app.py

from datetime import datetime, timedelta
import gradio as gr
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
import duckdb
import logging
from tabs.trades import (
    prepare_trades,
    get_overall_trades,
    get_overall_by_market_trades,
    get_overall_winning_trades,
    get_overall_winning_by_market_trades,
    plot_trades_by_week,
    plot_trades_per_market_by_week,
    plot_winning_trades_by_week,
    plot_winning_trades_per_market_by_week,
    integrated_plot_trades_per_market_by_week,
    integrated_plot_winning_trades_per_market_by_week,
)

from tabs.metrics import (
    trade_metric_choices,
    tool_metric_choices,
    default_trade_metric,
    default_tool_metric,
    plot_trade_details,
    plot2_trade_details,
    plot_trade_metrics,
    WIDTH,
    HEIGHT,
    plot_tool_metrics,
)

from tabs.tool_win import (
    get_tool_winning_rate,
    get_tool_winning_rate_by_market,
    get_overall_winning_rate,
    plot_tool_winnings_overall,
    plot_tool_winnings_by_tool,
)

from tabs.tool_accuracy import (
    plot_tools_weighted_accuracy_rotated_graph,
    plot_tools_accuracy_rotated_graph,
    compute_weighted_accuracy,
    plot_tools_accuracy_graph,
    plot_tools_weighted_accuracy_graph,
)

from tabs.invalid_markets import (
    plot_daily_dist_invalid_trades,
    plot_ratio_invalid_trades_per_market,
    plot_top_invalid_markets,
    plot_daily_nr_invalid_markets,
)

from tabs.error import (
    get_error_data,
    get_error_data_overall,
    plot_error_data,
    plot_tool_error_data,
    plot_week_error_data,
)
from tabs.about import about_olas_predict, about_this_dashboard

from scripts.utils import INC_TOOLS


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 get_last_one_month_data():
    """
    Get the last one month data from the tools.parquet file
    """
    logger.info("Getting last one month data")
    con = duckdb.connect(":memory:")
    one_months_ago = (datetime.now() - timedelta(days=60)).strftime("%Y-%m-%d")

    # Query to fetch data from all_trades_profitability.parquet
    query2 = f"""
    SELECT *
    FROM read_parquet('./data/all_trades_profitability.parquet')
    WHERE creation_timestamp >= '{one_months_ago}'
    """
    df2 = con.execute(query2).fetchdf()
    logger.info("Got last one month data from all_trades_profitability.parquet")

    query1 = f"""
    SELECT *
    FROM read_parquet('./data/tools.parquet')
    WHERE request_time >= '{one_months_ago}'
    """
    df1 = con.execute(query1).fetchdf()
    logger.info("Got last one month data from tools.parquet")

    con.close()

    return df1, df2


def get_all_data():
    """
    Get all data from the tools.parquet, tools_accuracy and trades parquet files
    """
    logger.info("Getting all data")
    con = duckdb.connect(":memory:")

    # Query to fetch invalid trades data
    query4 = f"""
    SELECT *
    FROM read_parquet('./data/invalid_trades.parquet')
    """
    df4 = con.execute(query4).fetchdf()

    # Query to fetch tools accuracy data
    query3 = f"""
    SELECT *
    FROM read_csv('./data/tools_accuracy.csv')
    """
    df3 = con.execute(query3).fetchdf()

    # Query to fetch data from all_trades_profitability.parquet
    query2 = f"""
    SELECT *
    FROM read_parquet('./data/all_trades_profitability.parquet')
    """
    df2 = con.execute(query2).fetchdf()
    logger.info("Got all data from all_trades_profitability.parquet")

    query1 = f"""
    SELECT *
    FROM read_parquet('./data/tools.parquet')
    """
    df1 = con.execute(query1).fetchdf()
    logger.info("Got all data from tools.parquet")

    con.close()

    return df1, df2, df3, df4


def prepare_data():
    """
    Prepare the data for the dashboard
    """
    tools_df, trades_df, tools_accuracy_info, invalid_trades = get_all_data()
    print(trades_df.info())

    tools_df["request_time"] = pd.to_datetime(tools_df["request_time"])
    trades_df["creation_timestamp"] = pd.to_datetime(trades_df["creation_timestamp"])

    trades_df = prepare_trades(trades_df)

