scripts/metrics.py

import pandas as pd
from tqdm import tqdm
from scripts.utils import get_next_week

DEFAULT_MECH_FEE = 0.01  # xDAI


def get_weekly_total_mech_calls(
    trader_data: pd.DataFrame, all_mech_calls_df: pd.DataFrame
) -> int:
    """Function to compute the total weekly number of mech calls for all markets
    that the trader bet upon"""

    trading_weeks = trader_data.month_year_week.unique()
    trader_address = trader_data.trader_address.unique()[0]
    if len(trading_weeks) > 1:
        raise ValueError("The trader data should contain only one week information")
    trading_week = trading_weeks[0]
    try:
        return all_mech_calls_df.loc[
            (all_mech_calls_df["trader_address"] == trader_address)
            & (all_mech_calls_df["month_year_week"] == trading_week),
            "total_mech_calls",
        ].iloc[0]
    except Exception as e:
        print(
            f"Error getting the number of mech calls for the trader {trader_address} and week {trading_week}"
        )
        return 280  # average number 40 mech calls in 7 days


def compute_metrics(
    trader_address: str,
    trader_data: pd.DataFrame,
    all_mech_calls: pd.DataFrame,
    live_metrics: bool = False,
    unknown_trader: bool = False,
) -> dict:

    if len(trader_data) == 0:
        # print("No data to compute metrics")
        return {}

    agg_metrics = {}
    agg_metrics["trader_address"] = trader_address
    total_bet_amounts = trader_data.collateral_amount.sum()
    if live_metrics:
        # the total is already computed in daily_info per trader address and trading day
        total_nr_mech_calls_all_markets = trader_data["num_mech_calls"].iloc[0]
    elif unknown_trader:
        # num of mech calls is always zero
        total_nr_mech_calls_all_markets = 0
    else:
        total_nr_mech_calls_all_markets = get_weekly_total_mech_calls(
            trader_data=trader_data, all_mech_calls_df=all_mech_calls
        )

    agg_metrics["bet_amount"] = total_bet_amounts
    agg_metrics["nr_mech_calls"] = total_nr_mech_calls_all_markets
    agg_metrics["staking"] = trader_data.iloc[0].staking
    agg_metrics["nr_trades"] = len(trader_data)
    if live_metrics:
        return agg_metrics
    total_earnings = trader_data.earnings.sum()
    agg_metrics["earnings"] = total_earnings
    total_fee_amounts = trader_data.mech_fee_amount.sum()

    total_costs = (
        total_bet_amounts
        + total_fee_amounts
        + (total_nr_mech_calls_all_markets * DEFAULT_MECH_FEE)
    )
    total_net_earnings = total_earnings - total_costs
    agg_metrics["net_earnings"] = total_net_earnings
    agg_metrics["roi"] = total_net_earnings / total_costs

    return agg_metrics


def compute_trader_metrics_by_market_creator(
    trader_address: str,
    traders_data: pd.DataFrame,
    all_mech_calls: pd.DataFrame,
    market_creator: str = "all",
    live_metrics: bool = False,
    unknown_trader: bool = False,
) -> dict:
    """This function computes for a specific time window (week or day) the different metrics:
    roi, net_earnings, earnings, bet_amount, nr_mech_calls and nr_trades.
    The global roi of the trader by computing the individual net profit and the individual costs values
    achieved per market and dividing both.
    It is possible to filter by market creator: quickstart, pearl, all"""
    assert "market_creator" in traders_data.columns
    filtered_traders_data = traders_data.loc[
        traders_data["trader_address"] == trader_address
    ]
    if market_creator != "all":  # compute only for the specific market creator
        filtered_traders_data = filtered_traders_data.loc[
            filtered_traders_data["market_creator"] == market_creator
        ]
        if len(filtered_traders_data) == 0:
            # tqdm.write(f"No data. Skipping market creator {market_creator}")
            return {}  # No Data

    metrics = compute_metrics(
        trader_address,
        filtered_traders_data,
        all_mech_calls,
        live_metrics,
        unknown_trader,
    )
    return metrics


