src/streamlit_app.py

from flask import Flask, request, jsonify, send_from_directory
import pandas as pd
import torch
from transformers import BertTokenizer, BertForSequenceClassification
from wordcloud import WordCloud
import uuid
import io
import base64
import os
from PIL import Image

app = Flask(__name__)
UPLOAD_FOLDER = "uploads"
# os.makedirs(UPLOAD_FOLDER, exist_ok=True)

@app.route('/uploads/<filename>')
def uploaded_file(filename):
    return send_from_directory(app.config['UPLOAD_FOLDER'], filename)

# Load model and tokenizer once
tokenizer = BertTokenizer.from_pretrained("bert-base-multilingual-cased")
model_path = "./src/emotion_final_model"
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = BertForSequenceClassification.from_pretrained(model_path).to(device)
model.eval()

# Label Mapping
label_mapping = {0: "negative", 1: "neutral", 2: "positive"}

@app.route('/predict', methods=['POST'])
def predict():
    data = request.get_json()
    text = data.get('text')

    if not text:
        return jsonify({"error": "No text provided"}), 400

    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
    inputs = {key: value.to(device) for key, value in inputs.items()}

    with torch.no_grad():
        outputs = model(**inputs)

    logits = outputs.logits
    predicted_class_idx = torch.argmax(logits, dim=-1).item()
    sentiment = label_mapping[predicted_class_idx]

    return jsonify({"sentiment": sentiment})

aspect_keywords = {
    "Quality": ["quality", "material", "durable", "performance", "sturdy", "broken", "defective", "معیار", "ٹوٹا ہوا", "خراب"],
    "Price": ["price", "cheap", "expensive", "value", "cost", "قیمت", "مہنگا", "سستا", "قیمت زیادہ"],
    "Delivery": ["delivery", "shipping", "arrived", "late", "courier", "ترسیل", "شپنگ", "تاخیر", "دیر سے پہنچا"],
    "Usability": ["easy to use", "setup", "installation", "instructions", "user-friendly", "آسان", "استعمال میں آسان", "سیٹ اپ", "تنصیب"],
    "Design": ["design", "style", "appearance", "color", "looks", "ڈیزائن", "خوبصورتی", "رنگ", "ساخت"],
    "Warranty/Support": ["warranty", "support", "return", "replacement", "service center", "وارنٹی", "واپسی", "تبادلہ", "سروس سینٹر"]
}

def detect_aspects(text):
    text_lower = text.lower()
    detected = []
    for aspect, keywords in aspect_keywords.items():
        if any(keyword in text_lower for keyword in keywords):
            detected.append(aspect)
    return detected

@app.route("/analyze", methods=["POST"])
def analyze():
    if 'file' not in request.files:
        return jsonify({"error": "No file uploaded"}), 400
    file = request.files['file']
    print(file.filename)
    df = pd.read_csv(file)
    print(df.to_string())
    total_positive = 0
    total_negative = 0
    total_neutral = 0
    all_text = ""
    # Aspect summary
    aspect_summary = {aspect: {"positive": 0, "negative": 0, "neutral": 0, "total": 0} for aspect in aspect_keywords}
    for text in df['Review'].dropna():
        inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
        inputs = {k: v.to(device) for k, v in inputs.items()}

        with torch.no_grad():
            outputs = model(**inputs)

        predicted_class_idx = torch.argmax(outputs.logits, dim=-1).item()
        sentiment = label_mapping[predicted_class_idx]

        if sentiment == "positive":
            total_positive += 1
        elif sentiment == "negative":
            total_negative += 1
        else:
            total_neutral += 1

        all_text += " " + text

        detected_aspects = detect_aspects(text)
        for aspect in detected_aspects:
            aspect_summary[aspect][sentiment] += 1
            aspect_summary[aspect]["total"] += 1

    # Generate WordCloud
    wordcloud = WordCloud(width=800, height=400, background_color='white', font_path='src/urdu_font.ttf').generate(all_text)

    # Save in uploads folder
    # if not os.path.exists("uploads"):
    #     os.makedirs("uploads")

    wordcloud_path = os.path.join("uploads", f"wordcloud{uuid.uuid4()}.png")
    wordcloud.to_file(wordcloud_path)

