scripts/pull_data.py

import logging
from datetime import datetime
import pandas as pd
from markets import (
    etl as mkt_etl,
    DEFAULT_FILENAME as MARKETS_FILENAME,
)
from tools import DEFAULT_FILENAME as TOOLS_FILENAME, generate_tools_file
from profitability import run_profitability_analysis, DEFAULT_60_DAYS_AGO_TIMESTAMP
from utils import (
    get_question,
    current_answer,
    RPC,
    measure_execution_time,
    DATA_DIR,
    HIST_DIR,
)
from get_mech_info import (
    get_mech_events_last_60_days,
    get_mech_events_since_last_run,
    update_json_files,
)
from update_tools_accuracy import compute_tools_accuracy
from cleaning_old_info import clean_old_data_from_parquet_files
from web3_utils import updating_timestamps


logging.basicConfig(level=logging.INFO)


def add_current_answer(tools_filename: str):
    # Get currentAnswer from FPMMS
    fpmms = pd.read_parquet(DATA_DIR / MARKETS_FILENAME)
    tools = pd.read_parquet(DATA_DIR / tools_filename)

    # Get the question from the tools
    logging.info("Getting the question and current answer for the tools")
    tools["title"] = tools["prompt_request"].apply(lambda x: get_question(x))
    tools["currentAnswer"] = tools["title"].apply(lambda x: current_answer(x, fpmms))

    tools["currentAnswer"] = tools["currentAnswer"].str.replace("yes", "Yes")
    tools["currentAnswer"] = tools["currentAnswer"].str.replace("no", "No")
    # Save the tools data after the updates on the content
    tools.to_parquet(DATA_DIR / tools_filename, index=False)
    del fpmms


def save_historical_data():
    """Function to save a copy of the main trades and tools file
    into the historical folder"""
    print("Saving historical data copies")
    current_datetime = datetime.now()

    timestamp = current_datetime.strftime("%Y%m%d_%H%M%S")

    try:
        tools = pd.read_parquet(DATA_DIR / "tools.parquet")
        filename = f"tools_{timestamp}.parquet"
        tools.to_parquet(HIST_DIR / filename, index=False)

    except Exception as e:
        print(f"Error saving tools file in the historical folder {e}")

    try:
        all_trades = pd.read_parquet(DATA_DIR / "all_trades_profitability.parquet")
        filename = f"all_trades_profitability_{timestamp}.parquet"
        all_trades.to_parquet(HIST_DIR / filename, index=False)

    except Exception as e:
        print(
            f"Error saving all_trades_profitability file in the historical folder {e}"
        )


@measure_execution_time
def only_new_weekly_analysis():
    """Run weekly analysis for the FPMMS project."""
    rpc = RPC
    # Run markets ETL
    logging.info("Running markets ETL")
    mkt_etl(MARKETS_FILENAME)
    logging.info("Markets ETL completed")

    # New tools ETL
    logging.info("Generating the mech json files")
    # get only new data
    latest_timestamp = get_mech_events_since_last_run()
    if latest_timestamp == None:
        print("Error while getting the mech events")
        return
    logging.info(f"Finished generating the mech json files from {latest_timestamp}")

    # Run tools ETL
    logging.info("Generate and parse the tools content")
    # generate only new file
    generate_tools_file("new_tools_info.json", "new_tools.parquet")
    logging.info("Tools ETL completed")

    add_current_answer("new_tools.parquet")

    # # Run profitability analysis
    logging.info("Running profitability analysis")
    run_profitability_analysis(
        rpc=rpc,
        tools_filename="new_tools.parquet",
        trades_filename="new_fpmmTrades.parquet",
        from_timestamp=int(latest_timestamp.timestamp()),
        merge=True,
    )

    logging.info("Profitability analysis completed")

    # merge new json files with old json files
    update_json_files()

    try:
        updating_timestamps(rpc, TOOLS_FILENAME)
    except Exception as e:
        logging.error("Error while updating timestamps of tools")
        print(e)

    save_historical_data()

    clean_old_data_from_parquet_files("2024-10-06")

    compute_tools_accuracy()

    logging.info("Weekly analysis files generated and saved")


def old_weekly_analysis():
    """Run weekly analysis for the FPMMS project."""
    rpc = RPC
    # Run markets ETL
    logging.info("Running markets ETL")
    mkt_etl(MARKETS_FILENAME)
    logging.info("Markets ETL completed")

    # New tools ETL
    logging.info("Generating the mech json files")

    get_mech_events_last_60_days()
    logging.info("Finished generating the mech json files")

    # Run tools ETL
    logging.info("Generate and parse the tools content")

    generate_tools_file("tools_info.json", TOOLS_FILENAME)
    logging.info("Tools ETL completed")
    add_current_answer(TOOLS_FILENAME)

    # Run profitability analysis
    logging.info("Running profitability analysis")
    run_profitability_analysis(
        rpc=rpc,
        tools_filename=TOOLS_FILENAME,
        trades_filename="fpmmTrades.parquet",
        from_timestamp=DEFAULT_60_DAYS_AGO_TIMESTAMP,
    )
    logging.info("Profitability analysis completed")

    try:
        updating_timestamps(rpc, TOOLS_FILENAME)
    except Exception as e:
        logging.error("Error while updating timestamps of tools")
        print(e)

    compute_tools_accuracy()

    logging.info("Weekly analysis files generated and saved")


if __name__ == "__main__":
    only_new_weekly_analysis()
    # weekly_analysis()
    # rpc = RPC
    # updating_timestamps(rpc)
    # compute_tools_accuracy()