diff --git a/.vscode/settings.json b/.vscode/settings.json index ffe1417..79ed090 100644 --- a/.vscode/settings.json +++ b/.vscode/settings.json @@ -1,18 +1,30 @@ { "cSpell.words": [ + "basereload", "boto", "botocore", "datatable", "displaylogo", + "downsample", "fastapi", + "finalise", + "finalised", "gridfs", "iloc", + "initialisation", + "initialised", "inplace", "ipynb", + "lemmatize", + "levelname", "levelno", "matplotlib", + "Multinomial", + "multiprocess", "nbconvert", "nbins", + "optimisation", + "organisation's", "Parcoords", "plotly", "proba", @@ -21,23 +33,28 @@ "pymongo", "pyplot", "redoc", + "serialise", "sklearn", "starlette", "sublinear", "Tfidf", + "threadsafe", "ticktext", "tickvals", "tinydb", + "tqdm", "uvicorn", "Vectorizer", - "xmargin" + "xmargin", + "xticks" ], "files.exclude": { ".env": true, ".venv": true, - "**/.cache": true, + "**/__pycache__": true, "**/.ipynb_checkpoints": true, "**/.mypy_cache": true, "**/.pytest_cache": true - } + }, + "notebook.output.textLineLimit": 400 } diff --git a/.vscode/tasks.json b/.vscode/tasks.json index 95e72f4..00c8480 100644 --- a/.vscode/tasks.json +++ b/.vscode/tasks.json @@ -4,9 +4,9 @@ { "label": "Format and lint Python", "type": "shell", - "command": "source .venv/bin/activate && scripts/format-python.sh great_ai && scripts/format-python.sh examples/simple", + "command": "source .env/bin/activate && scripts/format-python.sh great_ai && scripts/format-python.sh examples/simple", "windows": { - "command": ".venv\\bin\\activate.bat; scripts\\format-python.sh great_ai; scripts\\format-python.sh examples\\simple" + "command": ".env\\bin\\activate.bat; scripts\\format-python.sh great_ai; scripts\\format-python.sh examples\\simple" }, "group": "test", "presentation": { @@ -20,9 +20,9 @@ { "label": "Test Python", "type": "shell", - "command": "source .venv/bin/activate && python3 -m pytest great_ai", + "command": "source .env/bin/activate && python3 -m pytest great_ai", "windows": { - "command": ".venv\\bin\\activate.bat; python3 -m pytest great_ai" + "command": ".env\\bin\\activate.bat; python3 -m pytest great_ai" }, "group": "test", "presentation": { diff --git a/examples/simple/README.md b/examples/simple/README.md new file mode 100644 index 0000000..8d68c33 --- /dev/null +++ b/examples/simple/README.md @@ -0,0 +1,7 @@ +# Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus) + +![steps](diagrams/scope.svg) + +- [Part 1](data.ipynb) +- [Part 2](train.ipynb) +- [Part 3](deploy.ipynb) diff --git a/examples/simple/data.ipynb b/examples/simple/data.ipynb index 70e98f1..51419cd 100644 --- a/examples/simple/data.ipynb +++ b/examples/simple/data.ipynb @@ -5,57 +5,50 @@ "metadata": {}, "source": [ "# Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)\n", + "> Part 1: obtain and clean data\n", "\n", - "## Part 1: obtain clean data\n", - "\n", - "This can be achieved by downloading a public dataset (such as in this case), or by having a Data Engineer setup and give us access to the organisations's data.\n", - "\n", - "1. **Extract**: Download the semantic scholar dataset from a public S3 bucket\n", - "2. **Transform**: Project it to only keep the necessary components (text and labels), clean the textual content using `great_ai.utilities.clean`\n", - "3. **Load**: Upload the dataset (or a part of it) to a shared infrastructure using `great_ai.LargeFile` with its S3 backend\n", - "\n", - "> We will speed up the processing using `great_ai.utilities.parallel_map`" + "![position of this step in the lifecycle](diagrams/scope-data.svg)\n", + "> The blue boxes show the steps implemented in this notebook." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\u001b[38;5;39m2022-05-27 12:12:27,324 | INFO | Environment variable ENVIRONMENT is not set, defaulting to development mode\u001b[0m\n", - "\u001b[38;5;226m2022-05-27 12:12:27,324 | WARNING | Running in development mode ‼️\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:12:27,325 | INFO | Options: configured ✅\u001b[0m\n" - ] - } - ], + "outputs": [], "source": [ - "import json\n", - "from typing import List, Tuple\n", - "import urllib.request\n", - "from itertools import chain\n", - "import gzip\n", - "from great_ai.utilities.clean import clean\n", - "from great_ai.utilities.parallel_map import parallel_map\n", - "from great_ai.utilities.language import is_english, predict_language\n", - "from great_ai import configure, LargeFile\n", + "MAX_CHUNK_COUNT = 4" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Extract\n", "\n", + "This can be achieved by downloading a public dataset (such as in this case), or by having a Data Engineer setup and give us access to the organisation's data.\n", "\n", - "DATASET_KEY = \"semantic-scholar-dataset-small\"\n", - "MAX_FILE_COUNT = 12\n", - "configure()" + "In this case, we download the semantic scholar dataset from a public S3 bucket." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "'Processing 4 out of the 6002 available chunks'" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Download the list of available chunks\n", + "import urllib.request\n", "\n", "manifest = (\n", " urllib.request.urlopen(\n", @@ -63,8 +56,22 @@ " )\n", " .read()\n", " .decode()\n", - ")\n", - "chunks = manifest.split()[:MAX_FILE_COUNT]" + ") # a list of available chunks separated by '\\n' characters\n", + "\n", + "chunks = manifest.split()[:MAX_CHUNK_COUNT]\n", + "\n", + "f\"Processing {len(chunks)} out of the {len(manifest.split())} available chunks\"" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Transform\n", + "\n", + "- Filter out non-English abstracts using `great_ai.utilities.predict_language`\n", + "- Project it to only keep the necessary components (text and labels), clean the textual content using `great_ai.utilities.clean`\n", + "- We will speed up processing using `great_ai.utilities.parallel_map`." ] }, { @@ -76,18 +83,19 @@ "name": "stderr", "output_type": "stream", "text": [ - "\u001b[38;5;39m2022-05-27 12:12:28,639 | INFO | Starting parallel map (concurrency: 12, chunk size: 1)\u001b[0m\n" + "\u001b[38;5;226m2022-06-19 14:59:12,562 | WARNING | Limiting concurrency to 4 because there are only 4 chunks\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 14:59:12,563 | INFO | Starting parallel map (concurrency: 4, chunk size: 1)\u001b[0m\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "7a381a677ed240e08c1605cd0917616a", + "model_id": "ff8fc113515944cfa75127f4aba3d491", "version_major": 2, "version_minor": 0 }, "text/plain": [ - " 0%| | 0/12 [00:00 List[Tuple[str, List[str]]]:\n", + "def preprocess_chunk(chunk_key: str) -> List[Tuple[str, List[str]]]:\n", + " # Extract\n", " response = urllib.request.urlopen(\n", - " \"https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/\"\n", - " + chunk_key\n", - " ) # returns a gzipped JSON Lines file\n", + " f\"https://s3-us-west-2.amazonaws.com/ai2-s2-research-public/open-corpus/2022-02-01/{chunk_key}\"\n", + " ) # a