init

.gitignore

@@ -0,0 +1 @@
+model/*

Dockerfile

@@ -0,0 +1,27 @@
+# Gunakan base image dengan Python
+FROM python:3.11
+
+# Set environment variable untuk non-interaktif
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+# Buat direktori kerja untuk aplikasi
+WORKDIR /app
+
+# Salin file requirements.txt ke container
+COPY requirements.txt /app/
+
+# Install dependencies Python
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Salin seluruh file aplikasi ke container
+COPY . /app/
+
+# Jalankan skrip untuk mengunduh model dari Hugging Face
+RUN python download_model.py
+
+# Ekspos port default Flask (5000)
+EXPOSE 5000
+
+# Perintah untuk menjalankan aplikasi Flask
+CMD ["python", "app.py"]

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 akhyarr
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -8,4 +8,72 @@ pinned: false
 short_description: 'Simple Pos Tagger '
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# POS Tagger
+
+Proyek ini adalah implementasi sederhana dari POS (Part-of-Speech) Tagger menggunakan model dari Hugging Face. Aplikasi ini menggunakan Flask untuk backend dan HTML/CSS untuk frontend.
+
+## Persyaratan
+
+Pastikan Anda telah menginstal:
+
+- Python 3.6 atau lebih tinggi
+- pip (Python package installer)
+
+## Cara Menjalankan
+
+Ikuti langkah-langkah berikut untuk menjalankan proyek ini di mesin lokal Anda:
+
+### 1. Clone Repositori
+
+Clone repositori ini ke direktori lokal Anda menggunakan perintah berikut:
+
+```bash
+git clone https://github.com/rrayhka/pos-tagger.git
+```
+
+### 2. Install Dependencies
+
+Masuk ke direktori proyek yang baru saja di-clone dan install dependencies yang diperlukan:
+
+```bash
+cd pos-tagger
+pip install -r requirements.txt
+```
+
+### 3. Unduh Model
+
+Jalankan skrip `download_model.py` untuk mengunduh model dan tokenizer dari Hugging Face dan menyimpannya secara lokal:
+
+```bash
+python download_model.py
+```
+
+### 4. Jalankan Aplikasi
+
+Jalankan aplikasi Flask menggunakan perintah berikut:
+
+```bash
+python app.py
+```
+
+## File Utama
+
+- `app.py`: Script untuk menjalankan backend Flask.
+- `download_model.py`: Script untuk mengunduh dan menyimpan model dan tokenizer dari Hugging Face.
+- `index.html`: File HTML untuk frontend aplikasi.
+- `requirements.txt`: Daftar dependencies yang diperlukan untuk menjalankan aplikasi.
+
+## Menggunakan Aplikasi
+
+1. Buka `index.html` di browser Anda.
+2. Masukkan teks bahasa Indonesia di textarea yang disediakan.
+3. Klik tombol "Tag POS".
+4. Hasil POS tagging akan ditampilkan di bawah form input.
+
+## Kontribusi
+
+Jika Anda ingin berkontribusi pada proyek ini, silakan buat pull request atau buka isu di repositori GitHub.
+
+## Lisensi
+
+Proyek ini dilisensikan di bawah MIT License. Lihat file `LICENSE` untuk informasi lebih lanjut.

app.py

@@ -0,0 +1,27 @@
+from flask import Flask, request, jsonify, render_template
+from transformers import AutoModelForTokenClassification, AutoTokenizer, pipeline
+from flask_cors import CORS
+import logging
+
+logging.basicConfig(level=logging.DEBUG)
+
+app = Flask(__name__)
+CORS(app)
+model_path = "./model"
+model = AutoModelForTokenClassification.from_pretrained(model_path)
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+nlp = pipeline("token-classification", model=model, tokenizer=tokenizer)
+
+@app.route('/')
+def home(): return render_template('index.html')
+
+@app.route('/pos_tag', methods=['POST'])
+def pos_tag():
+    text = request.json.get('text')
+    if not text: return jsonify({"error": "Masukkan Teks"}), 400
+    if isinstance(text, str): text = text.encode('utf-8').decode('utf-8')
+    results = nlp(text)
+    tagged_tokens = [{"word": res["word"].replace('Ġ', ''), "tag": res["entity"].replace('B-', '').replace('I-', '')} for res in results]
+    return jsonify({"tagged_tokens": tagged_tokens})
+if __name__ == '__main__':
+    app.run(port=5007, debug=True)

download_model.py

@@ -0,0 +1,6 @@
+from transformers import AutoModelForTokenClassification, AutoTokenizer
+model_name = "w11wo/indonesian-roberta-base-posp-tagger"
+model = AutoModelForTokenClassification.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model.save_pretrained('./model')
+tokenizer.save_pretrained('./model')

