Spaces:
Sleeping
Sleeping
| import pandas as pd | |
| import numpy as np | |
| import matplotlib.pyplot as plt | |
| import seaborn as sns | |
| import nltk | |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification | |
| from scipy.special import softmax | |
| from tqdm.notebook import tqdm | |
| import gradio as gr | |
| # Download NLTK resources | |
| nltk.download('punkt') | |
| nltk.download('averaged_perceptron_tagger') | |
| # Load the model and tokenizer | |
| tokenizer = AutoTokenizer.from_pretrained('cardiffnlp/twitter-roberta-base-sentiment') | |
| model = AutoModelForSequenceClassification.from_pretrained('cardiffnlp/twitter-roberta-base-sentiment') | |
| # Define a function to calculate polarity scores using RoBERTa | |
| def polarity_scores_roberta(example): | |
| encoded_text = tokenizer(example, return_tensors='pt') | |
| output = model(**encoded_text) | |
| scores = output[0][0].detach().numpy() | |
| scores = softmax(scores) | |
| scores_dict = { | |
| 'roberta_neg': scores[0], | |
| 'roberta_neu': scores[1], | |
| 'roberta_pos': scores[2] | |
| } | |
| return scores_dict | |
| # Function to perform the analysis and return results | |
| def analyze_reviews(): | |
| df = pd.read_csv("Reviews.csv") | |
| df = df.head(200) # Limiting to 200 for faster processing | |
| # Plot the distribution of review scores | |
| ax = df['Score'].value_counts().sort_index().plot(kind='bar', title='Count of Reviews by Stars', figsize=(10, 5)) | |
| ax.set_xlabel('Review Stars') | |
| plt.tight_layout() | |
| plt.savefig('review_distribution.png') | |
| res = {} | |
| for i, row in tqdm(df.iterrows(), total=len(df)): | |
| try: | |
| text = row['Text'] | |
| myid = row['Id'] | |
| roberta_result = polarity_scores_roberta(text) | |
| res[myid] = roberta_result | |
| except RuntimeError: | |
| print(f'Broke for id {myid}') | |
| results_df = pd.DataFrame(res).T | |
| results_df = results_df.reset_index().rename(columns={'index': 'Id'}) | |
| results_df = results_df.merge(df, how='left') | |
| # Return plots and the DataFrame with results | |
| return 'review_distribution.png', results_df.head().to_html(), results_df.query('Score == 1').sort_values('roberta_pos', ascending=False)['Text'].values[0], results_df.query('Score == 5').sort_values('roberta_neg', ascending=False)['Text'].values[0] | |
| # Define the Gradio interface | |
| def gradio_interface(): | |
| csv_file = "sample_data/Reviews.csv" # Replace with the path to your CSV file | |
| plot_path, table_html, pos_review, neg_review = analyze_reviews(csv_file) | |
| return plot_path, table_html, pos_review, neg_review | |
| gr.Interface( | |
| fn=gradio_interface, | |
| inputs=None, # or simply remove this line | |
| outputs=[ | |
| gr.Image(type="filepath", label="Review Distribution"), | |
| gr.HTML(label="Sample Results DataFrame"), | |
| gr.Textbox(label="Most Positive 1-Star Review"), | |
| gr.Textbox(label="Most Negative 5-Star Review"), | |
| ], | |
| title="Review Sentiment Analysis with RoBERTa", | |
| description="Analyze sentiments in a preloaded CSV file of reviews using a RoBERTa model.", | |
| ).launch() | |