gzipped JSON Lines file\n", + "\n", " decompressed = gzip.decompress(response.read())\n", " decoded = decompressed.decode()\n", " chunk = [json.loads(line) for line in decoded.split(\"\\n\") if line]\n", "\n", - " all = [\n", - " # Create pairs of `(text, [domains])`\n", + " # Transform\n", + " return [\n", + " # Create pairs of `(text, [...domains])`\n", " # The text is cleaned to remove PDF extraction, web scraping, and other common artifacts\n", " (\n", " clean(\n", @@ -118,61 +131,79 @@ " c[\"fieldsOfStudy\"],\n", " )\n", " for c in chunk\n", - " ]\n", - "\n", - " return [\n", - " (content, domains)\n", - " for content, domains in all\n", - " if (domains and content and is_english(predict_language(content)))\n", + " if c[\"fieldsOfStudy\"] and is_english(predict_language(c[\"paperAbstract\"]))\n", " ]\n", "\n", "\n", - "clean_chunks = parallel_map(process_chunk, chunks)" + "preprocessed_chunks = parallel_map(preprocess_chunk, chunks)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, + "outputs": [], + "source": [ + "from itertools import chain\n", + "\n", + "preprocessed_data = list(chain(*preprocessed_chunks))\n", + "X, y = zip(\n", + " *preprocessed_data\n", + ") # X is the input, y is the expected (ground truth) output" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Load\n", + "\n", + "Upload the dataset (or a part of it) to a central repository using `great_ai.add_ground_truth`. This step automatically tags each datapoint with a split label according to the ratios we set. Additional tags can be also given.\n", + "\n", + "#### Use a different repository\n", + "\n", + "For the sake of simplicity, the tutorial uses the local hard drive (`great_ai.ParallelTinyDbDriver`) as the central repository.\n", + "This can be simply changed, for example, by the following snippet:\n", + "\n", + "```python\n", + "from great_ai import configure, MongoDbDriver\n", + "\n", + "configure(tracing_database=MongoDbDriver('mongodb://localhost:27017_or_something_like_that'))\n", + "```" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "\u001b[38;5;39m2022-05-27 12:22:35,833 | INFO | Fetching online versions of semantic-scholar-dataset-small\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:22:36,133 | INFO | Found versions: [2, 3]\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:22:39,542 | INFO | Copying file for semantic-scholar-dataset-small-4\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:22:39,843 | INFO | Compressing semantic-scholar-dataset-small-4\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:22:54,990 | INFO | Uploading semantic-scholar-dataset-small-4 to S3 from /tmp/large-file-l9z1mo61\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:23:19,988 | INFO | Uploading semantic-scholar-dataset-small-4.tar.gz 8.91/88.72 MB (10.0%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:23:41,914 | INFO | Uploading semantic-scholar-dataset-small-4.tar.gz 17.83/88.72 MB (20.1%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:24:06,996 | INFO | Uploading semantic-scholar-dataset-small-4.tar.gz 26.74/88.72 MB (30.1%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:24:30,563 | INFO | Uploading semantic-scholar-dataset-small-4.tar.gz 35.65/88.72 MB (40.2%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:24:59,623 | INFO | Uploading semantic-scholar-dataset-small-4.tar.gz 44.56/88.72 MB (50.2%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:25:28,237 | INFO | Uploading semantic-scholar-dataset-small-4.tar.gz 53.48/88.72 MB (60.3%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:25:59,432 | INFO | Uploading semantic-scholar-dataset-small-4.tar.gz 62.13/88.72 MB (70.0%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:26:25,016 | INFO | Uploading semantic-scholar-dataset-small-4.tar.gz 71.04/88.72 MB (80.1%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:26:55,491 | INFO | Uploading semantic-scholar-dataset-small-4.tar.gz 79.95/88.72 MB (90.1%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:27:26,801 | INFO | Uploading semantic-scholar-dataset-small-4.tar.gz 88.72/88.72 MB (100.0%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-27 12:27:28,540 | INFO | Removing old version (keep_last_n=1): semantic-scholar-dataset-small/2\u001b[0m\n" + "\u001b[38;5;226m2022-06-19 15:03:30,300 | WARNING | Environment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n", + "\u001b[38;5;226m2022-06-19 15:03:30,301 | WARNING | The selected persistence driver (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 15:03:30,301 | INFO | Options: configured ✅\u001b[0m\n" ] } ], "source": [ - "# Load\n", - "# Using the LargeFile GreatAI utility, the data will be made available on S3 (and in our local cache)\n", + "from great_ai import add_ground_truth\n", "\n", - "with LargeFile(DATASET_KEY, \"w\", keep_last_n=1) as f:\n", - " json.dump(list(chain(*clean_chunks)), f)" + "add_ground_truth(X, y, train_split_ratio=0.8, test_split_ratio=0.2)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Next: [Part 2](train.ipynb)" ] } ], "metadata": { - "interpreter": { - "hash": "9583b8c15346c7ad861da481b60c8e8605a71a48eda767f1640baa8f25efebcb" - }, "kernelspec": { - "display_name": "Python 3.9.2 ('.venv': venv)", + "display_name": "Python 3.10.4 ('.env': venv)", "language": "python", "name": "python3" }, @@ -186,9 +217,14 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.2" + "version": "3.10.4" }, - "orig_nbformat": 4 + "orig_nbformat": 4, + "vscode": { + "interpreter": { + "hash": "02dd6d3afbfa9fbbe1037d64ad9014965528a1ccad21929d6e72f466389a68ad" + } + } }, "nbformat": 4, "nbformat_minor": 2 diff --git a/examples/simple/deploy.ipynb b/examples/simple/deploy.ipynb index 7805e61..b946ae5 100644 --- a/examples/simple/deploy.ipynb +++ b/examples/simple/deploy.ipynb @@ -6,49 +6,54 @@ "source": [ "# Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)\n", "\n", - "## Part 3: Create production inference function\n", + "> Part 3: Create production inference function\n", "\n", - "In the [previous notebook](train.ipynb), we trained our AI model. Now, it's time to create **G**eneral **R**obust **E**nd-to-end **A**utomated **T**rustworthy deployment from it using the `GreatAI` Python package." + "![position of this step in the lifecycle](diagrams/scope-deploy.svg)\n", + "> The blue boxes show the steps implemented in this notebook.\n", + "\n", + "In [Part 2](train.ipynb), we trained our AI model. Now, it's time to create **G**eneral **R**obust **E**nd-to-end **A**utomated **T**rustworthy deployment from it using the `GreatAI` Python package." