Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,108 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pickle
+from collections import Counter
+import re
+from typing import Counter as TCounter, Tuple, List, Any
 
-"""
-# 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])),
-    ))
+# --- 1. CONFIGURATION ---
+
+# The n-gram range used during model training (e.g., (1, 4) for unigrams up to 4-grams)
+N_GRAM_RANGE = (1, 4) 
+# Filenames saved in the previous step
+MODEL_FILE = 'src/emotion.pkl'
+VECTORIZER_FILE = 'src/vectorizer.pkl'
+
+# --- 2. LOAD ARTIFACTS ---
+
+@st.cache_resource
+def load_artifacts():
+    """Loads the saved classifier model and DictVectorizer."""
+    try:
+        # Load the Model
+        with open(MODEL_FILE, 'rb') as model_file:
+            loaded_model = pickle.load(model_file)
+        
+        # Load the Vectorizer
+        with open(VECTORIZER_FILE, 'rb') as vec_file:
+            loaded_vectorizer = pickle.load(vec_file)
+        
+        return loaded_model, loaded_vectorizer
+    except FileNotFoundError:
+        st.error(f"Error: Required files ({MODEL_FILE} or {VECTORIZER_FILE}) not found. Please ensure they are in the correct directory.")
+        return None, None
+
+# --- 3. FEATURE EXTRACTION FUNCTION (CRITICAL!) ---
+
+# This function MUST be identical to the one used during model training.
+def create_feature(text: str, nrange: Tuple[int, int]) -> TCounter[str]:
+    """Extracts n-gram and punctuation features from a text string."""
+    text_features: List[str] = []
+    lower_text = text.lower()
+    
+    # Word N-Grams
+    text_alphanum = re.sub(r'[^a-z0-9#]', ' ', lower_text)
+    token = text_alphanum.split() 
+
+    for n in range(nrange[0], nrange[1] + 1):
+        if n > 0 and n <= len(token):
+            ngrams = [' '.join(token[i-n:i]) for i in range(n, len(token) + 1)]
+            text_features.extend(ngrams)
+
+    # Punctuation Features
+    text_punc = re.sub(r'[a-z0-9]', ' ', lower_text)
+    text_features.extend(text_punc.split())
+    
+    return Counter(text_features)
+
+# --- 4. PREDICTION LOGIC ---
+
+def predict_emotion(text: str, model: Any, vectorizer: Any) -> str:
+    """Processes text and returns the predicted emotion label."""
+    if not text:
+        return "Please enter text for analysis."
+
+    # 1. Convert Text to Features (Counter object)
+    feature_counter = create_feature(text, N_GRAM_RANGE)
+    
+    # 2. Vectorization (DictVectorizer expects a list of dictionaries/Counters)
+    # The saved vectorizer is used to ensure the features are ordered correctly.
+    X_processed = vectorizer.transform([feature_counter]) 
+    
+    # 3. Make Prediction
+    prediction = model.predict(X_processed)
+    
+    return prediction[0]
+
+# --- 5. STREAMLIT UI ---
+
+# Load the model artifacts
+model, vectorizer = load_artifacts()
+
+if model and vectorizer:
+    st.title("🗣️ Text Emotion Detection App")
+    st.markdown("Enter a sentence or text below to see the predicted emotion.")
+    
+    # User input area
+    user_input = st.text_area("Enter your text here:", "")
+    
+    if st.button("Predict Emotion"):
+        if user_input:
+            # Perform prediction
+            result = predict_emotion(user_input, model, vectorizer)
+            
+            # --- Result Display (Using visual cues) ---
+            st.subheader("Analysis Result")
+            
+            # Simple color-coding based on common emotions
+            if result == 'joy':
+                st.success(f"Predicted Emotion: **{result.upper()}** 🎉")
+            elif result in ['sadness', 'fear']:
+                st.warning(f"Predicted Emotion: **{result.upper()}** 😟")
+            elif result == 'anger':
+                st.error(f"Predicted Emotion: **{result.upper()}** 😡")
+            elif result == 'disgust':
+                st.markdown(f"Predicted Emotion: **{result.upper()}** 🤢", unsafe_allow_html=True)
+            else:
+                st.info(f"Predicted Emotion: **{result.upper()}**")
+        else:
+            st.warning("Please enter some text to predict.")