{ "cells": [ { "cell_type": "code", "execution_count": 37, "id": "8faa322a", "metadata": {}, "outputs": [], "source": [ "# !tar -cf southern_samples.tar.gz southern_samples" ] }, { "cell_type": "code", "execution_count": 24, "id": "ff2d9531", "metadata": {}, "outputs": [], "source": [ "# import json\n", "# with open(\"/mnt/data-ssd-1/data/southern-comfort/output/artifacts/web-sample-data/sample_manifest_web.json\") as f:\n", "# web_data = json.load(f)\n", "# for e in web_data[\"sample\"]:\n", "# with open(f\"southern_samples/{e['uid']}_text.txt\", \"w\") as f:\n", "# f.write(e[\"text\"])\n", "# with open(f\"southern_samples/{e['uid']}_text_normalized.txt\", \"w\") as f:\n", "# f.write(e[\"text_normalized\"])" ] }, { "cell_type": "code", "execution_count": 39, "id": "c59ef8c2", "metadata": {}, "outputs": [], "source": [ "from labelbox.data.annotation_types import (\n", " Label, ImageData, MaskData, LabelList, TextData, VideoData,\n", " ObjectAnnotation, ClassificationAnnotation, Polygon, Rectangle, Line, Mask,\n", " Point, Checklist, Radio, Text, TextEntity, ClassificationAnswer)\n", "from labelbox import (LabelingFrontend, Client, OntologyBuilder, Tool,\n", " Classification, Option)\n", "from shapely.ops import transform\n", "from shapely.affinity import affine_transform\n", "import requests\n", "import IPython\n", "from PIL import Image\n", "from io import BytesIO\n", "import numpy as np\n", "import os" ] }, { "cell_type": "code", "execution_count": 40, "id": "403e132c", "metadata": {}, "outputs": [], "source": [ "# Add your api key\n", "API_KEY = \"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySWQiOiJjbDF0bmE2OGE0aDQzMHpiaWZkMDI1ZDd1Iiwib3JnYW5pemF0aW9uSWQiOiJjbDJ5dnFxcnIxOHR1MDdiOGF0Z2hmd3gwIiwiYXBpS2V5SWQiOiJjbDNtNHgxc2IwZTdwMDdldWFsbjA3MngxIiwic2VjcmV0IjoiMmIyZjY5NDgwYTBmNjM4MjUzM2ZkNzc3M2Q4YjhlYmIiLCJpYXQiOjE2NTM1MTYzMDksImV4cCI6MjI4NDY2ODMwOX0.Wmt5SdtQOoOwCCCgNetCeJSagZdv6l_Jj0X9fL2ndCo\"\n", "client = Client(api_key=API_KEY)" ] }, { "cell_type": "code", "execution_count": null, "id": "96d6d364", "metadata": {}, "outputs": [], "source": [ "\n", "td = TextData(text=\"some text\",\n", " uid=\"ckrey6o07000008l50uk2gcr3\",\n", " external_id=\"my_text_data_row\")" ] }, { "cell_type": "code", "execution_count": null, "id": "4e067358", "metadata": {}, "outputs": [], "source": [ "entity_annotation = ObjectAnnotation(value=TextEntity(start=10, end=12),\n", " name=\"person\")\n", "\n", "entity_annotation = ObjectAnnotation(\n", " value=TextEntity(start=10, end=12),\n", " feature_schema_id=\"ckrgddyli000108mk0c0t9qya\")" ] }, { "cell_type": "code", "execution_count": null, "id": "47707a0e", "metadata": {}, "outputs": [], "source": [ "\n", "text_annotation = ClassificationAnnotation(\n", " name=\"my text class\", value=Text(answer=\"some text answer\"))\n", "\n", "text_annotation = ClassificationAnnotation(\n", " feature_schema_id=\"my text class\", value=Text(answer=\"some text answer\"))" ] }, { "cell_type": "code", "execution_count": null, "id": "6428cc3a", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "c8c75788", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 49, "id": "da5bd4cb", "metadata": {}, "outputs": [], "source": [ "dataset = client.create_dataset(name=\"my_test_dataset\")" ] }, { "cell_type": "code", "execution_count": null, "id": "386ee010", "metadata": {}, "outputs": [], "source": [ "# When uploading for MAL or MEA we need an ontology.\n", "# So let's create one\n", "\n", "# These names have to match our object names exactly!!\n", "ontology_builder = OntologyBuilder(\n", " classifications=[\n", " Classification(\n", " Classification.Type.TEXT,\n", " instructions=\"transcribe Audio\",\n", " )\n", " ]\n", ")\n", "\n", "editor = next(client.get_labeling_frontends(where=LabelingFrontend.name == \"Editor\"))\n", "project = client.get_project(\"cl3kma0ex1o5707b3845i3d9f\")\n", "\n", "project.setup(editor, ontology_builder.asdict())\n", "project.datasets.connect(dataset)\n", "\n", "ontology = OntologyBuilder.from_project(project)" ] }, { "cell_type": "code", "execution_count": null, "id": "a1dfea82", "metadata": {}, "outputs": [], "source": [ "cl3m4fuju27wu07v6138yf029" ] }, { "cell_type": "code", "execution_count": 52, "id": "3d542766", "metadata": {}, "outputs": [ { "ename": "ValidationError", "evalue": "2 validation errors for ObjectAnnotation\nvalue\n value is not a valid dict (type=type_error.dict)\nvalue\n value is not a valid dict (type=type_error.dict)", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mValidationError\u001b[0m Traceback (most recent call last)", "\u001b[0;32m/tmp/ipykernel_981942/3703131329.py\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 6\u001b[0m ),\n\u001b[1;32m 7\u001b[0m annotations=[\n\u001b[0;32m----> 8\u001b[0;31m ObjectAnnotation(\n\u001b[0m\u001b[1;32m 9\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"deer_nose\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 10\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"blabla\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", "\u001b[0;32m~/venvs/ml/lib/python3.8/site-packages/pydantic/main.cpython-38-x86_64-linux-gnu.so\u001b[0m in \u001b[0;36mpydantic.main.BaseModel.__init__\u001b[0;34m()\u001b[0m\n", "\u001b[0;31mValidationError\u001b[0m: 2 validation errors for ObjectAnnotation\nvalue\n value is not a valid dict (type=type_error.dict)\nvalue\n value is not a valid dict (type=type_error.dict)" ] } ], "source": [ "label = Label(\n", " data=AudioData(\n", " text=\"some text\",\n", " uid=\"ckrey6o07000008l50uk2gcr3\",\n", " external_id=\"my_text_data_row\"\n", " ),\n", " annotations=[\n", " ObjectAnnotation(\n", " name=\"deer_nose\",\n", " value=\"blabla\",\n", " classifications=[\n", " ClassificationAnnotation(\n", " name=\"my text class\", \n", " value=Text(answer=\"some text answer\")\n", " )\n", " ]\n", " ),\n", " ]\n", ")" ] }, { "cell_type": "code", "execution_count": null, "id": "3658e6ab", "metadata": {}, "outputs": [], "source": [ "label.assign_feature_schema_ids(ontology)" ] }, { "cell_type": "code", "execution_count": null, "id": "6e1811e3", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "6a9d0c91", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "ccbdac6c", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.10" } }, "nbformat": 4, "nbformat_minor": 5 }