hf application

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

Procfile.txt

@@ -0,0 +1 @@
+web: python app.py

app.py

@@ -0,0 +1,203 @@
+import gradio as gr
+import json
+import re
+import html
+import os
+import pandas as pd
+import re
+
+#models
+from transformers import AutoTokenizer, AutoModelForTokenClassification,AutoModelForSequenceClassification, pipeline
+import torch
+
+aspdevice = "cpu"
+    # Your aspect extraction logic
+model_id_ate = "gauneg/roberta-base-absa-ate-sentiment"
+tokenizer_ate = AutoTokenizer.from_pretrained(model_id_ate)
+model_ate = AutoModelForTokenClassification.from_pretrained(model_id_ate)
+senti_pipeline = pipeline(task='ner', model=model_ate, tokenizer=tokenizer_ate, device=aspdevice, aggregation_strategy='simple')
+
+# Your emotion detection logic
+emodevice = "mps" if torch.backends.mps.is_available() else 0 if torch.cuda.is_available() else -1
+emotion_model = "j-hartmann/emotion-english-distilroberta-base"
+emo_tokenizer = AutoTokenizer.from_pretrained(emotion_model)
+emo_model = AutoModelForSequenceClassification.from_pretrained(emotion_model)
+classifier = pipeline("text-classification", model=emo_model,tokenizer=emo_tokenizer, top_k=None, device=emodevice)
+
+def extract_full_word(text, start, end):
+    word_start = start
+    while word_start > 0 and re.match(r'\w', text[word_start - 1]):
+        word_start -= 1
+    word_end = end
+    while word_end < len(text) and re.match(r'\w', text[word_end]):
+        word_end += 1
+    return text[word_start:word_end].strip()
+
+def extract_full_analysis(review):
+    sentences = [rev.strip() for rev in review.split(".") if rev.strip()]
+    #aspect predictions
+    asppredictions = senti_pipeline(review)
+    #emotion predictions
+    emopredictions = classifier(sentences)
+    #Extract aspects
+    aspect_word = [
+        {"word": d["word"].strip(), "start": d["start"], "end": d["end"]}
+        for d in asppredictions
+    ]
+    # Extract sentiment  term
+    sentiments = [d["entity_group"] for d in asppredictions]
+    scores = [f"{d['score']:.4f}" for d in asppredictions]
+    refined_aspects = []
+    for aspect in aspect_word:
+        full_word = extract_full_word(review, aspect["start"], aspect["end"])
+        if len(full_word) >= 3:  
+            refined_aspects.append(full_word)
+    refined_aspects = list(dict.fromkeys(refined_aspects))  
+
+    flat_preds = [d for sentence_preds in emopredictions for d in sentence_preds if d["score"] >= 0.1]
+    emotions = [d["label"]  for d in flat_preds]
+    emotion_score = [d["score"]  for d in flat_preds]
+    dynamic_result ={
+        "review":        review,
+        "aspect_words": refined_aspects,
+        "sentiment":   sentiments,
+        "score":       scores,
+        "emotions":     emotions,
+        "emo-score": emotion_score
+    }
+    return dynamic_result
+
+with open('yelp3k.json', 'r', encoding='utf-8') as fp:
+    static_reviews = json.load(fp)
+def highlight_aspects(text, aspects):
+    aspects_sorted = sorted(aspects, key=len, reverse=True)
+    aspects_regex = [re.escape(asp) for asp in aspects_sorted]
+    pattern = r'\b(?:' + '|'.join(aspects_regex) + r')\b'
+    def replace_match(match):
+        return f'<span style="font-weight: bold; background-color: yellow;">{match.group()}</span>'
+    return re.sub(pattern, replace_match, text, flags=re.IGNORECASE)
+
+def format_review(review):
+    text = review[0]['review']
+    aspects = review[0]['aspect_words']
+
+    highlighted_text = highlight_aspects(text, aspects)
+    aspects = [asp.strip() for asp in review[0]['aspect_words']]
+    emotions = [emo.strip() for emo in review[0]['emotions']]
+    sentiments = [senti for senti in review[0]['sentiment']]
+    sentimentScores = [scor for scor in review[0]['score']]
+    emotionScores = [emscor for emscor in review[0]['emo-score']]
+
+    aspects_html = '<div class="cell-grid">' + "".join(f'<div class="cell-item">{html.escape(asp)}</div>' for asp in aspects) + '</div>'
+    emotions_html = '<div class="cell-grid">' + "".join(f'<div class="cell-item">{html.escape(emo)}</div>' for emo in emotions) + '</div>'
+    sentiments_html = '<div class="cell-grid">' + "".join(f'<div class="cell-item">{html.escape(senti)}</div>' for senti in sentiments) + '</div>'
+    sentiScor_html = '<div class="cell-grid">' + "".join(f'<div class="cell-item">{sentiscor}</div>' for sentiscor in sentimentScores) + '</div>'
