.ipynb_checkpoints/app-checkpoint.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7749520d-87e4-4afc-99ef-81648805978f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/usr/local/opt/[email protected]/bin/python3.10\n"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "print(sys.executable)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "5d134602-bc54-4e93-98c4-e5d4c3d86362",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['/Users/macbook/Desktop/SHK/Hugging Face Space/politweets', '/usr/local/Cellar/[email protected]/3.10.15/Frameworks/Python.framework/Versions/3.10/lib/python310.zip', '/usr/local/Cellar/[email protected]/3.10.15/Frameworks/Python.framework/Versions/3.10/lib/python3.10', '/usr/local/Cellar/[email protected]/3.10.15/Frameworks/Python.framework/Versions/3.10/lib/python3.10/lib-dynload', '', '/usr/local/lib/python3.10/site-packages']\n"
     ]
    }
   ],
   "source": [
    "import sys\n",
    "print(sys.path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "32eabc30-8a6b-49e3-bb08-a51cdf77d642",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting gradio\n",
      "  Using cached gradio-4.44.0-py3-none-any.whl (18.1 MB)\n",
      "Requirement already satisfied: huggingface-hub>=0.19.3 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (0.25.0)\n",
      "Collecting aiofiles<24.0,>=22.0\n",
      "  Using cached aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
      "Collecting pydub\n",
      "  Using cached pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
      "Collecting anyio<5.0,>=3.0\n",
      "  Using cached anyio-4.6.0-py3-none-any.whl (89 kB)\n",
      "Requirement already satisfied: matplotlib~=3.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (3.9.2)\n",
      "Collecting importlib-resources<7.0,>=1.3\n",
      "  Using cached importlib_resources-6.4.5-py3-none-any.whl (36 kB)\n",
      "Collecting ffmpy\n",
      "  Using cached ffmpy-0.4.0-py3-none-any.whl (5.8 kB)\n",
      "Collecting tomlkit==0.12.0\n",
      "  Using cached tomlkit-0.12.0-py3-none-any.whl (37 kB)\n",
      "Requirement already satisfied: markupsafe~=2.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (2.1.5)\n",
      "Requirement already satisfied: numpy<3.0,>=1.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (1.23.5)\n",
      "Requirement already satisfied: pyyaml<7.0,>=5.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (6.0.2)\n",
      "Requirement already satisfied: pandas<3.0,>=1.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (1.5.3)\n",
      "Requirement already satisfied: typing-extensions~=4.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (4.12.2)\n",
      "Collecting uvicorn>=0.14.0\n",
      "  Using cached uvicorn-0.30.6-py3-none-any.whl (62 kB)\n",
      "Requirement already satisfied: urllib3~=2.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (2.2.3)\n",
      "Collecting gradio-client==1.3.0\n",
      "  Using cached gradio_client-1.3.0-py3-none-any.whl (318 kB)\n",
      "Collecting orjson~=3.0\n",
      "  Using cached orjson-3.10.7-cp310-cp310-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl (251 kB)\n",
      "Collecting httpx>=0.24.1\n",
      "  Using cached httpx-0.27.2-py3-none-any.whl (76 kB)\n",
      "Requirement already satisfied: jinja2<4.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (3.1.4)\n",
      "Collecting ruff>=0.2.2\n",
      "  Using cached ruff-0.6.7-py3-none-macosx_10_12_x86_64.whl (10.0 MB)\n",
      "Requirement already satisfied: packaging in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (24.1)\n",
      "Collecting typer<1.0,>=0.12\n",
      "  Using cached typer-0.12.5-py3-none-any.whl (47 kB)\n",
      "Requirement already satisfied: pillow<11.0,>=8.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio) (9.4.0)\n",
      "Collecting semantic-version~=2.0\n",
      "  Using cached semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
      "Collecting fastapi<1.0\n",
      "  Using cached fastapi-0.115.0-py3-none-any.whl (94 kB)\n",
      "Collecting python-multipart>=0.0.9\n",
      "  Using cached python_multipart-0.0.10-py3-none-any.whl (22 kB)\n",
      "Collecting pydantic>=2.0\n",
      "  Using cached pydantic-2.9.2-py3-none-any.whl (434 kB)\n",
      "Requirement already satisfied: fsspec in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from gradio-client==1.3.0->gradio) (2024.6.1)\n",
      "Collecting websockets<13.0,>=10.0\n",
      "  Using cached websockets-12.0-cp310-cp310-macosx_10_9_x86_64.whl (121 kB)\n",
      "Requirement already satisfied: idna>=2.8 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from anyio<5.0,>=3.0->gradio) (3.10)\n",
      "Collecting sniffio>=1.1\n",
      "  Using cached sniffio-1.3.1-py3-none-any.whl (10 kB)\n",
