Update app.py

app.py

@@ -1,61 +1,42 @@
-import streamlit as st
-import re
-import nltk
-from nltk.corpus import stopwords
-from nltk import FreqDist
-from graphviz import Digraph
-
-nltk.download('punkt')
-nltk.download('stopwords')
-
-def remove_timestamps(text):
-    return re.sub(r'\d{1,2}:\d{2}\n.*\n', '', text)  # Updated regex pattern
-
-def process_text(text):
-    lines = text.split("\n")
-    processed_lines = []
-
-    for line in lines:
-        if line:
-            processed_lines.append(line)
-
-    outline = ""
-    for i, line in enumerate(processed_lines):
-        if i % 2 == 0:
-            outline += f"**{line}**\n"
-        else:
-            outline += f"- {line} 😄\n"
-
-    return outline
-
-def extract_high_information_words(text, top_n=10):
+def extract_context_words(text, high_information_words):
     words = nltk.word_tokenize(text)
-    words = [word.lower() for word in words if word.isalpha()]
+    context_words = []
 
-    stop_words = set(stopwords.words('english'))
-    filtered_words = [word for word in words if word not in stop_words]
-
-    freq_dist = FreqDist(filtered_words)
-    high_information_words = [word for word, _ in freq_dist.most_common(top_n)]
+    for index, word in enumerate(words):
+        if word.lower() in high_information_words:
+            before_word = words[index - 1] if index > 0 else None
+            after_word = words[index + 1] if index < len(words) - 1 else None
+            context_words.append((before_word, word, after_word))
 
-    return high_information_words
+    return context_words
 
-def create_relationship_graph(words):
+def create_context_graph(context_words):
     graph = Digraph()
 
-    for index, word in enumerate(words):
-        graph.node(str(index), word)
+    for index, (before_word, high_info_word, after_word) in enumerate(context_words):
+        graph.node(f'before{index}', before_word, shape='box') if before_word else None
+        graph.node(f'high{index}', high_info_word, shape='ellipse')
+        graph.node(f'after{index}', after_word, shape='diamond') if after_word else None
 
-        if index > 0:
-            graph.edge(str(index - 1), str(index), label=str(index))
+        if before_word:
+            graph.edge(f'before{index}', f'high{index}')
+        if after_word:
+            graph.edge(f'high{index}', f'after{index}')
 
     return graph
 
-def display_relationship_graph(words):
-    graph = create_relationship_graph(words)
+def display_context_graph(context_words):
+    graph = create_context_graph(context_words)
     st.graphviz_chart(graph)
 
-uploaded_file = st.file_uploader("Choose a .txt file", type=['txt'])
+def display_context_table(context_words):
+    table = "| Before | High Info Word | After |\n|--------|----------------|-------|\n"
+    for before, high, after in context_words:
+        table += f"| {before if before else ''} | {high} | {after if after else ''} |\n"
+    st.markdown(table)
+
+
+# ...
 
 if uploaded_file:
     file_text = uploaded_file.read().decode("utf-8")
@@ -65,5 +46,12 @@ if uploaded_file:
     st.markdown("**Top 10 High Information Words:**")
     st.write(top_words)
 
+    context_words = extract_context_words(text_without_timestamps, top_words)
     st.markdown("**Relationship Graph:**")
     display_relationship_graph(top_words)
+
+    st.markdown("**Context Graph:**")
+    display_context_graph(context_words)
+    
+    st.markdown("**Context Table:**")
+    display_context_table(context_words)