from datetime import datetime, timedelta
import os
import sys
import joblib
import numpy as np
os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
import yfinance as yf
import features
import matplotlib
matplotlib.use("Agg")

def Predict():

    # Get the Symbol from ARGV
    Symbol = sys.argv[1]

    # get the number of days ago to run the simulation for
    DaysBack = int(sys.argv[2])

    # calculate the time offsets
    end_date = datetime.now() - timedelta(days=DaysBack)
    start_date = end_date - timedelta(days=70)

    # convert to string formats
    start_str = start_date.strftime('%Y-%m-%d')
    end_str = end_date.strftime('%Y-%m-%d')

    # Define paths (consistent with your previous script)
    SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
    DATA_DIR = os.path.join(SCRIPT_DIR, "data")
    MODEL_PATH = os.path.join(DATA_DIR, "model.keras")

    # Pull 1 month of current data to make prediction against | for volatility 20
    df = yf.download(Symbol, start=start_str, end=end_str, auto_adjust=True, progress=False)
    if not df.empty:
        # Remove the horizontal ticker column
        df.columns = df.columns.get_level_values(0)
        # Add in the Vertical ticker column
        df['Ticker'] = Symbol
        # Make the feature set
        df = features.MakeFeatures(df)

    # Drop our predictor
    df.drop('Target_Close', axis=1, inplace=True)

    # Lazy load this so it doesnt interfere with yfinance
    from keras.models import load_model

    # Load the model
    reconstructed_model = load_model(MODEL_PATH)

    # Verify it loaded correctly
    reconstructed_model.summary()

    # Load the scalers
    feature_scaler = joblib.load(os.path.join(DATA_DIR, "feature_scaler.pkl"))
    target_scaler = joblib.load(os.path.join(DATA_DIR, "target_scaler.pkl"))

    # Scale the data
    scaled_data = feature_scaler.transform(df)

    # Predict
    scaled_predictions = reconstructed_model.predict(scaled_data)

    # Use the loaded target scaler to get back to % change
    actual_prediction = target_scaler.inverse_transform(scaled_predictions.reshape(-1, 1)).flatten()

    # 'predictions' will be a 2D array, flatten it if you want a simple list
    flat_predictions = actual_prediction

    # Get the overall trend to pull predictions from
    predictionTrend = 0
    with open("Target_Close_Average.txt", "r") as f:
        predictionTrend = float(f.read().strip())

    # Set the movement indicator
    movement_indicator = 0
    averagePrediction = np.mean(flat_predictions) + predictionTrend

    # Return to C# via stdout
    print(f"---RESULT_START---")
    print(averagePrediction)
    print(f"---RESULT_END---")

if __name__ == "__main__":
    Predict()