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, - "outputs": [], - "source": [ - "from typing import List\n", - "import re\n", - "from great_ai import ClassificationOutput, GreatAI, use_model\n", - "from sklearn.pipeline import Pipeline\n", - "from great_ai.utilities.clean import clean" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "\u001b[38;5;226m2022-05-28 18:17:13,344 | WARNING | Environment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 18:17:13,346 | INFO | Options: configured ✅\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 18:17:13,694 | INFO | Latest version of small-domain-prediction is 10 (from versions: 9, 10)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 18:17:13,694 | INFO | File small-domain-prediction-10 found in cache\u001b[0m\n" + "\u001b[38;5;226m2022-06-19 15:16:23,856 | WARNING | Environment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n", + "\u001b[38;5;226m2022-06-19 15:16:23,857 | WARNING | The selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 15:16:23,858 | INFO | Options: configured ✅\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 15:16:23,858 | INFO | Fetching cached versions of small-domain-prediction\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 15:16:23,859 | INFO | Latest version of small-domain-prediction is 12 (from versions: 9, 10, 11, 12)\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 15:16:23,860 | INFO | File small-domain-prediction-12 found in cache\u001b[0m\n" ] } ], "source": [ + "import re\n", + "from sklearn.pipeline import Pipeline\n", + "from great_ai.utilities import clean\n", + "from great_ai import (\n", + " MultiLabelClassificationOutput,\n", + " ClassificationOutput,\n", + " GreatAI,\n", + " use_model,\n", + " parameter,\n", + ")\n", + "\n", + "\n", "@GreatAI.deploy\n", "@use_model(\"small-domain-prediction\", version=\"latest\")\n", + "@parameter(\"explanation_length\", disable_logging=True)\n", "def predict_domain(\n", - " text: str, model: Pipeline, target_confidence: int = 50\n", - ") -> List[ClassificationOutput]:\n", + " text: str, model: Pipeline, target_confidence: int = 50, explanation_length: int = 5\n", + ") -> MultiLabelClassificationOutput:\n", " \"\"\"\n", " Predict the scientific domain of the input text.\n", - " Return labels until their sum likelihood is larger than target_confidence.\n", + " Return labels until their sum likelihood is larger than `target_confidence`.\n", " \"\"\"\n", " assert 0 <= target_confidence <= 100, \"invalid argument\"\n", "\n", @@ -58,9 +63,9 @@ "\n", " best_classes = sorted(enumerate(prediction), key=lambda v: v[1], reverse=True)\n", "\n", - " results: List[ClassificationOutput] = []\n", + " results = MultiLabelClassificationOutput()\n", " for class_index, probability in best_classes:\n", - " results.append(\n", + " results.labels.append(\n", " ClassificationOutput(\n", " label=model.named_steps[\"classifier\"].classes_[class_index],\n", " confidence=round(probability * 100),\n", @@ -80,76 +85,137 @@ " ),\n", " reverse=True,\n", " )\n", - " ][:5],\n", + " ][:explanation_length],\n", " )\n", " )\n", "\n", - " if sum(r.confidence for r in results) >= target_confidence:\n", + " if sum(r.confidence for r in results.labels) >= target_confidence:\n", " break\n", "\n", " return results" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Check accuracy on the test split" + ] + }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "\u001b[38;5;226m2022-06-19 15:16:29,300 | WARNING | Limiting concurrency to 10 because there are only 10 chunks\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 15:16:29,301 | INFO | Starting parallel map (concurrency: 10, chunk size: 1)\u001b[0m\n" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "34e54eabd5f945b8aa2809907964eec8", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/10 [00:00" + ] + }, + "metadata": {}, + "output_type": "display_data" } ], "source": [ - "# result = predict_domain(\n", - "# \"\"\"\n", - "# State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared characteristics among categories. Despite good performance, attributes have limitations: (1) finer-grained recognition requires commensurately more, and (2) attributes do not provide a natural language interface. We propose to overcome these limitations by training neural language models from scratch; i.e. without pre-training and only consuming words and characters. Our proposed models train end-to-end to align with the fine-grained and category-specific content of images. Natural language provides a flexible and compact way of encoding only the salient visual aspects for distinguishing categories. By training on raw text, our model can do inference on raw text as well, providing humans a familiar mode both for annotation and retrieval. Our model achieves strong performance on zero-shot text-based image retrieval and significantly outperforms the attribute-based state-of-the-art for zero-shot classification on the CaltechUCSD Birds 200-2011 dataset. \"\"\"\n", - "# )\n", + "if __name__ == \"__main__\":\n", + " from great_ai import query_ground_truth\n", + " from sklearn import metrics\n", "\n", - "# from pprint import pprint\n", + " data = query_ground_truth(\"test\", return_max_count=10)\n", "\n", - "# # pprint(result.dict(), width=120)" + " X = [d.input for d in data]\n", + " y_actual = [d.feedback for d in data]\n", + "\n", + " y_predicted = [d.output.labels[0].label for d in predict_domain.process_batch(X)]\n", + " y_actual_aligned = [p if p in a else a[0] for p, a in zip(y_predicted, y_actual)]\n", + "\n", + " import matplotlib.pyplot as plt\n", + "\n", + " # Configure matplotlib to have nice, high-resolution charts.\n", + "\n", + " %matplotlib inline\n", + "\n", + " plt.rcParams[\"figure.figsize\"] = (30, 15)\n", + " plt.rcParams[\"figure.facecolor\"] = \"white\"\n", + " plt.rcParams[\"font.size\"] = 12\n", + " plt.rcParams[\"axes.xmargin\"] = 0\n", + "\n", + " print(metrics.classification_report(y_actual_aligned, y_predicted))\n", + " metrics.ConfusionMatrixDisplay.from_predictions(\n", + " y_true=y_actual_aligned,\n", + " y_pred=y_predicted,\n", + " xticks_rotation=\"vertical\",\n", + " normalize=\"pred\",\n", + " values_format=\".2f\",\n", + " )" ] } ], "metadata": { - "interpreter": { - "hash": "9583b8c15346c7ad861da481b60c8e8605a71a48eda767f1640baa8f25efebcb" - }, "kernelspec": { - "display_name": "Python 3.9.2 ('.venv': venv)", + "display_name": "Python 3.10.4 ('.env': venv)", "language": "python", "name": "python3" }, @@ -163,9 +229,14 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.2" + "version": "3.10.4" }, - "orig_nbformat": 4 + "orig_nbformat": 4, + "vscode": { + "interpreter": { + "hash": "02dd6d3afbfa9fbbe1037d64ad9014965528a1ccad21929d6e72f466389a68ad" + } + } }, "nbformat": 4, "nbformat_minor": 2 diff --git a/examples/simple/diagrams/scope-data.svg b/examples/simple/diagrams/scope-data.svg new file mode 100644 index 0000000..8e232ec --- /dev/null +++ b/examples/simple/diagrams/scope-data.svg @@ -0,0 +1 @@ +
Preprocessed data
Preprocessed data
Data acquisition
(Data Engineering)
Data acquisition...
