Update app.py

app.py

@@ -1,20 +1,15 @@
-import os
 import gradio as gr
 import tensorflow as tf
-import pandas as pd
 
 from tensorflow.keras.layers import TextVectorization
 
-MAX_WORDS = 200000
+model_vect = tf.keras.models.Sequential()
+model_vect.add(tf.keras.Input(shape=(1,), dtype=tf.string))
+model_vect.add(vectorizer)
+model_vect.save('vect', save_format="tf")
 
-df = pd.read_csv(os.path.join('.', 'train.csv'))
-X = df['comment_text']
-
-vectorizer = TextVectorization(max_tokens=MAX_WORDS,
-                               output_sequence_length=1800,
-                               output_mode='int')
-
-vectorizer.adapt(X.values)
+loaded_vect_model = tf.keras.models.load_model('vect')
+vectorizer = loaded_vect_model.layers[0]
 
 model = tf.keras.models.load_model('toxicity.h5')