def fit(self, trainset):
AlgoBase.fit(self, trainset)
# Compute item similarity matrix based on content attributes
# Load up genre vectors for every movie
ml = Reviews ()
typeR = ml.getRestaurantType()
print("Computing content-based similarity matrix...")
# Compute genre distance for every movie combination as a 2x2 matrix
self.similarities = np.zeros((self.trainset.n_items, self.trainset.n_items))
for thisRating in range(self.trainset.n_items):
if (thisRating % 50 == 0):
print(thisRating, " of ", self.trainset.n_items)
for otherRating in range(thisRating+1, self.trainset.n_items):
thisplaceID = int(self.trainset.to_raw_iid(thisRating))
otherplaceID = int(self.trainset.to_raw_iid(otherRating))
typeSimilarity = self.computeTypeSimilarity(thisplaceID, otherplaceID, typeR)
distancesSimilarity = self.computeDistanceSimilarity(thisplaceID, otherplaceID)
#mesSimilarity = self.computeMiseEnSceneSimilarity(thisMovieID, otherMovieID, mes)
self.similarities[thisRating, otherRating] = typeSimilarity * distancesSimilarity
self.similarities[otherRating, thisRating] = self.similarities[thisRating, otherRating]
print("...done.")
return self
def LoadRevsData():
ml = Reviews()
print("Loading restaurants ratings...")
data = ml.loadRevDataSet()
print(
"\nComputing movie popularity ranks so we can measure novelty later..."
)
rankings = ml.getPopularityRanks()
return (ml, data, rankings)
Created on Fri May 3 16:29:32 2019
@author: hedi
"""
from ReviewsHandeling import Reviews
from surprise import KNNBasic
import heapq
from collections import defaultdict
from operator import itemgetter
testSubject = '1068'
k = 10
# Load our data set and compute the user similarity matrix
ml = Reviews()
data = ml.loadRevDataSet()
trainSet = data.build_full_trainset()
sim_options = {'name': 'cosine', 'user_based': True}
model = KNNBasic(sim_options=sim_options)
model.fit(trainSet)
simsMatrix = model.compute_similarities()
# Get top N similar users to our test subject
# (Alternate approach would be to select users up to some similarity threshold - try it!)
testUserInnerID = trainSet.to_inner_uid(testSubject)
similarityRow = simsMatrix[testUserInnerID]
# -*- coding: utf-8 -*- """ Created on Wed Apr 24 14:59:58 2019 @author: hedi """ from ReviewsHandeling import Reviews from KnnContentFiltering import KnnContentFiltering from EvaluationData import EvaluationData ml = Reviews() data = ml.loadRevDataSet() rankings = ml.getPopularityRanks() tt = EvaluationData(data, rankings) tt.GetTrainSet()