File size: 4,466 Bytes
59a3d03 fae49e7 533636b 05ec195 7204d99 9c2aa41 3832b1b 6268cef 3832b1b 05ec195 2ecaff0 3832b1b 05ec195 fe934dd 3832b1b fae49e7 1341687 3832b1b fe934dd 3832b1b f24967f fe934dd 6268cef 9c2aa41 fe934dd 3832b1b fe934dd fae49e7 f24967f 3832b1b f24967f fe934dd 1341687 b2e17db 1341687 b2e17db 5a29e86 b2e17db 59a3d03 1341687 9c2aa41 fe934dd 3832b1b 2ecaff0 05ec195 fae49e7 1341687 |
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 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
import os
import numpy as np
import pandas as pd
import streamlit as st
from transformers import (
pipeline,
AutoTokenizer,
AutoModelForSequenceClassification,
AutoModelForSeq2SeqLM
)
from keybert import KeyBERT
# ─── Sentiment & Keyword Models ─────────────────────────────────────────────
@st.cache_resource
def load_sentiment_pipeline():
model_name = "mayf/amazon_reviews_bert_ft"
tok = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
mdl = AutoModelForSequenceClassification.from_pretrained(
model_name,
use_auth_token=True
)
return pipeline(
"sentiment-analysis",
model=mdl,
tokenizer=tok,
return_all_scores=True
)
@st.cache_resource
def load_keybert_model():
return KeyBERT(model="all-MiniLM-L6-v2")
# ─── FLAN-T5 Generation Pipeline ────────────────────────────────────────────
@st.cache_resource
def load_flant5_pipeline():
seq_tok = AutoTokenizer.from_pretrained("google/flan-t5-base")
seq_model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base")
return pipeline(
"text2text-generation",
model=seq_model,
tokenizer=seq_tok,
max_new_tokens=300,
do_sample=True,
temperature=0.7
)
LABEL_MAP = {
"LABEL_0": "Very Negative",
"LABEL_1": "Negative",
"LABEL_2": "Neutral",
"LABEL_3": "Positive",
"LABEL_4": "Very Positive"
}
def main():
st.title("📊 Amazon Review Analyzer")
review = st.text_area("Enter your review:")
if not st.button("Analyze Review"):
return
if not review:
st.warning("Please enter a review to analyze.")
return
progress = st.progress(0)
# Load models
progress.text("Loading models...")
sentiment_pipeline = load_sentiment_pipeline()
kw_model = load_keybert_model()
generation_pipeline = load_flant5_pipeline()
progress.progress(20)
# Sentiment Analysis
progress.text("Analyzing sentiment...")
raw_scores = sentiment_pipeline(review)[0]
sentiment_results = {LABEL_MAP[item['label']]: float(item['score']) for item in raw_scores}
progress.progress(40)
# Keyword Extraction
progress.text("Extracting keywords...")
keywords = kw_model.extract_keywords(
review,
keyphrase_ngram_range=(1, 2),
stop_words="english",
top_n=3
)
progress.progress(60)
# Display Results
col1, col2 = st.columns(2)
with col1:
st.subheader("Sentiment Scores")
st.json({k: round(v, 4) for k, v in sentiment_results.items()})
with col2:
st.subheader("Top 3 Keywords")
for kw, score in keywords:
st.write(f"• {kw} ({score:.4f})")
# Bar Chart
progress.text("Rendering chart...")
df_scores = pd.DataFrame.from_dict(
sentiment_results,
orient='index',
columns=['score']
)
df_scores.index.name = 'Sentiment'
st.bar_chart(df_scores)
progress.progress(80)
# Highlight Highest Sentiment
max_label, max_score = max(sentiment_results.items(), key=lambda x: x[1])
st.markdown(f"**Highest Sentiment:** **{max_label}** ({max_score:.4f})")
# Generate Detailed Recommendations for select sentiments
progress.text("Generating detailed recommendations...")
if max_label in ["Very Negative", "Negative", "Neutral"]:
prompt = f"""
You are a senior product quality and customer experience specialist at an e-commerce food retailer.
Customer Review:
"{review}"
Instructions: Analyze the feedback and provide three distinct, actionable improvement recommendations. For each, include a concise title and a detailed explanation in 5–7 sentences, plus a bullet list of 3–5 execution steps and a measure of impact.
Output only the three numbered recommendations (1–3), each with its title, detailed explanation, steps, and impact measure.
"""
response = generation_pipeline(prompt)
detailed = response[0]["generated_text"]
st.markdown(detailed)
else:
st.info("Detailed recommendations are provided only for Neutral, Negative, or Very Negative reviews.")
# Done
progress.progress(100)
progress.text("Done!")
if __name__ == "__main__":
main()
|