Update README.md

README.md

@@ -1,3 +1,74 @@
 ---
 license: cc0-1.0
 ---
+
+**Note:** Due to nature of toxic comments, data and code contain explicit language.
+
+Data is from kaggle, the *Toxic Comment Classification Challenge*
+<br>
+https://www.kaggle.com/competitions/jigsaw-toxic-comment-classification-challenge/data?select=train.csv.zip
+
+Dataset used for training: https://huggingface.co/datasets/vluz/Tox
+
+Trained over 30 epoch in a runpod
+
+### 🤗 Running demo here:    
+https://huggingface.co/spaces/vluz/Tox
+
+<hr>
+
+Code requires pandas, tensorflow, and streamlit. All can be installed via `pip`.
+
+```python
+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.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)
+```
+
+
+Put `toxmodel.keras` and `vectorizer.pkl` into the `model` dir.     
+
+Then do:
+```
+stramlit run toxtest.py
+```
+
+Expected results from default prompt are positive for 0 and 2
+
+<hr>
+
+Full code can be found here:
+<br>
+https://github.com/vluz/ToxTest/
+<br>