Spaces:

letijo03
/

User-Input_SentimentAnalysis

Paused

App Files Files Community

letijo03 commited on Mar 13, 2025

Commit

6cfdd4c

verified ·

1 Parent(s): 149d5a7

Update app.py

Browse files

Files changed (1) hide show

app.py +101 -394

app.py CHANGED Viewed

@@ -1,394 +1,101 @@
-from flask import Flask, request, render_template_string, jsonify, send_from_directory
-import requests
-import pandas as pd
-import re
-import time
-from random import randint
-import os
-from transformers import AutoModelForSequenceClassification, XLMRobertaTokenizer
-import torch
-# Define the Flask app with a different variable name
-flask_app = Flask(__name__)
-# Load the pre-trained model and tokenizer from Hugging Face
-MODEL_NAME = "letijo03/xlm-r-shopee"
-tokenizer = XLMRobertaTokenizer.from_pretrained(MODEL_NAME)
-model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
-model.eval()  # Set the model to evaluation mode
-def get_ids_from_url(url):
-    # Try multiple patterns to extract shop_id and item_id
-    patterns = [
-        r"i\.(\d+)\.(\d+)",      # e.g. ...-i.123456.987654
-        r"/product/(\d+)/(\d+)"   # e.g. .../product/123456/987654
-    ]
-    for pattern in patterns:
-        match = re.search(pattern, url)
-        if match:
-            return int(match.group(1)), int(match.group(2))
-    raise ValueError("Invalid Shopee URL format. Please use a valid Shopee product URL.")
-def fetch_comments(shop_id, item_id, limit=50, offset=0, retries=3):
-    url = f"https://shopee.ph/api/v2/item/get_ratings?itemid={item_id}&shopid={shop_id}&limit={limit}&offset={offset}"
-    headers = {
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
-    }
-    for attempt in range(retries):
-        try:
-            response = requests.get(url, headers=headers)
-            response.raise_for_status()
-            return response.json()
-        except requests.exceptions.HTTPError as http_err:
-            print(f"HTTP error occurred: {http_err}")
-            if attempt < retries - 1:
-                time.sleep(2)
-        except Exception as err:
-            print(f"An error occurred: {err}")
-            if attempt < retries - 1:
-                time.sleep(2)
-    return None
-def extract_comments(data):
-    comments = []
-    if data and 'data' in data and 'ratings' in data['data']:
-        for rating in data['data']['ratings']:
-            comment_parts = []
-            if 'tag_info' in rating:
-                for tag in rating['tag_info']:
-                    tag_text = f"{tag.get('tag_name', '')}: {tag.get('tag_value', '')}"
-                    comment_parts.append(tag_text)
-            main_comment = rating.get('comment', '').strip()
-            if main_comment:
-                comment_parts.append(main_comment)
-            full_comment = "\n".join(comment_parts)
-            comment = {
-                'Username': rating.get('author_username', ''),
-                'Rating': rating.get('rating_star', 0),
-                'Date and Time': pd.to_datetime(rating.get('ctime', 0), unit='s').strftime('%Y-%m-%d %H:%M'),
-                'Comment': full_comment
-            }
-            comments.append(comment)
-    return comments
-def clean_data(df):
-    # Convert each comment to a string before applying regex
-    df['Comment'] = df['Comment'].apply(lambda x: re.sub(r'[^a-zA-Z0-9\s]', '', str(x)))
-    # Drop rows with empty comments after stripping whitespace
-    df = df[df['Comment'].str.strip() != '']
-    return df
-def classify_sentiment(text):
-    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
-    outputs = model(**inputs)
-    prediction = torch.argmax(outputs.logits, dim=-1)
-    return prediction.item()
-# Combined HTML and CSS template using render_template_string
-html_template = """
-<!DOCTYPE html>
-<html lang="en">
-<head>
-  <meta charset="UTF-8">
-  <meta name="viewport" content="width=device-width, initial-scale=1.0">
-  <title>Shopee Product Comment Sentiment Analysis</title>
-  <style>
-    /* Global styles */
-    body {
-        font-family: Arial, sans-serif;
-        background-color: #f5f5f5;
-        margin: 0;
-        padding: 0;
-        color: #333;
-    }
-    header {
-        background-color: #FF5722;
-        color: white;
-        padding: 20px;
-        text-align: center;
-    }
-    header h1 {
-        margin: 0;
-        font-size: 2em;
-    }
