New

src/streamlit_app.py

@@ -1,40 +1,54 @@
-import altair as alt
-import numpy as np
-import pandas as pd
+
 import streamlit as st
+import tensorflow as tf
+import numpy as np
+import re
+import nltk
+
+# Ensure NLTK sentence tokenizer is available
+nltk.download('punkt')
+from nltk.tokenize import sent_tokenize
+
+model = tf.keras.models.load_model('my_distilbert_classifier.keras')
+
+
+
+
+def predict_sentence_ai_probability(sentence):
+    preds = model.predict([sentence])
+    prob_ai = tf.sigmoid(preds[0][0]).numpy()
+    return prob_ai
+
+def predict_ai_generated_percentage(text, threshold=0.75):
+    text=text+"."
+    sentences = sent_tokenize(text)
+    ai_sentence_count = 0
+    results = []
+
+    for sentence in sentences:
+        prob = predict_sentence_ai_probability(sentence)
+        is_ai = prob >= threshold
+        results.append((sentence, prob, is_ai))
+        if is_ai:
+            ai_sentence_count += 1
+
+    total_sentences = len(sentences)
+    ai_percentage = (ai_sentence_count / total_sentences) * 100 if total_sentences > 0 else 0.0
+    return ai_percentage, results
+
+st.title("🧠 AI Content Detector")
+st.markdown("This tool detects the percentage of **AI-generated content** in your input text based on sentence-level analysis.")
+
+user_input = st.text_area("Paste your text here:", height=300)
 
-"""
-# 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])),
-    ))
+if st.button("Analyze"):
+    if user_input.strip() == "":
+        st.warning("Please enter some text to analyze.")
+    else:
+        ai_percentage, analysis_results = predict_ai_generated_percentage(user_input)
+        st.subheader("🔍 Sentence-level Analysis")
+        for i, (sentence, prob, is_ai) in enumerate(analysis_results, start=1):
+            label = "🟢 Human" if not is_ai else "🔴 AI"
+            st.markdown(f"**{i}.** _{sentence}_\n\n→ **Probability AI:** `{prob:.2%}` → {label}")
+        st.subheader("📊 Final Result")
+        st.success(f"Estimated **AI-generated content**: **{ai_percentage:.2f}%**")