    tools_accuracy_info = compute_weighted_accuracy(tools_accuracy_info)
    print("weighted accuracy info")
    print(tools_accuracy_info.head())

    invalid_trades["creation_timestamp"] = pd.to_datetime(
        invalid_trades["creation_timestamp"]
    )
    invalid_trades["creation_date"] = invalid_trades["creation_timestamp"].dt.date

    return tools_df, trades_df, tools_accuracy_info, invalid_trades


tools_df, trades_df, tools_accuracy_info, invalid_trades = prepare_data()


demo = gr.Blocks()

error_df = get_error_data(tools_df=tools_df, inc_tools=INC_TOOLS)
error_overall_df = get_error_data_overall(error_df=error_df)
winning_rate_df = get_tool_winning_rate(tools_df=tools_df, inc_tools=INC_TOOLS)
winning_rate_overall_df = get_overall_winning_rate(wins_df=winning_rate_df)
trades_count_df = get_overall_trades(trades_df=trades_df)
trades_winning_rate_df = get_overall_winning_trades(trades_df=trades_df)
trades_by_market = get_overall_by_market_trades(trades_df=trades_df)
winning_trades_by_market = get_overall_winning_by_market_trades(trades_df=trades_df)
with demo:
    gr.HTML("<h1>Olas Predict Actual Performance</h1>")
    gr.Markdown(
        "This app shows the actual performance of Olas Predict tools on the live market."
    )

    with gr.Tabs():
        with gr.TabItem("🔥Trades Dashboard"):
            with gr.Row():
                gr.Markdown("# Trend of weekly trades")
            with gr.Row():
                trades_by_week = integrated_plot_trades_per_market_by_week(
                    trades_df=trades_df
                )

            with gr.Row():
                gr.Markdown("# Percentage of winning trades per week")
            with gr.Row():
                all_wtrades_by_week = integrated_plot_winning_trades_per_market_by_week(
                    trades_df=trades_df
                )

            with gr.Row():
                gr.Markdown("# ⚖️ Trading metrics")
            with gr.Row():
                trade_details_selector = gr.Dropdown(
                    label="Select a trade metric",
                    choices=trade_metric_choices,
                    value=default_trade_metric,
                )
            with gr.Row():
                trade_details_plot = plot_trade_metrics(
                    metric_name=default_trade_metric,
                    trades_df=trades_df,
                    height=400,
                    width=1400,
                )

            def update_trade_details(trade_detail):
                return plot_trade_metrics(
                    metric_name=trade_detail,
                    trades_df=trades_df,
                    height=400,
                    width=1400,
                )

            trade_details_selector.change(
                update_trade_details,
                inputs=trade_details_selector,
                outputs=trade_details_plot,
            )

            with gr.Row():
                trade_details_selector
            with gr.Row():
                trade_details_plot

        with gr.TabItem("🚀 Tool Winning Dashboard"):
            with gr.Row():
                gr.Markdown("# All tools winning performance")

            with gr.Row():
                winning_selector = gr.Dropdown(
                    label="Select the tool metric",
                    choices=tool_metric_choices,
                    value=default_tool_metric,
                )

            with gr.Row():
                # plot_tool_metrics
                winning_plot = plot_tool_winnings_overall(
                    wins_df=winning_rate_overall_df,
                    winning_selector=default_tool_metric,
                )

            def update_tool_winnings_overall_plot(winning_selector):
                return plot_tool_winnings_overall(
                    wins_df=winning_rate_overall_df, winning_selector=winning_selector
                )

            winning_selector.change(
                update_tool_winnings_overall_plot,
                inputs=winning_selector,
                outputs=winning_plot,
            )

            with gr.Row():
                winning_selector
            with gr.Row():
                winning_plot

            with gr.Row():
                gr.Markdown("# Winning performance by each tool")

            with gr.Row():
                sel_tool = gr.Dropdown(
                    label="Select a tool", choices=INC_TOOLS, value=INC_TOOLS[0]
                )

            with gr.Row():
                tool_winnings_by_tool_plot = plot_tool_winnings_by_tool(
                    wins_df=winning_rate_df, tool=INC_TOOLS[0]
                )

            def update_tool_winnings_by_tool_plot(tool):
                return plot_tool_winnings_by_tool(wins_df=winning_rate_df, tool=tool)

