[GIT] Resolved conflicts in url.py

[CODE] Import paths are now relative instead of absolute in parsing/

.gitignore

 __pycache__/
 parsing/Taggers/treetagger/
 .ipynb_checkpoints/
+*.pyc

analysis/functions.py

@@ -11,7 +11,7 @@ def create_blacklist(user, corpus):
 def create_synonymes(user, corpus):
     pass
 
-def create_whitelist(user, corpus):
+def create_whitelist(user, corpus, size=100):
     cursor = connection.cursor()
     
     try:
@@ -51,7 +51,7 @@ def create_whitelist(user, corpus):
         AND
             n.type_id = %d
         AND
-            ngX.n >= 1
+        ngX.n >= 2
 
         GROUP BY
             ngX.id
@@ -60,16 +60,16 @@ def create_whitelist(user, corpus):
         ORDER BY
             occurrences DESC
         LIMIT
-            100
+            %d
         ;
-    """  % (white_list.id, corpus.id, type_document.id)
+    """  % (white_list.id, corpus.id, type_document.id, size)
 
     cursor.execute(query_whitelist)
 
     return white_list
 
 #def create_cooc(user, corpus, whitelist, blacklist, synonymes):
-def create_cooc(user=None, corpus=None, whitelist=None):
+def create_cooc(user=None, corpus=None, whitelist=None, size=150):
     cursor = connection.cursor()
 
     try:
@@ -127,11 +127,117 @@ def create_cooc(user=None, corpus=None, whitelist=None):
     ORDER BY
         score DESC
     LIMIT
-        150
-    """ % (cooc.pk, corpus.id, whitelist.id, whitelist.id)
+        %d
+    """ % (cooc.pk, corpus.id, whitelist.id, whitelist.id, size)
 
     cursor.execute(query_cooc)
     return cooc
 
+def get_cooc(request=None, corpus_id=None, cooc_id=None, type="node_link"):
+    import pandas as pd
+    from copy import copy
+    import numpy as np
+    import networkx as nx
+    from networkx.readwrite import json_graph
+    from gargantext_web.api import JsonHttpResponse
+    
+    from analysis.louvain import best_partition
+
+    matrix = defaultdict(lambda : defaultdict(float))
+    labels = dict()
+    weight = dict()
+
+    corpus = Node.objects.get(id=corpus_id)
+    type_cooc = NodeType.objects.get(name="Cooccurrence")
+
+    if Node.objects.filter(type=type_cooc, parent=corpus).first() is None:
+        print("Coocurrences do not exist yet, create it.")
+        if type == "node_link":
+            n = 150
+        elif type == "adjacency":
+            n = 50
+
+        whitelist = create_whitelist(request.user, corpus, size=n)
+        cooccurrence_node = create_cooc(user=request.user, corpus=corpus, whitelist=whitelist, size=n)
+        print(cooccurrence_node.id, "Cooc created")
+    else:
+        cooccurrence_node = Node.objects.filter(type=type_cooc, parent=corpus).first()
+
+    for cooccurrence in NodeNgramNgram.objects.filter(node=cooccurrence_node):
+        labels[cooccurrence.ngramx.id] = cooccurrence.ngramx.terms
+        labels[cooccurrence.ngramy.id] = cooccurrence.ngramy.terms
+        
+        matrix[cooccurrence.ngramx.id][cooccurrence.ngramy.id] = cooccurrence.score
+        matrix[cooccurrence.ngramy.id][cooccurrence.ngramx.id] = cooccurrence.score
+
+        weight[cooccurrence.ngramy.terms] = weight.get(cooccurrence.ngramy.terms, 0) + cooccurrence.score
+        weight[cooccurrence.ngramx.terms] = weight.get(cooccurrence.ngramx.terms, 0) + cooccurrence.score
+
+
+    df = pd.DataFrame(matrix).T.fillna(0)
+    x = copy(df.values)
+    x = x / x.sum(axis=1)
+
+    # Removing unconnected nodes
+    threshold = min(x.max(axis=1))
+    matrix_filtered = np.where(x >= threshold, 1, 0)
+    #matrix_filtered = np.where(x > threshold, x, 0)
+    #matrix_filtered = matrix_filtered.resize((90,90))
+    G = nx.from_numpy_matrix(matrix_filtered)
+    G = nx.relabel_nodes(G, dict(enumerate([ labels[label] for label in list(df.columns)])))
+    #G = nx.relabel_nodes(G, dict(enumerate(df.columns)))
+    
+    # Removing too connected nodes (find automatic way to do it)
+#    outdeg = G.degree()
+#    to_remove = [n for n in outdeg if outdeg[n] >= 10]
+#    G.remove_nodes_from(to_remove)
+
+    partition = best_partition(G)
+    
+        
+    if type == "node_link":
+        for node in G.nodes():
+            try:
+                #node,type(labels[node])
+                G.node[node]['label']   = node
+                G.node[node]['name']    = node
+                G.node[node]['size']    = weight[node]
+                G.node[node]['group']   = partition[node]
+                #G.add_edge(node, partition[node], weight=3)
+#            G.node[node]['color'] = '19,180,300'
+            except Exception as error:
+                print(error)
+
+        data = json_graph.node_link_data(G)
+    
+    elif type == "adjacency":
+        for node in G.nodes():
+            try:
+                #node,type(labels[node])
+                #G.node[node]['label']   = node
+                G.node[node]['name']    = node
+                #G.node[node]['size']    = weight[node]
+                G.node[node]['group']   = partition[node]
+                #G.add_edge(node, partition[node], weight=3)
+#            G.node[node]['color'] = '19,180,300'
+            except Exception as error:
+                print(error)
+        data = json_graph.node_link_data(G)
+     
+
+#    data = json_graph.node_link_data(G, attrs={\
+#            'source':'source',\
+#            'target':'target',\
+#            'weight':'weight',\
+#            #'label':'label',\
+#            #'color':'color',\
+#            'id':'id',})
+    #print(data)
+    return data
+
+
+
+
+
 
