[2])
print("LOGISTIC REGRESSION")
printResults(results[3])
print("Average time %s" % timer.getAverage())
w4 = weights.weight_promotion(product_info)
w5 = weights.weight_rating(product_info)
#w6 = weights.combine_weights([w1, w4, w2], [0.7, 0.5, 0.3])
for wi, w in enumerate([w1, w2, w3]):
def runForK(k):
dprint("Running for k: ", k)
with timer:
predicted = predict_buyers_for_products(B, testProducts, weights.cutOffK(w, k), m)
scores = validate_buyers_for_products(B_test, predicted, all_c)
#return tuple(np.average(list(scores), axis=0))
return list(scores)
results[mi][wi] = {k: runForK(k) for k in range(0, K)}
if saveto:
with open(saveto, 'wb') as f:
pickle.dump(Result(results, timer),f)
for i, r in results[0].items():
print("UNION W" + str(i+1))
printResults(r)
print()
for i, r in results[1].items():
print("INTERSECT W" + str(i+1))
printResults(r)
print("Average time %s" % timer.getAverage())
for k in map(int, np.linspace(230, 240, K)):
dprint("Running for k: ", k, k2)
predictedBuyers = predict_buyers_for_products(
B, testProducts,
weights.cutOffK(weights.bipartite_products_weights(B), k))
product_buyers = {
product: buyers
for product, buyers in predictedBuyers
}
predicted = list(m(buyer_products, product_buyers))
#scores = validate_buyers_for_products(B_test, predicted, all_c)
scores = validate_products_for_buyers(B_test, predicted, all_c)
#results[(k, k2)] = tuple(np.average(list(scores), axis=0))
results[mi][(k, k2)] = list(scores)
if saveto:
with open(saveto, 'wb') as f:
pickle.dump(Result(results, timer), f)
print('Intersect:')
printResults(results[0])
print('Union:')
printResults(results[1])
print("Average time %s" % timer.getAverage())