Update app.py

app.py

@@ -36,36 +36,62 @@ if query:
     print()
     print("Similarity to " + str(query))
     pd.set_option('display.max_rows', None)
-    print(table.head(100))
-    table.head(10).to_csv("clotting_sim1.csv", index=True)
+
+    csv = table.head(50).to_csv(index=False).encode('utf-8')
+    st.download_button(
+        label=f"Download words similar to {query} in .csv format",
+        data=csv,
+        file_name='clotting_sim1.csv',
+        mime='text/csv'
+    )
+
+    json = table.head(50).to_json(index=True).encode('utf-8')
+    st.download_button(
+        label=f"Download words similar to {query} in .js format",
+        data=json,
+        file_name='clotting_sim1.js',
+        mime='json'
+    )
+
+    print(table.head(10))
+    table.head(50).to_csv("clotting_sim1.csv", index=True)
+    table.head(50).to_json("clotting_sim1.js", index=True)
     st.header(f"Similar Words to {query}")
     st.write(table.head(50))
     #
+
     print()
     print("Human genes similar to " + str(query))
     df1 = table
-    df2 = pd.read_csv('Human Genes.csv')
+    df2 = pd.read_csv('Human_Genes.csv')
     m = df1.Word.isin(df2.symbol)
     df1 = df1[m]
     df1.rename(columns={'Word': 'Human Gene'}, inplace=True)
+
+    csv2 = df1.head(50).to_csv(index=False).encode('utf-8')
+    st.download_button(
+        label=f"Download genes similar to {query} in .csv format",
+        data=csv2,
+        file_name='clotting_sim2.csv',
+        mime='text/csv'
+    )
+
+    json2 = df1.head(50).to_json(index=True).encode('utf-8')
+    st.download_button(
+        label=f"Download words similar to {query} in .js format",
+        data=json2,
+        file_name='clotting_sim1.js',
+        mime='json'
+    )
     print(df1.head(10))
+    df1.head(50).to_csv("clotting_sim2.csv", index=True)
+    df1.head(50).to_json("clotting_sim2.js", index=True)
     print()
-    df1.head(10).to_csv("clotting_sim2.csv", index=True, header=False)
-    time.sleep(2)
     st.header(f"Similar Genes to {query}")
-    st.write(table.head(50))
-
-
-# findRelationships(query, df)
-
-
-
-
-
+    st.write(df1.head(50))
 
+from datasets import load_dataset
 
-# model = gensim.models.KeyedVectors.load_word2vec_format('pubmed_model_clotting', binary=True)
-# similar_words = model.most_similar(word)
-# output = json.dumps({"word": word, "similar_words": similar_words})
-# st.write(output)
+test_dataset = load_dataset("json", data_files="clotting_sim1.js", split="train")
 
+test_dataset.save_to_disk("sim1.hf")