 

gargantext_web/urls.py

@@ -11,12 +11,13 @@ import gargantext_web.api
 admin.autodiscover()
 
 urlpatterns = patterns('',
-    # url(r'^$', 'gargantext_web.views.home', name='home'),
-    # url(r'^blog/', include('blog.urls')),
+    
+    # Admin views
     url(r'^admin/', include(admin.site.urls)),
     url(r'^login/', include(admin.site.urls)),
     url(r'^grappelli/', include('grappelli.urls')),
     
+    # User views
     url(r'^$', views.home),
     
     url(r'^projects/$', views.projects),
@@ -27,26 +28,35 @@ urlpatterns = patterns('',
     url(r'^project/(\d+)/corpus/(\d+)/$', views.corpus),
     url(r'^project/(\d+)/corpus/(\d+)/delete/$', views.delete_corpus),
     
+    # Visualizations
     url(r'^corpus/(\d+)/explorer$', views.explorer_graph),
-    url(r'^chart$', views.explorer_chart),
-    url(r'^matrix$', views.explorer_matrix),
+    url(r'^corpus/(\d+)/matrix$', views.explorer_matrix),
     
-    #url(r'^exploration$', views.exploration),
-
+    # Getting data [which?]
     url(r'^chart/corpus/(\d+)/data.csv$', views.send_csv),
     url(r'^corpus/(\d+)/node_link.json$', views.node_link),
     url(r'^corpus/(\d+)/adjancy_matrix$', views.node_link),
+    url(r'^corpus/(\d+)/adjacency.json$', views.adjacency),
+
+
+    """RESTful API
+    These URLs allow operations on the database in a RESTful way.
+    """
 
-    url(r'^api$', gargantext_web.api.Root),
+    # retrieve all the metadata from a given node's children
     url(r'^api/nodes/(\d+)/children/metadata$', gargantext_web.api.NodesChildrenMetatadata.as_view()),
+    # retrieve the ngrams from a given node's children
+    url(r'^api/nodes/(\d+)/ngrams$', gargantext_web.api.CorpusController.ngrams),
+    # perform a query on a given node's children
     url(r'^api/nodes/(\d+)/children/queries$', gargantext_web.api.NodesChildrenQueries.as_view()),
-    
+    # get all the nodes
     url(r'^api/nodes$', gargantext_web.api.NodesController.get),
-    url(r'^api/nodes/(\d+)/ngrams$', gargantext_web.api.CorpusController.ngrams),
-    url(r'^api/nodes/(\d+)/data$', gargantext_web.api.CorpusController.data),
 