    # Convert image to base64
    with open(wordcloud_path, "rb") as image_file:
        encoded_image = base64.b64encode(image_file.read()).decode('utf-8')

    print({
        "total_positive": total_positive,
        "total_negative": total_negative,
        "total_neutral": total_neutral,
        "aspect_summary": aspect_summary,
        "wordcloud_image_path": wordcloud_path,
    })

    return jsonify({
        "total_positive": total_positive,
        "total_negative": total_negative,
        "total_neutral": total_neutral,
        "aspect_summary": aspect_summary,
        "wordcloud_image_path": wordcloud_path,
        # "wordcloud_image_base64": encoded_image
    })

def run_flask():
    app.run(host="0.0.0.0", port=5000)

import threading
threading.Thread(target=run_flask).start()

import streamlit as st
import pandas as pd
import plotly.express as px
from io import BytesIO, StringIO
from PIL import Image
import random
import requests
import os
import uuid
import tempfile

API_URL = 'http://127.0.0.1:5000/analyze'

# -------------------
# PAGE CONFIG & THEME
# -------------------
st.set_page_config(
    page_title="Multilingual Sentiment Analyzer", 
    layout="wide"
)

st.markdown("""
    <style>
        /* Light theme override */
        html, body, .stApp {
            background-color: #ffffff !important;
            color: #000000 !important;
        }

        h1, h2, h3, h4, h5, h6, p, div, span, label, section, .markdown-text-container {
            color: #000000 !important;
        }

        .stFileUploader > div, .stFileUploader div div {
            background-color: #f9f9f9 !important;
            border: 1px solid #ccc !important;
            color: #000000 !important;
        }
    </style>
""", unsafe_allow_html=True)

st.markdown("""
    <div style='text-align: center; padding-top: 10px;'>
        <h1 style='font-size: 40px;'>🌍 Multilingual Sentiment Analysis Dashboard</h1>
        <p style='font-size: 18px; color: #ccc; max-width: 720px; margin: auto;'>
    Upload a CSV to explore sentiment Report. With sentiment analysis, you can catch early signals, reduce risk, and validate market fit — even across global audiences.
        </p>
    </div>
""", unsafe_allow_html=True)

# -------------------
# DUMMY DATA FUNCTION
# -------------------
def load_dummy_data():
    return pd.DataFrame({
        "Review": [
            "La livraison était très rapide et le service excellent.",
            "The product quality was terrible, I want a refund.",
            "Servicio al cliente fue amable pero no resolvieron mi problema.",
            "Das Produkt kam beschädigt an und der Support war unhöflich.",
            "Great value for the price, I'm very happy!",
            "Muy mal embalaje, pero el envío fue rápido.",
            "客服很好，但产品描述不准确。",
            "Perfect fit, just as described. Will buy again!"
        ]
    })

# -------------------
# MAIN UPLOAD BLOCK (VISIBLE)
# -------------------
with st.expander("📁 Upload Your CSV File", expanded=True):
    uploaded_file = st.file_uploader("Choose a CSV file with reviews", type=["csv"])
    # Analysis button moved here, right after file upload
    run_analysis = st.button("🚀 Run Analysis", type="primary")

    # Load Data: Uploaded or Dummy
    if uploaded_file:
        try:
            # Read uploaded CSV file
            df = pd.read_csv(uploaded_file)
            if df.empty:
                st.error("The uploaded CSV file is empty.")
                df = load_dummy_data()
            else:
                st.success("✅ File uploaded successfully!")
        except Exception as e:
            st.error(f"Error reading CSV: {e}")
            df = load_dummy_data()
    else:
        st.info("Using built-in demo data. Upload a CSV to use your own.")
        df = load_dummy_data()
    
    # Preview data
    st.write("✅ App is running! Here's a sample:")
    st.dataframe(df.head())
    
    # Column selection
    # text_column = st.selectbox("📝 Select the column with review text:", df.columns)
    # enable_aspect = st.checkbox("🔍 Include Aspect Report (Optional)", value=True)
    text_column = 'Review'
    enable_aspect = True

# -------------------
# SENTIMENT METRICS
# -------------------
st.markdown("---")
st.markdown("### 🔎 Sentiment Analysis Results")

# MOCK SENTIMENT PREDICTION
def fake_sentiment_predict(text):
    return random.choice(["Positive", "Negative", "Neutral"]), round(random.uniform(0.65, 0.99), 2)

# Store the analyzed dataframe in session state
if 'analyzed_df' not in st.session_state:
    st.session_state.analyzed_df = df.copy()

# Initialize variables
positive, negative, neutral, total = 0, 0, 0, 0

# Process the data when the Run Analysis button is clicked
if run_analysis:
    if not enable_aspect:
        # Use fake predictions if not calling the API
        fake_results = [fake_sentiment_predict(text) for text in df[text_column]]
        sentiments, confidences = zip(*fake_results)
        
        # Update the analyzed dataframe
        st.session_state.analyzed_df = df.copy()
        st.session_state.analyzed_df["Sentiment"] = sentiments
        st.session_state.analyzed_df["Confidence"] = confidences

