Upload 4 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
+model/toxmodel.keras filter=lfs diff=lfs merge=lfs -text

model/toxmodel.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ed25b56fd7cd096a1e42ec40154d317d36cb9389f22a6178f3526d0fed6bad
+size 77972576

model/vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861c5a2adbc2c8501dfe0d2333f28c54a39d198fbf2473fe27d1cd552f622579
+size 2750076

requirements.txt

@@ -0,0 +1,2 @@
+pandas
+

toxtest.py

@@ -0,0 +1,46 @@
+import os
+import pickle
+import streamlit as st
+import tensorflow as tf
+from tensorflow.keras.layers import TextVectorization
+
+
+@st.cache_resource
+def load_model():
+    model = tf.keras.models.load_model(os.path.join("model", "toxmodel.keras"))
+    return model
+
+
+@st.cache_resource
+def load_vectorizer():
+    from_disk = pickle.load(open(os.path.join("model", "vectorizer.pkl"), "rb"))
+    new_v = TextVectorization.from_config(from_disk['config'])
+    new_v.adapt(tf.data.Dataset.from_tensor_slices(["xyz"])) # Keras bug
+    new_v.set_weights(from_disk['weights'])
+    return new_v
+
+
+@st.cache_resource
+def load_vocab():
+    vocab = {}
+    with open('vocab.txt', 'r') as f:
+        for line in f:
+            token, index = line.strip().split('\t')
+            vocab[token] = int(index)
+
+
+st.title("Toxic Comment Test")
+st.divider()
+model = load_model()
+vectorizer = load_vectorizer()
+input_text = st.text_area("Comment:", "I love you man, but fuck you!", height=150)
+if st.button("Test"):
+    with st.spinner("Testing..."):
+        inputv = vectorizer([input_text])
+        output = model.predict(inputv)
+        res = (output > 0.5)
+    st.write(["toxic","severe toxic","obscene","threat","insult","identity hate"], res)
+    st.write(output)
+    print(output)
+
+