Update src/streamlit_app.py

src/streamlit_app.py

@@ -92,30 +92,38 @@ def classify_sentences(text):
         sentence_scores.append((sentence, sentiment))
     return sentence_scores
 
-# Streamlit UI
-st.title("Sentiment Classification Model")
-
-url = st.text_input("Enter URL:")
-
-if url:
-    text = get_text_from_url(url)
-    if text:
-        scores, chunk_scores_list, chunks = classify_long_text(text)
-        scores_dict = {sentiment_labels[i]: scores[i] for i in range(len(sentiment_labels))}
-        
-        # Ensure the exact order of labels in the graph
-        sentiment_order = [
-            "very positive", "positive", "somewhat positive",
-            "neutral",
-            "somewhat negative", "negative", "very negative"
-        ]
-        ordered_scores_dict = OrderedDict((label, scores_dict[label]) for label in sentiment_order)
-        
-        # Prepare the DataFrame and reindex
-        df = pd.DataFrame.from_dict(ordered_scores_dict, orient='index', columns=['Likelihood']).reindex(sentiment_order)
-        
-        # Use Altair to plot the bar chart
-        chart = alt.Chart(df.reset_index()).mark_bar().encode(
+def render_analysis(text):
+    scores, chunk_scores_list, chunks = classify_long_text(text)
+    scores_dict = {sentiment_labels[i]: scores[i] for i in range(len(sentiment_labels))}
+
+    # Ensure the exact order of labels in the graph
+    sentiment_order = [
+        "very positive", "positive", "somewhat positive",
+        "neutral",
+        "somewhat negative", "negative", "very negative"
+    ]
+    ordered_scores_dict = OrderedDict((label, scores_dict[label]) for label in sentiment_order)
+
+    # Prepare the DataFrame and reindex
+    df = pd.DataFrame.from_dict(ordered_scores_dict, orient='index', columns=['Likelihood']).reindex(sentiment_order)
+
+    # Use Altair to plot the bar chart
+    chart = alt.Chart(df.reset_index()).mark_bar().encode(
+        x=alt.X('index', sort=sentiment_order, title='Sentiment'),
+        y='Likelihood'
+    ).properties(
+        width=600,
+        height=400
+    )
+    st.altair_chart(chart, use_container_width=True)
+
+    # Display each chunk and its own chart
+    for i, (chunk_scores, chunk) in enumerate(zip(chunk_scores_list, chunks)):
+        chunk_scores_dict = {sentiment_labels[j]: chunk_scores[j] for j in range(len(sentiment_labels))}
+        ordered_chunk_scores_dict = OrderedDict((label, chunk_scores_dict[label]) for label in sentiment_order)
+        df_chunk = pd.DataFrame.from_dict(ordered_chunk_scores_dict, orient='index', columns=['Likelihood']).reindex(sentiment_order)
+
+        chunk_chart = alt.Chart(df_chunk.reset_index()).mark_bar().encode(
             x=alt.X('index', sort=sentiment_order, title='Sentiment'),
             y='Likelihood'
         ).properties(
@@ -123,35 +131,36 @@ if url:
             height=400
         )
 
-        st.altair_chart(chart, use_container_width=True)
-
-        # Display each chunk and its own chart
-        for i, (chunk_scores, chunk) in enumerate(zip(chunk_scores_list, chunks)):
-            chunk_scores_dict = {sentiment_labels[j]: chunk_scores[j] for j in range(len(sentiment_labels))}
-            ordered_chunk_scores_dict = OrderedDict((label, chunk_scores_dict[label]) for label in sentiment_order)
-            df_chunk = pd.DataFrame.from_dict(ordered_chunk_scores_dict, orient='index', columns=['Likelihood']).reindex(sentiment_order)
-            
-            chunk_chart = alt.Chart(df_chunk.reset_index()).mark_bar().encode(
-                x=alt.X('index', sort=sentiment_order, title='Sentiment'),
-                y='Likelihood'
-            ).properties(
-                width=600,
-                height=400
-            )
-
-            st.write(f"Chunk {i + 1}:")
-            st.write(chunk)
-            st.altair_chart(chunk_chart, use_container_width=True)
-
-        # Sentence-level classification with background colors
-        st.write("Extracted Text with Sentiment Highlights:")
-        sentence_scores = classify_sentences(text)
-        for sentence, sentiment in sentence_scores:
-            bg_color = background_colors[sentiment]
-            st.markdown(f'<span style="background-color: {bg_color}">{sentence}</span>', unsafe_allow_html=True)
-
-    else:
-        st.write("Could not extract text from the provided URL.")
+        st.write(f"Chunk {i + 1}:")
+        st.write(chunk)
+        st.altair_chart(chunk_chart, use_container_width=True)
+
+    # Sentence-level classification with background colors
+    st.write("Extracted Text with Sentiment Highlights:")
+    sentence_scores = classify_sentences(text)
+    for sentence, sentiment in sentence_scores:
+        bg_color = background_colors[sentiment]
+        st.markdown(f'<span style="background-color: {bg_color}">{sentence}</span>', unsafe_allow_html=True)
+
+# Streamlit UI
+st.title("Sentiment Classification Model")
+
+tab_paste, tab_scrape = st.tabs(["Paste Text", "Scrape URL"])
+
+with tab_paste:
+    pasted_text = st.text_area("Paste text for analysis:", height=300, placeholder="Paste text here…")
+    if pasted_text and pasted_text.strip():
+        render_analysis(pasted_text.strip())
+
+with tab_scrape:
+    st.info("If the site returns 403 (forbidden), use the 'Paste Text' tab to analyze content manually.")
+    url = st.text_input("Enter URL:")
+    if url:
+        text = get_text_from_url(url)
+        if text:
+            render_analysis(text)
+        else:
+            st.write("Could not extract text from the provided URL.")
 
 # Additional information at the end
 st.markdown("""
@@ -161,4 +170,3 @@ The model is designed to be deployed in an automated pipeline capable of classif
 Interested in using this in an automated pipeline for bulk sentiment processing?
 Please [book an appointment](https://dejan.ai/call/) to discuss your needs.
 """)
-