Download app.py from ilsa15/Intelligent-Multi-Class-Natural-Language-Text-Sentiment-Classifier: direct link, hf CLI and curl.
- Browser
- Download file 13.6 kB
-
https://huggingface.co/spaces/ilsa15/Intelligent-Multi-Class-Natural-Language-Text-Sentiment-Classifier/resolve/main/app.py
- Command line
-
hf download hf://spaces/ilsa15/Intelligent-Multi-Class-Natural-Language-Text-Sentiment-Classifier/app.py
-
curl -L -o app.py https://huggingface.co/spaces/ilsa15/Intelligent-Multi-Class-Natural-Language-Text-Sentiment-Classifier/resolve/main/app.py
13.6 kB
| import re | |
| import string | |
| from pathlib import Path | |
| import gradio as gr | |
| import matplotlib | |
| matplotlib.use("Agg") | |
| import matplotlib.pyplot as plt | |
| import pandas as pd | |
| import nltk | |
| from nltk.corpus import stopwords | |
| from nltk.stem import WordNetLemmatizer | |
| from sklearn.feature_extraction.text import TfidfVectorizer | |
| from sklearn.linear_model import LogisticRegression | |
| from sklearn.metrics import ( | |
| accuracy_score, | |
| classification_report, | |
| confusion_matrix, | |
| f1_score, | |
| precision_score, | |
| recall_score, | |
| ) | |
| from sklearn.model_selection import train_test_split | |
| from sklearn.pipeline import Pipeline | |
| # Download NLTK resources | |
| for package in ("stopwords", "wordnet", "omw-1.4"): | |
| try: | |
| nltk.download(package, quiet=True) | |
| except Exception: | |
| pass | |
| try: | |
| STOP_WORDS = set(stopwords.words("english")) | |
| except LookupError: | |
| STOP_WORDS = { | |
| "a", "an", "the", "and", "or", "but", "if", "of", | |
| "at", "by", "for", "with", "to", "from", "in", "on", | |
| "is", "am", "are", "was", "were", "be", "been", | |
| "have", "has", "had", "do", "does", "did", "i", | |
| "you", "he", "she", "it", "we", "they", "this", | |
| "that", "these", "those", "my", "your", "our", | |
| "their", "me", "him", "her", "as", "not", "very", | |
| } | |
| LEMMATIZER = WordNetLemmatizer() | |
| def preprocess_text(text): | |
| text = str(text).lower() | |
| text = re.sub(r"https?://\S+|www\.\S+", " ", text) | |
| text = re.sub(r"\S+@\S+", " ", text) | |
| text = re.sub(r"\d+", " ", text) | |
| text = text.translate( | |
| str.maketrans("", "", string.punctuation) | |
| ) | |
| words = re.findall(r"\b[a-z]+\b", text) | |
| cleaned = [] | |
| for word in words: | |
| if word in STOP_WORDS or len(word) <= 1: | |
| continue | |
| try: | |
| word = LEMMATIZER.lemmatize(word) | |
| except LookupError: | |
| pass | |
| cleaned.append(word) | |
| return " ".join(cleaned) | |
| # Sample dataset | |
| def create_dataset(): | |
| examples = { | |
| "positive": [ | |
| "I absolutely love this product, it works wonderfully", | |
| "The service was excellent and the staff were helpful", | |
| "This is a fantastic experience, I am very happy", | |
| "The movie was brilliant and entertaining", | |
| "I am pleased with the quality and value", | |
| "The food tasted amazing and fresh", | |
| "Everything worked perfectly and I recommend it", | |
| "The delivery was quick and the package was great", | |
| "The support team solved my issue quickly", | |
| "I had a wonderful day and feel great", | |
| "The app is easy to use and very useful", | |
| "Beautiful design and impressive performance", | |
| "I enjoyed every moment of the event", | |
| "The results are better than I expected", | |
| "Excellent quality, friendly service, and fair price", | |
| "This book is inspiring and well written", | |
| "The update made the software much better", | |
| "I am satisfied with my purchase", | |
| "A lovely place with a welcoming atmosphere", | |
| "The course is helpful and easy to understand", | |
| "The new feature saves time and works well", | |
| "The staff were polite and made us feel welcome", | |
| "The trip was comfortable and memorable", | |
| "The headphones sound clear and feel comfortable", | |
| "I would happily buy this again", | |
| ], | |
| "negative": [ | |
| "I hate this product, it is terrible", | |
| "The service was awful and the staff were rude", | |
| "This was a disappointing experience", | |
| "The movie was boring and poorly made", | |
| "I am unhappy with the quality", | |
| "The food tasted stale and unpleasant", | |
| "Nothing worked and I cannot recommend it", | |
| "The delivery was late and the package was damaged", | |
| "The support team ignored my problem", | |
