import os
import joblib
import pandas as pd
from sklearn.impute import SimpleImputer

TEST_DATA_DIR = "datasets_test"

test_df_list = []
for file in os.listdir(TEST_DATA_DIR):
    file_path = os.path.join(TEST_DATA_DIR, file)
    data_test = pd.read_csv(file_path, delim_whitespace=True, skiprows=1,
                                       names=["tbid", "tphys", "r", "vr", "vt", "ik1", "ik2", "sm1", "sm2", "a", "e",
                                              "collapsed"])
    X_test = data_test.iloc[:, 1:-1].values

    imputer = SimpleImputer(strategy='mean')
    X_imputed = imputer.fit_transform(X_test)

    model_filename = 'trained_model.pkl'
    model = joblib.load(model_filename)

    predictions = model.predict(X_test)
    data_test['prediction'] = predictions

    save_path = os.path.join(TEST_DATA_DIR, file + '.pred')
    data_test.to_csv(save_path, index=False, sep=' ')