Upload 3 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+toxicity.keras filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,34 @@
+import tensorflow as tf
+from tensorflow.keras.layers import TextVectorization,LSTM
+import gradio as gr
+import pandas as pd
+import os
+
+df = pd.read_csv(os.path.join('jigsaw-toxic-comment-classification-challenge','train.csv', 'train.csv'))
+
+MAX_FEATURES = 200000 
+
+vectorizer = TextVectorization(max_tokens=MAX_FEATURES,
+                               output_sequence_length=1800,
+                               output_mode='int')
+
+# Adapt the vectorizer to the training data
+vectorizer.adapt(df['comment_text'].values)
+
+model = tf.keras.models.load_model('toxicity.keras')
+
+def score_comment(comment):
+    vectorized_comment = vectorizer([comment])
+    results = model.predict(vectorized_comment)
+    
+    text = ''
+    for idx, col in enumerate(df.columns[2:]):
+        text += '{}: {}\n'.format(col, results[0][idx]>0.5)
+
+    return text
+
+interface = gr.Interface(fn=score_comment, 
+                         inputs=gr.Textbox(lines=2, placeholder='Comment to score'),
+                        outputs='text')
+
+interface.launch(share=True)

requirements.txt

@@ -0,0 +1,4 @@
+tensorflow
+gradio
+pandas
+numpy

toxicity.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111e33518d819d1826e4751bcc32fd5c520ce0d8d71083350c1ff81f7b74daaf
+size 77953206