| "I had a horrible day and feel upset", | |
| "The app is confusing and keeps crashing", | |
| "Poor design and disappointing performance", | |
| "I regret attending this event", | |
| "The results were much worse than expected", | |
| "Bad quality, rude service, and high price", | |
| "This book is dull and badly written", | |
| "The update made the software worse", | |
| "I am dissatisfied with my purchase", | |
| "A noisy place with an unpleasant atmosphere", | |
| "The course is confusing and not helpful", | |
| "The new feature wastes time and fails often", | |
| "The staff were impolite and unwelcoming", | |
| "The trip was uncomfortable and stressful", | |
| "The headphones sound poor and hurt my ears", | |
| "I would never buy this again", | |
| ], | |
| "neutral": [ | |
| "The product arrived in a standard box", | |
| "The service started at nine in the morning", | |
| "I watched the movie yesterday", | |
| "The package contains three separate items", | |
| "The food was served on a white plate", | |
| "The app has five tabs on the main screen", | |
| "The delivery took two days", | |
| "The support team replied to my message", | |
| "I attended the event on Friday", | |
| "The book has twelve chapters", | |
| "The software update was released today", | |
| "I purchased the item last week", | |
| "The restaurant is located near the station", | |
| "The course includes six lessons", | |
| "The feature is available in the settings menu", | |
| "The staff asked me to wait outside", | |
| "The trip lasted around four hours", | |
| "The headphones come with a charging cable", | |
| "The meeting is scheduled for tomorrow", | |
| "The report contains several sections", | |
| "The website has a search bar", | |
| "The order includes a receipt", | |
| "The room has two windows", | |
| "The class begins at ten o'clock", | |
| "The device is available in black and white", | |
| ], | |
| } | |
| rows = [] | |
| for label, sentences in examples.items(): | |
| for sentence in sentences: | |
| rows.append({ | |
| "text": sentence, | |
| "sentiment": label, | |
| }) | |
| return pd.DataFrame(rows) | |
| DATA = create_dataset() | |
| DATA["clean_text"] = DATA["text"].apply(preprocess_text) | |
| # Save the dataset as a real file for Gradio's file component | |
| DATA_CSV_PATH = str(Path("sentiment_dataset.csv").resolve()) | |
| DATA[["text", "sentiment"]].to_csv( | |
| DATA_CSV_PATH, index=False | |
| ) | |
| # Split data into training and testing sets | |
| X_train, X_test, y_train, y_test = train_test_split( | |
| DATA["clean_text"], | |
| DATA["sentiment"], | |
| test_size=0.25, | |
| random_state=42, | |
| stratify=DATA["sentiment"], | |
| ) | |
| # Build and train the classifier | |
| MODEL = Pipeline([ | |
| ( | |
| "tfidf", | |
| TfidfVectorizer( | |
| ngram_range=(1, 2), | |
| sublinear_tf=True, | |
| ), | |
| ), | |
| ( | |
| "classifier", | |
| LogisticRegression( | |
| max_iter=1000, | |
| class_weight="balanced", | |
| ), | |
| ), | |
| ]) | |
| MODEL.fit(X_train, y_train) | |
| # Evaluate the model | |
| TEST_PREDICTIONS = MODEL.predict(X_test) | |
| LABELS = sorted(DATA["sentiment"].unique()) | |
| ACCURACY = accuracy_score(y_test, TEST_PREDICTIONS) | |
| MACRO_F1 = f1_score( | |
| y_test, TEST_PREDICTIONS, | |
| average="macro", zero_division=0 | |
| ) | |
| MACRO_PRECISION = precision_score( | |
| y_test, TEST_PREDICTIONS, | |
| average="macro", zero_division=0 | |
| ) | |
| MACRO_RECALL = recall_score( | |
| y_test, TEST_PREDICTIONS, | |
| average="macro", zero_division=0 | |
| ) | |
| REPORT = classification_report( | |
| y_test, | |
| TEST_PREDICTIONS, | |
| output_dict=True, | |
| zero_division=0, | |
| ) | |
| REPORT_DF = pd.DataFrame(REPORT).T.round(3) | |
| REPORT_DF.index.name = "Class" | |
| REPORT_DF = REPORT_DF.reset_index() | |
| CM = confusion_matrix( | |
| y_test, TEST_PREDICTIONS, labels=LABELS | |
| ) | |
| # Predict sentiment for user-entered text | |
| def predict_sentiment(text): | |
| if not text or not text.strip(): | |
| return ( | |
| "Please enter a sentence or review.", | |
| {}, | |
| "", | |
| ) | |
| cleaned = preprocess_text(text) | |
| if not cleaned: | |
| return ( | |
| "No useful words remained after preprocessing. " | |
| "Please enter a longer sentence.", | |
| {}, | |
| "", | |
| ) | |
| prediction = MODEL.predict([cleaned])[0] | |
| probabilities = MODEL.predict_proba([cleaned])[0] | |
| probability_data = { | |
