Upload 8 files

.gitattributes

@@ -32,3 +32,5 @@ 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
+jigsaw-toxic-comment-classification-challenge/test.csv/test.csv filter=lfs diff=lfs merge=lfs -text
+jigsaw-toxic-comment-classification-challenge/train.csv/train.csv filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,40 @@
+import os
+import pandas as pd
+import tensorflow as tf
+import numpy as np
+
+from tensorflow.keras.layers import TextVectorization
+import gradio as gr
+from tensorflow.keras.layers import TextVectorization
+
+modelbaru = tf.keras.models.load_model('toxicity.h5')
+
+MAX_FEATURES = 200000
+data = pd.read_csv(os.path.join('jigsaw-toxic-comment-classification-challenge', 'train.csv', 'train.csv'))
+x = data['comment_text']
+y = data[data.columns[2:]].values
+
+vectorizer = TextVectorization(max_tokens=MAX_FEATURES, output_sequence_length=1800, output_mode='int')
+vectorizer.adapt(x.values)
+vectorizer('Yo Whats up')[:3]
+vectorized_text = vectorizer(x.values)
+vectorized_text
+
+input_str = vectorizer('yo i fuckin hate you')
+res = modelbaru.predict(np.expand_dims(input_str,0))
+res > 0.5
+data.columns[2:]
+data.columns[2:-1]
+
+def score_comment(comment):
+    vectorized_comment = vectorizer([comment])
+    results = modelbaru.predict(vectorized_comment)
+
+    text = ''
+    for idx, col in enumerate(data.columns[2:-1]):
+        text += '{}: {}\n'.format(col, results[0][idx]>0.5)
+    
+    return text
+
+interface = gr.Interface(fn=score_comment, inputs=gr.inputs.Textbox(lines=2, placeholder='Toxic Detector by: AezersX'), outputs='text')
+interface.launch(share=True)

flagged/log.csv

@@ -0,0 +1,15 @@
+'comment','output','flag','username','timestamp'
+'','toxic: False
+severe_toxic: False
+obscene: False
+threat: False
+insult: False
+','','','2022-08-05 22:09:27.277332'
+'','toxic: False
+severe_toxic: False
+obscene: False
+threat: False
+insult: False
+','','','2022-08-05 22:09:29.066786'
+'test','','','','2022-12-22 19:43:56.796880'
+'test','','','','2022-12-22 19:43:57.836865'

jigsaw-toxic-comment-classification-challenge/test.csv/test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2513ce4abb98c4d1d216e3ca0d4377d57589a0989aa8c06a840509a16c786e8
+size 60354593

jigsaw-toxic-comment-classification-challenge/train.csv/train.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4084611bd27c939ba98e5e63bc3e5a2c1a4e99477dcba46c829e4c986c429d
+size 68802655

requirements.txt

@@ -0,0 +1,4 @@
+pandas
+tensorflow == 2.1.0
+numpy
+gradio

toxicity.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165dd163b69f9ba71c6a78193a3d2f3a196ff8d0916d4194e8f848f9ae423c7b
+size 77581464