diff --git a/examples/simple/data.ipynb b/examples/simple/data.ipynb
index 3965803..70e98f1 100644
--- a/examples/simple/data.ipynb
+++ b/examples/simple/data.ipynb
@@ -46,7 +46,6 @@
"\n",
"DATASET_KEY = \"semantic-scholar-dataset-small\"\n",
"MAX_FILE_COUNT = 12\n",
- "\n",
"configure()"
]
},
diff --git a/examples/simple/deploy.ipynb b/examples/simple/deploy.ipynb
new file mode 100644
index 0000000..ec3f1e2
--- /dev/null
+++ b/examples/simple/deploy.ipynb
@@ -0,0 +1,170 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)\n",
+ "\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."
+ ]
+ },
+ {
+ "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 15:02:20,852 | WARNING | Environment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-28 15:02:20,853 | INFO | Options: configured ✅\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-28 15:02:21,168 | INFO | Latest version of small-domain-prediction-v2 is 8 (from versions: 3, 4, 5, 6, 7, 8)\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-28 15:02:21,169 | INFO | File small-domain-prediction-v2-8 found in cache\u001b[0m\n"
+ ]
+ }
+ ],
+ "source": [
+ "@GreatAI.deploy\n",
+ "@use_model(\"small-domain-prediction-v2\", version=\"latest\")\n",
+ "def predict_domain(\n",
+ " text: str, model: Pipeline, target_confidence: int = 20\n",
+ ") -> List[ClassificationOutput]:\n",
+ " \"\"\"\n",
+ " Predict the scientific domain of the input text.\n",
+ " Return labels until their sum likelihood is larger than target_confidence.\n",
+ " \"\"\"\n",
+ " assert 0 <= target_confidence <= 100, \"invalid argument\"\n",
+ "\n",
+ " preprocessed = re.sub(r\"[^a-zA-Z ]\", \"\", clean(text, convert_to_ascii=True))\n",
+ " features = model.named_steps[\"vectorizer\"].transform([preprocessed])\n",
+ " prediction = model.named_steps[\"classifier\"].predict_proba(features)[0]\n",
+ "\n",
+ " best_classes = sorted(enumerate(prediction), key=lambda v: v[1], reverse=True)\n",
+ "\n",
+ " results: List[ClassificationOutput] = []\n",
+ " for class_index, probability in best_classes:\n",
+ " results.append(\n",
+ " ClassificationOutput(\n",
+ " label=model.named_steps[\"classifier\"].classes_[class_index],\n",
+ " confidence=round(probability * 100),\n",
+ " explanation=[\n",
+ " word\n",
+ " for _, word in sorted(\n",
+ " (\n",
+ " (weight, word)\n",
+ " for weight, word, count in zip(\n",
+ " model.named_steps[\"classifier\"].feature_log_prob_[\n",
+ " class_index\n",
+ " ],\n",
+ " model.named_steps[\"vectorizer\"].get_feature_names_out(),\n",
+ " features.A[0],\n",
+ " )\n",
+ " if count > 0\n",
+ " ),\n",
+ " reverse=True,\n",
+ " )\n",
+ " ][:5],\n",
+ " )\n",
+ " )\n",
+ "\n",
+ " if sum(r.confidence for r in results) >= target_confidence:\n",
+ " break\n",
+ "\n",
+ " return results"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'created': '2022-05-28T13:02:22.035886',\n",
+ " 'evaluation': None,\n",
+ " 'evaluation_id': 'c035d78e-dea9-415f-8f93-0dc4cd8dd7b5',\n",
+ " 'exception': None,\n",
+ " 'execution_time_ms': 94.814,\n",
+ " 'logged_values': {'arg:predict_domain:target_confidence': 20,\n",
+ " 'arg:predict_domain:text': '\\n'\n",
+ " ' State-of-the-art methods for zero-shot visual recognition formulate '\n",
+ " 'learning as a joint embedding problem of images and side information. '\n",
+ " 'In these formulations the current best complement to visual features '\n",
+ " 'are attributes: manually encoded vectors describing shared '\n",
+ " 'characteristics among categories. Despite good performance, attributes '\n",
+ " 'have limitations: (1) finer-grained recognition requires commensurately '\n",
+ " 'more, and (2) attributes do not provide a natural language interface. '\n",
+ " 'We propose to overcome these limitations by training neural language '\n",
+ " 'models from scratch; i.e. without pre-training and only consuming words '\n",
+ " 'and characters. Our proposed models train end-to-end to align with the '\n",
+ " 'fine-grained and category-specific content of images. Natural language '\n",
+ " 'provides a flexible and compact way of encoding only the salient visual '\n",
+ " 'aspects for distinguishing categories. By training on raw text, our '\n",
+ " 'model can do inference on raw text as well, providing humans a familiar '\n",
+ " 'mode both for annotation and retrieval. Our model achieves strong '\n",
+ " 'performance on zero-shot text-based image retrieval and significantly '\n",
+ " 'outperforms the attribute-based state-of-the-art for zero-shot '\n",
+ " 'classification on the CaltechUCSD Birds 200-2011 dataset. ',\n",
+ " 'arg:predict_domain:text:length': 1236},\n",
+ " 'models': [{'key': 'small-domain-prediction-v2', 'version': 8}],\n",
+ " 'output': [{'confidence': 99.0,\n",
+ " 'explanation': ['information', 'model', 'learning', 'proposed', 'image'],\n",
+ " 'label': 'Computer Science'}]}\n"
+ ]
+ }
+ ],
+ "source": [
+ "result = predict_domain(\"\"\"\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",
+ "\n",
+ "from pprint import pprint\n",
+ "pprint(result.dict(), width=120)"
+ ]
+ }
+ ],
+ "metadata": {
+ "interpreter": {
+ "hash": "9583b8c15346c7ad861da481b60c8e8605a71a48eda767f1640baa8f25efebcb"
+ },
+ "kernelspec": {
+ "display_name": "Python 3.9.2 ('.venv': venv)",
+ "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": "3.9.2"
+ },
+ "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/examples/simple/train.ipynb b/examples/simple/train.ipynb
index 65a0073..0dcaa17 100644
--- a/examples/simple/train.ipynb
+++ b/examples/simple/train.ipynb
@@ -4,18 +4,23 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "# Train domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)"
+ "# Train a domain classifier on the [semantic scholar dataset](https://api.semanticscholar.org/corpus)\n",
+ "\n",
+ "## Part 2: train a model\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",
+ "In this part, we hyperparameter-optimise and train a simple, Naive Bayes classifier which we then export for deployment using `great_ai.save_model`."
