import logging
import os
import pickle
from web3 import Web3
import pandas as pd
from functools import partial
from datetime import datetime
from markets import (
    etl as mkt_etl,
    DEFAULT_FILENAME as MARKETS_FILENAME,
)

TOOLS_FILENAME = "tools_2024.parquet"
from tools import (
    etl as tools_etl,
    update_tools_accuracy,
)
from pull_data import (
    DATA_DIR,
    parallelize_timestamp_conversion,
    block_number_to_timestamp,
)
from profitability import run_profitability_analysis
from get_mech_info import get_mech_info_2024
from utils import get_question, current_answer
import gc

logging.basicConfig(level=logging.INFO)


def roi_analysis():
    """Run ROI analysis for the trades done in 2024."""
    rpc = "https://lb.nodies.app/v1/406d8dcc043f4cb3959ed7d6673d311a"
    web3 = Web3(Web3.HTTPProvider(rpc))

    # Run markets ETL
    logging.info("Running markets ETL")
    mkt_etl(MARKETS_FILENAME)
    logging.info("Markets ETL completed")

    # Run tools ETL
    logging.info("Running tools ETL")

    # This etl is saving already the tools parquet file
    tools_etl(
        rpcs=[rpc],
        mech_info=get_mech_info_2024(),
        filename=TOOLS_FILENAME,
    )
    logging.info("Tools ETL completed")

    # Run profitability analysis
    if os.path.exists(DATA_DIR / "fpmmTrades.parquet"):
        os.remove(DATA_DIR / "fpmmTrades.parquet")
    logging.info("Running profitability analysis")
    date = "2024-01-01"
    datetime_jan_2024 = datetime.strptime(date, "%Y-%m-%d")
    timestamp_jan_2024 = int(datetime_jan_2024.timestamp())
    run_profitability_analysis(
        rpc=rpc,
        tools_filename=TOOLS_FILENAME,
        trades_filename="fpmmTrades.parquet",
        from_timestamp=timestamp_jan_2024,
    )
    logging.info("Profitability analysis completed")

    # 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")

    # Convert block number to timestamp
    logging.info("Converting block number to timestamp")
    t_map = pickle.load(open(DATA_DIR / "t_map.pkl", "rb"))
    tools["request_time"] = tools["request_block"].map(t_map)

    # Identify tools with missing request_time and fill them
    missing_time_indices = tools[tools["request_time"].isna()].index
    if not missing_time_indices.empty:
        partial_block_number_to_timestamp = partial(
            block_number_to_timestamp, web3=web3
        )
        missing_timestamps = parallelize_timestamp_conversion(
            tools.loc[missing_time_indices], partial_block_number_to_timestamp
        )

        # Update the original DataFrame with the missing timestamps
        for i, timestamp in zip(missing_time_indices, missing_timestamps):
            tools.at[i, "request_time"] = timestamp

    tools["request_month_year"] = pd.to_datetime(tools["request_time"]).dt.strftime(
        "%Y-%m"
    )
    tools["request_month_year_week"] = (
        pd.to_datetime(tools["request_time"]).dt.to_period("W").astype(str)
    )

    # Save the tools data after the updates on the content
    tools.to_parquet(DATA_DIR / TOOLS_FILENAME, index=False)

    # Update t_map with new timestamps
    new_timestamps = (
        tools[["request_block", "request_time"]]
        .dropna()
        .set_index("request_block")
        .to_dict()["request_time"]
    )
    t_map.update(new_timestamps)

    with open(DATA_DIR / "t_map_2024.pkl", "wb") as f:
        pickle.dump(t_map, f)

    # clean and release all memory
    del tools
    del fpmms
    del t_map
    gc.collect()

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


if __name__ == "__main__":
    roi_analysis()