import os

import pandas as pd
from sklearn.naive_bayes import GaussianNB
from sklearn import preprocessing
import joblib

TRAIN_DATA_DIR = "datasets_train_raw"
train_df_list = []
for file in os.listdir(TRAIN_DATA_DIR):
    file_path = os.path.join(TRAIN_DATA_DIR, file)
    df = pd.read_csv(file_path, delim_whitespace=True, skiprows=1,
                                       names=["tbid", "tphys", "r", "vr", "vt", "ik1", "ik2", "sm1", "sm2", "a", "e",
                                              "collapsed"])
    train_df_list.append(df)
data_train = pd.concat(train_df_list, ignore_index=True).sample(frac=1, random_state=42)

X_train = data_train.iloc[:, 1:-1].values
y_train = data_train.iloc[:, -1].values

lab = preprocessing.LabelEncoder()
y_train_transformed = lab.fit_transform(y_train)

clf = GaussianNB(var_smoothing=1e-07)
clf.fit(X_train, y_train_transformed)

joblib.dump(clf, 'trained_model.pkl')
joblib.dump(lab, 'label_encoder.pkl')