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import matplotlib.pyplot as plt\n",
- "from pathlib import Path\n",
"import pandas as pd\n",
"from sklearn import metrics, set_config\n",
"from sklearn.model_selection import train_test_split\n",
@@ -23,12 +28,9 @@
"from sklearn.pipeline import Pipeline\n",
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
"from sklearn.model_selection import GridSearchCV\n",
- "\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 save_model, configure, LargeFile\n",
- "\n",
- "from helpers import preprocess, lemmatize"
+ "import re\n",
+ "import plotly.express as px\n",
+ "from great_ai import save_model, configure, LargeFile"
]
},
{
@@ -40,30 +42,36 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 2,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[38;5;39m2022-05-27 21:28:11,641 | INFO | Environment variable ENVIRONMENT is not set, defaulting to development mode\u001b[0m\n",
+ "\u001b[38;5;226m2022-05-27 21:28:11,642 | WARNING | Running in development mode ‼️\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-27 21:28:11,643 | INFO | Options: configured ✅\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-27 21:28:11,683 | INFO | Fetching online versions of semantic-scholar-dataset-small\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-27 21:28:11,959 | INFO | Found versions: [3, 4]\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-27 21:28:11,960 | INFO | Latest version of semantic-scholar-dataset-small is 4\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-27 21:28:11,961 | INFO | File semantic-scholar-dataset-small-4 found in cache\u001b[0m\n"
+ ]
+ }
+ ],
"source": [
- "PREFIX = \"domain-\"\n",
- "DATASET_KEY = \"data\"\n",
- "MAX_FILE_COUNT = 5\n",
- "MODEL_KEY = \"small-domain-prediction-v2\""
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "configure()\n",
- "corpus_path = LargeFile(DATASET_KEY).get()\n",
+ "DATASET_KEY = \"semantic-scholar-dataset-small\"\n",
+ "MODEL_KEY = \"small-domain-prediction-v2\"\n",
+ "\n",
+ "%matplotlib inline\n",
"\n",
- "set_config(display=\"diagram\")\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"
+ "plt.rcParams[\"axes.xmargin\"] = 0\n",
+ "\n",
+ "configure()\n",
+ "corpus_path = LargeFile(DATASET_KEY).get()"
]
},
{
@@ -75,60 +83,1679255 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 3,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[38;5;39m2022-05-27 21:28:11,997 | INFO | Fetching online versions of semantic-scholar-dataset-small\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-27 21:28:12,289 | INFO | Found versions: [3, 4]\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-27 21:28:12,290 | INFO | Latest version of semantic-scholar-dataset-small is 4\u001b[0m\n",
+ "\u001b[38;5;39m2022-05-27 21:28:12,290 | INFO | File semantic-scholar-dataset-small-4 found in cache\u001b[0m\n"
+ ]
+ }
+ ],
"source": [
- "def clean_file(p: Path) -> None:\n",
- " try:\n",
- " processed_path = p.with_name(f\"{PREFIX}{p.stem}{p.suffix}\")\n",
- "\n",
- " if processed_path.exists():\n",
- " return\n",
- "\n",
- " with open(p) as f:\n",
- " content = json.load(f)\n",
- "\n",
- " result = {\n",
- " lemmatize(preprocess(f'{c[\"title\"]} {c[\"abstract\"]}')): c[\"domain\"]\n",
- " for c in content\n",
- " if (\n",
- " c[\"domain\"]\n",
- " and c[\"abstract\"]\n",
- " and is_english(predict_language(c[\"abstract\"]))\n",
- " )\n",
- " }\n",
- "\n",
- " with open(processed_path, \"w\") as f:\n",
- " json.dump(result, f)\n",
- " except Exception as e:\n",
- " print(f\"Error ({e}) processing {p}\")\n",
- "\n",
- "\n",
- "parallel_map(\n",
- " clean_file,\n",
- " list(corpus_path.glob(\"s2-corpus-*.json\"))[:MAX_FILE_COUNT],\n",
- " chunk_size=1,\n",
- ")\n",
- "None"
+ "with LargeFile(DATASET_KEY) as f:\n",
+ " data = json.load(f)"
]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ " \n",
+ " "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.plotly.v1+json": {
+ "config": {
+ "plotlyServerURL": "https://plot.ly"
+ },
+ "data": [
+ {
+ "alignmentgroup": "True",
+ "bingroup": "x",
+ "hovertemplate": "variable=0
value=%{x}
count=%{y}