            sel_tool.change(
                update_tool_winnings_by_tool_plot,
                inputs=sel_tool,
                outputs=tool_winnings_by_tool_plot,
            )

            with gr.Row():
                sel_tool
            with gr.Row():
                tool_winnings_by_tool_plot
        with gr.TabItem("🎯 Tool Accuracy Dashboard"):
            with gr.Row():
                gr.Markdown("# Tools accuracy ranking")
            with gr.Row():
                gr.Markdown(
                    "The data used for this metric is from the past two months. This accuracy is computed based on right answers from the total requests received."
                )

            with gr.Row():
                _ = plot_tools_accuracy_rotated_graph(tools_accuracy_info)

            with gr.Row():
                gr.Markdown("# Weighted accuracy ranking per tool")
            with gr.Row():
                gr.Markdown(
                    "This metric is an approximation to the real metric used by the trader since some parameters are only dynamically generated."
                )
            with gr.Row():
                gr.Markdown(
                    "The data used for this metric is from the past two months. This metric is computed using both the tool accuracy and the volume of requests received by the tool. The minimum value of this custom metric is 0 and the maximum value is 1. The higher the better is the tool."
                )
            with gr.Row():
                _ = plot_tools_weighted_accuracy_rotated_graph(tools_accuracy_info)

        with gr.TabItem("⛔ Invalid Markets Dashboard"):
            with gr.Row():
                gr.Markdown("# Daily distribution of invalid trades")
            with gr.Row():
                daily_trades = plot_daily_dist_invalid_trades(invalid_trades)

            # with gr.Row():
            #     gr.Markdown("# Ratio of invalid trades per market")
            # with gr.Row():
            #     plot_ratio_invalid_trades_per_market(invalid_trades)

            with gr.Row():
                gr.Markdown("# Top markets with invalid trades")
            with gr.Row():
                top_invalid_markets = plot_top_invalid_markets(invalid_trades)

            with gr.Row():
                gr.Markdown("# Daily distribution of invalid markets")
            with gr.Row():
                invalid_markets = plot_daily_nr_invalid_markets(invalid_trades)

        with gr.TabItem("🏥 Tool Error Dashboard"):
            with gr.Row():
                gr.Markdown("# All tools errors")
            with gr.Row():
                error_overall_plot = plot_error_data(error_all_df=error_overall_df)
            with gr.Row():
                gr.Markdown("# Error percentage per tool")
            with gr.Row():
                sel_tool = gr.Dropdown(
                    label="Select a tool", choices=INC_TOOLS, value=INC_TOOLS[0]
                )

            with gr.Row():
                tool_error_plot = plot_tool_error_data(
                    error_df=error_df, tool=INC_TOOLS[0]
                )

            def update_tool_error_plot(tool):
                return plot_tool_error_data(error_df=error_df, tool=tool)

            sel_tool.change(
                update_tool_error_plot, inputs=sel_tool, outputs=tool_error_plot
            )
            with gr.Row():
                sel_tool
            with gr.Row():
                tool_error_plot

            with gr.Row():
                gr.Markdown("# Tools distribution of errors per week")

            with gr.Row():
                choices = error_overall_df["request_month_year_week"].unique().tolist()
                # sort the choices by the latest week to be on the top
                choices = sorted(choices)
                sel_week = gr.Dropdown(
                    label="Select a week", choices=choices, value=choices[-1]
                )

            with gr.Row():
                week_error_plot = plot_week_error_data(
                    error_df=error_df, week=choices[-1]
                )

            def update_week_error_plot(selected_week):
                return plot_week_error_data(error_df=error_df, week=selected_week)

            sel_tool.change(
                update_tool_error_plot, inputs=sel_tool, outputs=tool_error_plot
            )
            sel_week.change(
                update_week_error_plot, inputs=sel_week, outputs=week_error_plot
            )

            with gr.Row():
                sel_tool
            with gr.Row():
                tool_error_plot
            with gr.Row():
                sel_week
            with gr.Row():
                week_error_plot

        with gr.TabItem("ℹ️ About"):
            with gr.Accordion("About Olas Predict"):
                gr.Markdown(about_olas_predict)

            with gr.Accordion("About this dashboard"):
                gr.Markdown(about_this_dashboard)

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