import gradio as gr
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
import openai
import matplotlib.pyplot as plt
from io import BytesIO
import base64
import os
from google.auth.transport.requests import Request
from google.oauth2.credentials import Credentials
from google_auth_oauthlib.flow import InstalledAppFlow
from googleapiclient.discovery import build

# Access the API key from Hugging Face Secrets
openai.api_key = os.environ.get("OPENAI_API_KEY")

# Sample dataset of resources
resources = pd.DataFrame({
    "Resource": ["Python Tutorial", "Math Basics", "Data Structures", "Machine Learning Intro"],
    "Type": ["Video", "Article", "Video", "Video"],
    "Learning Style": ["Visual", "Reading", "Visual", "Visual"]
})

# Global variables
tasks = []
points = 0

# Function to recommend resources
def recommend_resources(learning_style):
    vectorizer = TfidfVectorizer()
    tfidf_matrix = vectorizer.fit_transform(resources["Learning Style"])
    user_vector = vectorizer.transform([learning_style])
    similarities = cosine_similarity(user_vector, tfidf_matrix)
    recommended_index = similarities.argmax()
    return resources.iloc[recommended_index]

# Function to add a task
def add_task(task, deadline, priority):
    global tasks
    tasks.append({"Task": task, "Deadline": deadline, "Priority": priority, "Completed": False})
    return "Task added successfully!"

# Function to mark a task as completed
def mark_completed(task_index):
    global tasks, points
    if 0 <= task_index < len(tasks):
        tasks[task_index]["Completed"] = True
        points += 10  # Award 10 points for completing a task
        return f"Task marked as completed! You earned 10 points. Total points: {points}"
    return "Invalid task index."

# Function to visualize progress
def show_progress():
    completed = sum(1 for task in tasks if task["Completed"])
    remaining = len(tasks) - completed
    
    # Create a progress chart
    plt.bar(["Completed", "Remaining"], [completed, remaining], color=["green", "red"])
    plt.title("Study Progress")
    buffer = BytesIO()
    plt.savefig(buffer, format="png")
    buffer.seek(0)
    image_base64 = base64.b64encode(buffer.getvalue()).decode("utf-8")
    plt.close()
    return f"data:image/png;base64,{image_base64}"

# Function to interact with the chatbot
def chatbot(user_input):
    response = openai.Completion.create(
        engine="text-davinci-003",
        prompt=user_input,
        max_tokens=50
    )
    return response.choices[0].text.strip()

# Function to sync tasks with Google Calendar
def sync_with_calendar():
    creds = None
    if os.path.exists("token.json"):
        creds = Credentials.from_authorized_user_file("token.json", ["https://www.googleapis.com/auth/calendar"])
    if not creds or not creds.valid:
        if creds and creds.expired and creds.refresh_token:
            creds.refresh(Request())
        else:
            flow = InstalledAppFlow.from_client_secrets_file("credentials.json", ["https://www.googleapis.com/auth/calendar"])
            creds = flow.run_local_server(port=0)
        with open("token.json", "w") as token:
            token.write(creds.to_json())
    
    service = build("calendar", "v3", credentials=creds)
    for task in tasks:
        event = {
            "summary": task["Task"],
            "start": {"dateTime": task["Deadline"] + "T09:00:00", "timeZone": "UTC"},
            "end": {"dateTime": task["Deadline"] + "T10:00:00", "timeZone": "UTC"},
        }
        event = service.events().insert(calendarId="primary", body=event).execute()
    return "Tasks synced with Google Calendar!"

# Gradio Interface
with gr.Blocks() as demo:
    gr.Markdown("# AI-Powered Study Assistant")
    
    with gr.Tab("Task Management"):
        with gr.Row():
            task_input = gr.Textbox(label="Task")
            deadline_input = gr.Textbox(label="Deadline (YYYY-MM-DD)")
            priority_input = gr.Textbox(label="Priority (High/Medium/Low)")
        add_task_button = gr.Button("Add Task")
        task_output = gr.Textbox(label="Output")
        add_task_button.click(add_task, inputs=[task_input, deadline_input, priority_input], outputs=task_output)
        
        with gr.Row():
            task_index_input = gr.Number(label="Task Index to Mark as Completed")
            mark_completed_button = gr.Button("Mark Completed")
        mark_completed_output = gr.Textbox(label="Output")
        mark_completed_button.click(mark_completed, inputs=task_index_input, outputs=mark_completed_output)
        
        gr.Markdown("### Tasks")
        task_list = gr.Dataframe(headers=["Task", "Deadline", "Priority", "Completed"], value=tasks)
    
    with gr.Tab("Progress Tracking"):
        progress_button = gr.Button("Show Progress")
        progress_image = gr.Image(label="Progress Chart")
        progress_button.click(show_progress, outputs=progress_image)
    
    with gr.Tab("Chatbot"):
        chatbot_input = gr.Textbox(label="Ask a question:")
        chatbot_output = gr.Textbox(label="Chatbot Response")
        chatbot_button = gr.Button("Ask")
        chatbot_button.click(chatbot, inputs=chatbot_input, outputs=chatbot_output)
    
    with gr.Tab("Recommendations"):
        learning_style_input = gr.Textbox(label="Enter your preferred learning style (Visual/Reading):")
        recommendation_output = gr.Textbox(label="Recommended Resource")
        recommend_button = gr.Button("Get Recommendation")
        recommend_button.click(recommend_resources, inputs=learning_style_input, outputs=recommendation_output)
    
    with gr.Tab("Google Calendar Sync"):
        sync_button = gr.Button("Sync with Google Calendar")
        sync_output = gr.Textbox(label="Output")
        sync_button.click(sync_with_calendar, outputs=sync_output)

# Launch the app
demo.launch()