+    emoScor_html = '<div class="cell-grid">' + "".join(f'<div class="cell-item">{emoscor}</div>' for emoscor in emotionScores) + '</div>'
+    return f"""
+    <div style="border: 1px solid #ccc; padding: 10px; margin-bottom: 10px;">
+        <h4>Review</h4>
+        <p>{highlighted_text}</p>
+        <h3>Aspect Words</h3>
+        {aspects_html}
+        <h3>Sentiments</h3>
+        {sentiments_html}
+        <h3>Sentiments Score</h3>
+        {sentiScor_html}
+
+        <h3>Emotions</h3>
+        {emotions_html}
+        <h3>Emotions Score</h3>
+        {emoScor_html}
+
+    </div>
+    """
+
+# Format dynamic reviews
+def format_dynamic_reviews(reviews):
+    return "<div>" + "".join(format_review(rev) for rev in reviews) + "</div>"
+
+def get_static_review(index):
+    review = static_reviews[index]
+    highlighted_text = highlight_aspects(review['text'], review['aspect_word'].split(','))
+    stars_html = f"Stars: {review['stars']}"
+    aspects = [asp.strip() for asp in review['aspect_word'].split(',')]
+    emotions = [emo.strip() for emo in review['emotion'].split(',')]
+
+    aspects_html = '<h3>Aspect Words</h3><div class="cell-grid">' + "".join(f'<div class="cell-item">{html.escape(asp)}</div>' for asp in aspects) + '</div>'
+    emotions_html = '<h3>Emotions Extracted</h3><div class="cell-grid">' + "".join(f'<div class="cell-item">{html.escape(emo)}</div>' for emo in emotions) + '</div>'
+    
+    info_text = f"Review {index+1} of {len(static_reviews)}"
+    return highlighted_text, stars_html, aspects_html, emotions_html, info_text
+
+def navigate(direction, current_index):
+    if direction == 'prev':
+        return max(current_index - 1, 0)
+    return min(current_index + 1, len(static_reviews) - 1)
+
+def submit_new_review(text):
+    if not text.strip():
+        return "Please enter a review.", []
+    new_dynamic_reviews =[]
+    _reviews = extract_full_analysis(text)
+    new_dynamic_reviews.append(_reviews)
+    return format_review(new_dynamic_reviews), new_dynamic_reviews
+
+with gr.Blocks(css="""
+.cell-grid {
+    display: grid;
+    grid-template-columns: repeat(6, 1fr);
+    gap: 10px;
+}
+.cell-item {
+    background-color: #f0f0f0;
+    padding: 10px;
+    border: 1px solid #ccc;
+    text-align: center;
+}
+""") as demo:
+    # Header
+    gr.Markdown("# Yelp Review Demonstration for Aspect and Emotion Extracted")
+
+    # Static Reviews
+    with gr.Row():
+        with gr.Column(scale=11):
+            static_text = gr.HTML(label="Review Text")
+        with gr.Column(scale=1):
+            static_stars = gr.HTML(label="Stars")
+    static_aspects = gr.HTML(label=None)
+    static_emotions = gr.HTML(label="Emotions")
+    static_info = gr.Textbox(label="Review Info", interactive=False)
+    with gr.Row():
+        prev_button = gr.Button("Previous")
+        next_button = gr.Button("Next")
+
+    # Submit Form
+    gr.Markdown("## Submit Your Review")
+    with gr.Row():
+        with gr.Column(scale=8):
+            submit_text = gr.Textbox(label="Write your review", lines=5)
+            submit_button = gr.Button("Submit")
+
+    # Dynamic Reviews
+    gr.Markdown("## User Submitted Reviews")
+    dynamic_display = gr.HTML()
+
+    # States
+    current_static_index = gr.State(0)
+    dynamic_reviews_state = gr.State()
+
+    # Load Initial Data
+    demo.load(get_static_review, inputs=current_static_index, outputs=[static_text, static_stars, static_aspects, static_emotions, static_info])
+
+    # Event Handlers
+    prev_button.click(lambda ci: navigate('prev', ci), inputs=current_static_index, outputs=current_static_index).then(
+        get_static_review, inputs=current_static_index, outputs=[static_text, static_stars, static_aspects, static_emotions, static_info])
+    next_button.click(lambda ci: navigate('next', ci), inputs=current_static_index, outputs=current_static_index).then(
+        get_static_review, inputs=current_static_index, outputs=[static_text, static_stars, static_aspects, static_emotions, static_info])
+    submit_button.click(submit_new_review, inputs=submit_text, outputs=[dynamic_display, dynamic_reviews_state])
+
+# Launch
+if __name__ == "__main__":
+    port = int(os.environ.get('PORT', 7814))
+    demo.launch(server_name="0.0.0.0", server_port=port,share=True)
+# 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