      "Requirement already satisfied: exceptiongroup>=1.0.2 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from anyio<5.0,>=3.0->gradio) (1.2.2)\n",
      "Collecting starlette<0.39.0,>=0.37.2\n",
      "  Using cached starlette-0.38.5-py3-none-any.whl (71 kB)\n",
      "Requirement already satisfied: certifi in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from httpx>=0.24.1->gradio) (2024.8.30)\n",
      "Collecting httpcore==1.*\n",
      "  Using cached httpcore-1.0.5-py3-none-any.whl (77 kB)\n",
      "Collecting h11<0.15,>=0.13\n",
      "  Using cached h11-0.14.0-py3-none-any.whl (58 kB)\n",
      "Requirement already satisfied: requests in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from huggingface-hub>=0.19.3->gradio) (2.32.3)\n",
      "Requirement already satisfied: filelock in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from huggingface-hub>=0.19.3->gradio) (3.16.1)\n",
      "Requirement already satisfied: tqdm>=4.42.1 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from huggingface-hub>=0.19.3->gradio) (4.66.5)\n",
      "Requirement already satisfied: kiwisolver>=1.3.1 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from matplotlib~=3.0->gradio) (1.4.7)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from matplotlib~=3.0->gradio) (1.3.0)\n",
      "Requirement already satisfied: python-dateutil>=2.7 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from matplotlib~=3.0->gradio) (2.9.0.post0)\n",
      "Requirement already satisfied: cycler>=0.10 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from matplotlib~=3.0->gradio) (0.12.1)\n",
      "Requirement already satisfied: pyparsing>=2.3.1 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from matplotlib~=3.0->gradio) (3.2.0b1)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from matplotlib~=3.0->gradio) (4.53.1)\n",
      "Requirement already satisfied: pytz>=2020.1 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
      "Collecting pydantic-core==2.23.4\n",
      "  Using cached pydantic_core-2.23.4-cp310-cp310-macosx_10_12_x86_64.whl (1.9 MB)\n",
      "Collecting annotated-types>=0.6.0\n",
      "  Using cached annotated_types-0.7.0-py3-none-any.whl (13 kB)\n",
      "Requirement already satisfied: rich>=10.11.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from typer<1.0,>=0.12->gradio) (13.8.1)\n",
      "Collecting shellingham>=1.3.0\n",
      "  Using cached shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)\n",
      "Requirement already satisfied: click>=8.0.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from typer<1.0,>=0.12->gradio) (8.1.7)\n",
      "Requirement already satisfied: six>=1.5 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio) (1.16.0)\n",
      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.18.0)\n",
      "Requirement already satisfied: markdown-it-py>=2.2.0 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from requests->huggingface-hub>=0.19.3->gradio) (3.3.2)\n",
      "Requirement already satisfied: mdurl~=0.1 in /Users/macbook/.pyenv/versions/3.10.8/envs/politvenv/lib/python3.10/site-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
      "Installing collected packages: pydub, websockets, tomlkit, sniffio, shellingham, semantic-version, ruff, python-multipart, pydantic-core, orjson, importlib-resources, h11, ffmpy, annotated-types, aiofiles, uvicorn, pydantic, httpcore, anyio, typer, starlette, httpx, gradio-client, fastapi, gradio\n",
      "Successfully installed aiofiles-23.2.1 annotated-types-0.7.0 anyio-4.6.0 fastapi-0.115.0 ffmpy-0.4.0 gradio-4.44.0 gradio-client-1.3.0 h11-0.14.0 httpcore-1.0.5 httpx-0.27.2 importlib-resources-6.4.5 orjson-3.10.7 pydantic-2.9.2 pydantic-core-2.23.4 pydub-0.25.1 python-multipart-0.0.10 ruff-0.6.7 semantic-version-2.10.0 shellingham-1.5.4 sniffio-1.3.1 starlette-0.38.5 tomlkit-0.12.0 typer-0.12.5 uvicorn-0.30.6 websockets-12.0\n",
      "\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.2.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.2\u001b[0m\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpython -m pip install --upgrade pip\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "!pip install gradio\n",
    "#python3 -m pip install --pre autogluon.text==0.6.3b20230123"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c812ee32-9fe0-4087-a926-56a91a66ccb4",
   "metadata": {},
   "outputs": [],
   "source": [
    "#|default_exp app"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6850377a-b227-4183-90e6-a850e9a65761",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4.44.0\n"
     ]
    }
   ],
   "source": [
    "#|export\n",
    "#from fastai.vision.all import *\n",
    "import gradio as gr\n",
    "\n",
    "print(gr.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6e0bb471-02ca-484e-9a26-f5a36fe38ed4",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "#|export\n",