Exploration &
 model building
(Data Science)
Exploration &...
Trained models  & prototype inference code
Trained models  & protot...
Deploy with standard
 organisational methods
 (SysAdmin, Ops, DevOps)
Deploy with standard...
Use an AI deployment
SaaS/PaaS
(MLEM, Akkio, etc.) 
Use an AI deployment...
Transforming into
 production-ready service
(MLOps)
Transforming into...
Artifact combining the model with deplyoment best-practices
Artifact combining the mod...Viewer does not support full SVG 1.1 \ No newline at end of file diff --git a/examples/simple/diagrams/scope-deploy.svg b/examples/simple/diagrams/scope-deploy.svg new file mode 100644 index 0000000..b58ddf0 --- /dev/null +++ b/examples/simple/diagrams/scope-deploy.svg @@ -0,0 +1 @@ +
Preprocessed data
Preprocessed data
Data acquisition
(Data Engineering)
Data acquisition...
Exploration &
 model building
(Data Science)
Exploration &...
Trained models  & prototype inference code
Trained models  & protot...
Deploy with standard
 organisational methods
 (SysAdmin, Ops, DevOps)
Deploy with standard...
Use an AI deployment
SaaS/PaaS
(MLEM, Akkio, etc.) 
Use an AI deployment...
Transforming into
 production-ready service
(MLOps)
Transforming into...
Artifact combining the model with deplyoment best-practices
Artifact combining the mod...Viewer does not support full SVG 1.1 \ No newline at end of file diff --git a/examples/simple/diagrams/scope-train.svg b/examples/simple/diagrams/scope-train.svg new file mode 100644 index 0000000..6210bdf --- /dev/null +++ b/examples/simple/diagrams/scope-train.svg @@ -0,0 +1 @@ +
Preprocessed data
Preprocessed data
Data acquisition
(Data Engineering)
Data acquisition...
Exploration &
 model building
(Data Science)
Exploration &...
Trained models  & prototype inference code
Trained models  & protot...
Deploy with standard
 organisational methods
 (SysAdmin, Ops, DevOps)
Deploy with standard...
Use an AI deployment
SaaS/PaaS
(MLEM, Akkio, etc.) 
Use an AI deployment...
Transforming into
 production-ready service
(MLOps)
Transforming into...
Artifact combining the model with deplyoment best-practices
Artifact combining the mod...Viewer does not support full SVG 1.1 \ No newline at end of file diff --git a/examples/simple/diagrams/scope.svg b/examples/simple/diagrams/scope.svg new file mode 100644 index 0000000..b979c7e --- /dev/null +++ b/examples/simple/diagrams/scope.svg @@ -0,0 +1 @@ +
Preprocessed data
Preprocessed data
Data acquisition
(Data Engineering)
Data acquisition...
Exploration &
 model building
(Data Science)
Exploration &...
Trained models  & prototype inference code
Trained models  & protot...
Deploy with standard
 organisational methods
 (SysAdmin, Ops, DevOps)
Deploy with standard...
Use an AI deployment
SaaS/PaaS
(MLEM, Akkio, etc.) 
Use an AI deployment...
Transforming into
 production-ready service
(MLOps)
Transforming into...
Artifact combining the model with deplyoment best-practices
Artifact combining the mod...Viewer does not support full SVG 1.1 \ No newline at end of file diff --git a/mongo.ini b/examples/simple/mongo.ini similarity index 100% rename from mongo.ini rename to examples/simple/mongo.ini diff --git a/examples/simple/train.ipynb b/examples/simple/train.ipynb index 1d3898d..e558aa6 100644 --- a/examples/simple/train.ipynb +++ b/examples/simple/train.ipynb @@ -6,7 +6,10 @@ "source": [ "# Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)\n", "\n", - "## Part 2: train a model\n", + "> Part 2: train a model\n", + "\n", + "![position of this step in the lifecycle](diagrams/scope-train.svg)\n", + "> The blue boxes show the steps implemented in this notebook.\n", "\n", "In [Part 1](data.ipynb), we have cleaned and transformed our training data. We can now access this data using `great_ai.LargeFile`. Locally, it will gives us the cached version, otherwise, the latest version is downloaded from S3. \n", "\n", @@ -19,60 +22,14 @@ "metadata": {}, "outputs": [], "source": [ - "import json\n", - "import matplotlib.pyplot as plt\n", - "import pandas as pd\n", - "from collections import Counter\n", - "from sklearn import metrics, set_config\n", - "from sklearn.model_selection import train_test_split\n", - "from sklearn.naive_bayes import MultinomialNB\n", - "from sklearn.pipeline import Pipeline\n", - "from sklearn.feature_extraction.text import TfidfVectorizer\n", - "from sklearn.model_selection import GridSearchCV\n", - "import plotly.express as px\n", - "from great_ai import save_model, configure, LargeFile" + "MODEL_KEY = \"small-domain-prediction\"" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "## Configuration" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\u001b[38;5;226m2022-05-28 16:39:38,557 | WARNING | Environment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:39:38,559 | INFO | Options: configured ✅\u001b[0m\n" - ] - } - ], - "source": [ - "DATASET_KEY = \"semantic-scholar-dataset-small\"\n", - "MODEL_KEY = \"small-domain-prediction\"\n", - "\n", - "%matplotlib inline\n", - "\n", - "plt.rcParams[\"figure.figsize\"] = (30, 15)\n", - "plt.rcParams[\"figure.facecolor\"] = \"white\"\n", - "plt.rcParams[\"font.size\"] = 12\n", - "plt.rcParams[\"axes.xmargin\"] = 0\n", - "\n", - "configure()" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Preprocessing" + "## Load data that has been extracted in [part 1](data.ipynb)" ] }, { @@ -84,14 +41,18 @@ "name": "stderr", "output_type": "stream", "text": [ - "\u001b[38;5;39m2022-05-28 16:39:38,934 | INFO | Latest version of