-    url(r'^graph-it$', views.graph_it),
-    url(r'^ngrams$', views.ngrams),
+    # other (DEPRECATED, TO BE REMOVED)
+    url(r'^api/nodes$', gargantext_web.api.NodesController.get),
+    url(r'^api/corpus/(\d+)/ngrams$', gargantext_web.api.CorpusController.ngrams),
+    url(r'^api/corpus/(\d+)/metadata$', gargantext_web.api.CorpusController.metadata),
+    url(r'^api/corpus/(\d+)/data$', gargantext_web.api.CorpusController.data),
 )
 
 

gargantext_web/views.py

@@ -26,7 +26,6 @@ from collections import defaultdict
 
 from parsing.FileParsers import *
 
-
 # SOME FUNCTIONS
 
 def query_to_dicts(query_string, *query_args):
@@ -243,6 +242,7 @@ def project(request, project_id):
                 
                 # async
                 corpus.children.filter(type_id=type_document.pk).extract_ngrams(keys=['title',])
+                #corpus.children.filter(type_id=type_document.pk).extract_ngrams(keys=['title',])
 
             except Exception as error:
                 print(error)
@@ -367,7 +367,6 @@ def corpus(request, project_id, corpus_id):
     
     return HttpResponse(html)
 
-
 def delete_project(request, node_id):
     Node.objects.filter(id=node_id).all().delete()
     return HttpResponseRedirect('/projects/')
@@ -390,14 +389,16 @@ def explorer_graph(request, corpus_id):
     
     return HttpResponse(html)
 
-def explorer_matrix(request):
+def explorer_matrix(request, corpus_id):
     t = get_template('matrix.html')
     user = request.user
     date = datetime.datetime.now()
+    corpus = Node.objects.get(id=corpus_id)
 
     html = t.render(Context({\
             'user': user,\
             'date': date,\
+            'corpus': corpus,\
             }))
     
     return HttpResponse(html)
@@ -469,78 +470,27 @@ def send_csv(request, corpus_id):
 
     return response
 
-def node_link(request, corpus_id):
-    '''
-    Create the HttpResponse object with the graph dataset.
-    '''
 
-    import pandas as pd
-    from copy import copy
-    import numpy as np
-    import networkx as nx
-    from networkx.readwrite import json_graph
-    from gargantext_web.api import JsonHttpResponse
-    
-    from analysis.louvain import best_partition
-    from analysis.functions import create_whitelist, create_cooc
-
-    matrix = defaultdict(lambda : defaultdict(float))
-    labels = dict()
-    corpus = Node.objects.get(id=corpus_id)
-    type_cooc = NodeType.objects.get(name="Cooccurrence")
 
-    if Node.objects.filter(type=type_cooc, parent=corpus).first() is None:
-        print("Coocurrences do not exist yet, create it.")
-        whitelist = create_whitelist(request.user, corpus)
-        cooc = create_cooc(user=request.user, corpus=corpus, whitelist=whitelist)
-        print(cooc.id, "Cooc created")
-    else:
-        cooc = Node.objects.filter(type=type_cooc, parent=corpus).first()
+# To get the data
+from gargantext_web.api import JsonHttpResponse
+from analysis.functions import get_cooc
 
-    for cooccurrence in NodeNgramNgram.objects.filter(node=cooc):
-        labels[cooccurrence.ngramx.id] = cooccurrence.ngramx.terms
-        labels[cooccurrence.ngramy.id] = cooccurrence.ngramy.terms
-        
-        matrix[cooccurrence.ngramx.id][cooccurrence.ngramy.id] = cooccurrence.score
-        matrix[cooccurrence.ngramy.id][cooccurrence.ngramx.id] = cooccurrence.score
 
-    df = pd.DataFrame(matrix).T.fillna(0)
-    x = copy(df.values)
-    x = x / x.sum(axis=1)
+def node_link(request, corpus_id):
+    '''
+    Create the HttpResponse object with the node_link dataset.
+    '''
 
