File size: 589 Bytes
267e3a7 8081d0b 267e3a7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 |
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"))
|