Spaces:
Runtime error
Runtime error
soumyaprabhamaiti
commited on
Commit
•
5ce506c
1
Parent(s):
cc07f38
Add hate classifier app
Browse files- .gitattributes +35 -0
- .github/workflows/check_file_size.yml +16 -0
- .github/workflows/sync_to_hub.yml +20 -0
- README.md +11 -0
- app.py +51 -0
- model.h5 +3 -0
- requirements.txt +4 -0
- tokenizer.pickle +3 -0
- utils.py +38 -0
.gitattributes
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
.github/workflows/check_file_size.yml
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
name: Check file size
|
2 |
+
on: # or directly `on: [push]` to run the action on every push on any branch
|
3 |
+
pull_request:
|
4 |
+
branches: [main]
|
5 |
+
|
6 |
+
# to run this workflow manually from the Actions tab
|
7 |
+
workflow_dispatch:
|
8 |
+
|
9 |
+
jobs:
|
10 |
+
check-file-size:
|
11 |
+
runs-on: ubuntu-latest
|
12 |
+
steps:
|
13 |
+
- name: Check large files
|
14 |
+
uses: ActionsDesk/[email protected]
|
15 |
+
with:
|
16 |
+
filesizelimit: 10485760 # this is 10MB so we can sync to HF Spaces
|
.github/workflows/sync_to_hub.yml
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
name: Sync to Hugging Face hub
|
2 |
+
on:
|
3 |
+
push:
|
4 |
+
branches: [main]
|
5 |
+
|
6 |
+
# to run this workflow manually from the Actions tab
|
7 |
+
workflow_dispatch:
|
8 |
+
|
9 |
+
jobs:
|
10 |
+
sync-to-hub:
|
11 |
+
runs-on: ubuntu-latest
|
12 |
+
steps:
|
13 |
+
- uses: actions/checkout@v3
|
14 |
+
with:
|
15 |
+
fetch-depth: 0
|
16 |
+
lfs: true
|
17 |
+
- name: Push to hub
|
18 |
+
env:
|
19 |
+
HF: ${{ secrets.HF }}
|
20 |
+
run: git push --force https://soumyaprabhamaiti:[email protected]/spaces/soumyaprabhamaiti/hate_speech_classifier main
|
README.md
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Hate Speech Classifier
|
3 |
+
emoji: 📊
|
4 |
+
colorFrom: gray
|
5 |
+
colorTo: blue
|
6 |
+
sdk: gradio
|
7 |
+
sdk_version: 3.42.0
|
8 |
+
app_file: app.py
|
9 |
+
pinned: false
|
10 |
+
license: mit
|
11 |
+
---
|
app.py
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pickle
|
2 |
+
|
3 |
+
import gradio as gr
|
4 |
+
import numpy as np
|
5 |
+
import tensorflow as tf
|
6 |
+
|
7 |
+
from utils import clean_text, tokenize_and_pad
|
8 |
+
|
9 |
+
# Load pre-trained TensorFlow model
|
10 |
+
model = tf.keras.models.load_model('model.h5')
|
11 |
+
|
12 |
+
# Load tokenizer
|
13 |
+
with open('tokenizer.pickle', 'rb') as handle:
|
14 |
+
tokenizer = pickle.load(handle)
|
15 |
+
print(type(tokenizer))
|
16 |
+
|
17 |
+
# Constants
|
18 |
+
MAX_LEN = 300
|
19 |
+
|
20 |
+
|
21 |
+
def predict_hate_speech(text):
|
22 |
+
# Clean the text
|
23 |
+
cleaned_text = clean_text(text)
|
24 |
+
|
25 |
+
|
26 |
+
# Tokenize and pad the text
|
27 |
+
preprocessed_text = tokenize_and_pad([cleaned_text], tokenizer, MAX_LEN)
|
28 |
+
|
29 |
+
# Make a prediction
|
30 |
+
prediction = model.predict(preprocessed_text)
|
31 |
+
|
32 |
+
# Assuming you have two classes: "Hate" and "Not Hate"
|
33 |
+
if prediction > 0.5:
|
34 |
+
result = "Hate"
|
35 |
+
else:
|
36 |
+
result = "Not Hate"
|
37 |
+
|
38 |
+
return result
|
39 |
+
|
40 |
+
|
41 |
+
# Create a Gradio interface
|
42 |
+
iface = gr.Interface(
|
43 |
+
fn=predict_hate_speech,
|
44 |
+
inputs=gr.Textbox(label="Input Text"),
|
45 |
+
outputs=gr.Textbox(label="Output Prediction"),
|
46 |
+
title="Hate Speech Classification",
|
47 |
+
description="A simple hate speech classifier. Enter a text and click submit to make a prediction."
|
48 |
+
)
|
49 |
+
|
50 |
+
# Run the Gradio app
|
51 |
+
iface.launch()
|
model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b836d0f75bb836d9cd0cfcd0657e35cfd659a7c4085af86ddec382cfdb9275dc
|
3 |
+
size 40676464
|
requirements.txt
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
tensorflow
|
2 |
+
numpy
|
3 |
+
gradio
|
4 |
+
nltk
|
tokenizer.pickle
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f982b4524646588f84f61f9cb9bc49998672afccc012f355af7eb787117bd1a0
|
3 |
+
size 1701049
|
utils.py
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import re
|
2 |
+
import string
|
3 |
+
from collections.abc import Iterable
|
4 |
+
|
5 |
+
import nltk
|
6 |
+
import numpy as np
|
7 |
+
from keras.preprocessing.text import Tokenizer
|
8 |
+
from keras.utils import pad_sequences
|
9 |
+
from nltk.corpus import stopwords
|
10 |
+
|
11 |
+
nltk.download('stopwords')
|
12 |
+
|
13 |
+
|
14 |
+
# Apply regex and do cleaning.
|
15 |
+
def clean_text(words: str) -> str:
|
16 |
+
words = str(words).lower()
|
17 |
+
words = re.sub('\[.*?\]', '', words)
|
18 |
+
words = re.sub('https?://\S+|www\.\S+', '', words)
|
19 |
+
words = re.sub('<.*?>+', '', words)
|
20 |
+
words = re.sub(r'@\w+', '', words)
|
21 |
+
words = re.sub('[%s]' % re.escape(string.punctuation), '', words)
|
22 |
+
words = re.sub('\n', '', words)
|
23 |
+
words = re.sub('\w*\d\w*', '', words)
|
24 |
+
|
25 |
+
stopword = set(stopwords.words('english'))
|
26 |
+
words = ' '.join(
|
27 |
+
[word for word in words.split(' ') if word not in stopword])
|
28 |
+
|
29 |
+
stemmer = nltk.SnowballStemmer("english")
|
30 |
+
words = ' '.join([stemmer.stem(word) for word in words.split(' ')])
|
31 |
+
|
32 |
+
return words
|
33 |
+
|
34 |
+
|
35 |
+
def tokenize_and_pad(text_list: Iterable[str], tokenizer: Tokenizer, max_len: int) -> np.ndarray[np.str_]:
|
36 |
+
sequences = tokenizer.texts_to_sequences(text_list)
|
37 |
+
sequences_matrix = pad_sequences(sequences, maxlen=max_len)
|
38 |
+
return sequences_matrix
|