import time 

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import gradio as gr

from datasets import load_dataset
from sklearn.datasets import fetch_openml
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report

LOGS_DATASET_URI = 'pgurazada1/machine-failure-mlops-demo-logs'


def get_data():
    """
    Connect to the HuggingFace dataset where the logs are stored.
    Pull the data into a dataframe
    """
    data = load_dataset(LOGS_DATASET_URI)
    sample_df = data['train'].to_pandas().sample(100)

    return sample_df

def load_training_data():
    dataset = fetch_openml(data_id=42890, as_frame=True, parser="auto")
    data_df = dataset.data
    
    target = 'Machine failure'
    numeric_features = [
        'Air temperature [K]',
        'Process temperature [K]',
        'Rotational speed [rpm]',
        'Torque [Nm]',
        'Tool wear [min]'
    ]
    
    categorical_features = ['Type']

    X = data_df[numeric_features + categorical_features]
    y = data_df[target]

    Xtrain, Xtest, ytrain, ytest = train_test_split(
        X, y,
        test_size=0.2,
        random_state=42
    )

    return Xtrain, ytrain

def check_model_drift():
    sample_df = get_data()
    p_pos_label_training_data = 0.03475
    training_data_size = 8000
    p_pos_label_sample_logs = sample_df.prediction.value_counts()
    
    return p_pos_label_sample_logs
    
    
with gr.Blocks() as demo:
    gr.Markdown("# Real-time Monitoring Dashboard")

    gr.Markdown("Snapshot of live data")
    
    with gr.Row():
        with gr.Column():
            gr.DataFrame(get_data, every=5)
        with gr.Column():
            gr.TextBox(f"Data refreshed at {time.time()}", every=5)

demo.queue().launch()