requirements.txt

@@ -0,0 +1,218 @@
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.4
+aiohttp==3.11.10
+aiosignal==1.3.2
+annotated-types==0.7.0
+anyio==4.7.0
+appnope==0.1.4
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+asgiref==3.8.1
+asttokens==3.0.0
+async-lru==2.0.4
+attrs==24.3.0
+babel==2.16.0
+backoff==2.2.1
+bcrypt==4.2.1
+beautifulsoup4==4.12.3
+bleach==6.2.0
+build==1.2.2.post1
+cachetools==5.5.0
+certifi==2024.12.14
+cffi==1.17.1
+charset-normalizer==3.4.0
+chroma-hnswlib==0.7.6
+#chromadb==0.5.23
+chromadb>=0.6.0
+click==8.1.7
+coloredlogs==15.0.1
+comm==0.2.2
+contourpy==1.3.1
+cycler==0.12.1
+dataclasses-json==0.6.7
+debugpy==1.8.11
+decorator==5.1.1
+defusedxml==0.7.1
+Deprecated==1.2.15
+distro==1.9.0
+durationpy==0.9
+executing==2.1.0
+fastapi==0.115.6
+fastjsonschema==2.21.1
+ffmpy==0.4.0
+filelock==3.16.1
+flatbuffers==24.3.25
+fonttools==4.55.3
+fqdn==1.5.1
+frozenlist==1.5.0
+fsspec==2024.10.0
+google-auth==2.37.0
+googleapis-common-protos==1.66.0
+gradio==5.9.1
+gradio_client==1.5.2
+grpcio==1.68.1
+h11==0.14.0
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.28.1
+httpx-sse==0.4.0
+huggingface-hub==0.27.0
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.5.0
+importlib_resources==6.4.5
+ipykernel==6.29.5
+ipython==8.30.0
+ipywidgets==8.1.5
+isoduration==20.11.0
+jedi==0.19.2
+Jinja2==3.1.4
+jiter==0.8.2
+json5==0.10.0
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+jupyter-events==0.11.0
+jupyter-lsp==2.2.5
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+jupyter_server==2.14.2
+jupyter_server_terminals==0.5.3
+jupyterlab==4.3.3
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.27.3
+jupyterlab_widgets==3.0.13
+kagglehub==0.3.5
+kiwisolver==1.4.7
+kubernetes==31.0.0
+langchain==0.3.12
+#langchain-chroma==0.1.4
+langchain-chroma>=0.1.5
+langchain-community==0.3.12
+langchain-core==0.3.25
+langchain-openai==0.2.12
+langchain-text-splitters==0.3.3
+langsmith==0.2.3
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.23.1
+matplotlib==3.10.0
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mistune==3.0.2
+mmh3==5.0.1
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+nbclient==0.10.1
+nbconvert==7.16.4
+nbformat==5.10.4
+nest-asyncio==1.6.0
+networkx==3.4.2
+notebook==7.3.1
+notebook_shim==0.2.4
+numpy==1.26.4
+oauthlib==3.2.2
+onnxruntime==1.20.1
+openai==1.57.4
+opentelemetry-api==1.29.0
+opentelemetry-exporter-otlp-proto-common==1.29.0
+opentelemetry-exporter-otlp-proto-grpc==1.29.0
+opentelemetry-instrumentation==0.50b0
+opentelemetry-instrumentation-asgi==0.50b0
+opentelemetry-instrumentation-fastapi==0.50b0
+opentelemetry-proto==1.29.0
+opentelemetry-sdk==1.29.0
+opentelemetry-semantic-conventions==0.50b0
+opentelemetry-util-http==0.50b0
+orjson==3.10.12
+overrides==7.7.0
+packaging==24.2
+pandas==2.2.3
+pandocfilters==1.5.1
+parso==0.8.4
+pexpect==4.9.0
+pillow==11.0.0
+platformdirs==4.3.6
+posthog==3.7.4
+prometheus_client==0.21.1
+prompt_toolkit==3.0.48
+propcache==0.2.1
+protobuf==5.29.1
+psutil==6.1.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycparser==2.22
+pydantic==2.10.3
+pydantic-settings==2.7.0
+pydantic_core==2.27.1
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.2.0
+PyPika==0.48.9
+pyproject_hooks==1.2.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-json-logger==3.2.1
+python-multipart==0.0.20
+pytz==2024.2
+PyYAML==6.0.2
+pyzmq==26.2.0
+referencing==0.35.1
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+requests-toolbelt==1.0.0
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rich==13.9.4
+rpds-py==0.22.3
+rsa==4.9
+ruff==0.8.3
+safehttpx==0.1.6
+safetensors==0.4.5
+seaborn==0.13.2
+semantic-version==2.10.0
+Send2Trash==1.8.3
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+soupsieve==2.6
+SQLAlchemy==2.0.36
+stack-data==0.6.3
+starlette==0.41.3
+sympy==1.13.1
+tenacity==9.0.0
+terminado==0.18.1
+tiktoken==0.8.0
+tinycss2==1.4.0
+tokenizers==0.21.0
+tomlkit==0.13.2
+torch==2.5.1
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+transformers==4.47.1
+typer==0.15.1
+types-python-dateutil==2.9.0.20241206
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.2
+uri-template==1.3.0
+urllib3==2.2.3
+uvicorn==0.34.0
+watchfiles==1.0.3
+wcwidth==0.2.13
+webcolors==24.11.1
+webencodings==0.5.1
+websocket-client==1.8.0
+websockets==14.1
+widgetsnbextension==4.0.13
+wrapt==1.17.0
+yarl==1.18.3
+zipp==3.21.0