| label.title(): float(probability) | |
| for label, probability in zip( | |
| MODEL.classes_, probabilities | |
| ) | |
| } | |
| icons = { | |
| "positive": "π", | |
| "negative": "π", | |
| "neutral": "π", | |
| } | |
| confidence = probability_data[prediction.title()] | |
| result = ( | |
| f"### {icons.get(prediction, 'π¬')} " | |
| f"Predicted sentiment: {prediction.title()}\n\n" | |
| f"**Estimated confidence:** {confidence:.1%}\n\n" | |
| "Confidence is the model's estimate, not a guarantee." | |
| ) | |
| return result, probability_data, cleaned | |
| # Confusion matrix visualization | |
| def make_confusion_matrix(): | |
| fig, ax = plt.subplots(figsize=(6, 4)) | |
| ax.imshow(CM, interpolation="nearest", cmap="Blues") | |
| ax.set_xticks(range(len(LABELS))) | |
| ax.set_yticks(range(len(LABELS))) | |
| ax.set_xticklabels( | |
| [label.title() for label in LABELS] | |
| ) | |
| ax.set_yticklabels( | |
| [label.title() for label in LABELS] | |
| ) | |
| ax.set_xlabel("Predicted label") | |
| ax.set_ylabel("True label") | |
| ax.set_title("Confusion Matrix") | |
| threshold = CM.max() / 2 | |
| for row in range(CM.shape[0]): | |
| for col in range(CM.shape[1]): | |
| ax.text( | |
| col, | |
| row, | |
| str(CM[row, col]), | |
| ha="center", | |
| va="center", | |
| color=( | |
| "white" | |
| if CM[row, col] > threshold | |
| else "black" | |
| ), | |
| ) | |
| fig.tight_layout() | |
| return fig | |
| # Gradio interface | |
| with gr.Blocks( | |
| title="Intelligent Multi-Class Sentiment Classifier" | |
| ) as demo: | |
| gr.Markdown( | |
| """ | |
| # π¬ Intelligent Multi-Class Sentiment Classifier | |
| Classify text into **positive**, **negative**, or **neutral** | |
| sentiment using NLP preprocessing, TF-IDF, and Logistic Regression. | |
| """ | |
| ) | |
| with gr.Tab("π Predict Sentiment"): | |
| text_input = gr.Textbox( | |
| label="Enter a sentence or review", | |
| placeholder=( | |
| "Example: The product is excellent " | |
| "and easy to use!" | |
| ), | |
| lines=4, | |
| ) | |
| analyze_button = gr.Button( | |
| "Analyze Sentiment", | |
| variant="primary", | |
| ) | |
| prediction_output = gr.Markdown() | |
| probability_output = gr.Label( | |
| label="Class probabilities", | |
| num_top_classes=3, | |
| ) | |
| cleaned_output = gr.Textbox( | |
| label="Preprocessed text", | |
| interactive=False, | |
| ) | |
| analyze_button.click( | |
| fn=predict_sentiment, | |
| inputs=text_input, | |
| outputs=[ | |
| prediction_output, | |
| probability_output, | |
| cleaned_output, | |
| ], | |
| ) | |
| text_input.submit( | |
| fn=predict_sentiment, | |
| inputs=text_input, | |
| outputs=[ | |
| prediction_output, | |
| probability_output, | |
| cleaned_output, | |
| ], | |
| ) | |
| gr.Examples( | |
| examples=[ | |
| ["I absolutely love this product"], | |
| ["The service was awful and disappointing"], | |
| ["The meeting is scheduled for tomorrow"], | |
| ], | |
| inputs=text_input, | |
| ) | |
| with gr.Tab("π Model Evaluation"): | |
| gr.Markdown("### Held-out test set performance") | |
| with gr.Row(): | |
| gr.Number( | |
| value=round(ACCURACY, 3), | |
| label="Accuracy", | |
| interactive=False, | |
| ) | |
| gr.Number( | |
| value=round(MACRO_F1, 3), | |
| label="Macro F1-score", | |
| interactive=False, | |
| ) | |
| gr.Number( | |
| value=round(MACRO_PRECISION, 3), | |
| label="Macro Precision", | |
| interactive=False, | |
| ) | |
| gr.Number( | |
| value=round(MACRO_RECALL, 3), | |
| label="Macro Recall", | |
| interactive=False, | |
| ) | |
| gr.Markdown("### Classification report") | |
| gr.Dataframe( | |
| value=REPORT_DF, | |
| interactive=False, | |
| ) | |
| gr.Markdown("### Confusion matrix") | |
| gr.Plot(value=make_confusion_matrix()) | |
| with gr.Tab("ποΈ Dataset"): | |
| gr.Markdown( | |
| f"The built-in dataset contains **{len(DATA)} examples** " | |
| "across three sentiment classes. It is intended for " | |
| "educational demonstration." | |
| ) | |
| gr.Dataframe( | |
| value=DATA[["text", "sentiment"]], | |
| interactive=False, | |
| ) | |
| gr.File( | |
| value=DATA_CSV_PATH, | |
| label="Sample dataset CSV", | |
| interactive=False, | |
| ) | |
| gr.Markdown( | |
| """ | |
| --- | |
| **Note:** This educational prototype uses a small sample dataset. | |
| Predictions and evaluation scores are not production-grade benchmarks. | |
| """ | |
| ) | |
| if __name__ == "__main__": | |
| demo.launch(theme=gr.themes.Soft()) | |