semantic-scholar-dataset-small is 4 (from versions: 3, 4)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:39:38,934 | INFO | File semantic-scholar-dataset-small-4 found in cache\u001b[0m\n" + "\u001b[38;5;226m2022-06-19 15:08:22,338 | WARNING | Environment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n", + "\u001b[38;5;226m2022-06-19 15:08:22,338 | WARNING | The selected persistence driver (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 15:08:22,339 | INFO | Options: configured ✅\u001b[0m\n" ] } ], "source": [ - "with LargeFile(DATASET_KEY) as f:\n", - " data = json.load(f)" + "from great_ai import query_ground_truth\n", + "\n", + "data = query_ground_truth(\"train\")\n", + "X = [d.input for d in data for domain in d.feedback]\n", + "y = [domain for d in data for domain in d.feedback]" ] }, { @@ -99,92 +60,6 @@ "execution_count": 4, "metadata": {}, "outputs": [ - { - "data": { - "text/html": [ - " \n", - " " - ] - }, - "metadata": {}, - "output_type": "display_data" - }, { "data": { "application/vnd.plotly.v1+json": { @@ -211,64 +86,52 @@ "x": [ "Medicine", "Computer Science", + "Biology", "Chemistry", "Materials Science", "Engineering", - "Biology", - "Psychology", "Physics", - "Biology, Medicine", - "Political Science", + "Psychology", "Mathematics", "Business", + "Political Science", "Sociology", - "Geography", - "Chemistry, Medicine", "Economics", - "History", + "Geography", "Environmental Science", "Geology", "Art", - "Philosophy", - "Psychology, Medicine", - "Medicine, Biology", - "Materials Science, Medicine", - "Mathematics, Computer Science" + "History", + "Philosophy" ], "xaxis": "x", "y": [ - 61418, - 22787, - 19812, - 18886, - 15702, - 14051, - 11335, - 10889, - 10286, - 9514, - 8252, - 7664, - 7663, - 6784, - 6120, - 5582, - 5562, - 5383, - 5361, - 5039, - 2868, + 16996, + 5836, + 5354, + 5135, + 4200, + 3663, + 2643, + 2463, 2386, - 1644, - 1241, - 1145 + 1362, + 1304, + 1297, + 1087, + 1060, + 968, + 943, + 515, + 497, + 332 ], "yaxis": "y" } ], "layout": { "barmode": "relative", - "height": 800, + "height": 400, "legend": { "tracegroupgap": 0 }, @@ -1113,67 +976,19 @@ } } } - }, - "text/html": [ - "
" - ] + } }, "metadata": {}, "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Found 279684 documents\n" - ] } ], "source": [ - "df = pd.DataFrame(\n", - " Counter(\", \".join(domains) for _, domains in data).most_common(25),\n", - " columns=[\"x\", \"y\"],\n", - ")\n", - "px.bar(x=df[\"x\"], y=df[\"y\"], width=1200, height=800).show()\n", - "print(f\"Found {len(data)} documents\")" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": {}, - "outputs": [], - "source": [ - "X_train, X_test, y_train, y_test = train_test_split(\n", - " [d[0] for d in data], [d[1] for d in data], test_size=0.1, random_state=1\n", - ")\n", + "import pandas as pd\n", + "from collections import Counter\n", + "import plotly.express as px\n", "\n", - "X_train = [x for x, y in zip(X_train, y_train) for domain in y]\n", - "y_train = [domain for x, y in zip(X_train, y_train) for domain in y]" + "df = pd.DataFrame(Counter(y).most_common(), columns=[\"domain\", \"count\"])\n", + "px.bar(x=df[\"domain\"], y=df[\"count\"], width=1200, height=400).show()" ] }, { @@ -1185,153 +1000,729 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ + "from sklearn.naive_bayes import MultinomialNB\n", + "from sklearn.pipeline import Pipeline\n", + "from sklearn.feature_extraction.text import TfidfVectorizer\n", + "\n", + "\n", "def create_pipeline() -> Pipeline:\n", " return Pipeline(\n", " steps=[\n", - " (\"vectorizer\", TfidfVectorizer()),\n", + " (\"vectorizer\", TfidfVectorizer(sublinear_tf=True)),\n", " (\"classifier\", MultinomialNB()),\n", " ]\n", " )" ] }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Fitting 3 folds for each of 24 candidates, totalling 72 fits\n" + ] + }, + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
mean_fit_timestd_fit_timemean_score_timestd_score_timeparam_classifier__alphaparam_classifier__fit_priorparam_vectorizer__max_dfparam_vectorizer__min_dfparamssplit0_test_scoresplit1_test_scoresplit2_test_scoremean_test_scorestd_test_scorerank_test_score
77.7969240.3213143.7560430.0278600.5False0.0520{'classifier__alpha': 0.5, 'classifier__fit_pr...0.5080130.5090860.5144550.5105180.0028181
108.0556640.2069843.7485170.0880120.5False0.120{'classifier__alpha': 0.5, 'classifier__fit_pr...0.5037290.5064170.5118950.5073470.0033982
117.7483600.4843613.8632160.0720480.5False0.1100{'classifier__alpha': 0.5, 'classifier__fit_pr...0.5022110.4989490.5037440.5016350.0020003
87.4006490.0873203.6584420.0117350.5False0.05100{'classifier__alpha': 0.5, 'classifier__fit_pr...0.5014320.4939700.5013860.4989290.0035074
198.1479690.4019803.9771190.2840281False0.0520{'classifier__alpha': 1, 'classifier__fit_prio...0.4864100.4918910.4925150.4902720.0027435
207.4724140.1303203.7711360.1464061False0.05100{'classifier__alpha': 1, 'classifier__fit_prio...0.4868680.4891420.4926650.4895580.0023856
237.3955850.3261622.3320310.2541461False0.1100{'classifier__alpha': 1, 'classifier__fit_prio...0.4894890.4899870.4885430.4893400.0005997
227.4520600.1620722.9374730.1164431False0.120{'classifier__alpha': 1, 'classifier__fit_prio...0.4787480.4851740.4846850.4828690.0029218
67.8363800.3746694.0074290.2511990.5False0.055{'classifier__alpha': 0.5, 'classifier__fit_pr...0.4727930.4764600.4795830.4762790.0027759
27.8394440.1749643.9141050.3797350.5True0.05100{'classifier__alpha': 0.5, 'classifier__fit_pr...0.4692240.4721790.4767580.4727200.00310010
