app.py

from datetime import datetime
import gradio as gr
import pandas as pd
import duckdb
import logging

from tabs.tokens_pwc_dist import (
    get_extreme_cases,
)
from tabs.dist_gap import (
    get_distribution_plot,
    get_correlation_map,
    get_kde_with_trades,
    get_kde_with_total_bet_amount,
    get_dist_gap_time_evolution,
)


def get_logger():
    logger = logging.getLogger(__name__)
    logger.setLevel(logging.DEBUG)
    # stream handler and formatter
    stream_handler = logging.StreamHandler()
    stream_handler.setLevel(logging.DEBUG)
    formatter = logging.Formatter(
        "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
    )
    stream_handler.setFormatter(formatter)
    logger.addHandler(stream_handler)
    return logger


logger = get_logger()


def prepare_data():
    """
    Get all data from the parquet files
    """
    logger.info("Getting all data")
    con = duckdb.connect(":memory:")

    # Query to fetch invalid trades data
    query = f"""
    SELECT *
    FROM read_parquet('./live_data/markets_live_data.parquet')
    """
    df = con.execute(query).fetchdf()
    df["sample_datetime"] = df["sample_timestamp"].apply(
        lambda x: datetime.fromtimestamp(x)
    )
    df["opening_datetime"] = df["openingTimestamp"].apply(
        lambda x: datetime.fromtimestamp(int(x))
    )
    df["days_to_resolution"] = (df["opening_datetime"] - df["sample_datetime"]).dt.days
    return df


demo = gr.Blocks()
markets_data = prepare_data()
live_markets_data = markets_data.loc[markets_data["open"] == True]
# filter only those with trades
markets_data = markets_data.loc[markets_data["total_trades"] > 0]
with demo:
    gr.HTML("<h1>Olas Predict Live Markets </h1>")
    gr.Markdown("This app shows the distributions of predictions on the live markets.")
    best_market_id, best_gap, worst_market_id, worst_gap = get_extreme_cases(
        live_markets_data
    )
    with gr.Tabs():
        with gr.TabItem("💹 Probability distributions of some markets"):
            with gr.Row():
                gr.Markdown("Best case: a market with a low gap between distributions")
            with gr.Row():
                gr.Markdown(
                    f"Market id = {best_market_id} Dist gap = {round(best_gap,2)}"
                )
            with gr.Row():
                # with gr.Column(min_width=350):
                #     gr.Markdown("# Evolution of outcomes probability based on tokens")
                #     best_market_tokens_dist = get_based_tokens_distribution(
                #         best_market_id, live_markets_data
                #     )
                # with gr.Column(min_width=350):
                #     gr.Markdown("# Evolution of outcomes probability based on votes")
                #     best_market_votes_dist = get_based_votes_distribution(
                #         best_market_id, live_markets_data
                #     )
                best_case = get_dist_gap_time_evolution(
                    best_market_id, live_markets_data
                )

            with gr.Row():
                gr.Markdown("Worst case: a market with a high distribution gap metric")
            with gr.Row():
                gr.Markdown(
                    f"Market id = {worst_market_id} Dist gap = {round(worst_gap,2)}"
                )

            with gr.Row():
                # with gr.Column(min_width=350):
                #     # gr.Markdown("# Evolution of outcomes probability based on tokens")
                #     worst_market_tokens_dist = get_based_tokens_distribution(
                #         worst_market_id, live_markets_data
                #     )
                # with gr.Column(min_width=350):
                #     worst_market_votes_dist = get_based_votes_distribution(
                #         worst_market_id, live_markets_data
                #     )

                worst_case = get_dist_gap_time_evolution(
                    worst_market_id, live_markets_data
                )

        with gr.TabItem("📏 Distribution gap metric for all markets"):
            # remove samples with no trades
            with gr.Row():
                gr.Markdown(
                    "This metric measures the difference between the probability distribution based on the tokens distribution and the one based on the price weighted distribution"
                )
            with gr.Row():
                gr.Markdown("# Density distribution")
            with gr.Row():
                kde_plot = get_distribution_plot(markets_data)

            with gr.Row():
                with gr.Column(min_width=350):
                    gr.Markdown("# Relationship with number of trades")
                    kde_trades_plot = get_kde_with_trades(markets_data)
                with gr.Column(min_width=350):
                    gr.Markdown("# Relationship with total bet amount")
                    kde_total_bet_amount_plot = get_kde_with_total_bet_amount(
                        markets_data
                    )

            with gr.Row():
                gr.Markdown(
                    "# Correlation analysis between the metric and market variables"
                )

            with gr.Row():
                correlation_plot = get_correlation_map(markets_data)

    demo.queue(default_concurrency_limit=40).launch()