def dump_factors():
numfactors = int(request.args['numfactors'].strip())
model = AlternatingLeastSquares(factors=numfactors, dtype=np.float32, use_gpu=False, iterations=30)
model.approximate_recommend = False
model.approximate_similar_items = False
data = {'userid': [], 'productid': [], 'purchase_count': []}
for userid in purchases:
for productid in purchases[userid]:
data['userid'].append(userid)
data['productid'].append(productid)
data['purchase_count'].append(purchases[userid][productid])
df = pd.DataFrame(data)
df['userid'] = df['userid'].astype("category")
df['productid'] = df['productid'].astype("category")
userids = list(df['userid'].cat.categories)
userids_reverse = dict(zip(userids, list(range(len(userids)))))
productids = list(df['productid'].cat.categories)
productids_reverse = dict(zip(productids, list(range(len(productids)))))
purchases_matrix = coo_matrix((df['purchase_count'].astype(np.float32),
(df['productid'].cat.codes.copy(),
df['userid'].cat.codes.copy())))
print("Matrix shape: %s, max value: %.2f" % (np.shape(purchases_matrix), np.max(purchases_matrix)))
purchases_matrix = bm25_weight(purchases_matrix, K1=2.0, B=0.25)
purchases_matrix_T = purchases_matrix.T.tocsr()
purchases_matrix = purchases_matrix.tocsr() # to support indexing in recommend/similar_items functions
model.fit(purchases_matrix)
np.savetxt('item_factors.csv', model.item_factors, delimiter=',')
np.savetxt('user_factors.csv', model.user_factors, delimiter=',')
with open('item_ids.csv', 'w') as f:
for pid in productids_reverse:
f.write("%s,%d,%s\n" % (pid, productids_reverse[pid], recommendation.sub(r',', ' ', productnames[pid])))
with open('user_ids.csv', 'w') as f:
for uid in userids_reverse:
f.write("%s,%d,%s\n" % (uid, userids_reverse[uid], recommendation.sub(r',', ' ', usernames[uid])))
return 'OK\n'
def build_imf(prod_user_matrix, alpha):
"""
Builds models with the utility matrix and model parameters
"""
# Build model
print("Building IMF model with alpha: {} ...".format(alpha))
model = AlternatingLeastSquares(factors=75,
regularization=0.01,
iterations=15,
use_cg=True)
model.approximate_similar_items = False
model.fit(confidence_matrix(prod_user_matrix, alpha))
return model