import streamlit as st
import requests
import os
import json
import pandas as pd
import time
import matplotlib.pyplot as plt

# Function to call the Together AI model
def call_ai_model(all_message):
    url = "https://api.together.xyz/v1/chat/completions"
    payload = {
        "model": "NousResearch/Nous-Hermes-2-Yi-34B",
        "temperature": 1.05,
        "top_p": 0.9,
        "top_k": 50,
        "repetition_penalty": 1,
        "n": 1,
        "messages": [{"role": "user", "content": all_message}],
        "stream_tokens": True,
    }

    TOGETHER_API_KEY = os.getenv('TOGETHER_API_KEY')
    if TOGETHER_API_KEY is None:
        raise ValueError("TOGETHER_API_KEY environment variable not set.")
    
    headers = {
        "accept": "application/json",
        "content-type": "application/json",
        "Authorization": f"Bearer {TOGETHER_API_KEY}",
    }

    response = requests.post(url, json=payload, headers=headers, stream=True)
    response.raise_for_status()  # Ensure HTTP request was successful

    return response

# Function to request numeric performance data from AI
def get_numeric_performance_data(temperature):
    all_message = (
        f"Provide the expected numeric sports performance value (as a score) at a temperature of {temperature}°C."
    )
    response = call_ai_model(all_message)
    generated_text = ""
    for line in response.iter_lines():
        if line:
            line_content = line.decode('utf-8')
            if line_content.startswith("data: "):
                line_content = line_content[6:]  # Strip "data: " prefix
            try:
                json_data = json.loads(line_content)
                if "choices" in json_data:
                    delta = json_data["choices"][0]["delta"]
                    if "content" in delta and delta["content"].strip().replace('.', '', 1).isdigit():
                        return float(delta["content"].strip())
            except json.JSONDecodeError:
                continue
    return None

# Streamlit app layout
st.title("Climate Impact on Sports Performance and Infrastructure")
st.write("Analyze and visualize the impact of climate conditions on sports performance and infrastructure.")

# Inputs for climate conditions
temperature = st.number_input("Temperature (°C):", min_value=-50, max_value=50, value=25)
humidity = st.number_input("Humidity (%):", min_value=0, max_value=100, value=50)
wind_speed = st.number_input("Wind Speed (km/h):", min_value=0.0, max_value=200.0, value=15.0)
uv_index = st.number_input("UV Index:", min_value=0, max_value=11, value=5)
air_quality_index = st.number_input("Air Quality Index:", min_value=0, max_value=500, value=100)
precipitation = st.number_input("Precipitation (mm):", min_value=0.0, max_value=500.0, value=10.0)
atmospheric_pressure = st.number_input("Atmospheric Pressure (hPa):", min_value=900, max_value=1100, value=1013)

if st.button("Generate Prediction"):
    all_message = (
        f"Assess the impact on sports performance and infrastructure based on climate conditions: "
        f"Temperature {temperature}°C, Humidity {humidity}%, Wind Speed {wind_speed} km/h, UV Index {uv_index}, "
        f"Air Quality Index {air_quality_index}, Precipitation {precipitation} mm, Atmospheric Pressure {atmospheric_pressure} hPa."
    )

    try:
        with st.spinner("Analyzing climate conditions..."):
            response = call_ai_model(all_message)

        st.success("Initial analysis complete. Generating detailed predictions...")

        generated_text = ""
        for line in response.iter_lines():
            if line:
                line_content = line.decode('utf-8')
                if line_content.startswith("data: "):
                    line_content = line_content[6:]  # Strip "data: " prefix
                try:
                    json_data = json.loads(line_content)
                    if "choices" in json_data:
                        delta = json_data["choices"][0]["delta"]
                        if "content" in delta and delta["content"].strip().replace('.', '', 1).isdigit():
                            generated_text += delta["content"]
                except json.JSONDecodeError:
                    continue

        st.success("Detailed predictions generated.")

        # Prepare data for visualization
        results_data = {
            "Condition": ["Temperature", "Humidity", "Wind Speed", "UV Index", "Air Quality Index", "Precipitation", "Atmospheric Pressure"],
            "Value": [temperature, humidity, wind_speed, uv_index, air_quality_index, precipitation, atmospheric_pressure]
        }
        results_df = pd.DataFrame(results_data)

        # Display results in a table
        st.subheader("Results Summary")
        st.table(results_df)

        # Display prediction
        st.markdown("**Predicted Impact on Performance and Infrastructure:**")
        st.markdown(generated_text.strip())

        st.success("Generating performance data...")

        # Generate numeric performance data for different temperatures
        temperatures = range(-10, 41, 5)  # Temperatures from -10°C to 40°C in 5°C increments
        performance_values = []
        for temp in temperatures:
            st.spinner(f"Fetching performance data for {temp}°C...")
            performance_value = get_numeric_performance_data(temp)
            if performance_value is not None:
                performance_values.append(performance_value)
            time.sleep(1)

        if performance_values:
            # Generate line graph
            fig, ax = plt.subplots()
            ax.plot(temperatures, performance_values, marker='o')
            ax.set_xlabel('Temperature (°C)')
            ax.set_ylabel('Performance Score')
            ax.set_title('Temperature vs. Numeric Sports Performance')
            st.pyplot(fig)

    except ValueError as ve:
        st.error(f"Configuration error: {ve}")
    except requests.exceptions.RequestException as re:
        st.error(f"Request error: {re}")
    except Exception as e:
        st.error(f"An unexpected error occurred: {e}")