Spaces:
Runtime error
Runtime error
Upload app.py
Browse files
app.py
CHANGED
|
@@ -1,32 +1,94 @@
|
|
| 1 |
-
|
| 2 |
import gradio as gr
|
| 3 |
-
|
|
|
|
| 4 |
|
| 5 |
# Load your model and tokenizer from local paths
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
model_path = '.'
|
| 7 |
tokenizer_path = '.'
|
| 8 |
|
| 9 |
model_sentiment = AutoModelForSequenceClassification.from_pretrained(model_path)
|
| 10 |
tokenizer_sentiment = AutoTokenizer.from_pretrained(tokenizer_path)
|
| 11 |
|
| 12 |
-
# Initialize the
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
# Define the sentiment analysis function
|
| 16 |
def analyze_sentiment(text):
|
| 17 |
-
predictions =
|
| 18 |
label_mapping = {'LABEL_0': 'Negative', 'LABEL_1': 'Neutral', 'LABEL_2': 'Positive'}
|
| 19 |
predicted_label = label_mapping[predictions[0]['label']]
|
| 20 |
confidence = f"{predictions[0]['score'] * 100:.2f}%"
|
| 21 |
return predicted_label, confidence
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
# Create the Gradio interface
|
| 24 |
interface = gr.Interface(
|
| 25 |
-
fn=
|
| 26 |
-
inputs=gr.Textbox(lines=2, placeholder="Enter
|
| 27 |
-
outputs=[
|
| 28 |
-
|
| 29 |
-
|
|
|
|
|
|
|
|
|
|
| 30 |
)
|
| 31 |
|
| 32 |
if __name__ == "__main__":
|
|
|
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
+
import torch
|
| 3 |
+
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification, AutoConfig
|
| 4 |
|
| 5 |
# Load your model and tokenizer from local paths
|
| 6 |
+
model_NER = AutoModelForTokenClassification.from_pretrained(
|
| 7 |
+
pretrained_model_name_or_path=None,
|
| 8 |
+
config="config_2.json",
|
| 9 |
+
state_dict=torch.load("model_2.safetensors", map_location=torch.device('cpu'))
|
| 10 |
+
)
|
| 11 |
+
|
| 12 |
+
tokenizer_NER = AutoTokenizer.from_pretrained(
|
| 13 |
+
pretrained_model_name_or_path=None,
|
| 14 |
+
tokenizer_file="tokenizer_2.json",
|
| 15 |
+
special_tokens_map_file="special_tokens_map_2.json",
|
| 16 |
+
tokenizer_config_file="tokenizer_config_2.json",
|
| 17 |
+
vocab_file="vocab_2.txt"
|
| 18 |
+
)
|
| 19 |
+
|
| 20 |
+
# Load sentiment analysis model and tokenizer
|
| 21 |
model_path = '.'
|
| 22 |
tokenizer_path = '.'
|
| 23 |
|
| 24 |
model_sentiment = AutoModelForSequenceClassification.from_pretrained(model_path)
|
| 25 |
tokenizer_sentiment = AutoTokenizer.from_pretrained(tokenizer_path)
|
| 26 |
|
| 27 |
+
# Initialize the pipelines
|
| 28 |
+
clf_sentiment = pipeline("text-classification", model=model_sentiment, tokenizer=tokenizer_sentiment)
|
| 29 |
+
clf_ner = pipeline("ner", model=model_NER, tokenizer=tokenizer_NER)
|
| 30 |
+
|
| 31 |
+
# Load the model configuration to get the labels for NER
|
| 32 |
+
config = AutoConfig.from_pretrained("config_2.json")
|
| 33 |
+
label_list = config.id2label
|
| 34 |
|
| 35 |
# Define the sentiment analysis function
|
| 36 |
def analyze_sentiment(text):
|
| 37 |
+
predictions = clf_sentiment(text)
|
| 38 |
label_mapping = {'LABEL_0': 'Negative', 'LABEL_1': 'Neutral', 'LABEL_2': 'Positive'}
|
| 39 |
predicted_label = label_mapping[predictions[0]['label']]
|
| 40 |
confidence = f"{predictions[0]['score'] * 100:.2f}%"
|
| 41 |
return predicted_label, confidence
|
| 42 |
|
| 43 |
+
|
| 44 |
+
def analyze_ner(input_text):
|
| 45 |
+
predictions = clf_ner(input_text)
|
| 46 |
+
|
| 47 |
+
merged_tokens = []
|
| 48 |
+
current_word = ""
|
| 49 |
+
current_tag = None
|
| 50 |
+
current_confidence = 0
|
| 51 |
+
|
| 52 |
+
for pred in predictions:
|
| 53 |
+
token = pred['word']
|
| 54 |
+
tag = label_list[int(pred['entity'].split('_')[-1])]
|
| 55 |
+
confidence = pred['score']
|
| 56 |
+
|
| 57 |
+
if token.startswith("##"):
|
| 58 |
+
current_word += token[2:]
|
| 59 |
+
current_confidence = min(current_confidence, confidence)
|
| 60 |
+
else:
|
| 61 |
+
if current_word:
|
| 62 |
+
merged_tokens.append((current_word, current_tag, current_confidence))
|
| 63 |
+
current_word = token
|
| 64 |
+
current_tag = tag
|
| 65 |
+
current_confidence = confidence
|
| 66 |
+
|
| 67 |
+
if current_word:
|
| 68 |
+
merged_tokens.append((current_word, current_tag, current_confidence))
|
| 69 |
+
|
| 70 |
+
results = []
|
| 71 |
+
for word, tag, confidence in merged_tokens:
|
| 72 |
+
results.append(f"Entity: {word}, Tag: {tag}, Confidence: {confidence:.2f}")
|
| 73 |
+
|
| 74 |
+
return "\n".join(results)
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
def analyze_text(text):
|
| 78 |
+
sentiment_result = analyze_sentiment(text)
|
| 79 |
+
ner_result = analyze_ner(text)
|
| 80 |
+
return sentiment_result, ner_result
|
| 81 |
+
|
| 82 |
# Create the Gradio interface
|
| 83 |
interface = gr.Interface(
|
| 84 |
+
fn=analyze_text,
|
| 85 |
+
inputs=gr.Textbox(lines=2, placeholder="Enter text here..."),
|
| 86 |
+
outputs=[
|
| 87 |
+
gr.Textbox(label="Sentiment Analysis Result"),
|
| 88 |
+
gr.Textbox(label="Named Entity Recognition Result")
|
| 89 |
+
],
|
| 90 |
+
title="Text Analysis",
|
| 91 |
+
description="This interface allows you to perform Sentiment Analysis and Named Entity Recognition (NER) on text."
|
| 92 |
)
|
| 93 |
|
| 94 |
if __name__ == "__main__":
|