# source: https://raw.githubusercontent.com/sfmskywalker/trading-bots/f36c636fe8b699032ac019b1149117bb3fcc604c/freqtrade-freqai/user_data/strategies/FreqaiTrend.py
"""Bot C: FreqAI adaptive ML strategy.

A LightGBM regressor is continuously retrained on the last 30 days of data
per pair and predicts the mean price move over the next 12 hours. Entries and
exits follow the model's prediction — this is the statistical-learning
counterpart to the LLM-driven bots.
"""
import talib.abstract as ta
from freqtrade.strategy import IStrategy
from pandas import DataFrame


class Github_sfmskywalker_trading_bots__FreqaiTrend__20260704_201743(IStrategy):
    INTERFACE_VERSION = 3

    timeframe = "1h"
    can_short = False
    process_only_new_candles = True
    startup_candle_count = 120

    minimal_roi = {"0": 0.10, "720": 0.03, "1440": 0.01}
    stoploss = -0.05
    trailing_stop = True
    trailing_stop_positive = 0.02
    trailing_stop_positive_offset = 0.04
    trailing_only_offset_is_reached = True

    entry_threshold = 0.01   # predicted 12h move must exceed +1%
    exit_threshold = -0.005  # exit when prediction turns below -0.5%

    def feature_engineering_expand_all(self, dataframe: DataFrame, period: int,
                                       metadata: dict, **kwargs) -> DataFrame:
        dataframe["%-rsi-period"] = ta.RSI(dataframe, timeperiod=period)
        dataframe["%-ema-period"] = ta.EMA(dataframe, timeperiod=period)
        dataframe["%-adx-period"] = ta.ADX(dataframe, timeperiod=period)
        dataframe["%-relative_volume-period"] = (
            dataframe["volume"] / dataframe["volume"].rolling(period).mean()
        )
        return dataframe

    def feature_engineering_expand_basic(self, dataframe: DataFrame,
                                         metadata: dict, **kwargs) -> DataFrame:
        dataframe["%-pct-change"] = dataframe["close"].pct_change()
        dataframe["%-raw_volume"] = dataframe["volume"]
        dataframe["%-raw_price"] = dataframe["close"]
        return dataframe

    def feature_engineering_standard(self, dataframe: DataFrame,
                                     metadata: dict, **kwargs) -> DataFrame:
        dataframe["%-day_of_week"] = dataframe["date"].dt.dayofweek
        dataframe["%-hour_of_day"] = dataframe["date"].dt.hour
        return dataframe

    def set_freqai_targets(self, dataframe: DataFrame, metadata: dict,
                           **kwargs) -> DataFrame:
        label_period = self.freqai_info["feature_parameters"]["label_period_candles"]
        dataframe["&-target"] = (
            dataframe["close"].shift(-label_period).rolling(label_period).mean()
            / dataframe["close"] - 1
        )
        return dataframe

    def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
        return self.freqai.start(dataframe, metadata, self)

    def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
        dataframe.loc[
            (dataframe["do_predict"] == 1)
            & (dataframe["&-target"] > self.entry_threshold)
            & (dataframe["volume"] > 0),
            "enter_long",
        ] = 1
        return dataframe

    def populate_exit_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
        dataframe.loc[
            (dataframe["do_predict"] != 1)
            | (dataframe["&-target"] < self.exit_threshold),
            "exit_long",
        ] = 1
        return dataframe