import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
import pickle 

product_descriptions = pd.read_csv("./train.csv")
product_descriptions = product_descriptions.dropna()

vectorizer = TfidfVectorizer(stop_words='english')
X1 = vectorizer.fit_transform(product_descriptions["product_descriptions"])

true_k = 10
model = KMeans(n_clusters=true_k, init='k-means++', max_iter=100, n_init=1)
model.fit(X1)


pickle.dump(model, open("model.pkl", "wb"))
pickle.dump(vectorizer, open("vectorizer.pkl", "wb"))