-    main {
-        padding: 20px;
-        max-width: 900px;
-        margin: 0 auto;
-        background-color: white;
-        border-radius: 8px;
-        box-shadow: 0px 4px 6px rgba(0, 0, 0, 0.1);
-    }
-    form {
-        margin: 20px auto;
-        max-width: 400px;
-        display: flex;
-        flex-direction: column;
-        gap: 15px;
-        background-color: #f9f9f9;
-        padding: 20px;
-        border-radius: 8px;
-        box-shadow: 0px 2px 4px rgba(0, 0, 0, 0.1);
-    }
-    input, button {
-        padding: 12px;
-        font-size: 1.1em;
-        border: 1px solid #ccc;
-        border-radius: 6px;
-    }
-    input {
-        background-color: #fff;
-    }
-    button {
-        background-color: #FF5722;
-        color: white;
-        border: none;
-        cursor: pointer;
-        transition: background-color 0.3s ease;
-    }
-    button:hover {
-        background-color: #E64A19;
-    }
-    input:focus {
-        border-color: #FF5722;
-        outline: none;
-    }
-    .error-message {
-        color: red;
-        font-weight: bold;
-    }
-    .success-message {
-        color: green;
-        font-weight: bold;
-    }
-    #loadingContainer {
-        display: flex;
-        flex-direction: column;
-        justify-content: center;
-        align-items: center;
-        font-size: 16px;
-        color: #FF5722;
-        height: 100vh;
-        position: absolute;
-        top: 0;
-        left: 0;
-        right: 0;
-        bottom: 0;
-        background-color: rgba(255, 255, 255, 0.8);
-        z-index: 9999;
-        text-align: center;
-    }
-    .spinner {
-        border: 4px solid rgba(0, 0, 0, 0.1);
-        border-left-color: #FF5722;
-        border-radius: 50%;
-        width: 50px;
-        height: 50px;
-        animation: spin 1s linear infinite;
-        margin-top: 10px;
-    }
-    @keyframes spin {
-        to { transform: rotate(360deg); }
-    }
-    #chartContainer {
-        display: flex;
-        justify-content: center;
-        align-items: center;
-        width: 100%;
-        max-width: 800px;
-        height: 600px;
-        margin: 20px auto;
-    }
-    img {
-        display: block;
-        margin: 0 auto;
-        max-width: 100%;
-        height: auto;
-    }
-    footer {
-        background-color: #333;
-        color: white;
-        text-align: center;
-        padding: 10px 0;
-        position: relative;
-        bottom: 0;
-        width: 100%;
-    }
-    .result-message {
-        display: flex;
-        flex-direction: column;
-        justify-content: center;
-        align-items: center;
-        text-align: center;
-        margin-top: 20px;
-    }
-    .error-message {
-        color: red;
-        font-size: 18px;
-        font-weight: bold;
-    }
-    .success-message {
-        color: green;
-        font-size: 18px;
-        font-weight: bold;
-    }
-    .download-link {
-        margin-top: 15px;
-        padding: 10px 20px;
-        background-color: #FF5722;
-        color: white;
-        text-decoration: none;
-        border-radius: 5px;
-        font-size: 16px;
-        font-weight: bold;
-        display: inline-block;
-    }
-    .download-link:hover {
-        background-color: #e64a19;
-    }
-  </style>
-  <script type="text/javascript" src="https://www.gstatic.com/charts/loader.js"></script>
-</head>
-<body>
-  <header>
-    <h1>Shopee Product Comment Sentiment Analysis</h1>
-  </header>
-  <main>
-    <form id="scrapeForm">
-      <label for="url">Enter Shopee Product URL:</label>
-      <input type="text" id="url" name="url" placeholder="Enter the URL here" required>
-      <button type="submit">Generate</button>
-    </form>
-    <div id="loadingContainer" style="display: none;">
-      <p id="loadingText">Scraping, please wait...</p>
-      <div class="spinner"></div>
-    </div>
-    <div id="result"></div>
-    <div id="downloadLink" style="margin-top: 20px;"></div>
-    <div id="chartContainer" style="margin-top: 5px;"></div>
-  </main>
-  <footer>
-    <p>&copy; 2025 Shopee Product Comment Sentiment Analysis. All Rights Reserved.</p>
-  </footer>
-  <script>
-    google.charts.load('current', { 'packages': ['corechart'] });
-    function drawPieChart(chartData) {
-      const data = google.visualization.arrayToDataTable(chartData);
-      const options = {
-        title: 'Sentiment Distribution',