def merge_trader_weekly_metrics(
    trader: str,
    weekly_data: pd.DataFrame,
    all_mech_calls: pd.DataFrame,
    week: str,
    unknown_trader: bool = False,
) -> pd.DataFrame:
    trader_metrics = []
    # computation as specification 1 for all types of markets
    weekly_metrics_all = compute_trader_metrics_by_market_creator(
        trader,
        weekly_data,
        all_mech_calls=all_mech_calls,
        market_creator="all",
        live_metrics=False,
        unknown_trader=unknown_trader,
    )
    weekly_metrics_all["month_year_week"] = week
    weekly_metrics_all["market_creator"] = "all"
    trader_metrics.append(weekly_metrics_all)

    # computation as specification 1 for quickstart markets
    weekly_metrics_qs = compute_trader_metrics_by_market_creator(
        trader,
        weekly_data,
        all_mech_calls=all_mech_calls,
        market_creator="quickstart",
        live_metrics=False,
        unknown_trader=unknown_trader,
    )
    if len(weekly_metrics_qs) > 0:
        weekly_metrics_qs["month_year_week"] = week
        weekly_metrics_qs["market_creator"] = "quickstart"
        trader_metrics.append(weekly_metrics_qs)
    # computation as specification 1 for pearl markets
    weekly_metrics_pearl = compute_trader_metrics_by_market_creator(
        trader,
        weekly_data,
        all_mech_calls=all_mech_calls,
        market_creator="pearl",
        live_metrics=False,
        unknown_trader=unknown_trader,
    )
    if len(weekly_metrics_pearl) > 0:
        weekly_metrics_pearl["month_year_week"] = week
        weekly_metrics_pearl["market_creator"] = "pearl"
        trader_metrics.append(weekly_metrics_pearl)
    result = pd.DataFrame.from_dict(trader_metrics, orient="columns")
    return result


def merge_trader_daily_metrics(
    trader: str,
    daily_data: pd.DataFrame,
    day: str,
    live_metrics: bool = False,
) -> pd.DataFrame:
    trader_metrics = []
    # computation as specification 1 for all types of markets
    daily_metrics_all = compute_trader_metrics_by_market_creator(
        trader,
        daily_data,
        all_mech_calls=None,
        market_creator="all",
        live_metrics=live_metrics,
    )
    daily_metrics_all["creation_date"] = day
    # staking label is at the trader level
    daily_metrics_all["market_creator"] = "all"
    trader_metrics.append(daily_metrics_all)

    # computation as specification 1 for quickstart markets
    daily_metrics_qs = compute_trader_metrics_by_market_creator(
        trader,
        daily_data,
        all_mech_calls=None,
        market_creator="quickstart",
        live_metrics=live_metrics,
    )
    if len(daily_metrics_qs) > 0:
        daily_metrics_qs["creation_date"] = day
        daily_metrics_qs["market_creator"] = "quickstart"
        trader_metrics.append(daily_metrics_qs)
    # computation as specification 1 for pearl markets
    daily_metrics_pearl = compute_trader_metrics_by_market_creator(
        trader,
        daily_data,
        all_mech_calls=None,
        market_creator="pearl",
        live_metrics=live_metrics,
    )
    if len(daily_metrics_pearl) > 0:
        daily_metrics_pearl["creation_date"] = day
        daily_metrics_pearl["market_creator"] = "pearl"
        trader_metrics.append(daily_metrics_pearl)
    result = pd.DataFrame.from_dict(trader_metrics, orient="columns")
    return result


def win_metrics_trader_level(weekly_data):
    winning_trades = (
        weekly_data.groupby(
            ["month_year_week", "market_creator", "trader_address"], sort=False
        )["winning_trade"].sum()
        / weekly_data.groupby(
            ["month_year_week", "market_creator", "trader_address"], sort=False
        )["winning_trade"].count()
        * 100
    )
    # winning_trades is a series, give it a dataframe
    winning_trades = winning_trades.reset_index()
    winning_trades.columns = winning_trades.columns.astype(str)
    winning_trades.rename(columns={"winning_trade": "winning_perc"}, inplace=True)
    return winning_trades