57.9484540.4113643.9684440.0900300.5True0.1100{'classifier__alpha': 0.5, 'classifier__fit_pr...0.4693100.4719160.4769000.4727080.00314911
97.3735920.1430283.7776980.0089900.5False0.15{'classifier__alpha': 0.5, 'classifier__fit_pr...0.4631560.4667830.4634600.4644660.00164312
17.4068390.0419733.8386340.1166340.5True0.0520{'classifier__alpha': 0.5, 'classifier__fit_pr...0.4623150.4629750.4631920.4628270.00037313
47.4815330.2243443.7898210.0980980.5True0.120{'classifier__alpha': 0.5, 'classifier__fit_pr...0.4575040.4608530.4599410.4594330.00141414
147.7497250.4684694.1395340.1401731True0.05100{'classifier__alpha': 1, 'classifier__fit_prio...0.4429300.4431830.4495770.4452300.00307615
177.7038460.3575084.0341540.2655091True0.1100{'classifier__alpha': 1, 'classifier__fit_prio...0.4390580.4434290.4493360.4439410.00421216
187.5531050.0560774.0949780.1988131False0.055{'classifier__alpha': 1, 'classifier__fit_prio...0.4214880.4275300.4223290.4237820.00267217
137.4380300.2375453.9158240.0298231True0.0520{'classifier__alpha': 1, 'classifier__fit_prio...0.4041520.4113730.4068580.4074610.00297918
218.0571890.4350523.3052220.3489951False0.15{'classifier__alpha': 1, 'classifier__fit_prio...0.3971820.4052470.4015050.4013110.00329519
167.7107480.5592834.0344210.0735221True0.120{'classifier__alpha': 1, 'classifier__fit_prio...0.3920460.3979950.3961140.3953850.00248320
07.6146470.4662523.8982200.0986180.5True0.055{'classifier__alpha': 0.5, 'classifier__fit_pr...0.3851560.3888660.3865090.3868440.00153321
38.1768930.2528214.0719520.2657730.5True0.15{'classifier__alpha': 0.5, 'classifier__fit_pr...0.3710790.3770720.3745310.3742280.00245622
127.6064350.2390013.8757930.1092251True0.055{'classifier__alpha': 1, 'classifier__fit_prio...0.2770310.2880650.2879130.2843360.00516623
158.0779710.7337004.1357210.2353071True0.15{'classifier__alpha': 1, 'classifier__fit_prio...0.2604150.2672010.2669810.2648660.00314824
\n", + "
" + ], + "text/plain": [ + " mean_fit_time std_fit_time mean_score_time std_score_time \\\n", + "7 7.796924 0.321314 3.756043 0.027860 \n", + "10 8.055664 0.206984 3.748517 0.088012 \n", + "11 7.748360 0.484361 3.863216 0.072048 \n", + "8 7.400649 0.087320 3.658442 0.011735 \n", + "19 8.147969 0.401980 3.977119 0.284028 \n", + "20 7.472414 0.130320 3.771136 0.146406 \n", + "23 7.395585 0.326162 2.332031 0.254146 \n", + "22 7.452060 0.162072 2.937473 0.116443 \n", + "6 7.836380 0.374669 4.007429 0.251199 \n", + "2 7.839444 0.174964 3.914105 0.379735 \n", + "5 7.948454 0.411364 3.968444 0.090030 \n", + "9 7.373592 0.143028 3.777698 0.008990 \n", + "1 7.406839 0.041973 3.838634 0.116634 \n", + "4 7.481533 0.224344 3.789821 0.098098 \n", + "14 7.749725 0.468469 4.139534 0.140173 \n", + "17 7.703846 0.357508 4.034154 0.265509 \n", + "18 7.553105 0.056077 4.094978 0.198813 \n", + "13 7.438030 0.237545 3.915824 0.029823 \n", + "21 8.057189 0.435052 3.305222 0.348995 \n", + "16 7.710748 0.559283 4.034421 0.073522 \n", + "0 7.614647 0.466252 3.898220 0.098618 \n", + "3 8.176893 0.252821 4.071952 0.265773 \n", + "12 7.606435 0.239001 3.875793 0.109225 \n", + "15 8.077971 0.733700 4.135721 0.235307 \n", + "\n", + " param_classifier__alpha param_classifier__fit_prior \\\n", + "7 0.5 False \n", + "10 0.5 False \n", + "11 0.5 False \n", + "8 0.5 False \n", + "19 1 False \n", + "20 1 False \n", + "23 1 False \n", + "22 1 False \n", + "6 0.5 False \n", + "2 0.5 True \n", + "5 0.5 True \n", + "9 0.5 False \n", + "1 0.5 True \n", + "4 0.5 True \n", + "14 1 True \n", + "17 1 True \n", + "18 1 False \n", + "13 1 True \n", + "21 1 False \n", + "16 1 True \n", + "0 0.5 True \n", + "3 0.5 True \n", + "12 1 True \n", + "15 1 True \n", + "\n", + " param_vectorizer__max_df param_vectorizer__min_df \\\n", + "7 0.05 20 \n", + "10 0.1 20 \n", + "11 0.1 100 \n", + "8 0.05 100 \n", + "19 0.05 20 \n", + "20 0.05 100 \n", + "23 0.1 100 \n", + "22 0.1 20 \n", + "6 0.05 5 \n", + "2 0.05 100 \n", + "5 0.1 100 \n", + "9 0.1 5 \n", + "1 0.05 20 \n", + "4 0.1 20 \n", + "14 0.05 100 \n", + "17 0.1 100 \n", + "18 0.05 5 \n", + "13 0.05 20 \n", + "21 0.1 5 \n", + "16 0.1 20 \n", + "0 0.05 5 \n", + "3 0.1 5 \n", + "12 0.05 5 \n", + "15 0.1 5 \n", + "\n", + " params split0_test_score \\\n", + "7 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.508013 \n", + "10 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.503729 \n", + "11 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.502211 \n", + "8 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.501432 \n", + "19 {'classifier__alpha': 1, 'classifier__fit_prio... 0.486410 \n", + "20 {'classifier__alpha': 1, 'classifier__fit_prio... 0.486868 \n", + "23 {'classifier__alpha': 1, 'classifier__fit_prio... 0.489489 \n", + "22 {'classifier__alpha': 1, 'classifier__fit_prio... 0.478748 \n", + "6 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.472793 \n", + "2 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.469224 \n", + "5 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.469310 \n", + "9 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.463156 \n", + "1 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.462315 \n", + "4 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.457504 \n", + "14 {'classifier__alpha': 1, 'classifier__fit_prio... 0.442930 \n", + "17 {'classifier__alpha': 1, 'classifier__fit_prio... 0.439058 \n", + "18 {'classifier__alpha': 1, 'classifier__fit_prio... 0.421488 \n", + "13 {'classifier__alpha': 1, 'classifier__fit_prio... 0.404152 \n", + "21 {'classifier__alpha': 