Update app.py

app.py

@@ -91,19 +91,21 @@ if query:
     table = (pd.DataFrame(table))
     table.index.name = 'Rank'
     table.columns = ['Word', 'SIMILARITY']
-    print()
-    print("Similarity to " + str(query))
+
+    # print()
+    # print("Similarity to " + str(query))
     pd.set_option('display.max_rows', None)
-    print(table.head(50))
+    table2 = table.copy()
+    # print(table.head(50))
     # table.head(10).to_csv("clotting_sim1.csv", index=True)
     # short_table = table.head(50)
     # print(table)
 
 
     # calculate the sizes of the squares in the treemap
-    short_table = table.head(10)
+    short_table = table2.head(10).round(2)
     short_table.index += 1
-    short_table.index = 1 / short_table.index
+    short_table.index = (1 / short_table.index)*10
     sizes = short_table.index.tolist()
 
     cmap = plt.cm.Greens(np.linspace(0.05, .5, len(sizes)))
@@ -118,47 +120,52 @@ if query:
     # plt.legend("upper right", bbox_to_anchor=(-.2, 0))
     fig = plt.gcf()
     fig.patch.set_facecolor('#CCFFFF')
+    # print(table.head(10)["SIMILARITY"])
     # # display the treemap in Streamlit
-
-    rank_num = list(short_table.index.tolist())
-    avg_size = sum(sizes) / len(short_table.index)
-    print(rank_num)
+    table2["SIMILARITY"] = 'Similarity Score ' + table2.head(10)["SIMILARITY"].round(2).astype(str)
+    # rank_num = list(short_table.index.tolist())
+    # avg_size = sum(sizes) / len(short_table.index)
+    # print(rank_num)
     # print(sizes)
-    fig = px.treemap(short_table, path=[short_table.index], values=sizes, color=sizes, color_continuous_scale='greens',
-                     color_continuous_midpoint=avg_size)
+    fig = px.treemap(path=[short_table.index], values=sizes, hover_name=(table2.head(10)['SIMILARITY']))
     fig.update(layout_coloraxis_showscale=False)
     fig.update_layout(autosize=True, paper_bgcolor="#CCFFFF")
+    fig.update_annotations(visible=False)
+    fig.update_traces(marker=dict(cornerradius=5), root_color="#CCFFFF", hovertemplate=None,
+                      hoverlabel_bgcolor="lightgreen", hoverlabel_bordercolor="#000000")
+    fig.update_layout(uniformtext=dict(minsize=15, mode='hide'), treemapcolorway=["lightgreen"])
 
 
-    treemap1, treemap2 = st.columns(2)
-    with treemap1:
-        st.subheader(f"Top 10 Words closely related to {query}")
-        # st.pyplot(fig)
-        # plt.clf()
-        st.plotly_chart(fig, use_container_width=True)
+    # treemap1, treemap2 = st.columns(2)
+    # with treemap1:
+    st.subheader(f"Top 10 Words closely related to {query}")
+    # st.pyplot(fig)
+    # plt.clf()
+    st.plotly_chart(fig, use_container_width=True)
 
-        csv = table.head(100).to_csv().encode('utf-8')
-        st.download_button(label="download top 100 words (csv)", data=csv, file_name=f'{database_name}_words.csv', mime='text/csv')
 
+    csv = table.head(100).to_csv().encode('utf-8')
+    st.download_button(label="download top 100 words (csv)", data=csv, file_name=f'{database_name}_words.csv', mime='text/csv')
+    st.markdown("---")
     # st.write(short_table)
     #
 
-    print()
-    print("Human genes similar to " + str(query))
+    # print()
+    # print("Human genes similar to " + str(query))
     df1 = table
     df2 = pd.read_csv('Human_Genes.csv')
     m = df1.Word.isin(df2.symbol)
     df1 = df1[m]
     df1.rename(columns={'Word': 'Human Gene'}, inplace=True)
     df1["Human Gene"] = df1["Human Gene"].str.upper()
-    print(df1.head(50))
+    # print(df1.head(50))
     print()
     # df1.head(50).to_csv("clotting_sim2.csv", index=True, header=False)
     # time.sleep(2)
 
 
     df10 = df1.head(10)
-    df10.index = 1 / df10.index
+    df10.index = (1 / df10.index)*10000
     sizes = df10.index.tolist()
 
     cmap2 = plt.cm.Blues(np.linspace(0.05, .5, len(sizes)))
@@ -174,30 +181,27 @@ if query:
     fig2 = plt.gcf()
     fig2.patch.set_facecolor('#CCFFFF')
     #
-
-
-
-    # link_ref = '<a href="http://google.com" style="cursor: pointer" target="_blank" rel="noopener noreferrer">{}</a>'
-    # df10['SIMILARITY'] = df10['SIMILARITY'].apply(lambda item: link_ref.format(item, "{}"))
-    rank_num = list(df10.index.tolist())
-    avg_size = sum(sizes) / len(df10.index)
-    print(rank_num)
-    # print(sizes)
-    fig = px.treemap(path=[df10.index], values=sizes, color=sizes, color_continuous_scale='greens',
-                     color_continuous_midpoint=avg_size)
+    print(df10["SIMILARITY"])
+    # rank_num = list(df10.index.tolist())
+    # avg_size = sum(sizes) / len(df10.index)
+    df10["SIMILARITY"] = 'Similarity Score ' + df10["SIMILARITY"].round(2).astype(str)
+    fig = px.treemap(path=[df10.index], values=sizes, hover_name=(df10['SIMILARITY']))
     fig.update(layout_coloraxis_showscale=False)
-    fig.update_layout(autosize=True, paper_bgcolor="#CCFFFF", uniformtext_mode="hide", plot_bgcolor="#fff")
-    fig.update_traces(root_color='rgba(0,0,0,0)')
+    fig.update_layout(autosize=True, paper_bgcolor="#CCFFFF")
+    fig.update_annotations(visible=False)
+    fig.update_traces(marker=dict(cornerradius=5), root_color="#CCFFFF", hovertemplate=None,
+                      hoverlabel_bgcolor="lightblue", hoverlabel_bordercolor="#000000")
+    fig.update_layout(uniformtext=dict(minsize=20, mode='hide'), treemapcolorway=["lightblue"])
 
 
     # # display the treemap in Streamlit
-    with treemap2:
-        st.subheader(f"Top 10 Genes closely related to {query}")
+    # with treemap2:
+    st.subheader(f"Top 10 Genes closely related to {query}")
         # st.pyplot(fig2)
-        st.plotly_chart(fig, use_container_width=True)
+    st.plotly_chart(fig, use_container_width=True)
 
-        csv = df1.head(100).to_csv().encode('utf-8')
-        st.download_button(label="download top 100 genes (csv)", data=csv, file_name=f'{database_name}_genes.csv',
+    csv = df1.head(100).to_csv().encode('utf-8')
+    st.download_button(label="download top 100 genes (csv)", data=csv, file_name=f'{database_name}_genes.csv',
                        mime='text/csv')
     st.markdown("---")
     st.subheader("Cancer-related videos")