khandelwalkishna15
commited on
Commit
•
4f76b9d
1
Parent(s):
bfa5bb3
new changes
Browse files
app.py
CHANGED
@@ -5,15 +5,15 @@ model_name = "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis"
|
|
5 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
6 |
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
7 |
|
8 |
-
#
|
9 |
-
st.title("Financial Sentiment Analysis
|
10 |
|
11 |
-
#
|
12 |
text_input = st.text_area("Enter Financial News:", "Tesla stock is soaring after record-breaking earnings.")
|
13 |
|
14 |
# Function to perform sentiment analysis
|
15 |
def predict_sentiment(text):
|
16 |
-
inputs = tokenizer(text, return_tensors="pt")
|
17 |
outputs = model(**inputs)
|
18 |
sentiment_class = outputs.logits.argmax(dim=1).item()
|
19 |
sentiment_mapping = {0: 'Negative', 1: 'Neutral', 2: 'Positive'}
|
@@ -23,28 +23,43 @@ def predict_sentiment(text):
|
|
23 |
# Button to trigger sentiment analysis
|
24 |
if st.button("Analyze Sentiment"):
|
25 |
# Check if the input text is not empty
|
26 |
-
if text_input:
|
27 |
-
#
|
28 |
with st.spinner("Analyzing sentiment..."):
|
29 |
sentiment = predict_sentiment(text_input)
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
else:
|
36 |
-
st.warning("Please enter some text for sentiment analysis.")
|
37 |
|
38 |
-
# Optional:
|
39 |
if st.checkbox("Show Raw Sentiment Scores"):
|
40 |
-
if text_input:
|
41 |
inputs = tokenizer(text_input, return_tensors="pt")
|
42 |
outputs = model(**inputs)
|
43 |
raw_scores = outputs.logits[0].tolist()
|
44 |
st.info(f"Raw Sentiment Scores: {raw_scores}")
|
45 |
|
46 |
-
#
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
|
|
|
5 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
6 |
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
7 |
|
8 |
+
# Seting the page title
|
9 |
+
st.title("Financial Sentiment Analysis")
|
10 |
|
11 |
+
# Adding a text input for the user to input financial news
|
12 |
text_input = st.text_area("Enter Financial News:", "Tesla stock is soaring after record-breaking earnings.")
|
13 |
|
14 |
# Function to perform sentiment analysis
|
15 |
def predict_sentiment(text):
|
16 |
+
inputs = tokenizer(text, return_tensors="pt", max_length=1022, truncation=True)
|
17 |
outputs = model(**inputs)
|
18 |
sentiment_class = outputs.logits.argmax(dim=1).item()
|
19 |
sentiment_mapping = {0: 'Negative', 1: 'Neutral', 2: 'Positive'}
|
|
|
23 |
# Button to trigger sentiment analysis
|
24 |
if st.button("Analyze Sentiment"):
|
25 |
# Check if the input text is not empty
|
26 |
+
if text_input and text_input.strip(): # Check if input is not empty or contains only whitespaces
|
27 |
+
# Showing loading spinner while processing
|
28 |
with st.spinner("Analyzing sentiment..."):
|
29 |
sentiment = predict_sentiment(text_input)
|
30 |
+
|
31 |
+
# Extracting confidence scores
|
32 |
+
inputs = tokenizer(text_input, return_tensors="pt")
|
33 |
+
outputs = model(**inputs)
|
34 |
+
confidence_scores = outputs.logits.softmax(dim=1)[0].tolist()
|
35 |
+
|
36 |
+
# Considering a threshold for sentiment prediction
|
37 |
+
threshold = 0.5
|
38 |
+
|
39 |
+
# Change the success message background color based on sentiment and threshold
|
40 |
+
if sentiment == 'Positive' and confidence_scores[2] > threshold:
|
41 |
+
st.success(f"Sentiment: {sentiment} (Confidence: {confidence_scores[2]:.3f})")
|
42 |
+
elif sentiment == 'Negative' and confidence_scores[0] > threshold:
|
43 |
+
st.error(f"Sentiment: {sentiment} (Confidence: {confidence_scores[0]:.3f})")
|
44 |
+
elif sentiment == 'Neutral' and confidence_scores[1] > threshold:
|
45 |
+
st.info(f"Sentiment: {sentiment} (Confidence: {confidence_scores[1]:.3f})")
|
46 |
+
else:
|
47 |
+
st.warning("Low confidence, or sentiment not above threshold. Please try again.")
|
48 |
+
|
49 |
else:
|
50 |
+
st.warning("Please enter some valid text for sentiment analysis.")
|
51 |
|
52 |
+
# Optional: Displaying the raw sentiment scores
|
53 |
if st.checkbox("Show Raw Sentiment Scores"):
|
54 |
+
if text_input and text_input.strip():
|
55 |
inputs = tokenizer(text_input, return_tensors="pt")
|
56 |
outputs = model(**inputs)
|
57 |
raw_scores = outputs.logits[0].tolist()
|
58 |
st.info(f"Raw Sentiment Scores: {raw_scores}")
|
59 |
|
60 |
+
# footer
|
61 |
+
st.markdown(
|
62 |
+
"""
|
63 |
+
**Built with [Streamlit](https://streamlit.io/) and [Transformers](https://huggingface.co/models).**
|
64 |
+
"""
|
65 |
+
)
|