src/prediction_compile.py

import streamlit as st
import os
import re
import pickle
import joblib
import nltk
import numpy as np
import pandas as pd
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow import keras
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.stem import PorterStemmer
from huggingface_hub import hf_hub_download

# =============================================
# Setup NLTK with container-safe path
# =============================================
nltk_data_path = os.path.join("/tmp", "nltk_data")
os.makedirs(nltk_data_path, exist_ok=True)
nltk.data.path.append(nltk_data_path)
nltk.download("stopwords", download_dir=nltk_data_path)
nltk.download("punkt", download_dir=nltk_data_path)

# =============================================
# HF Hub repo
# =============================================
repo_id = "BesottenJenny/acre-sentiment-models"

# =============================================
# Cached loading functions
# =============================================
@st.cache_resource
def load_sentiment_model():
    path = hf_hub_download(repo_id=repo_id, filename="best_model.keras")
    return keras.models.load_model(path)

@st.cache_resource
def load_tokenizer_params():
    tokenizer_path = hf_hub_download(repo_id=repo_id, filename="tokenizer.pkl")
    params_path = hf_hub_download(repo_id=repo_id, filename="params.pkl")
    with open(tokenizer_path, "rb") as f:
        tokenizer = pickle.load(f)
    with open(params_path, "rb") as f:
        params = pickle.load(f)
    return tokenizer, params

@st.cache_resource
def load_topic_models():
    neg_path = hf_hub_download(repo_id=repo_id, filename="fastopic_negative_model.pkl")
    pos_path = hf_hub_download(repo_id=repo_id, filename="fastopic_positive_model.pkl")
    neg_model = joblib.load(neg_path)
    pos_model = joblib.load(pos_path)
    return neg_model, pos_model

# Load models
sentiment_model = load_sentiment_model()
tokenizer, params = load_tokenizer_params()
topic_model_neg, topic_model_pos = load_topic_models()
max_len = params["max_len"]

# =============================================
# Text preprocessing
# =============================================
negations = {"not", "no", "never"}
stpwrds_en = set(stopwords.words("english")) - negations
stemmer = PorterStemmer()

replacements = {
    "sia": "sq",
    "flown": "fly",
    "flew": "fly",
    "alway": "always",
    "boarding": "board",
    "told": "tell",
    "said": "say",
    "booked": "book",
    "paid": "pay",
    "well": "good",
    "aircraft": "plane"
}

def text_preprocessing(text):
    text = text.lower()
    text = re.sub(r"\n", " ", text)
    text = text.strip()
    text = re.sub(r'[^a-z0-9\s]', ' ', text)
    tokens = word_tokenize(text)
    tokens = [replacements.get(word, word) for word in tokens]
    tokens = [word for word in tokens if word not in stpwrds_en]
    tokens = [stemmer.stem(word) for word in tokens]
    return "emptytext" if len(tokens) == 0 else ' '.join(tokens)

# =============================================
# Streamlit App
# =============================================
def run():
    st.title("ACRE - Automated Customer Review Analysis")
    st.subheader("Sentiment & Topic Prediction for SQ Customer Reviews")
    st.markdown(
        "Enter a customer review below to predict sentiment and topic."
    )

    with st.form(key='review_form'):
        text = st.text_area("Customer Review", value="--customer review--")
        submitted = st.form_submit_button("Predict")

    if submitted:
        processed = text_preprocessing(text)
        seq = tokenizer.texts_to_sequences([processed])
        padded = pad_sequences(seq, maxlen=max_len, padding="post", truncating="post")

        # Sentiment
        pred_probs = sentiment_model.predict(padded)
        pred_class = np.argmax(pred_probs, axis=1)[0]
        confidence = float(np.max(pred_probs))
        label_map = {0: "Negative", 1: "Positive"}
        sentiment_label = label_map[pred_class]

        st.write(f"**Sentiment:** {sentiment_label} (Confidence: {confidence:.2f})")

        # Topic Modeling
        if sentiment_label == "Negative":
            result = topic_model_neg.transform([text])
        else:
            result = topic_model_pos.transform([text])

        topics, probs = result
        st.write(f"**Topic ID(s):** {topics}")
        st.write(f"**Probabilities:** {probs.tolist()}")

if __name__ == "__main__":
    run()