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+torch
+flask
+flask-cors

templates/index.html

@@ -0,0 +1,217 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>POS Tagger</title>
+    <style>
+        body {
+            font-family: Arial, sans-serif;
+            margin: 0;
+            padding: 20px;
+            background-color: #f4f4f4;
+        }
+
+        .container {
+            max-width: 600px;
+            margin: auto;
+            padding: 20px;
+            background: #fff;
+            box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);
+        }
+
+        textarea {
+            width: 95%;
+            height: 100px;
+            padding: 10px;
+            margin-bottom: 10px;
+        }
+
+        button {
+            display: inline-block;
+            padding: 10px 20px;
+            background: #007bff;
+            color: #fff;
+            border: none;
+            cursor: pointer;
+        }
+
+        button:hover {
+            background: #0056b3;
+        }
+
+        .results {
+            margin-top: 20px;
+        }
+
+        .results span {
+            display: inline-block;
+            padding: 5px;
+            margin-right: 3.5px;
+            margin-bottom: 6.5px;
+            border-radius: 4px;
+
+        }
+
+        .PPO {
+            background-color: #ffadad;
+            color: #000;
+        }
+
+        .KUA {
+            background-color: #ffd6a5;
+            color: #000;
+        }
+
+        .ADV {
+            background-color: #fdffb6;
+            color: #000;
+        }
+
+        .PRN {
+            background-color: #caffbf;
+            color: #000;
+        }
+
+        .VBI {
+            background-color: #9bf6ff;
+            color: #000;
+        }
+
+        .PAR {
+            background-color: #a0c4ff;
+            color: #000;
+        }
+
+        .VBP {
+            background-color: #bdb2ff;
+            color: #000;
+        }
+
+        .NNP {
+            background-color: #ffc6ff;
+            color: #000;
+        }
+
+        .UNS {
+            background-color: #fffffc;
+            color: #000;
+        }
+
+        .VBT {
+            background-color: #d0f4de;
+            color: #000;
+        }
+
+        .VBL {
+            background-color: #a2d2ff;
+            color: #000;
+        }
+
+        .NNO {
+            background-color: #ffadad;
+            color: #000;
+        }
+
+        .ADJ {
+            background-color: #ffd6a5;
+            color: #000;
+        }
+
+        .PRR {
+            background-color: #fdffb6;
+            color: #000;
+        }
+
+        .PRK {
+            background-color: #caffbf;
+            color: #000;
+        }
+
+        .CCN {
+            background-color: #9bf6ff;
+            color: #000;
+        }
+
+        .ADK {
+            background-color: #bdb2ff;
+            color: #000;
+        }
+
+        .ART {
+            background-color: #ffc6ff;
+            color: #000;
+        }
+
+        .CSN {
+            background-color: #979745;
+            color: #000;
+        }
+
+        .NUM {
+            background-color: #d0f4de;
+            color: #000;
+        }
+
+        .SYM {
+            background-color: #a2d2ff;
+            color: #000;
+        }
+
+        .INT {
+            background-color: #ffadad;
+            color: #000;
+        }
+
+        .NEG {
+            background-color: #ffd6a5;
+            color: #000;
+        }
+
+        .PRI {
+            background-color: #fdffb6;
+            color: #000;
+        }
+
+        .VBE {
+            background-color: #caffbf;
+            color: #000;
+        }
+    </style>
+</head>
+
+<body>
+    <div class="container">
+        <h1>POS Tagger</h1>
+        <form id="posForm">
+            <textarea id="textInput" placeholder="Masukkan teks bahasa Indonesia di sini" required></textarea>
+            <button type="submit">Tag POS</button>
+        </form>
+        <div class="results" id="results"></div>
+    </div>
+    <script>
+        document.getElementById('posForm').addEventListener('submit', async function (e) {
+            e.preventDefault();
+            const text = document.getElementById('textInput').value;
+            const response = await fetch('http://127.0.0.1:5007/pos_tag', {
+                method: 'POST',
+                headers: {
+                    'Content-Type': 'application/json',
+                },
+                body: JSON.stringify({ text }),
+            });
+            const data = await response.json();
+            const resultsDiv = document.getElementById('results');
+            resultsDiv.innerHTML = '';
+            data.tagged_tokens.forEach(token => {
+                const span = document.createElement('span');
+                span.textContent = `${token.word} (${token.tag})`;
+                span.className = token.tag;
+                resultsDiv.appendChild(span);
+            });
+        });
+    </script>
+</body>
+
+</html>