Python model.Keyword类代码示例

    def receive_feedbacks(self, session, feedbacks):
        """
        Receive feedbacks from user
        
        The format of feedback is:
        {
        "docs": [[doc_id, feedback_value], ...],
        "kws": [[keyword_id, feedback_value], ...],
        "dockws": [[keyword_id, doc_id, feedback_value], ...]
        }
        """
        print "propagation started..."
        for doc_fb in feedbacks.get("docs", []):
            doc_id, fb = doc_fb
            doc = Document.get(doc_id)
            
            self.ppgt.fb_from_doc(doc, fb, session)

        for kw_fb in feedbacks.get("kws", []):
            kw_id, fb = kw_fb
            kw = Keyword.get(kw_id)
            
            self.ppgt.fb_from_kw(kw, fb, session)

        for dockw_fb in feedbacks.get("dockws", []):
            kw_id, doc_id, fb = dockw_fb
            doc = Document.get(doc_id)
            kw = Keyword.get(kw_id)
            
            self.ppgt.fb_from_dockw(kw, doc, fb, session)

        # propagation is done
        # updates the feedback value 
        self.upd.update(session)
        print "propagation finished"

    def setUp(self):
                #make the fmim
        kw_filters = [self.my_kw_filter]
        doc_filters = [self.kw_count_filter, self.has_database_filter]
        
        
        self.r = LinRelRecommender(2, 2, 
                                   1.0, 0.1, 1.0, 0.1,
                                   #the default configuration
                                   kw_filters = None, doc_filters = [self.kw_count_filter, self.has_database_filter],
                                   **fmim.__dict__)
        
        self.session = get_session()
        
        self.session.update_kw_feedback(Keyword.get("redis"), .7)
        self.session.update_kw_feedback(Keyword.get("database"), .6)
        
        self.session.update_doc_feedback(Document.get(1), .7)
        self.session.update_doc_feedback(Document.get(2), .7)
        self.session.update_doc_feedback(Document.get(8), .7)

        filtered_kws = self.r._filter_objs(kw_filters, kws = Keyword.all_kws)
        filtered_docs = self.r._filter_objs(doc_filters, docs = Document.all_docs)
        
        kw2doc_submat, kw_ind_map, kw_ind_map_r = self.r._submatrix_and_indexing(filtered_kws, filtered_docs, fmim.kw2doc_m, fmim.kw_ind, fmim.doc_ind)
        doc2kw_submat, doc_ind_map, doc_ind_map_r = self.r._submatrix_and_indexing(filtered_docs, filtered_kws, fmim.doc2kw_m, fmim.doc_ind, fmim.kw_ind)
        
        self.fmim = FeatureMatrixAndIndexMapping(kw_ind_map, doc_ind_map, kw2doc_submat, doc2kw_submat, kw_ind_map_r, doc_ind_map_r)

 def recommend_keywords(self, fmim,
                        session, top_n, mu, c, 
                        sampler=None):
     """
     fmim: FeatureMatrixAndIndexMapping, the fmim for the sub-matrix        
     session: Session,
     top_n: how many kws are returned
     mu,c: float, the parameters for LinRel algorithm
     
     Return
     KeywordList: a list of keyword ids as well as their scores
     """        
     kws = Keyword.get_many(fmim.kw_ind.keys())
     fbs = dict([(kw.id, kw.fb(session)) for kw in kws])
     
     id_with_scores, id_with_explt_scores, id_with_explr_scores = self.generic_rank(fmim.kw2doc_m, fbs, 
                                                                                    fmim.kw_ind, fmim.kw_ind_r,
                                                                                    mu, c)
     
     kws = []
     for kw_id, score in id_with_scores.items()[:top_n]:
         kw = Keyword.get(kw_id)
         kw['score'] = score
         kw['recommended'] = True
         kws.append(kw)
         
     return kws

    def test_get_many(self):
        doc_ids = [1,2]
        kw_ids = ["a", "the"]
        
        self.assertEqual(Document.get_many([1,2]), 
                         Document.get_many(doc_ids))

        self.assertEqual(Keyword.get_many(["a", "the"]), 
                         Keyword.get_many(kw_ids))

    def test_add_kws(self):
        iter1 = Keyword.get_many(["redis", "database", "mysql"])
        iter2 = Keyword.get_many(["redis", "database", "python"])
        
        self.session.add_kw_recom_list(iter1)        
        self.assertEqual([iter1], self.session.recom_kws)

        self.session.add_kw_recom_list(iter2)        
        self.assertEqual([iter1, iter2], self.session.recom_kws)