        # Count sentiment
        sentiment_counts = pd.Series(sentiments).value_counts()
        positive = sentiment_counts.get("Positive", 0)
        negative = sentiment_counts.get("Negative", 0)
        neutral = sentiment_counts.get("Neutral", 0)
        total = positive + negative + neutral
    else:
        # API Call will be made - handled below
        pass

def percent(part):
    return f"{round((part / total) * 100)}%" if total else "0%"

# Layout: Cards + Chart
card_col, chart_col = st.columns([1.2, 2])

with card_col:
    st.markdown("""
    <style>
    .card-container {
        max-width: 10px;
        margin: 0 auto;
    }
    .card {
        padding: 10px;
        border-radius: 12px;
        margin-bottom: 10px;
        font-size: 16px;
        font-weight: 500;
        line-height: 1.5;
        background-color: var(--secondary-background-color);
        border: 1px solid rgba(255,255,255,0.15);
        color: white;
        text-align: center;
    }
    .card strong {
        font-size: 20px;
        display: block;
        margin-top: 5px;
    }
    </style>
    <div class="card-container">
    """, unsafe_allow_html=True)

if total > 0:  # Only display chart if we have data
    with chart_col:
        fig = px.pie(
            names=["Positive", "Negative", "Neutral"],
            values=[positive, negative, neutral],
            color_discrete_map={
                "Positive": "#66bb6a",
                "Negative": "#ef5350",
                "Neutral": "#42a5f5"
            }
        )
        fig.update_traces(
            textinfo='percent+label',
            hoverinfo='label+percent+value',
            pull=[0.03, 0.03, 0.03]
        )
        fig.update_layout(
            margin=dict(t=20, b=20, l=10, r=10),
            paper_bgcolor="rgba(0,0,0,0)",
            plot_bgcolor="rgba(0,0,0,0)",
            font_color="white"
        )
        st.plotly_chart(fig, use_container_width=True)

# -------------------
# ASPECT REPORT (API Call)
# -------------------
if run_analysis and enable_aspect:
    st.subheader("📌 Aspect Sentiment Summary")

    with st.spinner("Fetching Aspect Report from API..."):
        try:
            # Create a dataframe with only the text column
            api_df = df.copy()
            
            # Create a unique filename with UUID
            unique_filename = f"temp_reviews_{uuid.uuid4()}.csv"
            
            # Write to a physical temporary file with UUID in name
            with tempfile.NamedTemporaryFile(delete=False, suffix=unique_filename) as tmp:
                api_df.to_csv(tmp.name, index=False)
                tmp_file_path = tmp.name
            
            # Open the file in binary mode
            with open(tmp_file_path, 'rb') as file:
                # Send the actual file
                files = {'file': (unique_filename, file, 'text/csv')}
                
                response = requests.post(API_URL, files=files)
            
            # Clean up temporary file
            try:
                os.unlink(tmp_file_path)
            except:
                pass  # Silently fail if we can't delete the temp file
            
            if response.status_code == 200:
                response_json = response.json()

                # Store API response in session state
                st.session_state.api_response_json = response_json
                
                # Update metrics from API response
                positive = response_json.get("total_positive", 0)
                negative = response_json.get("total_negative", 0)
                neutral = response_json.get("total_neutral", 0)
                total = positive + negative + neutral
                
                # Calculate percentages for Excel report if not provided by API
                if "positive_percentage" not in response_json and total > 0:
                    response_json["positive_percentage"] = round((positive / total) * 100)
                    response_json["negative_percentage"] = round((negative / total) * 100)
                    response_json["neutral_percentage"] = round((neutral / total) * 100)
                
                # Add total reviews to response_json if not present
                if "total_reviews" not in response_json:
                    response_json["total_reviews"] = total
                
                # Update metrics from API response
                positive = response_json.get("total_positive", 0)
                negative = response_json.get("total_negative", 0)
                neutral = response_json.get("total_neutral", 0)
                total = positive + negative + neutral
                
                # Update the metrics cards with new data
                with card_col:
                    st.markdown(f"""
                    <div class="card" style="border-color:#bfbfbf;">
                        📊 <strong>Total Reviews</strong>
                        {total}
                    </div>
                    <div class="card" style="border-color:#66bb6a;">
                        ✅ <strong>{positive} Positive</strong>
                        {percent(positive)} of total
                    </div>
                    <div class="card" style="border-color:#ef5350;">
                        ❗ <strong>{negative} Negative</strong>
                        {percent(negative)} of total
                    </div>
                    <div class="card" style="border-color:#42a5f5;">
                        😐 <strong>{neutral} Neutral</strong>
                        {percent(neutral)} of total
                    </div>
                    </div>
                    """, unsafe_allow_html=True)
                