def compute_weekly_metrics_by_market_creator(
    traders_data: pd.DataFrame,
    all_mech_calls: pd.DataFrame,
    trader_filter: str = None,
    unknown_trader: bool = False,
) -> pd.DataFrame:
    """Function to compute the metrics at the trader level per week
    and with different categories by market creator"""
    contents = []
    all_weeks = list(traders_data.month_year_week.unique())
    next_week = get_next_week()
    print(f"next week = {next_week}")
    for week in all_weeks:
        # skip the next week since data is not complete
        if week == next_week:
            continue
        weekly_data = traders_data.loc[traders_data["month_year_week"] == week]
        print(f"Computing weekly metrics for week ={week} by market creator")
        # traverse each trader
        traders = list(weekly_data.trader_address.unique())
        for trader in tqdm(traders, desc=f"Trader' metrics", unit="metrics"):
            if trader_filter is None:
                contents.append(
                    merge_trader_weekly_metrics(
                        trader, weekly_data, all_mech_calls, week, unknown_trader
                    )
                )
            elif trader_filter == "Olas":
                filtered_data = weekly_data.loc[weekly_data["staking"] != "non_Olas"]
                contents.append(
                    merge_trader_weekly_metrics(
                        trader, filtered_data, all_mech_calls, week
                    )
                )
            else:  # non_Olas traders
                filtered_data = weekly_data.loc[weekly_data["staking"] == "non_Olas"]
                contents.append(
                    merge_trader_weekly_metrics(
                        trader, filtered_data, all_mech_calls, week
                    )
                )

    print("End computing all weekly metrics by market creator")
    return pd.concat(contents, ignore_index=True)


def compute_daily_metrics_by_market_creator(
    traders_data: pd.DataFrame,
    trader_filter: str = None,
    live_metrics: bool = False,
) -> pd.DataFrame:
    """Function to compute the metrics at the trader level per day
    and with different categories by market creator"""
    contents = []

    all_days = list(traders_data.creation_date.unique())
    for day in all_days:
        daily_data = traders_data.loc[traders_data["creation_date"] == day]
        print(f"Computing daily metrics for {day}")
        # traverse each trader
        traders = list(daily_data.trader_address.unique())
        for trader in tqdm(traders, desc=f"Trader' daily metrics", unit="metrics"):
            if trader_filter is None:
                contents.append(
                    merge_trader_daily_metrics(trader, daily_data, day, live_metrics)
                )
            elif trader_filter == "Olas":
                filtered_data = daily_data.loc[daily_data["staking"] != "non_Olas"]
                contents.append(
                    merge_trader_daily_metrics(trader, filtered_data, day, live_metrics)
                )
            else:  # non_Olas traders
                filtered_data = daily_data.loc[daily_data["staking"] == "non_Olas"]
                contents.append(
                    merge_trader_daily_metrics(trader, filtered_data, day, live_metrics)
                )
    print("End computing all daily metrics by market creator")
    print(f"length of contents = {len(contents)}")
    return pd.concat(contents, ignore_index=True)


def compute_winning_metrics_by_trader(
    traders_data: pd.DataFrame, unknown_info: pd.DataFrame, trader_filter: str = None
) -> pd.DataFrame:
    """Function to compute the winning metrics at the trader level per week and with different market creators"""
    if len(unknown_info) > 0:
        all_data = pd.concat([traders_data, unknown_info], axis=0)
    else:
        all_data = traders_data

    market_all = all_data.copy(deep=True)
    market_all["market_creator"] = "all"

    # merging both dataframes
    final_traders = pd.concat([market_all, all_data], ignore_index=True)
    final_traders = final_traders.sort_values(by="creation_timestamp", ascending=True)

    if trader_filter == "non_Olas":  # non_Olas
        final_traders = final_traders.loc[final_traders["staking"] == "non_Olas"]
    elif trader_filter == "Olas":
        final_traders = final_traders.loc[final_traders["staking"] != "non_Olas"]
    else:  # all traders
        print("No filtering")

    if len(final_traders) == 0:
        return pd.DataFrame()
    winning_df = win_metrics_trader_level(final_traders)
    winning_df.head()
    return winning_df