-        is3D: true,
-        width: '100%',
-        height: 600,
-        slices: {
-          0: { color: '#4caf50' },
-          1: { color: '#ffc107' },
-          2: { color: '#f44336' }
-        },
-        pieSliceText: 'percentage',
-        tooltip: { trigger: 'focus' }
-      };
-      const chart = new google.visualization.PieChart(document.getElementById('chartContainer'));
-      chart.draw(data, options);
-    }
-    document.getElementById("scrapeForm").onsubmit = async function(e) {
-      e.preventDefault();
-      const url = document.getElementById("url").value;
-      const resultDiv = document.getElementById("result");
-      const downloadLinkDiv = document.getElementById("downloadLink");
-      const chartDiv = document.getElementById("chartContainer");
-      const loadingContainer = document.getElementById("loadingContainer");
-      loadingContainer.style.display = "flex";
-      resultDiv.innerHTML = "";
-      downloadLinkDiv.innerHTML = "";
-      chartDiv.innerHTML = "";
-      try {
-        const response = await fetch('/scrape', {
-          method: 'POST',
-          headers: { 'Content-Type': 'application/x-www-form-urlencoded' },
-          body: new URLSearchParams({ 'url': url })
-        });
-        const data = await response.json();
-        loadingContainer.style.display = "none";
-        if (data.error) {
-          resultDiv.innerHTML = `<div class="result-message"><p class="error-message">${data.error}</p></div>`;
-        } else {
-          resultDiv.innerHTML = `<div class="result-message"><p class="success-message">${data.message}</p></div>`;
-          if (data.filename) {
-            downloadLinkDiv.innerHTML = `<div class="result-message"><a href="/download/${data.filename}" download class="download-link">Download CSV</a></div>`;
-          }
-          if (data.chart_data) {
-            google.charts.setOnLoadCallback(() => drawPieChart(data.chart_data));
-          }
-        }
-      } catch (error) {
-        loadingContainer.style.display = "none";
-        resultDiv.innerHTML = `<p class="error-message">Error sending request: ${error.message}</p>`;
-        console.error('Fetch error:', error);
-      }
-    };
-  </script>
-</body>
-</html>
-"""
-@flask_app.route('/')
-def index():
-    return render_template_string(html_template)
-@flask_app.route('/scrape', methods=['POST'])
-def scrape():
-    url = request.form.get('url')
-    try:
-        shop_id, item_id = get_ids_from_url(url)
-    except ValueError as e:
-        return jsonify({'error': str(e)})
-    all_comments = []
-    offset = 0
-    limit = 50
-    while True:
-        data = fetch_comments(shop_id, item_id, limit=limit, offset=offset)
-        if data is None:
-            break
-        comments = extract_comments(data)
-        if not comments:
-            break
-        all_comments.extend(comments)
-        if len(comments) < limit:
-            break
-        offset += limit
-        time.sleep(randint(2, 5))
-    if all_comments:
-        df = pd.DataFrame(all_comments)
-        df = clean_data(df)
-        df['Sentiment'] = df['Comment'].apply(classify_sentiment)
-        sentiment_counts = df['Sentiment'].value_counts().to_dict()
-        chart_data = [["Sentiment", "Count"]]
-        for sentiment, count in sentiment_counts.items():
-            sentiment_label = "Positive" if sentiment == 2 else "Neutral" if sentiment == 1 else "Negative"
-            chart_data.append([sentiment_label, count])
-        csv_filename = 'shopee_comments_formatted.csv'
-        os.makedirs('static', exist_ok=True)
-        csv_filepath = os.path.join('static', csv_filename)
-        df.to_csv(csv_filepath, index=False)
-        return jsonify({
-            'message': 'Successfully scraped and analyzed comments.',
-            'filename': csv_filename,
-            'chart_data': chart_data
-        })
-    else:
-        return jsonify({'error': 'No comments found or unable to fetch comments.'})
-@flask_app.route('/download/<filename>')
-def download_file(filename):
-    return send_from_directory('static', filename, as_attachment=True)
-# Wrap the Flask app as an ASGI app so that the module-level variable 'app' is ASGI-compatible
-from asgiref.wsgi import WsgiToAsgi
-app = WsgiToAsgi(flask_app)
-if __name__ == '__main__':
-    import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("PORT", 7860)))