-    # Removing unconnected nodes
-    threshold = min(x.max(axis=1))
-    matrix_filtered = np.where(x > threshold, 1, 0)
-    #matrix_filtered = np.where(x > threshold, x, 0)
-    
-    G = nx.from_numpy_matrix(matrix_filtered)
-    G = nx.relabel_nodes(G, dict(enumerate([ labels[x] for x in list(df.columns)])))
-    #G = nx.relabel_nodes(G, dict(enumerate(df.columns)))
-    
-    # Removing too connected nodes (find automatic way to do it)
-#    outdeg = G.degree()
-#    to_remove = [n for n in outdeg if outdeg[n] >= 10]
-#    G.remove_nodes_from(to_remove)
+   
+    data = get_cooc(request=request, corpus_id=corpus_id, type="node_link")
+    return JsonHttpResponse(data)
 
-    partition = best_partition(G)
-    
-    for node in G.nodes():
-        try:
-            #node,type(labels[node])
-            G.node[node]['label'] = node
-#            G.node[node]['color'] = '19,180,300'
-        except Exception as error:
-            print(error)
-    
-    data = json_graph.node_link_data(G)
-#    data = json_graph.node_link_data(G, attrs={\
-#            'source':'source',\
-#            'target':'target',\
-#            'weight':'weight',\
-#            #'label':'label',\
-#            #'color':'color',\
-#            'id':'id',})
-    #print(data)
+def adjacency(request, corpus_id):
+    '''
+    Create the HttpResponse object with the adjacency dataset.
+    '''
+    data = get_cooc(request=request, corpus_id=corpus_id, type="adjacency")
     return JsonHttpResponse(data)
 
 
@@ -555,7 +505,6 @@ def graph_it(request):
     }))    
     return HttpResponse(html)
 
-
 def ngrams(request):
     '''The ngrams list.'''
     t = get_template('ngrams.html')

init/README.rst

@@ -4,23 +4,30 @@ Install the requirements
 1)  Install all the Debian packages listed in dependances.deb
     (also: sudo apt-get install postgresql-contrib)
 
-2)  Create a virtual enironnement with pyvenv: apt-get install python-virtualenv
+2)  Create a Pythton virtual enironnement
 
-3)  Type: source [your virtual environment directory]/bin/activate
-
-4)  Do your work!
+    On Debian:
+    ---------
+    sudo apt-get install python3.4-venv
+    pyvenv3 /srv/gargantext_env
 
-5)  Type: deactivate
+    On ubuntu:
+    ---------
+    sudo apt-get install python-pip
+    sudo pip install -U pip
+    sudo pip install -U virtualenv
 
+    ensuite tu peux créer ton virtualenv dans le dossier de travail ou à un
+    endroit choisi :
 
-Configure stuff
----------------
+    sudo virtualenv -p python3 /srv/gargantext_env
 
-1)  ln -s [the project folder] /srv/gargantext
+3)  Type: source [your virtual environment directory]/bin/activate
 
-2)  ln -s [your folder for tree tagger] [the project folder]/parsing/Tagger/treetagger
+4)  sudo chown -R user:user /srv/gargantext_env
+    pip install -r /srv/gargantext/init/requirements.txt
 
-Warning: for ln, path has to be absolute!
+5)  Type: deactivate
 
 
 In PostreSQL
@@ -52,6 +59,36 @@ Populate the database
 python manage.py syncdb
 
 
+Last steps of configuration:
+----------------------------
+
+1) If your project is not in /srv/gargantext:
+    ln -s [the project folder] /srv/gargantext
+
+2) build gargantext_lib
+    wget http://docs.delanoe.org/gargantext_lib.tar.bz2
+    cd /srv/
+    sudo tar xvjf gargantext_lib.tar.bz2
+    sudo chown user:user /srv/gargantext_lib
+
+3) Explorer: 
+cd /srv/gargantext_lib/js
+git clone git@github.com:PkSM3/garg.git
+
+4)  Adapt all symlinks:
+ln -s [your folder for tree tagger] [the project folder]/parsing/Tagger/treetagger
+Warning: for ln, path has to be absolute!
+
+5) patch CTE
+patch /srv/gargantext_env/lib/python3.4/site-packages/cte_tree/models.py /srv/gargantext/init/cte_tree.models.diff
+
+6) init nodetypes and main variables
+/srv/gargantext/manage.py shell < /srv/gargantext/init/init.py
+
+
+Extras:
+======
+
 Start the Python Notebook server
 --------------------------------
 
