|
--- |
|
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 |
|
|
|
A copy of the data exists on the `data` directory. |
|
|
|
Trained over 20 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"])) # fix for 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() |
|
default_prompt = "i love you man, but fuck you!" |
|
input_text = st.text_area("Comment:", default_prompt, height=150).lower() |
|
if st.button("Test"): |
|
if not input_text: |
|
st.write("⚠ Warning: Empty prompt.") |
|
elif len(input_text) < 15: |
|
st.write("⚠ Warning: Model is far less accurate with a small prompt.") |
|
if input_text == default_prompt: |
|
st.write("Expected results from default prompt are positive for 0 and 2") |
|
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 result from default prompt is 0 and 2 |
|
|
|
<hr> |
|
|
|
Full code can be found here: |
|
<br> |
|
https://github.com/vluz/ToxTest/ |
|
<br> |
