File size: 4,952 Bytes
1ed82ec |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 |
import pandas as pd
from scripts.utils import DATA_DIR, TMP_DIR
from datetime import datetime, timezone
from tqdm import tqdm
def transform_to_datetime(x):
return datetime.fromtimestamp(int(x), tz=timezone.utc)
def get_daily_total_mech_calls(trader_data: pd.DataFrame) -> int:
"""Function to compute the total daily number of mech calls for all markets
that the trader bet upon"""
daily_markets = trader_data.title.unique()
trading_day = trader_data.creation_date.unique()
if len(trading_day) > 1:
raise ValueError("The trader data should contain only one day information")
total_mech_calls = 0
for market in daily_markets:
# in num_mech_calls we have the total mech calls done for that market that day
total_mech_calls_on_market = trader_data.loc[
trader_data["title"] == market, "num_mech_calls"
].iloc[0]
total_mech_calls += total_mech_calls_on_market
return total_mech_calls
def get_weekly_total_mech_calls(trader_data: pd.DataFrame) -> int:
"""Function to compute the total weekly number of mech calls for all markets
that the trader bet upon"""
try:
all_mech_calls_df = pd.read_parquet(DATA_DIR / "weekly_mech_calls.parquet")
except Exception:
print("Error reading the weekly_mech_calls file")
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]
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]
def compute_weekly_total_mech_calls(
trader: str, week: str, weekly_trades: pd.DataFrame, weekly_tools: pd.DataFrame
) -> dict:
weekly_total_mech_calls_dict = {}
weekly_total_mech_calls_dict["trader_address"] = trader
weekly_total_mech_calls_dict["month_year_week"] = week
weekly_total_mech_calls_dict["total_trades"] = len(weekly_trades)
weekly_total_mech_calls_dict["total_mech_calls"] = len(weekly_tools)
return weekly_total_mech_calls_dict
def compute_total_mech_calls():
"""Function to compute the total number of mech calls for all traders and all markets
at a weekly level"""
try:
print("Reading tools file")
tools = pd.read_parquet(TMP_DIR / "tools.parquet")
tools["request_time"] = pd.to_datetime(tools["request_time"])
tools["request_date"] = tools["request_time"].dt.date
tools = tools.sort_values(by="request_time", ascending=True)
tools["month_year_week"] = (
tools["request_time"].dt.to_period("W").dt.strftime("%b-%d")
)
except Exception as e:
print(f"Error updating the invalid trades parquet {e}")
try:
print("Reading trades weekly info file")
fpmmTrades = pd.read_parquet(DATA_DIR / "fpmmTrades.parquet")
fpmmTrades["creationTimestamp"] = fpmmTrades["creationTimestamp"].apply(
lambda x: transform_to_datetime(x)
)
fpmmTrades["creation_timestamp"] = pd.to_datetime(
fpmmTrades["creationTimestamp"]
)
fpmmTrades["creation_date"] = fpmmTrades["creation_timestamp"].dt.date
fpmmTrades = fpmmTrades.sort_values(by="creation_timestamp", ascending=True)
fpmmTrades["month_year_week"] = (
fpmmTrades["creation_timestamp"].dt.to_period("W").dt.strftime("%b-%d")
)
except Exception as e:
print(f"Error reading fpmmTrades parquet {e}")
nr_traders = len(fpmmTrades["trader_address"].unique())
all_mech_calls = []
for trader in tqdm(
fpmmTrades["trader_address"].unique(),
total=nr_traders,
desc="creating mech calls estimation dataframe",
):
# compute the mech calls estimations for each trader
all_trades = fpmmTrades[fpmmTrades["trader_address"] == trader]
all_tools = tools[tools["trader_address"] == trader]
weeks = fpmmTrades.month_year_week.unique()
for week in weeks:
weekly_trades = all_trades.loc[all_trades["month_year_week"] == week]
weekly_tools = all_tools.loc[all_tools["month_year_week"] == week]
weekly_mech_calls_dict = compute_weekly_total_mech_calls(
trader, week, weekly_trades, weekly_tools
)
all_mech_calls.append(weekly_mech_calls_dict)
all_mech_calls_df: pd.DataFrame = pd.DataFrame.from_dict(
all_mech_calls, orient="columns"
)
print("Saving weekly_mech_calls.parquet file")
print(all_mech_calls_df.total_mech_calls.describe())
all_mech_calls_df.to_parquet(DATA_DIR / "weekly_mech_calls.parquet", index=False)
if __name__ == "__main__":
compute_total_mech_calls()
|