    "learn = load_learner('model.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "42242b57-3569-46f2-9966-c737dd6e6f16",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4e41db23-e369-413d-ab25-f85cd21af0c4",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/macbook/.pyenv/versions/politvenv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "import gradio as gr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "411ef985-d45e-4b17-b33c-24fde7c00b4f",
   "metadata": {},
   "outputs": [],
   "source": [
    "#import gradio as gr\n",
    "from autogluon.text import TextPredictor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "7de002b3-e67f-46b9-95d1-e07a1bea7f5a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load your saved AutoGluon model\n",
    "predictor = TextPredictor.load(\"trained_autogluon\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "d3093469-f35f-4008-9da4-340c64a9f85a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define a prediction function for text classification\n",
    "def classify_text(text):\n",
    "    single_row = pd.DataFrame([text], columns=[\"text\"])\n",
    "    prediction = predictor.predict(single_row)\n",
    "    return prediction[0]\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "873463fb-4911-4fe3-8f1f-36fa4c03f8a1",
   "metadata": {},
   "outputs": [],
   "source": [
    "description_text = \"\"\"\n",
    "This [model](https://huggingface.co/manifesto-project/manifestoberta-xlm-roberta-56policy-topics-sentence-2023-1-1) was trained on over 8000 German tweets. The label definitions can be found in this [handbook](https://manifesto-project.wzb.eu/coding_schemes/mp_v4) from the Manifesto Project.\n",
    "\n",
    "With this app you can classify statements into political topics like this:\n",
    "\n",
    "1. Enter some text in the input box.\n",
    "2. Click 'Submit' or press 'Enter' to get the classification result.\n",
    "3. If you want to know the label's definition, look it up [here](https://manifesto-project.wzb.eu/coding_schemes/mp_v4).\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "8e2ad81f-5b87-47c1-a60a-fd45616e8fb0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a Gradio interface\n",
    "demo = gr.Interface(\n",
    "    fn=classify_text,\n",
    "    inputs=\"text\",\n",
    "    outputs=\"label\",\n",
    "    title=\"Manifestoberta fine-tuned on Politweets\",\n",
    "    description=description_text\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "18d88162-30cc-4a6b-8581-793ed65aef0f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7873\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7873/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Launch the app\n",
    "demo.launch()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3123914a-a490-4395-917b-1ef5c1056c57",
   "metadata": {},
   "source": [
    "## More Customization\n",
    "This is probably the way to go if I want more functionality and control.\n",
    "But for now I don't really want to get into that stuff."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "5f37d50d-281b-42a8-bcc3-26cc27b54507",
   "metadata": {},
   "outputs": [],
   "source": [
    "with gr.Blocks() as demo:\n",
    "    gr.Interface(\n",
    "    fn=classify_text,\n",
    "    inputs=\"text\",\n",
    "    outputs=\"label\"\n",
    "    )\n",
    "\n",
    "    # Add explanation at the top using Markdown\n",
    "    gr.Markdown(\"\"\"\n",
    "    ### AutoGluon Text Classification Demo\n",
    "    \n",
    "    This app classifies text using a model trained with AutoGluon. \n",
    "    To use the app:\n",
    "    1. Enter your text in the input box below.\n",
    "    2. Click the 'Submit' button to get the classification result.\n",
    "    \n",
    "    For more details, visit [AutoGluon Documentation](https://auto.gluon.ai/stable/index.html).\n",
    "    \"\"\")\n",
    "    \n",
    "    # Add input, output, and button\n",
    "    text_input = gr.Textbox(label=\"Enter your text\")\n",
    "    output = gr.Label(label=\"Classification\")\n",
    "    submit_btn = gr.Button(\"Submit\")\n",
    "\n",
    "    # Link the button to the function\n",
    "    submit_btn.click(classify_text, inputs=text_input, outputs=output)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "8652a1b0-8f65-4983-8bdd-a57117fee5da",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7866\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7866/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "demo.launch()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f245aa88-4746-4aed-85c1-a09bdcbb6710",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "politvenvnotebook",
   "language": "python",
   "name": "politvenvnotebook"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}