+from flask import Flask, request, render_template_string, jsonify
+from transformers import AutoModelForSequenceClassification, XLMRobertaTokenizer
+import torch
+from asgiref.wsgi import WsgiToAsgi
+# Define the Flask app
+flask_app = Flask(__name__)
+# Load the pre-trained model and tokenizer
+MODEL_NAME = "letijo03/xlm-r-shopee"
+tokenizer = XLMRobertaTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
+model.eval()  # Set the model to evaluation mode
+def classify_sentiment(text):
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    outputs = model(**inputs)
+    prediction = torch.argmax(outputs.logits, dim=-1)
+    return prediction.item()
+# HTML template for user input
+html_template = """
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>Comment Sentiment Analysis</title>
+  <style>
+    body { font-family: Arial, sans-serif; background-color: #f5f5f5; margin: 0; padding: 0; color: #333; }
+    header { background-color: #FF5722; color: white; padding: 20px; text-align: center; }
+    main { padding: 20px; max-width: 900px; margin: 0 auto; background-color: white; border-radius: 8px; box-shadow: 0px 4px 6px rgba(0, 0, 0, 0.1); }
+    form { margin: 20px auto; max-width: 600px; display: flex; flex-direction: column; gap: 15px; background-color: #f9f9f9; padding: 20px; border-radius: 8px; box-shadow: 0px 2px 4px rgba(0, 0, 0, 0.1); }
+    textarea, button { padding: 12px; font-size: 1.1em; border: 1px solid #ccc; border-radius: 6px; }
+    textarea { background-color: #fff; resize: vertical; min-height: 100px; }
+    button { background-color: #FF5722; color: white; border: none; cursor: pointer; transition: background-color 0.3s ease; }
+    button:hover { background-color: #E64A19; }
+    .result-message { text-align: center; margin-top: 20px; font-size: 18px; font-weight: bold; }
+  </style>
+  <script>
+    document.addEventListener("DOMContentLoaded", function() {
+      document.getElementById("commentForm").onsubmit = async function(e) {
+        e.preventDefault();
+        const comment = document.getElementById("comment").value;
+        const resultDiv = document.getElementById("result");
+        resultDiv.innerHTML = "";
+        try {
+          const response = await fetch('/analyze', {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/x-www-form-urlencoded' },
+            body: new URLSearchParams({ 'comment': comment })
+          });
+          const data = await response.json();
+          if (data.error) {
+            resultDiv.innerHTML = `<p class="result-message" style="color:red;">${data.error}</p>`;
+          } else {
+            resultDiv.innerHTML = `<p class="result-message" style="color:green;">${data.message}</p>`;
+          }
+        } catch (error) {
+          resultDiv.innerHTML = `<p class="result-message" style="color:red;">Error sending request: ${error.message}</p>`;
+          console.error('Fetch error:', error);
+        }
+      };
+    });
+  </script>
+</head>
+<body>
+  <header>
+    <h1>Comment Sentiment Analysis</h1>
+  </header>
+  <main>
+    <form id="commentForm">
+      <label for="comment">Enter your comment:</label>
+      <textarea id="comment" name="comment" placeholder="Type your comment here..." required></textarea>
+      <button type="submit">Analyze Sentiment</button>
+    </form>
+    <div id="result"></div>
+  </main>
+</body>
+</html>
+"""
+@flask_app.route('/')
+def index():
+    return render_template_string(html_template)
+@flask_app.route('/analyze', methods=['POST'])
+def analyze():
+    comment = request.form.get('comment')
+    if not comment or comment.strip() == "":
+        return jsonify({'error': 'Please provide a valid comment.'})
+    sentiment = classify_sentiment(comment)
+    sentiment_label = "Positive" if sentiment == 2 else "Neutral" if sentiment == 1 else "Negative"
+    return jsonify({'message': f'Sentiment analysis complete. The sentiment is: {sentiment_label}.'})
+# Wrap the Flask app as an ASGI app
+app = WsgiToAsgi(flask_app)
+if __name__ == '__main__':
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)