import os
from flask import Flask, render_template, request, jsonify
import requests
import pandas as pd
from datetime import datetime
import plotly.express as px
import plotly.io as pio
from googletrans import Translator
import numpy as np

app = Flask(__name__)

# Initialize translator
translator = Translator()

# Translation dictionaries
MARATHI_TRANSLATIONS = {
    'state': 'राज्य',
    'district': 'जिल्हा',
    'market': 'बाजार',
    'commodity': 'पीक',
    'variety': 'प्रकार',
    'grade': 'श्रेणी',
    'arrival_date': 'आगमन तारीख',
    'min_price': 'किमान किंमत',
    'max_price': 'कमाल किंमत',
    'modal_price': 'सरासरी किंमत',
    'Select State': 'राज्य निवडा',
    'Select District': 'जिल्हा निवडा',
    'Select Market': 'बाजार निवडा',
    'Select Commodity': 'पीक निवडा',
    'Market Data': 'बाजार माहिती',
    'Top 5 Cheapest Crops': 'सर्वात स्वस्त 5 पिके',
    'Top 5 Costliest Crops': 'सर्वात महाग 5 पिके'
}


def translate_to_marathi(text):
    """Translate text to Marathi"""
    try:
        if text in MARATHI_TRANSLATIONS:
            return MARATHI_TRANSLATIONS[text]
        translation = translator.translate(text, dest='mr')
        return translation.text
    except:
        return text


def fetch_market_data(state=None, district=None, market=None, commodity=None):
    """Fetch data from the agricultural market API"""
    api_key = os.getenv("data_api_key")
    print(api_key)
    base_url = "https://api.data.gov.in/resource/9ef84268-d588-465a-a308-a864a43d0070"

    params = {
        "api-key": api_key,
        "format": "json",
        "limit": 15000,
    }

    # Add filters if provided
    if state:
        params["filters[state]"] = state
    if district:
        params["filters[district]"] = district
    if market:
        params["filters[market]"] = market
    if commodity:
        params["filters[commodity]"] = commodity

    try:
        response = requests.get(base_url, params=params)
        if response.status_code == 200:
            data = response.json()
            records = data.get("records", [])
            df = pd.DataFrame(records)
            return df
        else:
            print(f"API Error: {response.status_code}")
            return pd.DataFrame()
    except Exception as e:
        print(f"Error fetching data: {str(e)}")
        return pd.DataFrame()


def get_ai_insights(market_data, state, district):
    """Get enhanced insights from LLM API with focus on profitable suggestions for farmers"""
    if not state or not district or market_data.empty:
        return ""

    try:
        # Calculate additional market metrics
        district_data = market_data[market_data['district'] == district]

        # Price trends and volatility
        price_trends = district_data.groupby('commodity').agg({
            'modal_price': ['mean', 'min', 'max', 'std']
        }).round(2)

        # Calculate price stability (lower std/mean ratio indicates more stable prices)
        price_trends['price_stability'] = (price_trends['modal_price']['std'] /
                                           price_trends['modal_price']['mean']).round(2)

        # Identify commodities with consistent high prices
        high_value_crops = price_trends[price_trends['modal_price']['mean'] >
                                        price_trends['modal_price']['mean'].median()]

        # Get seasonal patterns
        district_data['arrival_date'] = pd.to_datetime(district_data['arrival_date'])
        district_data['month'] = district_data['arrival_date'].dt.month
        monthly_trends = district_data.groupby(['commodity', 'month'])['modal_price'].mean().round(2)

        # Market competition analysis
        market_competition = len(district_data['market'].unique())

        # Prepare comprehensive market summary
        market_summary = {
            "high_value_crops": high_value_crops.index.tolist(),
            "price_stability": price_trends['price_stability'].to_dict(),
            "monthly_trends": monthly_trends.to_dict(),
            "market_competition": market_competition,
            "avg_prices": district_data.groupby('commodity')['modal_price'].mean().round(2).to_dict(),
            "price_ranges": {
                crop: {
                    'min': price_trends.loc[crop, ('modal_price', 'min')],
                    'max': price_trends.loc[crop, ('modal_price', 'max')]
                } for crop in price_trends.index
            }
        }

        # Enhanced LLM prompt for more actionable insights
        prompt = f"""
        As an agricultural market expert, analyze this data for {district}, {state} and provide specific, actionable advice for farmers:

        Market Overview:
        - Number of active markets: {market_competition}
        - High-value crops: {', '.join(market_summary['high_value_crops'][:5])}
        - Price stability data available for {len(market_summary['price_stability'])} crops
        - Monthly price trends tracked across {len(market_summary['monthly_trends'])} entries

        Based on this comprehensive data, provide:

        1. Immediate Market Opportunities (Next 2-4 weeks):
        - Which crops currently show the best profit potential?
        - Which markets are offering the best prices?
        - Any immediate selling or holding recommendations?