                # Update the pie chart
                with chart_col:
                    fig = px.pie(
                        names=["Positive", "Negative", "Neutral"],
                        values=[positive, negative, neutral],
                        color_discrete_map={
                            "Positive": "#66bb6a",
                            "Negative": "#ef5350",
                            "Neutral": "#42a5f5"
                        }
                    )
                    fig.update_traces(
                        textinfo='percent+label',
                        hoverinfo='label+percent+value',
                        pull=[0.03, 0.03, 0.03]
                    )
                    fig.update_layout(
                        margin=dict(t=20, b=20, l=10, r=10),
                        paper_bgcolor="rgba(0,0,0,0)",
                        plot_bgcolor="rgba(0,0,0,0)",
                        font_color="white"
                    )
                    st.plotly_chart(fig, use_container_width=True)

                # Update the analyzed dataframe with sentiment results from API
                if "review_details" in response_json:
                    # Create a new dataframe from the API results
                    api_result_df = pd.DataFrame(response_json["review_details"])
                    
                    # Store it in session state
                    st.session_state.analyzed_df = api_result_df
                else:
                    # If review_details not provided, create basic sentiment columns
                    st.session_state.analyzed_df = df.copy()
                    # Try to extract sentiments if available in the API response
                    if "sentiments" in response_json:
                        st.session_state.analyzed_df["Sentiment"] = response_json["sentiments"]
                    # Add any other available result fields
                    for key in ["confidences", "languages"]:
                        if key in response_json:
                            column_name = key.rstrip("s").capitalize()  # Convert "confidences" to "Confidence"
                            st.session_state.analyzed_df[column_name] = response_json[key]

                # Prepare aspect DataFrame
                aspect_rows = []
                for aspect, values in response_json["aspect_summary"].items():
                    aspect_rows.append({
                        "Aspect": aspect,
                        "Positive": values["positive"],
                        "Negative": values["negative"],
                        "Neutral": values["neutral"],
                        "Total": values["total"]
                    })
                aspect_df = pd.DataFrame(aspect_rows)
                
                # Display aspect data if we have any
                if not aspect_df.empty and aspect_df["Total"].sum() > 0:

                    # Store aspect dataframe in session state
                    st.session_state.aspect_dataframe = aspect_df
                    st.dataframe(aspect_df)

                    # Prepare data for bar chart
                    melted = aspect_df.melt(
                        id_vars="Aspect",
                        value_vars=["Positive", "Negative", "Neutral"],
                        var_name="Sentiment",
                        value_name="Count"
                    )

                    col1, col2 = st.columns([4, 2]) 

                    with col1:
                        st.markdown("### 📊 Sentiment by Aspect")
                        bar_chart = px.bar(
                            melted,
                            x="Aspect",
                            y="Count",
                            color="Sentiment",
                            barmode="group",
                            title=None,
                            color_discrete_map={
                                "Positive": "#66bb6a",
                                "Negative": "#ef5350",
                                "Neutral": "#42a5f5"
                            }
                        )
                        # Update chart theme for dark mode
                        bar_chart.update_layout(
                            paper_bgcolor="rgba(0,0,0,0)",
                            plot_bgcolor="rgba(0,0,0,0)",
                            font_color="white",
                            xaxis=dict(gridcolor="rgba(255,255,255,0.1)"),
                            yaxis=dict(gridcolor="rgba(255,255,255,0.1)")
                        )
                        st.plotly_chart(bar_chart, use_container_width=True)

                    with col2:
                        st.markdown("### 🌀 Review Keywords")

                        # Try to display wordcloud from API
                        if "wordcloud_image_base64" in response_json:
                            import base64
                            st.markdown("<div style='padding-top:60px'></div>", unsafe_allow_html=True)
                            st.image(
                                BytesIO(base64.b64decode(response_json["wordcloud_image_base64"])),
                                caption="Keyword Cloud", 
                                use_container_width=True
                            )
                        else:
                            try:
                                # Try local wordcloud file as fallback
                                wordcloud_path = response_json.get("wordcloud_image_path")
                                if wordcloud_path and os.path.exists(wordcloud_path):
                                    image = Image.open(wordcloud_path)
                                    st.markdown("<div style='padding-top:60px'></div>", unsafe_allow_html=True)
                                    st.image(image, caption="Keywords", use_container_width=True)
                                else:
                                    # Try default wordcloud
                                    if os.path.exists("wordcloud.jpg"):
                                        image = Image.open("wordcloud.jpg")
                                        st.markdown("<div style='padding-top:60px'></div>", unsafe_allow_html=True)
                                        st.image(image, caption="Keywords", use_container_width=True)
                            except Exception as e:
                                st.warning(f"⚠ Word cloud image not found: {e}")
                else:
                    st.info("No aspects detected in the reviews.")
            else:
                st.error(f"API Error: {response.status_code} - {response.text}")
        except Exception as e:
            st.error(f"API call failed: {e}")
            import traceback
            st.code(traceback.format_exc(), language="python")