@@ -65,4 +102,4 @@ Start the Django server
 -----------------------
 
 In Pyvenv:
-python manage.py runserver
+python manage.py runserver
\ No newline at end of file

init/dependances.deb → init/dependances.sh

-
-
+sudo apt-get install postgresql
+sudo apt-get install postgresql-contrib
 sudo apt-get install python-virtualenv
-sudo apt-cache search libpng
 sudo apt-get install libpng12-dev
 sudo apt-get install libpng-dev
-apt-cache search freetype
-apt-cache search freetype | grep dev
+sudo apt-cache search freetype
 sudo apt-get install libfreetype6-dev
 sudo apt-cache search python-dev
 sudo apt-get install python-dev
 sudo apt-get install libpq-dev
+sudo apt-get postgresql-contrib
+sudo aptèget install libpq-dev
 
-
-
-postgresql-contrib
-
-libpq-dev
-# rajouter david
-#
-#
+# Pour avoir toutes les dependences de matpolotlib (c'est sale, trouver
+sudo apt-get build-dep python-matplotlib
 #Paquets Debian a installer
 # easy_install -U distribute (matplotlib)
 #lxml
-libffi-dev
-libxml2-dev
-libxslt1-dev
+sudo apt-get install libffi-dev
+sudo apt-get install libxml2-dev
+sudo apt-get install libxslt1-dev
 
 # ipython readline
-libncurses5-dev
-pandoc
-
+sudo apt-get install libncurses5-dev
+sudo apt-get install pandoc
 
 # scipy:
-gfortran
-libopenblas-dev
-liblapack-dev
+sudo apt-get install gfortran
+sudo apt-get install libopenblas-dev
+sudo apt-get install liblapack-dev
 
 

init/init.py

@@ -82,6 +82,13 @@ except Exception as error:
     typeDoc     = NodeType(name='Synonyme')
     typeDoc.save()
 
+try:
+    typeDoc     = NodeType.objects.get(name='Cooccurrence')
+except Exception as error:
+    print(error)
+    typeDoc     = NodeType(name='Cooccurrence')
+    typeDoc.save()
+
 
 
 # In[33]:

init/requirements.txt

@@ -4,13 +4,16 @@ Jinja2==2.7.3
 MarkupSafe==0.23
 Pillow==2.5.3
 Pygments==1.6
+SQLAlchemy==0.9.8
 South==1.0
+aldjemy==0.3.51
 amqp==1.4.6
 anyjson==0.3.3
 billiard==3.3.0.18
 celery==3.1.15
 certifi==14.05.14
 cffi==0.8.6
+chardet==2.3.0
 cryptography==0.6
 decorator==3.4.0
 django-autoslug==1.7.2
@@ -27,9 +30,9 @@ graphviz==0.4
 ipython==2.2.0
 kombu==3.0.23
 lxml==3.3.6
-matplotlib==1.4.0
+#matplotlib==1.4.0
 networkx==1.9
-nltk==3.0a4
+#nltk==3.0a4
 nose==1.3.4
 numpy==1.8.2
 pandas==0.14.1

node/models.py

@@ -200,6 +200,7 @@ class Node(CTENode):
         self.node_resource.update(parsed=True)
 
     
+    @current_app.task(filter=task_method)
     def extract_ngrams(self, keys, ngramsextractorscache=None, ngramscaches=None):
         # if there is no cache...
         if ngramsextractorscache is None:

parsing/FileParsers/EuropressFileParser.py

-
-
 import re
 import locale
 from lxml import etree
 from datetime import datetime, date
 
-from parsing.FileParsers.FileParser import FileParser
-from parsing.NgramsExtractors import *
+from .FileParser import FileParser
+from ..NgramsExtractors import *
 
