File size: 3,503 Bytes
320009b ca0169a 320009b ca0169a 320009b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
import torch
import gradio as gr
import pandas as pd
import matplotlib.pyplot as plt
# Use a pipeline as a high-level helper
from transformers import pipeline
# model_path = ("../Models/models--distilbert--distilbert-base-uncased-finetuned-sst-2-english"
# "/snapshots/714eb0fa89d2f80546fda750413ed43d93601a13")
analyzer = pipeline("text-classification",
model="distilbert/distilbert-base-uncased-finetuned-sst-2-english")
# analyzer = pipeline("text-classification",
# model=model_path)
# print(analyzer(["This production is good", "This product was quite expensive"]))
def sentiment_analyzer(review):
sentiment = analyzer(review)
return sentiment[0]['label']
def sentiment_bar_chart(df):
sentiment_counts = df['Sentiment'].value_counts()
# Create a bar chart
fig, ax = plt.subplots()
sentiment_counts.plot(kind='pie', ax=ax, autopct='%1.1f%%', color=['green', 'red'])
ax.set_title('Review Sentiment Counts')
ax.set_xlabel('Sentiment')
ax.set_ylabel('Count')
# ax.set_xticklabels(['Positive', 'Negative'], rotation=0)
# Return the figure object
return fig
def read_reviews_and_analyze_sentiment(file_object):
if file_object.name.endswith('.xlsx'):
# Load the Excel file into a DataFrame
df = pd.read_excel(file_object)
# Check if 'Review' column is in the DataFrame
if 'Reviews' not in df.columns:
raise ValueError("Excel file must contain a 'Review' column.")
# Apply the get_sentiment function to each review in the DataFrame
df['Sentiment'] = df['Reviews'].apply(sentiment_analyzer)
elif file_object.name.endswith('.docx'):
# Read the content of the DOCX file
doc = Document(file_object)
reviews = [para.text for para in doc.paragraphs if para.text.strip()]
df = pd.DataFrame({'Reviews': reviews})
df['Sentiment'] = df['Reviews'].apply(sentiment_analyzer)
elif file_object.name.endswith('.pdf'):
# Read the content of the PDF file
reader = PdfReader(file_object)
text = ""
for page in reader.pages:
text += page.extract_text()
reviews = text.split('\n') # Assuming reviews are newline separated
df = pd.DataFrame({'Reviews': reviews})
df['Sentiment'] = df['Reviews'].apply(sentiment_analyzer)
else:
raise ValueError("Unsupported file format. Please upload .xlsx, .pdf, or .docx files.")
chart_object = sentiment_bar_chart(df)
return df, chart_object
# result = read_reviews_and_analyze_sentiment("../Files/Prod-review.xlsx")
# print(result)
# Example usage:
# df = read_reviews_and_analyze_sentiment('path_to_your_excel_file.xlsx')
# print(df)
demo = gr.Interface(fn=read_reviews_and_analyze_sentiment,
inputs=[gr.File(file_types=["xlsx", "pdf", "docx"], label="Upload your review comment file")],
outputs=[gr.Dataframe(label="Sentiments"), gr.Plot(label="Sentiment Analysis"),gr.Textbox(label="Single Sentence Sentiment Analysis")],
title="@GenAILearniverse Project 3: Sentiment Analyzer",
description="THIS APPLICATION WILL BE USED TO ANALYZE THE SENTIMENT BASED ON FILE UPLAODED.")
demo.launch()
# Example usage:
# Assuming you have a dataframe `df` with appropriate data
# fig = sentiment_bar_chart(df)
# fig.show() # This line is just to visualize the plot in a local environment
|