import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline
import joblib

# Load dataset
df = pd.read_csv("disease_dataset.csv")

# Split data
X = df["symptoms"]
y = df["disease"]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create a pipeline with TF-IDF and Naive Bayes
model = make_pipeline(TfidfVectorizer(), MultinomialNB())
model.fit(X_train, y_train)

# Save the model
joblib.dump(model, "disease_model.pkl")
print("Model trained and saved!")