 
 

parsing/FileParsers/FileParser.py

@@ -3,7 +3,7 @@ import dateutil.parser
 import zipfile
 import chardet
 
-from parsing.Caches import LanguagesCache
+from ..Caches import LanguagesCache
     
 
 class FileParser:

parsing/FileParsers/IsiFileParser.py

-from parsing.FileParsers.RisFileParser import RisFileParser
+from .RisFileParser import RisFileParser
 
 
 class IsiFileParser(RisFileParser):

parsing/FileParsers/PubmedFileParser.py

 from django.db import transaction
 from lxml import etree
-from parsing.FileParsers.FileParser import FileParser
-from parsing.NgramsExtractors import *
+from .FileParser import FileParser
+from ..NgramsExtractors import *
 
 class PubmedFileParser(FileParser):
     

parsing/FileParsers/RisFileParser.py

 from django.db import transaction
-from parsing.FileParsers.FileParser import FileParser
+from .FileParser import FileParser
 
 
 class RisFileParser(FileParser):

parsing/NgramsExtractors/EnglishNgramsExtractor.py

-from parsing.NgramsExtractors.NgramsExtractor import NgramsExtractor
-from parsing.Taggers import NltkTagger
+from .NgramsExtractor import NgramsExtractor
+from ..Taggers import NltkTagger
 
 
 class EnglishNgramsExtractor(NgramsExtractor):

parsing/Taggers/NltkTagger.py

-from parsing.Taggers.Tagger import Tagger
+from .Tagger import Tagger
 
 import nltk
 

parsing/Taggers/TreeTagger.py

-from parsing.Taggers.Tagger import Tagger
+from .Tagger import Tagger
 
 import subprocess
 import threading

parsing/Taggers/test.py

-# from NltkTagger import NltkTagger
-# tagger = NltkTagger()
-# text0 = "Forman Brown (1901–1996) was one of the world's leaders in puppet theatre in his day, as well as an important early gay novelist. He was a member of the Yale Puppeteers and the driving force behind Turnabout Theatre. He was born in Otsego, Michigan, in 1901 and died in 1996, two days after his 95th birthday. Brown briefly taught at North Carolina State College, followed by an extensive tour of Europe."
-# text1 = "James Patrick (born c. 1940) is the pseudonym of a Scottish sociologist, which he used to publish a book A Glasgow Gang Observed. It attracted some attention in Scotland when it was published in 1973. It was based on research he had done in 1966, when he was aged 26. At that time he was working as a teacher in an Approved School, a Scottish reformatory. One gang member in the school, \"Tim Malloy\" (born 1950, also a pseudonym and a generic term for a Glasgow Catholic), agreed to infiltrate him into his gang in Maryhill in Glasgow. Patrick spent four months as a gang member, observing their behaviour."
-
-from TreeTagger import TreeTagger
-tagger = TreeTagger()
-text0 = "La saison 1921-1922 du Foot-Ball Club Juventus est la vingtième de l'histoire du club, créé vingt-cinq ans plus tôt en 1897. La société turinoise qui fête cette année son 25e anniversaire prend part à l'édition du championnat dissident d'Italie de la CCI (appelé alors la Première division), la dernière édition d'une compétition annuelle de football avant l'ère fasciste de Mussolini."
-text1 = "Le terme oblong désigne une forme qui est plus longue que large et dont les angles sont arrondis. En langage bibliographique, oblong signifie un format dont la largeur excède la hauteur. Ce qui correspond au format paysage en termes informatiques et \"à l'italienne\", pour l'imprimerie."
-text2 = "Les sanglots longs des violons de l'automne bercent mon coeur d'une langueur monotone."
-
-print()
-print(tagger.tag_text(text0))
-print()
-print(tagger.tag_text(text1))
-print()
-print(tagger.tag_text(text2))
-print()
\ No newline at end of file

