src/models/train_baseline.py

import os
import mlflow
import mlflow.sklearn
import pandas as pd

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.metrics import accuracy_score, f1_score, classification_report
import joblib


train_df = pd.read_csv("data/splits/train.csv")
val_df = pd.read_csv("data/splits/val.csv")

X_train = train_df["clean_text"]
y_train = train_df["label_text"]

X_val = val_df["clean_text"]
y_val = val_df["label_text"]

os.makedirs("models", exist_ok=True)

mlflow.set_experiment("bbc-document-classification")

with mlflow.start_run(run_name="tfidf_logistic_regression"):

    model = Pipeline([
        ("tfidf", TfidfVectorizer(max_features=5000)),
        ("classifier", LogisticRegression(max_iter=1000))
    ])

    model.fit(X_train, y_train)

    y_pred = model.predict(X_val)

    accuracy = accuracy_score(y_val, y_pred)
    f1 = f1_score(y_val, y_pred, average="weighted")

    print("Accuracy:", accuracy)
    print("F1 Score:", f1)
    print("\nClassification Report:")
    print(classification_report(y_val, y_pred))

    mlflow.log_param("model", "TF-IDF + Logistic Regression")
    mlflow.log_param("max_features", 5000)
    mlflow.log_metric("accuracy", accuracy)
    mlflow.log_metric("f1_score", f1)

    joblib.dump(model, "models/baseline_model.pkl")
    mlflow.sklearn.log_model(model, "baseline_model")

print("Baseline model training completed.")