src/models/train.py

import pandas as pd
import pickle
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

from src.pipeline.build_pipeline import build_pipeline


def train_model():
    columns = ['target', 'id', 'date','flag','user','text']

    data = pd.read_csv(
    'data/training.csv',
    names=columns,
    encoding='ISO-8859-1'
)

    data.replace({'target': {4: 1}}, inplace=True)

    
    data = data.sample(1000, random_state=42)

    X = data['text']
    y = data['target']

    x_train, x_test, y_train, y_test = train_test_split(
        X, y, test_size=0.2, stratify=y, random_state=2
    )

    pipeline = build_pipeline()

    pipeline.fit(x_train, y_train)

    print("Train Accuracy:", accuracy_score(y_train, pipeline.predict(x_train)))
    print("Test Accuracy:", accuracy_score(y_test, pipeline.predict(x_test)))

    
    with open('artifacts/model.pkl', 'wb') as f:
        pickle.dump(pipeline, f)
# testing
# def test_ok():
#     hdshsdhfs
if __name__ == "__main__":
    train_model()