Update app.py

app.py

@@ -3,8 +3,9 @@ import time
 import json
 from gensim.models import Word2Vec
 import pandas as pd
-from datasets import load_dataset
-from datasets import Dataset
+import matplotlib.pyplot as plt
+import squarify
+import numpy as np
 
 # Define the HTML and CSS styles
 html_temp = """
@@ -20,8 +21,8 @@ st.markdown(html_temp, unsafe_allow_html=True)
 st.write("This is my Streamlit app with HTML and CSS formatting.")
 
 query = st.text_input("Enter a word")
-# query = input ("Enter your keyword(s):")
 query = query.lower()
+# query = input ("Enter your keyword(s):")
 
 if query:
     model = Word2Vec.load("pubmed_model_clotting")  # you can continue training with the loaded model!
@@ -39,28 +40,31 @@ if query:
     print()
     print("Similarity to " + str(query))
     pd.set_option('display.max_rows', None)
-
-    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)
+    print(table.head(50))
+    table.head(10).to_csv("clotting_sim1.csv", index=True)
+    # short_table = table.head(50)
+    # print(table)
     st.header(f"Similar Words to {query}")
-    st.write(table.head(50))
+
+    # calculate the sizes of the squares in the treemap
+    short_table = table.head(20)
+    short_table.index += 1
+    short_table.index = 1 / short_table.index
+    sizes = short_table.index.tolist()
+
+    cmap = plt.cm.Greens(np.linspace(0.05, .5, len(sizes)))
+    color = [cmap[i] for i in range(len(sizes))]
+
+    short_table.set_index('Word', inplace=True)
+    squarify.plot(sizes=sizes, label=short_table.index.tolist(), color=color, pad=.005, text_kwargs={'fontsize': 6})
+    # # plot the treemap using matplotlib
+    plt.axis('off')
+    fig = plt.gcf()
+    # # display the treemap in Streamlit
+    st.pyplot(fig)
+    plt.clf()
+
+    # st.write(short_table)
     #
 
     print()
@@ -70,36 +74,44 @@ if query:
     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)
+    df1["Human Gene"] = df1["Human Gene"].str.upper()
+    print(df1.head(50))
     print()
+    df1.head(50).to_csv("clotting_sim2.csv", index=True, header=False)
+    # time.sleep(2)
     st.header(f"Similar Genes to {query}")
-    st.write(df1.head(50))
+
+    df1 = df1.head(20)
+    df1.index = 1/df1.index
+    sizes = df1.index.tolist()
+
+    cmap2 = plt.cm.Blues(np.linspace(0.05, .5, len(sizes)))
+    color2 = [cmap2[i] for i in range(len(sizes))]
+
+    df1.set_index('Human Gene', inplace=True)
+    squarify.plot(sizes=sizes, label=df1.index.tolist(), color=color2, pad=.005, text_kwargs={'fontsize': 8})
+    #
+    # # plot the treemap using matplotlib
+
+    plt.axis('off')
+    fig2 = plt.gcf()
+    # plt.show()
+    #
+    # # display the treemap in Streamlit
+    st.pyplot(fig2)
+
+
+
+# findRelationships(query, df)
+
+
+
 
 
-    # arrow_dataset = Dataset.from_pandas(df1.head(50))
-    # arrow_dataset.save_to_disk("https://huggingface.co/datasets/jfataphd/word2vec_dataset/sim2")
 
-    # arrow_dataset_reloaded = load_from_disk('sim2.js')
-    # arrow_dataset_reloaded
-    
- 
 
+# 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)