Shridhartd commited on
Commit
9a34bd2
·
verified ·
1 Parent(s): 9e73e44

Upload 2 files

Browse files
Files changed (2) hide show
  1. app.py +28 -0
  2. requirements.txt +5 -0
app.py ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ from transformers import AutoTokenizer, AutoModel
3
+ import torch
4
+ import numpy as np
5
+ from sklearn.linear_model import LogisticRegression
6
+
7
+ # Load Hugging Face model
8
+ model_name = "bert-base-uncased"
9
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
10
+ model = AutoModel.from_pretrained(model_name)
11
+
12
+ # Function to get text embeddings
13
+ def get_embedding(text):
14
+ inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
15
+ with torch.no_grad():
16
+ outputs = model(**inputs)
17
+ return outputs.last_hidden_state[:, 0, :].numpy()
18
+
19
+ # Sample dataset (sentiment analysis)
20
+ texts = ["I love this!", "This is terrible.", "Fantastic experience!", "I hate it."]
21
+ labels = [1, 0, 1, 0] # 1 = Positive, 0 = Negative
22
+
23
+ # Convert text to embeddings
24
+ X = np.vstack([get_embedding(text) for text in texts])
25
+ y = np.array(labels)
26
+
27
+ # Train Logistic Regression model
28
+ clf =
requirements.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ transformers
2
+ scikit-learn
3
+ torch
4
+ streamlit
5
+ numpy