1, 'classifier__fit_prio... 0.397182 \n", + "16 {'classifier__alpha': 1, 'classifier__fit_prio... 0.392046 \n", + "0 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.385156 \n", + "3 {'classifier__alpha': 0.5, 'classifier__fit_pr... 0.371079 \n", + "12 {'classifier__alpha': 1, 'classifier__fit_prio... 0.277031 \n", + "15 {'classifier__alpha': 1, 'classifier__fit_prio... 0.260415 \n", + "\n", + " split1_test_score split2_test_score mean_test_score std_test_score \\\n", + "7 0.509086 0.514455 0.510518 0.002818 \n", + "10 0.506417 0.511895 0.507347 0.003398 \n", + "11 0.498949 0.503744 0.501635 0.002000 \n", + "8 0.493970 0.501386 0.498929 0.003507 \n", + "19 0.491891 0.492515 0.490272 0.002743 \n", + "20 0.489142 0.492665 0.489558 0.002385 \n", + "23 0.489987 0.488543 0.489340 0.000599 \n", + "22 0.485174 0.484685 0.482869 0.002921 \n", + "6 0.476460 0.479583 0.476279 0.002775 \n", + "2 0.472179 0.476758 0.472720 0.003100 \n", + "5 0.471916 0.476900 0.472708 0.003149 \n", + "9 0.466783 0.463460 0.464466 0.001643 \n", + "1 0.462975 0.463192 0.462827 0.000373 \n", + "4 0.460853 0.459941 0.459433 0.001414 \n", + "14 0.443183 0.449577 0.445230 0.003076 \n", + "17 0.443429 0.449336 0.443941 0.004212 \n", + "18 0.427530 0.422329 0.423782 0.002672 \n", + "13 0.411373 0.406858 0.407461 0.002979 \n", + "21 0.405247 0.401505 0.401311 0.003295 \n", + "16 0.397995 0.396114 0.395385 0.002483 \n", + "0 0.388866 0.386509 0.386844 0.001533 \n", + "3 0.377072 0.374531 0.374228 0.002456 \n", + "12 0.288065 0.287913 0.284336 0.005166 \n", + "15 0.267201 0.266981 0.264866 0.003148 \n", + "\n", + " rank_test_score \n", + "7 1 \n", + "10 2 \n", + "11 3 \n", + "8 4 \n", + "19 5 \n", + "20 6 \n", + "23 7 \n", + "22 8 \n", + "6 9 \n", + "2 10 \n", + "5 11 \n", + "9 12 \n", + "1 13 \n", + "4 14 \n", + "14 15 \n", + "17 16 \n", + "18 17 \n", + "13 18 \n", + "21 19 \n", + "16 20 \n", + "0 21 \n", + "3 22 \n", + "12 23 \n", + "15 24 " + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "from sklearn.model_selection import GridSearchCV\n", + "\n", + "optimisation_pipeline = GridSearchCV(\n", + " create_pipeline(),\n", + " {\n", + " \"vectorizer__min_df\": [5, 20, 100],\n", + " \"vectorizer__max_df\": [0.05, 0.1],\n", + " \"classifier__alpha\": [0.5, 1],\n", + " \"classifier__fit_prior\": [True, False],\n", + " },\n", + " scoring=\"f1_macro\",\n", + " cv=3,\n", + " n_jobs=-1,\n", + " verbose=1,\n", + ")\n", + "optimisation_pipeline.fit(X, y)\n", + "\n", + "results = pd.DataFrame(optimisation_pipeline.cv_results_)\n", + "results.sort_values(\"rank_test_score\")" + ] + }, { "cell_type": "code", "execution_count": 7, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Fitting 3 folds for each of 144 candidates, totalling 432 fits\n" - ] - } - ], - "source": [ - "optimisation_pipeline = GridSearchCV(\n", - " create_pipeline(),\n", - " {\n", - " \"vectorizer__max_df\": [0.05, 0.1, 0.2],\n", - " \"vectorizer__min_df\": [5, 20, 100, 200],\n", - " \"vectorizer__sublinear_tf\": [True, False],\n", - " \"classifier__alpha\": [0.1, 0.5, 1],\n", - " \"classifier__fit_prior\": [True, False],\n", - " },\n", - " scoring=\"f1_macro\",\n", - " cv=3,\n", - " n_jobs=-1,\n", - " verbose=1,\n", - ")\n", - "optimisation_pipeline.fit(X_train, y_train)\n", - "\n", - "results = pd.DataFrame(optimisation_pipeline.cv_results_)\n", - "results.sort_values(\"rank_test_score\")" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, "outputs": [ { "data": { "text/html": [ - "
Pipeline(steps=[('vectorizer', TfidfVectorizer(max_df=0.1, min_df=5)),\n",
-       "                ('classifier', MultinomialNB(alpha=0.1, fit_prior=False))])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" + "
Pipeline(steps=[('vectorizer',\n",
+       "                 TfidfVectorizer(max_df=0.05, min_df=20, sublinear_tf=True)),\n",
+       "                ('classifier', MultinomialNB(alpha=0.5, fit_prior=False))])
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" ], "text/plain": [ - "Pipeline(steps=[('vectorizer', TfidfVectorizer(max_df=0.1, min_df=5)),\n", - " ('classifier', MultinomialNB(alpha=0.1, fit_prior=False))])" + "Pipeline(steps=[('vectorizer',\n", + " TfidfVectorizer(max_df=0.05, min_df=20, sublinear_tf=True)),\n", + " ('classifier', MultinomialNB(alpha=0.5, fit_prior=False))])" ] }, - "execution_count": 8, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ + "from sklearn import set_config\n", + "\n", "set_config(display=\"diagram\")\n", "\n", "classifier = create_pipeline()\n", "classifier.set_params(**optimisation_pipeline.best_params_)\n", - "classifier.fit(X_train, y_train)" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Check accuracy on the test split" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - " precision recall f1-score support\n", - "\n", - " Art 0.46 0.50 0.48 536\n", - " Biology 0.74 0.78 0.76 2432\n", - " Business 0.48 0.68 0.56 781\n", - " Chemistry 0.79 0.66 0.72 2516\n", - " Computer Science 0.81 0.70 0.75 2651\n", - " Economics 0.64 0.58 0.61 614\n", - " Engineering 0.55 0.52 0.53 1666\n", - "Environmental Science 0.50 0.68 0.58 598\n", - " Geography 0.50 0.49 0.49 732\n", - " Geology 0.73 0.76 0.74 563\n", - " History 0.37 0.56 0.45 531\n", - " Materials Science 0.74 0.76 0.75 2078\n", - " Mathematics 0.76 0.74 0.75 983\n", - " Medicine 0.95 0.76 0.85 6620\n", - " Philosophy 0.46 0.51 0.48 299\n", - " Physics 0.68 0.77 0.72 1169\n", - " Political Science 0.49 0.60 0.54 995\n", - " Psychology 0.53 0.76 0.63 1357\n", - " Sociology 0.41 