Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,49 @@
-import altair as alt
-import numpy as np
-import pandas as pd
-import streamlit as st
+import os
+os.environ["STREAMLIT_BROWSER_GATHER_USAGE_STATS"] = "false"
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+import streamlit as st
+import spacy
+import benepar
+from nltk import Tree
+import nltk
+
+# Setup NLTK and benepar
+nltk.download('punkt')
+benepar.download('benepar_en3')
+
+nlp = spacy.load("en_core_web_sm")
+if "benepar" not in nlp.pipe_names:
+    nlp.add_pipe("benepar", config={"model": "benepar_en3"})
+
+st.set_page_config(page_title="Syntax Parser Comparison Tool", layout="wide")
+st.title("🌐 Syntax Parser Comparison Tool")
+st.write("This tool compares Dependency Parsing, Constituency Parsing, and a simulated Abstract Syntax Representation (ASR).")
+
+sentence = st.text_input("Enter a sentence:", "John eats an apple.")
+
+if sentence:
+    doc = nlp(sentence)
+    sent = list(doc.sents)[0]
+
+    col1, col2, col3 = st.columns(3)
+
+    with col1:
+        st.header("Dependency Parsing")
+        for token in sent:
+            st.write(f"{token.text} --> {token.dep_} --> {token.head.text}")
+        st.code(" ".join(f"({token.text}, {token.dep_}, {token.head.text})" for token in sent))
+
+    with col2:
+        st.header("Constituency Parsing")
+        tree = sent._.parse_string
+        st.text(tree)
+        st.code(Tree.fromstring(tree).pformat())
+
+    with col3:
+        st.header("Simulated ASR Output")
+        st.write("Combining phrase structure with dependency head annotations:")
+        for token in sent:
+            if token.dep_ in ("nsubj", "obj", "det", "ROOT"):
+                st.write(f"[{token.text}] - {token.dep_} --> {token.head.text} ({token.pos_})")
+        st.markdown("_(ASR is simulated by combining POS tags, dependency heads, and phrase information.)_")
+        st.code(" ".join(f"[{token.text}: {token.dep_} → {token.head.text}]({token.pos_})" for token in sent))