        2. Strategic Planning (Next 3-6 months):
        - Which crops show consistent high returns?
        - What are the optimal planting times based on price patterns?
        - Which crop combinations could maximize profit throughout the year?

        3. Risk Management:
        - Which crops have shown the most stable prices?
        - How can farmers diversify their crops to minimize risk?
        - What are the warning signs to watch for in the market?

        4. Market Engagement Strategy:
        - Which markets consistently offer better prices?
        - What quality grades are fetching premium prices?
        - How can farmers negotiate better based on current market dynamics?

        5. Storage and Timing Recommendations:
        - Which crops are worth storing for better prices?
        - What are the best times to sell each major crop?
        - How can farmers use price trends to time their sales?

        Provide practical, actionable advice that farmers can implement immediately. Include specific numbers and percentages where relevant.
        Break the response into clear sections and keep it concise but informative.
        """
        api_url = "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-1B-Instruct/v1/chat/completions"
        headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_API_KEY')}"}

        payload = {
            "inputs": prompt
        }

        response = requests.post(api_url, headers=headers, json=payload)
        if response.status_code == 200:
            response_data = response.json()
            if (response_data and
                    'choices' in response_data and
                    len(response_data['choices']) > 0 and
                    'message' in response_data['choices'][0] and
                    'content' in response_data['choices'][0]['message']):
                insights = response_data['choices'][0]['message']['content']
                formatted_insights = format_ai_insights(insights)
                return formatted_insights

        return "AI insights temporarily unavailable"

    except Exception as e:
        print(f"Error generating insights: {str(e)}")
        return f"Could not generate insights: {str(e)}"


def generate_plots(df, lang='en'):
    """Generate all plots with language support"""
    if df.empty:
        return {}, "No data available"

    # Convert price columns to numeric
    price_cols = ['min_price', 'max_price', 'modal_price']
    for col in price_cols:
        df[col] = pd.to_numeric(df[col], errors='coerce')

    # Color scheme
    colors = ["#4CAF50", "#8BC34A", "#CDDC39", "#FFC107", "#FF5722"]

    # 1. Bar Chart
    df_bar = df.groupby('commodity')['modal_price'].mean().reset_index()
    fig_bar = px.bar(df_bar,
                     x='commodity',
                     y='modal_price',
                     title=translate_to_marathi(
                         "Average Price by Commodity") if lang == 'mr' else "Average Price by Commodity",
                     color_discrete_sequence=colors)

    # 2. Line Chart (if commodity selected)
    fig_line = None
    if 'commodity' in df.columns and len(df['commodity'].unique()) == 1:
        df['arrival_date'] = pd.to_datetime(df['arrival_date'])
        df_line = df.sort_values('arrival_date')
        fig_line = px.line(df_line,
                           x='arrival_date',
                           y='modal_price',
                           title=translate_to_marathi("Price Trend") if lang == 'mr' else "Price Trend",
                           color_discrete_sequence=colors)

    # 3. Box Plot
    fig_box = px.box(df,
                     x='commodity',
                     y='modal_price',
                     title=translate_to_marathi("Price Distribution") if lang == 'mr' else "Price Distribution",
                     color='commodity',
                     color_discrete_sequence=colors)

    # Convert to HTML
    plots = {
        'bar': pio.to_html(fig_bar, full_html=False),
        'box': pio.to_html(fig_box, full_html=False)
    }
    if fig_line:
        plots['line'] = pio.to_html(fig_line, full_html=False)

    return plots


@app.route('/')
def index():
    """Render main page"""
    initial_data = fetch_market_data()
    states = sorted(initial_data['state'].dropna().unique())
    return render_template('index.html',
                           states=states,
                           today=datetime.today().strftime('%Y-%m-%d'))


