[UPDATE] tfidf ok

analysis/functions.py

@@ -197,11 +197,11 @@ def get_cooc(request=None, corpus_id=None, cooc_id=None, type='node_link', n=150
     partition = best_partition(G)
     
     if type == "node_link":
-        
+
         for node in G.nodes():
             try:
                 #node,type(labels[node])
-                G.node[node]['id'] = ids[node]
+                G.node[node]['pk'] = ids[node]
                 G.node[node]['label']   = node
                 # G.node[node]['pk']      = ids[str(node)]
                 G.node[node]['size']    = weight[ids[node]]
@@ -209,8 +209,21 @@ def get_cooc(request=None, corpus_id=None, cooc_id=None, type='node_link', n=150
                 # G.add_edge(node, "cluster " + str(partition[node]), weight=3)
             except Exception as error:
                 print("error01: ",error)
-
+        
         data = json_graph.node_link_data(G)
+
+        links = []
+        i=1
+        for e in G.edges_iter():
+            s = e[0]
+            t = e[1]
+            info = { "id":i , "source":ids[s] , "target":ids[t]}
+            # print(info)
+            links.append(info)
+            i+=1
+        # print(data)
+        data["links"] = []
+        data["links"] = links
     
     elif type == "adjacency":
         for node in G.nodes():

gargantext_web/urls.py

@@ -52,7 +52,7 @@ urlpatterns = patterns('',
     url(r'^corpus/(\d+)/node_link.json$', views.node_link), # => api.analysis('type': 'node_link', 'format' : 'json')
     url(r'^corpus/(\d+)/adjacency.json$', views.adjacency), # => api.analysis('type': 'adjacency', 'format' : 'json')
     
-    url(r'^api/tfidf/(\d+)/(\d+(?:,\d+)+)$', views_optimized.tfidf),
+    url(r'^api/tfidf/(\d+)/(\w+)$', views_optimized.tfidf),
     # url(r'^api/tfidf/(\d+)/(\w+)$', views.tfidf),
     url(r'^api/tfidf2/(\d+)/(\w+)$', views.tfidf2),
 

gargantext_web/views_optimized.py

@@ -13,6 +13,7 @@ from node.admin import CustomForm
 from gargantext_web.db import *
 from gargantext_web.settings import DEBUG, MEDIA_ROOT
 from gargantext_web.api import JsonHttpResponse
+import json
 
 from parsing.corpustools import add_resource, parse_resources, extract_ngrams, compute_tfidf
 
@@ -163,12 +164,15 @@ def project(request, project_id):
         'number'        : corpora_count,
     })
 
-def tfidf(request, corpus_id, ngram_ids, limit=6):
+def tfidf(request, corpus_id, ngram_ids):
     """Takes IDs of corpus and ngram and returns list of relevent documents in json format
     according to TFIDF score (order is decreasing).
     """
+    limit=6
+    nodes_list = []
     # filter input
-    ngram_ids = ngram_ids.split(',')
+    ngram_ids = ngram_ids.split('a')
+    ngram_ids = [int(i) for i in ngram_ids]
     # request data
     nodes_query = (session
         .query(Node, func.sum(NodeNodeNgram.score))
@@ -180,7 +184,6 @@ def tfidf(request, corpus_id, ngram_ids, limit=6):
         .limit(limit)
     )
     # convert query result to a list of dicts
-    nodes_list = []
     for node, score in nodes_query:
         node_dict = {
             'id': node.id,
@@ -190,5 +193,6 @@ def tfidf(request, corpus_id, ngram_ids, limit=6):
             if key in node.metadata:
                 node_dict[key] = node.metadata[key]
         nodes_list.append(node_dict)
-    # return the result
-    return JsonHttpResponse(nodes_list)
+
+    data = json.dumps(nodes_list) 
+    return JsonHttpResponse(data)

scrap_pubmed/views.py

@@ -40,7 +40,7 @@ def getGlobalStats(request ):
 	alist = ["bar","foo"]
 
 	if request.method == "POST":
-		N = 1000
+		N = 10
 		query = request.POST["query"]
 		print ("LOG::TIME:_ "+datetime.datetime.now().isoformat()+" query =", query )
 		print ("LOG::TIME:_ "+datetime.datetime.now().isoformat()+" N =", N )