static/css/d3matrix.css

+/* Copyright 2013 Michael Bostock. All rights reserved. Do not copy. */
+
+/*@import url(http://fonts.googleapis.com/css?family=PT+Serif|PT+Serif:b|PT+Serif:i|PT+Sans|PT+Sans:b);*/
+
+html {
+  min-width: 1040px;
+}
+
+.ocks-org body {
+  background: #fcfcfa;
+  color: #333;
+  font-family: "PT Serif", serif;
+  margin: 1em auto 4em auto;
+  position: relative;
+  width: 960px;
+}
+
+.ocks-org header,
+.ocks-org footer,
+.ocks-org aside,
+.ocks-org h1,
+.ocks-org h2,
+.ocks-org h3,
+.ocks-org h4 {
+  font-family: "PT Sans", sans-serif;
+}
+
+.ocks-org h1,
+.ocks-org h2,
+.ocks-org h3,
+.ocks-org h4 {
+  color: #000;
+}
+
+.ocks-org header,
+.ocks-org footer {
+  color: #636363;
+}
+
+h1 {
+  font-size: 64px;
+  font-weight: 300;
+  letter-spacing: -2px;
+  margin: .3em 0 .1em 0;
+}
+
+h2 {
+  margin-top: 2em;
+}
+
+h1, h2 {
+  text-rendering: optimizeLegibility;
+}
+
+h2 a[name],
+h2 a[id] {
+  color: #ccc;
+  right: 100%;
+  padding: 0 .3em;
+  position: absolute;
+}
+
+header,
+footer {
+  font-size: small;
+}
+
+.ocks-org header aside,
+.ocks-org footer aside {
+  float: left;
+  margin-right: .5em;
+}
+
+.ocks-org header aside:after,
+.ocks-org footer aside:after {
+  padding-left: .5em;
+  content: "/";
+}
+
+footer {
+  margin-top: 8em;
+}
+
+h1 ~ aside {
+  font-size: small;
+  right: 0;
+  position: absolute;
+  width: 180px;
+}
+
+.attribution {
+  font-size: small;
+  margin-bottom: 2em;
+}
+
+body > p, li > p {
+  line-height: 1.5em;
+}
+
+body > p {
+  width: 720px;
+}
+
+body > blockquote {
+  width: 640px;
+}
+
+blockquote q {
+  display: block;
+  font-style: oblique;
+}
+
+ul {
+  padding: 0;
+}
+
+li {
+  width: 690px;
+  margin-left: 30px;
+}
+
+a {
+  color: steelblue;
+}
+
+a:not(:hover) {
+  text-decoration: none;
+}
+
+pre, code, textarea {
+  font-family: "Menlo", monospace;
+}
+
+code {
+  line-height: 1em;
+}
+
+textarea {
+  font-size: 100%;
+}
+
+body > pre {
+  border-left: solid 2px #ccc;
+  padding-left: 18px;
+  margin: 2em 0 2em -20px;
+}
+
+.html .value,
+.javascript .string,
+.javascript .regexp {
+  color: #756bb1;
+}
+
+.html .tag,
+.css .tag,
+.javascript .keyword {
+  color: #3182bd;
+}
+
+.comment {
+  color: #636363;
+}
+
+.html .doctype,
+.javascript .number {
+  color: #31a354;
+}
+
+.html .attribute,
+.css .attribute,
+.javascript .class,
+.javascript .special {
+  color: #e6550d;
+}
+
+svg {
+  font: 10px sans-serif;
+}
+
+.axis path, .axis line {
+  fill: none;
+  stroke: #000;
+  shape-rendering: crispEdges;
+}
+
+sup, sub {
+  line-height: 0;
+}
+
+q:before {
+  content: "“";
+}
+
+q:after {
+  content: "”";
+}
+
+blockquote q {
+  line-height: 1.5em;
+  display: inline;
+}
+
+blockquote q:before,
+blockquote q:after {
+  content: "";
+}

templates/corpus.html

@@ -127,8 +127,8 @@
 						<div class="jumbotron">
 						<h3><a href="/corpus/{{ corpus.id }}/explorer">Visualizations</a></h3>
 						<ol>
-								<li>Matrix</li>
-								<li>Static maps</li>
+								<li><a href="/corpus/{{ corpus.id }}/matrix">Adjacency matrix</a></li>
+								<li><a href="/corpus/{{ corpus.id }}/explorer">Static maps</a></li>
 								<li>Dynamics maps</li>
 						</ol>
 						</div>