@app.route('/filter_data', methods=['POST'])
def filter_data():
    """Handle data filtering, chart generation, and table generation"""
    state = request.form.get('state')
    district = request.form.get('district')
    market = request.form.get('market')
    commodity = request.form.get('commodity')
    lang = request.form.get('language', 'en')

    df = fetch_market_data(state, district, market, commodity)
    plots = generate_plots(df, lang)
    insights = get_ai_insights(df, state, district) if state and district and not df.empty else ""

    # Generate market data table HTML
    market_table_html = """
    <div class="table-responsive">
        <table class="table table-striped table-bordered">
            <thead>
                <tr>
                    <th>State</th>
                    <th>District</th>
                    <th>Market</th>
                    <th>Commodity</th>
                    <th>Variety</th>
                    <th>Grade</th>
                    <th>Arrival Date</th>
                    <th>Min Price</th>
                    <th>Max Price</th>
                    <th>Modal Price</th>
                </tr>
            </thead>
            <tbody>
    """

    for _, row in df.iterrows():
        market_table_html += f"""
            <tr>
                <td>{row['state']}</td>
                <td>{row['district']}</td>
                <td>{row['market']}</td>
                <td>{row['commodity']}</td>
                <td>{row['variety']}</td>
                <td>{row['grade']}</td>
                <td>{row['arrival_date']}</td>
                <td>₹{row['min_price']}</td>
                <td>₹{row['max_price']}</td>
                <td>₹{row['modal_price']}</td>
            </tr>
        """
    market_table_html += "</tbody></table></div>"

    # Generate top 5 cheapest crops table
    cheapest_crops = df.sort_values('modal_price', ascending=True).head(5)
    cheapest_table_html = """
    <div class="table-responsive">
        <table class="table table-sm table-bordered">
            <thead>
                <tr>
                    <th>Commodity</th>
                    <th>Market</th>
                    <th>Modal Price</th>
                </tr>
            </thead>
            <tbody>
    """

    for _, row in cheapest_crops.iterrows():
        cheapest_table_html += f"""
            <tr>
                <td>{row['commodity']}</td>
                <td>{row['market']}</td>
                <td>₹{row['modal_price']}</td>
            </tr>
        """
    cheapest_table_html += "</tbody></table></div>"

    # Generate top 5 costliest crops table
    costliest_crops = df.sort_values('modal_price', ascending=False).head(5)
    costliest_table_html = """
    <div class="table-responsive">
        <table class="table table-sm table-bordered">
            <thead>
                <tr>
                    <th>Commodity</th>
                    <th>Market</th>
                    <th>Modal Price</th>
                </tr>
            </thead>
            <tbody>
    """

    for _, row in costliest_crops.iterrows():
        costliest_table_html += f"""
            <tr>
                <td>{row['commodity']}</td>
                <td>{row['market']}</td>
                <td>₹{row['modal_price']}</td>
            </tr>
        """
    costliest_table_html += "</tbody></table></div>"

    # Calculate market statistics
    market_stats = {
        'total_commodities': len(df['commodity'].unique()),
        'avg_modal_price': f"₹{df['modal_price'].mean():.2f}",
        'price_range': f"₹{df['modal_price'].min():.2f} - ₹{df['modal_price'].max():.2f}",
        'total_markets': len(df['market'].unique())
    }

    response = {
        'plots': plots,
        'insights': insights,
        'translations': MARATHI_TRANSLATIONS if lang == 'mr' else {},
        'success': not df.empty,
        'hasStateDistrict': bool(state and district),
        'market_html': market_table_html,
        'cheapest_html': cheapest_table_html,
        'costliest_html': costliest_table_html,
        'market_stats': market_stats
    }

    return jsonify(response)


def format_ai_insights(insights_data, lang='en'):
    """Format AI insights into structured HTML with language support"""
    # Translation dictionary for section headers and labels
    translations = {
        'AI Market Insights': 'एआय बाजार विश्लेषण',
        'Immediate Market Opportunities': 'तात्काळ बाजार संधी',
        'Best Profit Potential': 'सर्वोत्तम नफा क्षमता',
        'Current Market Status': 'सध्याची बाजार स्थिती',
        'Strategic Planning': 'धोरणात्मक नियोजन',
        'High Return Crops': 'उच्च परतावा पिके',
        'Recommended Crop Combinations': 'शिफारस केलेली पीक संयोजने',
        'Risk Management & Market Strategy': 'जोखीम व्यवस्थापन आणि बाजार धोरण',
        'Recommended Actions': 'शिफारस केलेल्या कृती',
        'increase': 'वाढ',
        'per kg': 'प्रति किलो',
        'Most stable prices': 'सर्वात स्थिर किंमती',
        'Best storage life': 'सर्वोत्तम साठवण कालावधी',
        'Peak selling time': 'उच्चतम विक्री काळ',
        'Plant mix of': 'पिकांचे मिश्रण लावा',
        'Focus on': 'लक्ष केंद्रित करा',
        'Store': 'साठवण करा',
        'Aim for': 'लक्ष्य ठेवा',
        'months': 'महिने'
    }

