Spaces:
Sleeping
Sleeping
File size: 3,869 Bytes
14fa848 30d04c6 14fa848 30d04c6 b5dd5bc 30d04c6 b5dd5bc 30d04c6 b5dd5bc 30d04c6 100e8bf 30d04c6 b5dd5bc 30d04c6 100e8bf 30d04c6 b2cc9b7 30d04c6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
import streamlit as st
import wandb
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForTokenClassification
x = st.slider('Select a value')
st.write(x, 'squared is', x * x)
@st.cache_resource()
def load_trained_model():
tokenizer = AutoTokenizer.from_pretrained("LampOfSocrates/bert-cased-plodcw-sourav")
model = AutoModelForTokenClassification.from_pretrained("LampOfSocrates/bert-cased-plodcw-sourav")
# Mapping labels
id2label = model.config.id2label
# Print the label mapping
print(f"Can recognise the following labels {id2label}")
# Load the NER model and tokenizer from Hugging Face
#ner_pipeline = pipeline("ner", model="dbmdz/bert-large-cased-finetuned-conll03-english")
ner_pipeline = pipeline("ner", model=model, tokenizer = tokenizer)
return ner_pipeline
def load_data():
from datasets import load_dataset
dat_CW = load_dataset("surrey-nlp/PLOD-CW")
def render_entities(tokens, entities):
"""
Renders a page with a 2-column table showing the entity corresponding to each token.
"""
# Page configuration
st.set_page_config(page_title="NER Token Entities", layout="centered")
# Custom CSS for chilled and cool theme
st.markdown("""
<style>
body {
font-family: 'Arial', sans-serif;
background-color: #f0f0f5;
color: #333333;
}
table {
width: 100%;
border-collapse: collapse;
}
th, td {
padding: 12px;
text-align: left;
border-bottom: 1px solid #dddddd;
}
th {
background-color: #4CAF50;
color: white;
}
tr:hover {
background-color: #f5f5f5;
}
</style>
""", unsafe_allow_html=True)
# Title and description
st.title("Token Entities Table")
st.write("This table shows the entity corresponding to each token in a cool and chilled theme.")
# Create the table
table_data = {"Token": tokens, "Entity": entities}
st.table(table_data)
def prep_page():
model = load_trained_model()
# Streamlit app
st.title("Named Entity Recognition with BERT on PLOD-CW")
st.write("Enter a sentence to see the named entities recognized by the model.")
# Text input
text = st.text_area("Enter your sentence here:")
# Perform NER and display results
if text:
st.write("Entities recognized:")
entities = model(text)
# Create a dictionary to map entity labels to colors
label_colors = {
'B-LF': 'lightblue',
'B-O': 'lightgreen',
'B-AC': 'lightcoral',
'I-LF': 'lightyellow'
}
# Prepare the HTML output with styled entities
def get_entity_html(text, entities):
html = ""
last_idx = 0
for entity in entities:
start = entity['start']
end = entity['end']
label = entity['entity']
entity_text = text[start:end]
color = label_colors.get(label, 'lightgray')
# Append the text before the entity
html += text[last_idx:start]
# Append the entity with styling
html += f'<mark style="background-color: {color}; border-radius: 3px;">{entity_text}</mark>'
last_idx = end
# Append any remaining text after the last entity
html += text[last_idx:]
return html
# Generate and display the styled HTML
styled_text = get_entity_html(text, entities)
st.markdown(styled_text, unsafe_allow_html=True)
render_entities(text, entities)
if __name__ == '__main__':
prep_page() |