templates/explorer.html

@@ -120,22 +120,19 @@
                   </ul>
 
 
-                  <!--
+                  
                   <ul id="colorGraph" class="nav navbar-nav navbar-right">
                      <li class="dropdown">
-                      <a href="#" class="dropdown-toggle" data-toggle="dropdown">
-                              <img title="Set Colors" src="{% static "js/libs/img2/colors.png" %}"  width="20px"><b class="caret"></b></img>
-                      </a>                      
+	                 	<a href="#" class="dropdown-toggle" data-toggle="dropdown">
+	                          <img title="Set Colors" src="{% static "js/libs/img2/colors.png" %}" width="20px"><b class="caret"></b></img>
+	                 	</a>                     
                       <ul class="dropdown-menu">
-                        <li><a href="#" onclick='clustersBy("country")'>By Country</a></li>
-                        <li><a href="#" onclick='clustersBy("acronym")'>By Acronym</a></li>
+                        <li><a href="#" onclick='clustersBy("group")'>By Group</a></li>
                         <li><a href="#" onclick='clustersBy("default")'>By Default</a></li>
-                        <li class="divider"></li>
-                        <li><a href="#"> <span class="glyphicon glyphicon-repeat"></span> <strike>Properties</strike></a></li>
                       </ul>
                      </li>
                   </ul>
-                  -->
+                  <!---->
 
 
 
@@ -361,7 +358,7 @@
     <script type="text/javascript" src="{% static "js/libs/jquery/jquery.easytabs.min.js" %}"></script>
     
     
-    <script src="{% static "js/libs/bootstrap/js/bootstrap.min.js" %}"></script>
+    <!--<script src="{% static "js/libs/bootstrap/js/bootstrap.min.js" %}"></script>-->
     <script src="{% static "js/libs/bootstrap/js/bootstrap-modal.js" %}" type="text/javascript"></script>
     <script src="{% static "js/libs/bootstrap/js/bootstrap-hover-dropdown.min.js" %}" type="text/javascript"></script>
     

templates/matrix.html

@@ -5,6 +5,22 @@
 {% load staticfiles %}
 <link rel="stylesheet" href="{% static "css/bootstrap.css" %}">
 <link rel="stylesheet" href="{% static "css/bootstrap-theme.min.css" %}">
+<link rel="stylesheet" href="{% static "css/d3matrix.css" %}">
+
+<style>
+.background {
+  fill: #eee;
+}
+
+line {
+  stroke: #fff;
+}
+
+text.active {
+  fill: red;
+}
+</style>
+
 {% endblock %}
 
 
@@ -17,7 +33,11 @@
         </div>
 </div>
 
-<script src="{% static "js/d3/d3.v2.min.js" %}></script>
+<div id="graphid" style="visibility: hidden;">/corpus/{{ corpus.id }}/adjacency.json</div>
+
+
+<script src="{% static "js/jquery/jquery.min.js" %}" type="text/javascript"></script>
+<script src="{% static "js/d3/d3.v2.min.js" %}"></script>
 
 <p>Order: <select id="order">
   <option value="name">by Name</option>
@@ -39,11 +59,12 @@ var x = d3.scale.ordinal().rangeBands([0, width]),
 var svg = d3.select("body").append("svg")
     .attr("width", width + margin.left + margin.right)
     .attr("height", height + margin.top + margin.bottom)
-    .style("margin-left", -margin.left + "px")
+    //.style("margin-left", -margin.left + "px")
   .append("g")
     .attr("transform", "translate(" + margin.left + "," + margin.top + ")");
 
-		d3.json("{% static "img/miserables.json" %}, function(miserables) {
+    var filename = document.getElementById("graphid").innerHTML
+		d3.json(filename, function(miserables) {
   var matrix = [],
       nodes = miserables.nodes,
       n = nodes.length;
@@ -57,12 +78,12 @@ var svg = d3.select("body").append("svg")
 
   // Convert links to matrix; count character occurrences.
   miserables.links.forEach(function(link) {
-    matrix[link.source][link.target].z += link.value;
-    matrix[link.target][link.source].z += link.value;
-    matrix[link.source][link.source].z += link.value;
-    matrix[link.target][link.target].z += link.value;
-    nodes[link.source].count += link.value;
-    nodes[link.target].count += link.value;
+    matrix[link.source][link.target].z += link.weight;
+    matrix[link.target][link.source].z += link.weight;
+    matrix[link.source][link.source].z += link.weight;
+    matrix[link.target][link.target].z += link.weight;
+    nodes[link.source].count += link.weight;
+    nodes[link.target].count += link.weight;
   });
 
   // Precompute the orders.

templates/project.html

@@ -146,7 +146,7 @@
             data: [
             {% if donut %}
             {% for part in donut %}
-						{label: '{{ part.source }}, {{part.count}} docs', value: {{ part.part }} },
+						{label: '{{ part.source }}', value: {{ part.part }} },
             {% endfor %}
             {% endif %}