0.50 0.45 848\n", - "\n", - " accuracy 0.69 27969\n", - " macro avg 0.61 0.65 0.62 27969\n", - " weighted avg 0.72 0.69 0.70 27969\n", - "\n" - ] - }, - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "predicted = classifier.predict(X_test)\n", - "\n", - "y_test_aligned = [p if p in y else y[0] for p, y in zip(predicted, y_test)]\n", - "\n", - "print(metrics.classification_report(y_test_aligned, predicted))\n", - "\n", - "metrics.ConfusionMatrixDisplay.from_predictions(\n", - " y_true=y_test_aligned,\n", - " y_pred=predicted,\n", - " xticks_rotation=\"vertical\",\n", - " normalize=\"pred\",\n", - " values_format=\".2f\",\n", - ")\n", - "None" + "classifier.fit(X, y)" ] }, { @@ -1343,52 +1734,41 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ - "\u001b[38;5;39m2022-05-28 16:31:47,508 | INFO | Copying file for small-domain-prediction-9\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:31:47,557 | INFO | Compressing small-domain-prediction-9\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:31:50,579 | INFO | Uploading small-domain-prediction-9 to S3 from /tmp/large-file-clv9sq4v\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:31:53,887 | INFO | Uploading small-domain-prediction-9.tar.gz 1.57/14.00 MB (11.2%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:31:56,787 | INFO | Uploading small-domain-prediction-9.tar.gz 2.88/14.00 MB (20.6%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:31:59,948 | INFO | Uploading small-domain-prediction-9.tar.gz 4.46/14.00 MB (31.8%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:32:03,008 | INFO | Uploading small-domain-prediction-9.tar.gz 5.77/14.00 MB (41.2%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:32:06,887 | INFO | Uploading small-domain-prediction-9.tar.gz 7.08/14.00 MB (50.6%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:32:11,267 | INFO | Uploading small-domain-prediction-9.tar.gz 8.65/14.00 MB (61.8%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:32:17,170 | INFO | Uploading small-domain-prediction-9.tar.gz 9.96/14.00 MB (71.2%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:32:21,838 | INFO | Uploading small-domain-prediction-9.tar.gz 11.38/14.00 MB (81.3%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:32:25,730 | INFO | Uploading small-domain-prediction-9.tar.gz 12.69/14.00 MB (90.6%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:32:28,363 | INFO | Uploading small-domain-prediction-9.tar.gz 14.00/14.00 MB (100.0%)\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:32:31,633 | INFO | Removing old version (keep_last_n=5): small-domain-prediction-v2/3\u001b[0m\n", - "\u001b[38;5;39m2022-05-28 16:32:31,675 | INFO | Model small-domain-prediction uploaded with version 9\u001b[0m\n" + "\u001b[38;5;39m2022-06-19 15:12:58,312 | INFO | Fetching cached versions of small-domain-prediction\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 15:12:59,027 | INFO | Copying file for small-domain-prediction-12\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 15:12:59,039 | INFO | Compressing small-domain-prediction-12\u001b[0m\n", + "\u001b[38;5;39m2022-06-19 15:12:59,842 | INFO | Model small-domain-prediction uploaded with version 12\u001b[0m\n" ] }, { "data": { "text/plain": [ - "'small-domain-prediction:9'" + "'small-domain-prediction:12'" ] }, - "execution_count": 10, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ + "from great_ai import save_model\n", + "\n", + "\n", "save_model(classifier, key=MODEL_KEY, keep_last_n=5)" ] } ], "metadata": { - "interpreter": { - "hash": "9583b8c15346c7ad861da481b60c8e8605a71a48eda767f1640baa8f25efebcb" - }, "kernelspec": { - "display_name": "Python 3.9.2 ('.venv': venv)", + "display_name": "Python 3.10.4 ('.env': venv)", "language": "python", "name": "python3" }, @@ -1402,9 +1782,14 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.2" + "version": "3.10.4" }, - "orig_nbformat": 4 + "orig_nbformat": 4, + "vscode": { + "interpreter": { + "hash": "02dd6d3afbfa9fbbe1037d64ad9014965528a1ccad21929d6e72f466389a68ad" + } + } }, "nbformat": 4, "nbformat_minor": 2 diff --git a/scope-data.drawio.svg b/scope-data.drawio.svg new file mode 100644 index 0000000..9766712 --- /dev/null +++ b/scope-data.drawio.svg @@ -0,0 +1,212 @@ + + + + + + + + + + +
+
+
+ + Preprocessed data + +
+
+
+ + + Preprocessed data + + + + + + + + + +
+
+
+ + + Data acquisition + + +
+ (Data Engineering) +
+
+
+ + + Data acquisition... + + + + + + + + + +
+
+
+ + + Exploration & +
+ model building + + +
+ (Data Science) +
+
+
+ + + Exploration &... + + + + + + + + + + +
+
+
+ + Trained models  & prototype inference code + +
+
+
+ + + Trained models  & protot... + + + + + + + + + +
+
+
+ + Deploy with standard +
+ organisational methods + +
+ + (SysAdmin, Ops, DevOps) + +
+
+
+ + + Deploy with standard... + + + + + + + + + +
+
+
+ + Use an AI deployment +
+ SaaS/PaaS + +
+ + (MLEM, Akkio, etc.) + +
+
+
+ + + Use an AI deployment... + + + + + + + +
+
+
+ + Transforming into +
+ production-ready service + +
+ (MLOps) +
+
+
+ + + Transforming into... + + + + + + + + + + + + +
+
+
+ + Artifact combining the model with deplyoment best-practices + +
+
+
+ + + Artifact combining the mod... + + + + + + + + + + + Viewer does not support full SVG 1.1 + + + + \ No newline at end of file diff --git a/scope.drawio b/scope.drawio deleted file mode 100644 index 258f4b6..0000000 --- a/scope.drawio +++ /dev/null @@ -1 +0,0 @@ -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 \ No newline at end of file