Upload app.ipynb

app.ipynb

@@ -0,0 +1,116 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 764
+        },
+        "id": "NfhpwnF_ZFT2",
+        "outputId": "4b1a8307-1484-4661-96de-747c277bd12d"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.11/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning: \n",
+            "The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
+            "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
+            "You will be able to reuse this secret in all of your notebooks.\n",
+            "Please note that authentication is recommended but still optional to access public models or datasets.\n",
+            "  warnings.warn(\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "nama-user-anda/nama-model-spam-anda is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'\n",
+            "If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=<your_token>`\n",
+            "It looks like you are running Gradio on a hosted a Jupyter notebook. For the Gradio app to work, sharing must be enabled. Automatically setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
+            "\n",
+            "Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n",
+            "* Running on public URL: https://07f424aa3bc95e504a.gradio.live\n",
+            "\n",
+            "This share link expires in 1 week. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<IPython.core.display.HTML object>"
+            ],
+            "text/html": [
+              "<div><iframe src=\"https://07f424aa3bc95e504a.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+            ]
+          },
+          "metadata": {}
+        }
+      ],
+      "source": [
+        "import gradio as gr\n",
+        "from transformers import pipeline\n",
+        "\n",
+        "# 1. Muat pipeline klasifikasi teks dari model Anda di Hub\n",
+        "# Pastikan model Anda sudah publik atau Anda login di environment\n",
+        "try:\n",
+        "    classifier = pipeline(\"text-classification\", model=\"nama-user-anda/nama-model-spam-anda\") # <-- GANTI INI\n",
+        "except Exception as e:\n",
+        "    # Jika gagal, tampilkan error. Mungkin modelnya private atau salah nama.\n",
+        "    print(e)\n",
+        "    classifier = None\n",
+        "\n",
+        "# 2. Buat fungsi untuk prediksi\n",
+        "# Fungsi ini akan menerima input teks dari user dan mengembalikan output\n",
+        "def predict_spam(text):\n",
+        "    if classifier is None:\n",
+        "        return {\"Error\": \"Model tidak berhasil dimuat, periksa nama model di kode atau log di Space.\"}\n",
+        "\n",
+        "    # Pipeline akan mengembalikan list berisi dictionary\n",
+        "    # Contoh: [{'label': 'SPAM', 'score': 0.99...}]\n",
+        "    prediction = classifier(text)\n",
+        "\n",
+        "    # Kita format outputnya agar lebih mudah dibaca oleh Gradio\n",
+        "    # Kita akan menggunakan komponen Label di Gradio, jadi kita return dictionary\n",
+        "    return {p['label']: p['score'] for p in prediction}\n",
+        "\n",
+        "# 3. Definisikan antarmuka Gradio\n",
+        "# Ini adalah bagian yang mengatur tampilan (input, output, judul, dll.)\n",
+        "demo = gr.Interface(\n",
+        "    fn=predict_spam,  # Fungsi yang akan dijalankan saat tombol \"Submit\" ditekan\n",
+        "    inputs=gr.Textbox(lines=5, label=\"Text\", placeholder=\"Masukkan teks untuk diklasifikasikan...\"),\n",
+        "    outputs=gr.Label(num_top_classes=2, label=\"Output\"), # gr.Label cocok untuk output klasifikasi\n",
+        "    title=\"Klasifikasi Teks - Anti Spam Indonesia\",\n",
+        "    description=\"Masukkan teks untuk diklasifikasikan oleh model hasil fine-tuning. Cocok untuk deteksi spam, penipuan, dll. Model oleh: [Nama Anda].\",\n",
+        "    examples=[\n",
+        "        [\"Selamat! Anda memenangkan undian hadiah 100 juta rupiah, klik link ini segera!\"],\n",
+        "        [\"Pak, nanti sore jadi rapat ya di kantor jam 4.\"],\n",
+        "        [\"Diskon besar! Beli 1 gratis 1 untuk semua produk elektronik. Kunjungi situs kami sekarang juga.\"]\n",
+        "    ]\n",
+        ")\n",
+        "\n",
+        "# 4. Luncurkan aplikasi\n",
+        "if __name__ == \"__main__\":\n",
+        "    demo.launch()"
+      ]
+    }
+  ]
+}