Mourya0402 commited on
Commit
d85158b
·
verified ·
1 Parent(s): 55d9814

Upload 4 files

Browse files
Files changed (4) hide show
  1. README.md +46 -14
  2. app.py +36 -0
  3. requirements.txt +4 -0
  4. sentiment.py +48 -0
README.md CHANGED
@@ -1,14 +1,46 @@
1
- ---
2
- title: Sentiment Analysis
3
- emoji: ⚡
4
- colorFrom: pink
5
- colorTo: red
6
- sdk: gradio
7
- sdk_version: 5.46.1
8
- app_file: app.py
9
- pinned: false
10
- license: mit
11
- short_description: po or neg
12
- ---
13
-
14
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Text Sentiment Analyzer (Local)
2
+
3
+ A **simple local** Gradio app that classifies text sentiment using a Hugging Face Transformers pipeline
4
+ (`distilbert-base-uncased-finetuned-sst-2-english`). No remote APIs.
5
+
6
+ ## Quickstart
7
+
8
+ ```bash
9
+ python -m venv .venv && source .venv/bin/activate # Windows: .venv\Scripts\activate
10
+ pip install -r requirements.txt
11
+ python app.py
12
+ ```
13
+
14
+ Open the printed local URL and paste any text. Use the **Neutral margin** slider to make the
15
+ classifier return **NEUTRAL** when POS vs NEG is too close to call.
16
+
17
+ ## Why this fits Deliverable 2
18
+
19
+ - **Runs locally** on your hardware (no `InferenceClient`, no external API).
20
+ - Clear contrast vs. your API-based product from Deliverable 1.
21
+ - Includes **tests** and a **GitHub Action** that runs `pytest` on push/PR.
22
+
23
+ ## Project layout
24
+
25
+ ```
26
+ sentiment_local/
27
+ ├─ app.py
28
+ ├─ sentiment.py
29
+ ├─ requirements.txt
30
+ ├─ README.md
31
+ ├─ tests/
32
+ │ └─ test_sentiment.py
33
+ └─ .github/workflows/
34
+ └─ ci.yml
35
+ ```
36
+
37
+ ## Notes
38
+
39
+ - On the first run, Transformers will **download the model weights** to your machine
40
+ (cached under `~/.cache/huggingface/`). Subsequent runs are fully local.
41
+ - If you need strictly offline installs, pre-download the model:
42
+ ```bash
43
+ python -c "from transformers import AutoTokenizer, AutoModelForSequenceClassification; \
44
+ AutoTokenizer.from_pretrained('distilbert-base-uncased-finetuned-sst-2-english'); \
45
+ AutoModelForSequenceClassification.from_pretrained('distilbert-base-uncased-finetuned-sst-2-english')"
46
+ ```
app.py ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ import gradio as gr
3
+ from sentiment import analyze_batch, load_pipeline
4
+
5
+ INTRO = """
6
+ # Text Sentiment Analyzer (Local)
7
+ Runs **fully local** using a Hugging Face Transformers pipeline—no external APIs.
8
+ Default model: `distilbert-base-uncased-finetuned-sst-2-english`.
9
+ """
10
+
11
+ pipe = None
12
+
13
+ def predict(text, neutral_margin):
14
+ global pipe
15
+ if not text or not text.strip():
16
+ return [{"label": "NEUTRAL", "score": 1.0}], "Please enter some text."
17
+ if pipe is None:
18
+ pipe = load_pipeline()
19
+ results = analyze_batch([text], pipe=pipe, neutral_margin=neutral_margin)
20
+ pretty = [f"**{r['label']}** (conf: {r['score']:.3f})" for r in results]
21
+ return results, "\n".join(pretty)
22
+
23
+ with gr.Blocks() as demo:
24
+ gr.Markdown(INTRO)
25
+ with gr.Row():
26
+ with gr.Column():
27
+ inp = gr.Textbox(label="Input text", placeholder="Paste a review, tweet, etc.", lines=6)
28
+ neutral_margin = gr.Slider(0.0, 0.5, value=0.15, step=0.01, label="Neutral margin (wider margin => more NEUTRAL)")
29
+ btn = gr.Button("Analyze", variant="primary")
30
+ with gr.Column():
31
+ out_json = gr.JSON(label="Raw output")
32
+ out_md = gr.Markdown(label="Friendly view")
33
+ btn.click(predict, inputs=[inp, neutral_margin], outputs=[out_json, out_md])
34
+
35
+ if __name__ == "__main__":
36
+ demo.launch()
requirements.txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ gradio>=4.44.0
2
+ transformers>=4.44.2
3
+ torch>=2.2.0
4
+ pytest>=8.2.0
sentiment.py ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ from typing import List, Dict, Optional
3
+ from transformers import pipeline
4
+
5
+ LABEL_POS = "POSITIVE"
6
+ LABEL_NEG = "NEGATIVE"
7
+ LABEL_NEU = "NEUTRAL"
8
+
9
+ def load_pipeline(model_name: str = "distilbert-base-uncased-finetuned-sst-2-english"):
10
+ """
11
+ Loads a local sentiment-analysis pipeline.
12
+ NOTE: On first run, Transformers may download model weights to your machine.
13
+ """
14
+ return pipeline("sentiment-analysis", model=model_name)
15
+
16
+ def soften_to_neutral(pos_score: float, neg_score: float, margin: float) -> Optional[str]:
17
+ """
18
+ If the top class wins by less than `margin`, return NEUTRAL.
19
+ margin in [0, 0.5]. Larger => more neutral outputs.
20
+ """
21
+ gap = abs(pos_score - neg_score)
22
+ return LABEL_NEU if gap < margin else None
23
+
24
+ def postprocess(raw_item: Dict, margin: float) -> Dict:
25
+ label = raw_item["label"].upper()
26
+ score = float(raw_item["score"])
27
+ pos = score if label == LABEL_POS else 1.0 - score # two-class trick
28
+ neg = 1.0 - pos
29
+ neutral = soften_to_neutral(pos, neg, margin)
30
+ if neutral:
31
+ return {"label": LABEL_NEU, "score": float(1.0 - abs(pos - neg))}
32
+ # Return winning class + score
33
+ if pos >= neg:
34
+ return {"label": LABEL_POS, "score": pos}
35
+ else:
36
+ return {"label": LABEL_NEG, "score": neg}
37
+
38
+ def analyze_batch(texts: List[str], pipe=None, neutral_margin: float = 0.15) -> List[Dict]:
39
+ """
40
+ Runs local inference on a list of strings and applies neutral margin postprocessing.
41
+ """
42
+ if pipe is None:
43
+ pipe = load_pipeline()
44
+ raw = pipe(texts, truncation=True)
45
+ # HF pipeline returns single dict for single input; normalize to list
46
+ if isinstance(raw, dict):
47
+ raw = [raw]
48
+ return [postprocess(item, neutral_margin) for item in raw]