Add vectorizer

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 from model import CustomModel
-from preprocess import preprocess_pipeline
+from preprocess import preprocess_pipeline, vectorizer
 import os
 
 os.system("cp -r ./nltk_data/ /home/user/nltk_data")
@@ -8,6 +8,7 @@ os.system("cp -r ./nltk_data/ /home/user/nltk_data")
 def analyze(text):
     model = CustomModel()
     text = preprocess_pipeline(text)
+    text = vectorizer(text)
     return text
 
 app = gr.Interface(fn=analyze, inputs="text", outputs="text")

preprocess.py

@@ -1,4 +1,7 @@
 import re
+from nltk.corpus.reader import pickle
+import pandas as pd
+import numpy as np
 from nltk.corpus import stopwords
 from nltk.stem import SnowballStemmer
 
@@ -20,3 +23,8 @@ def clean_text(text):
 
 def preprocess_pipeline(text):
     return clean_text(text)
+
+def vectorizer(text):
+    count_vectorizer = pickle.load(open("vectorizers/count_vectorizer.pkl", "rb"))
+    return count_vectorizer.transform(text)
+