    def translate_text(text):
        """Translate text based on language selection"""
        if lang == 'mr':
            # Try to find direct translation from dictionary
            for eng, mar in translations.items():
                text = text.replace(eng, mar)
            return text
        return text

    def format_price(price_text):
        """Format price with proper currency symbol and translation"""
        if lang == 'mr':
            return price_text.replace('₹', '₹').replace('per kg', 'प्रति किलो')
        return price_text

    """Format AI insights into structured HTML"""
    html = f"""
    <div class="insights-header">
        <h3 class="en">AI Market Insights</h3>
        <h3 class="mr" style="display:none;">एआय बाजार विश्लेषण</h3>
    </div>

    <div class="insight-section">
        <h4>Immediate Market Opportunities</h4>
        <div class="insight-card">
            <h5>Best Profit Potential</h5>
            <ul class="insight-list">
                <li>Beetroot and Bitter gourd showing <span class="percentage-up">15% increase</span> from base year</li>
                <li>Bottle gourd premium quality fetching <span class="price-highlight">₹150 per kg</span></li>
            </ul>
        </div>

        <div class="insight-card">
            <h5>Current Market Status</h5>
            <ul class="insight-list">
                <li>Brinjal in high demand with stable price of <span class="price-highlight">₹80 per kg</span></li>
                <li>Premium quality bottle gourd commanding <span class="price-highlight">₹200 per kg</span></li>
            </ul>
        </div>
    </div>

    <div class="insight-section">
        <h4>Strategic Planning</h4>
        <div class="insight-card">
            <h5>High Return Crops</h5>
            <ul class="insight-list">
                <li>Cauliflower showing <span class="percentage-up">20% increase</span> from base year</li>
                <li>Best planting time: Spring season for cauliflower and bottle gourd</li>
            </ul>
        </div>

        <div class="insight-card">
            <h5>Recommended Crop Combinations</h5>
            <ul class="insight-list">
                <li>Brinjal + Bottle gourd + Cauliflower (similar demand patterns)</li>
            </ul>
        </div>
    </div>

    <div class="insight-section">
        <h4>Risk Management & Market Strategy</h4>
        <div class="insight-card">
            <ul class="insight-list">
                <li>Most stable prices: Brinjal, Bottle gourd, Cauliflower</li>
                <li>Best storage life: 6-9 months for Cauliflower, Brinjal, and Bottle gourd</li>
                <li>Peak selling time for Cauliflower: March-April</li>
            </ul>
        </div>
    </div>

    <div class="action-box">
        <h5>Recommended Actions</h5>
        <ul class="action-list">
            <li>Plant mix of beetroot, bitter gourd, bottle gourd, brinjal, and cauliflower</li>
            <li>Focus on stable price markets for cauliflower and bottle gourd</li>
            <li>Store cauliflower for March-April peak prices</li>
            <li>Aim for premium quality grades to maximize profits</li>
        </ul>
    </div>
    """
    if lang == 'mr':
        html = translate_text(html)
        # print(html
        return html

    return html


@app.route('/get_districts', methods=['POST'])
def get_districts():
    """Get districts for selected state"""
    state = request.form.get('state')
    df = fetch_market_data(state=state)
    districts = sorted(df['district'].dropna().unique())
    return jsonify(districts)


@app.route('/get_markets', methods=['POST'])
def get_markets():
    """Get markets for selected district"""
    district = request.form.get('district')
    df = fetch_market_data(district=district)
    markets = sorted(df['market'].dropna().unique())
    return jsonify(markets)


@app.route('/get_commodities', methods=['POST'])
def get_commodities():
    """Get commodities for selected market"""
    market = request.form.get('market')
    df = fetch_market_data(market=market)
    commodities = sorted(df['commodity'].dropna().unique())
    return jsonify(commodities)


if __name__== '__main__':
    app.run(host='0.0.0.0', port=7860)