    def test_one(self):
        docs = [Document.get_many([1,2]), Document.get_many([1,2]), Document.get_many([2,1])]
        kws = [Keyword.get_many(["redis", "database"]), Keyword.get_many(["redis", "database"]), Keyword.get_many(["redis", "database"])]

        scores = self.e.evaluate(docs, kws)
        expected = ([1,1,1], [1,1,1])
        
        self.assertArrayAlmostEqual(expected[0], scores[0])
        self.assertArrayAlmostEqual(expected[1], scores[1])

    def test_kw_fb_filter(self):
        kw = Keyword.get("redis")
        kw.rec_fb_from_doc(Document.get(1), 1, self.session)
        self.session.add_doc_recom_list(Document.get_many([1, 2, 6]))
        self.session.update_kw_feedback(kw, kw.fb_weighted_sum(self.session))

        actual = FilterRepository.filters["kw_fb"]([kw])
        expected = Keyword.get_many(["redis"])

        self.assertEqual(expected, actual)

 def test_associated_keywords_from_documents(self):
     kws = self.r.associated_keywords_from_docs(Document.get_many([1,2]))
     self.assertEqual(set(Keyword.get_many(["a", "database", "redis", "the"])),
                      set(kws))
     
     exclude_kws = [Keyword.get("redis")]
     kws = self.r.associated_keywords_from_docs(Document.get_many([1,2]), exclude_kws)
     
     self.assertEqual(set(Keyword.get_many(["a", "database", "the"])), 
                      set(kws))

    def test_kw_fb_threshold_filter(self):
        #change the feedback
        self.session.update_kw_feedback(Keyword.get("python"), .2)
        self.session.update_kw_feedback(Keyword.get("a"), .0999999)
        
        actual = kw_fb_threshold_filter(0.1, self.session, 
                                        kws = Keyword.all_kws, with_fb = False)
        expected = Keyword.get_many(["python"])

        self.assertEqual(expected, actual)

    def test_two(self):
        docs = [Document.get_many([8,10]), Document.get_many([3,4]), Document.get_many([2,1])]
        kws = [Keyword.get_many(["a", "the"]), Keyword.get_many(["python", "database"]), Keyword.get_many(["database", "redis"])]

        scores = self.e.evaluate(docs, kws)
        expected = ([0.34491169135422844, 0.1726882003112921, 1.0],
                    [0.4834283906452939, 0.759679156743632, 0.9999999999999999])

        self.assertArrayAlmostEqual(expected[0], scores[0])
        self.assertArrayAlmostEqual(expected[1], scores[1])

    def test_sample_documents_associated_with_keywords(self):
        """
        normal case
        """
        docs = self.r.sample_documents_associated_with_keywords(Keyword.get_many(["python", "redis"]), 2)

        self.assertEqual(2, len(docs))

        for doc in docs:
            self.assertTrue((Keyword.get("python") in doc.keywords) or \
                            (Keyword.get("redis") in doc.keywords))

    def test_affected_kws(self):
        kws = [Keyword.get("python"), Keyword.get("redis")]
        
        self.session.add_affected_kws(*kws)
        self.assertEqual(kws, self.session.affected_kws)

        kw3 = Keyword.get("a")
        kws.append(kw3)
        self.session.add_affected_kws(kw3)
        self.assertEqual(set(kws), 
                         set(self.session.affected_kws))

    def test_kw_hashable(self):
        d = {}
        kwlist1 = Keyword.get_many(["redis", "a", "the"])
        kwlist2 = Keyword.get_many(["a", "the", "redis"])
        kwlist3 = Keyword.get_many(["redis", "a", "python"])

        d[kwlist1] = 1
        d[kwlist2] = 2 #override
        d[kwlist3] = 3 

        self.assertEqual({kwlist1:2, kwlist3: 3}, d)

    def test_model2modellist_similarity(self):
        #for keywords
        kw = Keyword.get("redis")
        kwlist = Keyword.get_many(["database", "mysql"])

        self.assertAlmostEqual(0.3754029265429976, kw.similarity_to(kwlist))
        
        #for documents
        doc = Document.get(6)
        doclist = Document.get_many([1, 2])
        
        self.assertAlmostEqual(0.7382455893131392, doc.similarity_to(doclist))

    def test_modellist2modellist_similarity(self):
        #for keywords
        kwlist1 = Keyword.get_many(["redis", "a"])
        kwlist2 = Keyword.get_many(["database", "the"])

        self.assertAlmostEqual(0.42205423035497763, kwlist1.similarity_to(kwlist2))
        
        #for documents
        doclist1 = Document.get_many([3,5])
        doclist2 = Document.get_many([4,6])
        
        self.assertAlmostEqual(0.6990609119502719, doclist1.similarity_to(doclist2))