from data_analysis_engine.dataset_builder import add_technical_indicators
from data_analysis_engine.models.xgboost_model import XGBoostModel
import pandas as pd
import os
import glob

def analyze_stocks_pipeline(cds_dir, model_path, top_n=10, output_path="prediction_result.csv"):
    model = XGBoostModel()
    model.load_model(model_path)

    results = []

    csv_files = glob.glob(os.path.join(cds_dir, "*_ohlcv.csv"))
    for file in csv_files:
        symbol = os.path.basename(file).replace("_ohlcv.csv", "")
        df = pd.read_csv(file)
        df = add_technical_indicators(df)

        feature_cols = [
            'open', 'high', 'low', 'close', 'volume',
            'sma_5', 'sma_10', 'rsi_14', 'macd',
            'boll_upper', 'boll_lower'
        ]
        X = df[feature_cols].dropna()
        if X.empty:
            continue

        prob = model.predict_proba(X.tail(1))  # 이미 float 값임
        results.append({"symbol": symbol, "predicted_score": prob})

    result_df = pd.DataFrame(results)
    result_df.sort_values(by="predicted_score", ascending=False, inplace=True)
    result_df.head(top_n).to_csv(output_path, index=False)
    print("✅ 예측 결과 저장 완료:", output_path)