update

lrt/__init__.py

@@ -1,2 +1,3 @@
 from .lrt import LiteratureResearchTool
-from .clustering import Configuration
+from .clustering import Configuration
+from .utils import Article, ArticleList

lrt/utils/article.py

@@ -1,4 +1,5 @@
 from typing import List, Union, Optional
+import pandas as pd
 class Article:
     '''
     attributes:
@@ -31,6 +32,15 @@ class Article:
 
         return ret
 
+    def getDict(self) -> dict:
+        return {
+            'title': self.title,
+            'authors': self.authors,
+            'abstract': self.abstract,
+            'url': self.url,
+            'publication_year': self.publication_year
+        }
+
 class ArticleList:
     '''
     list of articles
@@ -72,6 +82,12 @@ class ArticleList:
     def __len__(self):
         return len(self.__list__)
 
+    def getDataFrame(self) ->pd.DataFrame:
+        return pd.DataFrame(
+            [x.getDict() for x in self.__list__]
+        )
+
+
     @classmethod
     def parse_ieee_articles(cls,items: Union[dict, List[dict]]):
         if isinstance(items,dict):
@@ -391,4 +407,6 @@ if __name__ == '__main__':
     print(pwc_articles)
 
     for i in ieee_articles:
-        print(i)
+        print(i)
+
+    print(pwc_articles.getDataFrame())

widgets/body.py

@@ -1,16 +1,18 @@
 import streamlit as st
 from api_ import ArxivQuery, IEEEQuery, PaperWithCodeQuery
+from lrt.clustering.clusters import SingleCluster
+from lrt import ArticleList
 from lrt_instance import *
-from pyecharts.charts import Bar
-from pyecharts import options as opts
-import streamlit.components.v1 as st_render
-from .utils import generate_html_pyecharts
+# from pyecharts.charts import Bar
+# from pyecharts import options as opts
+# import streamlit.components.v1 as st_render
+# from .utils import generate_html_pyecharts
 from .charts import build_bar_charts
 
 def __preview__(platforms, num_papers, num_papers_preview, query_input,start_year,end_year):
     with st.spinner('Searching...'):
         paperInGeneral = st.empty()  # paper的大概
-        paperInGeneral_md = '''# Query Results Preview
+        paperInGeneral_md = '''# 0 Query Results Preview
 We have found following papers for you! (displaying 5 papers for each literature platforms)
 '''
         if 'IEEE' in platforms:
@@ -67,28 +69,34 @@ def render_body(platforms, num_papers, num_papers_preview, query_input, show_pre
         generator =  baseline_lrt(query_input,num_papers,start_year,end_year,platforms, best_k=k)
         for i,plat in enumerate(platforms):
             clusters, articles = next(generator)
-            st.markdown(f'''# {plat} Results''')
+            st.markdown(f'''# {i+1} {plat} Results''')
             clusters.sort()
 
-            st.markdown(f'''## Clusters Overview''')
-            st.markdown(f'''Here we show the overview of the clusters, more specifically,''')
+            st.markdown(f'''## {i+1}.1 Clusters Overview''')
+            st.markdown(f'''In this section we show the overview of the clusters, more specifically,''')
             st.markdown(f'''\n- the number of papers in each cluster\n- the number of keyphrases of each cluster''')
-            '''
-            plot using pyecharts
-            bar = (
-                Bar()
-                .add_xaxis([f'Cluster {i + 1}' for i in range(len(clusters))])
-                .add_yaxis("number of papers", [len(c) for c in clusters])
-                .add_yaxis("number of keyphrases", [len(c.get_keyphrases()) for c in clusters])
-            )
-            html = generate_html_pyecharts(bar, 'tmp.html')
-            st_render.html(html, height=500, width=1000)
-            '''
             st.bokeh_chart(build_bar_charts(
                 x_range=[f'Cluster {i + 1}' for i in range(len(clusters))],
                 y_names= ['Number of Papers', 'Number of Keyphrases'],
                 y_data=[[len(c) for c in clusters],[len(c.get_keyphrases()) for c in clusters]]
             ))
 
+            st.markdown(f'''## {i+1}.2 Cluster Details''')
+            st.markdown(f'''In this section we show the details of each cluster, including''')
+            st.markdown(f'''\n- the article information in the cluster\n- the keyphrases of the cluster''')
+            for j,cluster in enumerate(clusters):
+                assert isinstance(cluster,SingleCluster) #TODO: remove this line
+                ids = cluster.elements()
+                articles_in_cluster = ArticleList([articles[id] for id in ids])
+                st.markdown(f'''**Cluster {j + 1}**''')
+                st.dataframe(articles_in_cluster.getDataFrame())
+                st.markdown(f'''The top 5 keyphrases of this cluster are:''')
+                md = ''
+                for keyphrase in cluster.top_5_keyphrases:
+                    md += f'''- `{keyphrase}`\n'''
+                st.markdown(md)
+
+
+