#!/usr/bin/env python
# coding: utf-8

# # Pages report

# This notebook is a workaround to build indivual page reports. It defines the main functions to display a report (`display_report(pagename)`). That allow other notebooks to import and explore the various data about the computed data from wikipedia pages and subsequent relationshipts (networks of users-pages, pages-pages and users-users). It also include synthesis of time wise analysis like page views analytics.
# 
# This page is mainly used by the [page explorer](page explorer.ipynb) notebook.

# In[1]:


get_ipython().run_line_magic('run', '"libraries.ipynb"')
get_ipython().run_line_magic('config', "InlineBackend.figure_formats=['svg']")

import networkx as nx
from IPython.display import display, HTML


# # importing datasets

# In[2]:


# list of page names
pages = codecs.open("data/pagenames.txt","r", "utf-8-sig").readlines()
pages = map(lambda x: x.strip(), pages)

# page graph obtained by projecting page-editor bi-partite graph
pages_graph = nx.read_gexf("data/pages-linked-by-coeditors.gexf")

# page graph obtained by projecting page-editor bi-partite graph
pages_editors_graph = nx.read_gexf("data/pages-editors.gexf")


# In[3]:


def table_to_html(data, cols=[]):
    html = "<table>"
    html += "<tr>"
    for column_content in cols:
        html += "<th>%s</th>" % (column_content)
    html += "</tr>"
    
    for d in data:
        html += "<tr>"
        for column_content in d:
            html += "<td>%s</td>" % (column_content)
        html += "</tr>"
    html += "</table>"
        
    return HTML(html)


# ## top editors

# In[4]:


def display_top_editors(page):    
    top_editors = pages_editors_graph["p:%s" % (page)]    
    top_editors = sorted(top_editors.items(), key=lambda x: (-x[1]["revisions"], -pages_editors_graph.node[x[0]]["revisions"]))

    # print top_editors
    
    data = []

    for name, edits in top_editors[0:10]:
        data.append(["<a href=\"http://en.wikipedia.org/wiki/User:{0}\" target=\"_blank\">{0}</a>".format(name.split(":")[1]),
                     edits["revisions"],
                    pages_editors_graph.node[name]["revisions"]])

    display(table_to_html(data, ["editor name", "edits on that page", "edits over the corpus"]))

display_top_editors("Pi")    


# ## pageviews and revisions

# In[5]:


def display_pageviews_revisions(page):
    pageviews = pd.DataFrame.from_csv("data/pageviews/%s.weekly.csv" % (page))
    revisions = pd.DataFrame.from_csv("data/revisions/%s.weekly.csv" % (page))

    pageviews.plot(figsize=(12, 2), subplots=False, linewidth="0.5", ylim=0, colormap="Spectral", rot=0)    
    revisions.plot(figsize=(12, 2), linewidth="0.5", ylim=0)
    plt.show() 

display_pageviews_revisions("Pi")


# ## local graph

# In[6]:


def display_local_graph(page):
    g1 = nx.read_gexf("data/reading_maps/pages-coedited-reduced-3.gexf")
    nbunch = [ page ]
    nbunch.extend( list(g1.to_undirected()[page]))
    g2 = g1.subgraph(nbunch)

    #nx.draw_spring(g2)
    
    pos = nx.spring_layout(g2,iterations=50)
   
    nx.draw_networkx_nodes(g2, pos)
    nx.draw_networkx_edges(g2, pos)
    nx.draw_networkx_labels(g2, pos)
    
    plt.axis('off')
    plt.show()


display_local_graph("Paraboloid")


# # final report

# In[7]:


def display_report(page):
    display(HTML("<h2>%s</h2>" % (page)))
    
    #display(HTML("<div style=\"float:left\">"))    
    display(HTML("<h3>co-edited pages</h3>"))

    nb = sorted(pages_graph["p:%s" % (page)].items(),
            key=lambda (k,x): -int(x["coeditors"]))

    data = []

    # calculate rank in neighbor top co-edited ranking
    for name, info in nb:
        nb_mirror = sorted(pages_graph[name].items(),
                key=lambda (k,x): -int(x["coeditors"]))
        nb_mirror = [ x[0] for x in nb_mirror ]
        
        editors = pages_editors_graph[name]        
        info["editors"] = len(editors)
        info["exclusive editors"] = len([n for n in editors if len(pages_editors_graph[n]) == 1 ])

        info["ranking"] = nb_mirror.index("p:%s" % (page)) + 1

    #print nb

    for name, info in nb[0:10]:
        data.append([ u"<a href=\"http://en.wikipedia.org/wiki/{0}\" target=\"_blank\">{0}</a>".format(name.split(":")[1]),
                     info["editors"],
                     info["coeditors"],
                     float(info["coeditors"]) / float(info["editors"]),
                     info["exclusive editors"],
                     info["ranking"]])

    display(table_to_html(data, ["page name", "editors", "co-editors", "co-editors/editors", "exclusive editors" ,"ranking"]))
    #display(HTML("</div>"))    

    #display(HTML("<div style=\"float:left\">"))    
    display(HTML("<h3>ranked first in</h3>"))

    nb_list = [ x[0] for x in nb ]
    data = []

    nb2 = sorted(nb, key=lambda (x): x[1]["ranking"])
    for name, info in nb2[0:10]:
        editors = pages_editors_graph[name]        
        info["editors"] = len(editors)
        info["exclusive editors"] = len([n for n in editors if len(pages_editors_graph[n]) == 1 ])

        data.append([ u"<a href=\"http://en.wikipedia.org/wiki/{0}\" target=\"_blank\">{0}</a>".format(name.split(":")[1]),
                     info["editors"],
                     info["coeditors"],
                     float(info["coeditors"]) / float(info["editors"]),
                     info["exclusive editors"],
                     info["ranking"]])  

    display(table_to_html(data, ["page name", "editors", "co-editors", "co-editors/editors", "exclusive editors" ,"ranking"]))
#     display(HTML("</div>"))    
#     display(HTML("<div style=\"clear:both\"></div>"))
    
    display(HTML("<h3>pageviews and revisions</h3>"))
    display_pageviews_revisions(page)
    
    display(HTML("<h3>top editors</h3>"))
    display_top_editors(page)

    display(HTML("<h3>local subgraph</h3>"))
    display_local_graph(page)
    
#display_report("3-sphere")


# In[8]:


if __name__ == "__main__":
    display_report("3-sphere")