[FIX] Some bugs with new functions for cooc.

analysis/cooccurrences.py

@@ -55,6 +55,7 @@ def cooc(corpus=None
     cooc_query = (session.query(NodeNgramX.ngram_id, NodeNgramY.ngram_id, func.count())
              .join(Node, Node.id == NodeNgramX.node_id)
              .join(NodeNgramY, NodeNgramY.node_id == Node.id)
+             .filter(Node.parent_id==corpus.id, Node.type_id==doc_id)
                 )
 
 
@@ -81,14 +82,14 @@ def cooc(corpus=None
     cooc_query = (cooc_query.filter(Node.parent_id == corpus.id, Node.type_id == doc_id)
              .filter(NodeNgramX.ngram_id < NodeNgramY.ngram_id)
 
-             .group_by(NodeNgramX.ngram_id, NodeNgramY.ngram_id)
+             .group_by(Node.id, NodeNgramX.ngram_id, NodeNgramY.ngram_id)
              .order_by(func.count())
 
              .limit(limit)
              )
 
     matrix = WeightedMatrix(cooc_query)
-    print(matrix)
+    #print(matrix)
 
     if cvalue_id is not None :
         #miam = get_or_create_node(nodetype='Cvalue', corpus=corpus)

analysis/functions.py

@@ -181,17 +181,18 @@ def get_cooc(request=None, corpus=None, cooc_id=None, type='node_link', size=siz
     miam_id = get_or_create_node(nodetype='MiamList', corpus=corpus).id
     stop_id = get_or_create_node(nodetype='StopList', corpus=corpus).id
     group_id = get_or_create_node(nodetype='Group', corpus=corpus).id
-    
+    cooc_id = get_or_create_node(nodetype='Cooccurrence', corpus=corpus).id
+    session.query(NodeNgramNgram).filter(NodeNgramNgram.node_id==cooc_id).delete()
     #cooc_id = cooc(corpus=corpus, miam_id=miam_id, stop_id=stop_id, limit=size)
     cooc_id = cooc(corpus=corpus, miam_id=miam_id, group_id=group_id, stop_id=stop_id, limit=size)
     #cooc_id = cooc(corpus=corpus, miam_id=miam_id, limit=size)
 
-    print([n for n in session.query(NodeNgramNgram).filter(NodeNgramNgram.node_id==cooc_id).all()])
+    #print([n for n in session.query(NodeNgramNgram).filter(NodeNgramNgram.node_id==cooc_id).all()])
     for cooccurrence in session.query(NodeNgramNgram).filter(NodeNgramNgram.node_id==cooc_id).all():
         #print(cooccurrence)
         # print(cooccurrence.ngramx.terms," <=> ",cooccurrence.ngramy.terms,"\t",cooccurrence.score)
-        labels[cooccurrence.ngramx_id] = session.query(Ngram.terms).filter(Ngram.id == cooccurrence.ngramx_id).first()[0]
-        labels[cooccurrence.ngramy_id] = session.query(Ngram.terms).filter(Ngram.id == cooccurrence.ngramy_id).first()[0]
+        labels[cooccurrence.ngramx_id] = session.query(Ngram.id).filter(Ngram.id == cooccurrence.ngramx_id).first()[0]
+        labels[cooccurrence.ngramy_id] = session.query(Ngram.id).filter(Ngram.id == cooccurrence.ngramy_id).first()[0]
 
         matrix[cooccurrence.ngramx_id][cooccurrence.ngramy_id] = cooccurrence.score
         matrix[cooccurrence.ngramy_id][cooccurrence.ngramx_id] = cooccurrence.score

gargantext_web/urls.py

@@ -76,6 +76,7 @@ urlpatterns = patterns('',
     
     url(r'^ngrams$', views.ngrams),  # to be removed
     url(r'^nodeinfo/(\d+)$', views.nodeinfo), # to be removed ?
+    url(r'^tfidf/(\d+)/(\w+)$', views_optimized.tfidf),
     
     url(r'^project/(\d+)/corpus/(\d+)/(\w+)/update$', views.update_nodes),
     # TODO rest to update corpus and information for progress bar

gargantext_web/views_optimized.py

@@ -15,6 +15,7 @@ from threading import Thread
 
 from node.admin import CustomForm
 from gargantext_web.db import *
+from gargantext_web.db import get_or_create_node
 from gargantext_web.settings import DEBUG, MEDIA_ROOT
 from rest_v1_0.api import JsonHttpResponse
 
@@ -28,7 +29,6 @@ from gargantext_web.celery import apply_workflow
 
 from admin.utils import ensure_dir
 
-
 def project(request, project_id):
 
     # do we have a valid project id?
@@ -200,11 +200,15 @@ def tfidf(request, corpus_id, ngram_ids):
     # filter input
     ngram_ids = ngram_ids.split('a')
     ngram_ids = [int(i) for i in ngram_ids]
+
+    corpus = session.query(Node).filter(Node.id==corpus_id).first()
+    tfidf_id = get_or_create_node(corpus=corpus, nodetype='Tfidf').id
+    print(tfidf_id)
     # request data
     nodes_query = (session
         .query(Node, func.sum(NodeNodeNgram.score))
         .join(NodeNodeNgram, NodeNodeNgram.nodey_id == Node.id)
-        .filter(NodeNodeNgram.nodex_id == corpus_id)
+        .filter(NodeNodeNgram.nodex_id == tfidf_id)
         .filter(NodeNodeNgram.ngram_id.in_(ngram_ids))
         .group_by(Node)
         .order_by(func.sum(NodeNodeNgram.score).desc())

rest_v1_0/urls.py

 from django.conf.urls import patterns, url
 
+from gargantext_web import views_optimized
+
 from rest_v1_0 import api, ngrams
 
 urlpatterns = patterns('',
@@ -32,6 +34,6 @@ urlpatterns = patterns('',
     url(r'nodes/(\d+)/ngrams$', api.CorpusController.ngrams),
     url(r'nodes/(\d+)/ngrams$', api.CorpusController.ngrams),
     
-    #url(r'tfidf/(\d+)/(\w+)$', views_optimized.tfidf),
+    url(r'tfidf/(\d+)/(\w+)$', views_optimized.tfidf),
 )