# -------------------
# DOWNLOAD BUTTON
# -------------------
if run_analysis or total > 0:
    st.subheader("📥 Download Analyzed File")

    def generate_excel_report(df, aspect_data=None, response_json=None):
        output = BytesIO()
        
        with pd.ExcelWriter(output, engine='xlsxwriter') as writer:
            # Sheet 1: Main sentiment results
            df.to_excel(writer, index=False, sheet_name='Sentiment_Report')
            
            # Sheet 2: Aspect analysis (if available)
            if aspect_data is not None and not aspect_data.empty:
                aspect_data.to_excel(writer, index=False, sheet_name='Aspect_Analysis')
            
            # Sheet 3: Summary stats (if API response available)
            if response_json:
                # Create a summary dataframe
                summary_data = {
                    'Metric': ['Total Reviews', 'Positive', 'Negative', 'Neutral'],
                    'Count': [
                        response_json.get('total_reviews', 0),
                        response_json.get('total_positive', 0),
                        response_json.get('total_negative', 0),
                        response_json.get('total_neutral', 0)
                    ],
                    'Percentage': [
                        '100%',
                        f"{response_json.get('positive_percentage', 0)}%",
                        f"{response_json.get('negative_percentage', 0)}%",
                        f"{response_json.get('neutral_percentage', 0)}%"
                    ]
                }
                summary_df = pd.DataFrame(summary_data)
                summary_df.to_excel(writer, index=False, sheet_name='Summary')
                
                # Add any other relevant data from API response
                if 'review_details' in response_json:
                    details_df = pd.DataFrame(response_json['review_details'])
                    details_df.to_excel(writer, index=False, sheet_name='Review_Details')
            
            # Get workbook and add some formatting
            workbook = writer.book
            
            # Add formatting
            header_format = workbook.add_format({
                'bold': True,
                'text_wrap': True,
                'valign': 'top',
                'border': 1
            })
            
            # Apply formatting to each worksheet safely
            for sheet_name in writer.sheets:
                worksheet = writer.sheets[sheet_name]
                # Get column names from the DataFrame based on sheet name
                if sheet_name == 'Sentiment_Report':
                    columns = df.columns
                elif sheet_name == 'Aspect_Analysis' and aspect_data is not None:
                    columns = aspect_data.columns
                elif sheet_name == 'Summary':
                    columns = summary_data.keys()
                elif sheet_name == 'Review_Details' and 'review_details' in response_json:
                    columns = details_df.columns
                else:
                    continue
                    
                # Write headers with formatting
                for col_num, value in enumerate(columns):
                    worksheet.write(0, col_num, value, header_format)
                
                # Auto-adjust columns' width (supported in newer versions)
                try:
                    worksheet.autofit()
                except AttributeError:
                    # Fallback for older xlsxwriter versions
                    for col_num, value in enumerate(columns):
                        # Set width based on header content
                        worksheet.set_column(col_num, col_num, max(10, len(str(value)) + 2))
        
        return output.getvalue()

    # Store API response in session state to access it for download
    if 'api_response_json' not in st.session_state:
        st.session_state.api_response_json = None
    if 'aspect_dataframe' not in st.session_state:
        st.session_state.aspect_dataframe = None

    # Update these values when API response is received
    if run_analysis and enable_aspect and 'response_json' in locals():
        st.session_state.api_response_json = response_json
        if 'aspect_df' in locals() and not aspect_df.empty:
            st.session_state.aspect_dataframe = aspect_df

    st.download_button(
        label="📥 Download Results as Excel",
        data=generate_excel_report(
            st.session_state.analyzed_df,  # Use the analyzed dataframe instead of original df
            st.session_state.aspect_dataframe, 
            st.session_state.api_response_json
        ),
        file_name="sentiment_analysis_report.xlsx",
        mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
    )

# Add a footer with dark theme
st.markdown("""
<div style="text-align: center; margin-top: 50px; padding: 20px; color: #888; font-size: 14px;">
    <p>Multilingual Sentiment Analysis Dashboard | Made with Streamlit</p>
</div>
""", unsafe_allow_html=True)