From 47854c78f2014afdb529523f1c11b3965934373a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Cabrero-Holgueras?= Date: Wed, 12 Jun 2024 14:36:53 +0000 Subject: [PATCH 1/4] feat: added spam_detection demo --- examples/README.md | 1 + .../spam_detection/01_model_provider.ipynb | 1056 +++++++++ .../spam_detection/02_model_inference.ipynb | 491 ++++ examples/spam_detection/README.md | 11 + examples/spam_detection/model/.gitignore | 5 + examples/spam_detection/nada-project.toml | 7 + examples/spam_detection/requirements.txt | 4 + examples/spam_detection/src/config.py | 3 + examples/spam_detection/src/main.py | 28 + examples/spam_detection/tests/test.yaml | 2010 +++++++++++++++++ nada_ai/linear_model/__init__.py | 2 +- nada_ai/linear_model/linear_regression.py | 18 + poetry.lock | 58 +- pyproject.toml | 4 +- 14 files changed, 3690 insertions(+), 8 deletions(-) create mode 100644 examples/spam_detection/01_model_provider.ipynb create mode 100644 examples/spam_detection/02_model_inference.ipynb create mode 100644 examples/spam_detection/README.md create mode 100644 examples/spam_detection/model/.gitignore create mode 100644 examples/spam_detection/nada-project.toml create mode 100644 examples/spam_detection/requirements.txt create mode 100644 examples/spam_detection/src/config.py create mode 100644 examples/spam_detection/src/main.py create mode 100644 examples/spam_detection/tests/test.yaml diff --git a/examples/README.md b/examples/README.md index 39f1b1d..77cbf08 100644 --- a/examples/README.md +++ b/examples/README.md @@ -6,6 +6,7 @@ The following are the currently available examples: - [Neural Net](./neural_net): shows how to build & run a simple Feed-Forward Neural Net (both linear layers & activations) using Nada AI - [Complex Model](./complex_model): shows how to build more intricate model architectures using Nada AI. Contains convolutions, pooling operations, linear layers and activations - [Time Series](./time_series): shows how to run a Facebook Prophet time series forecasting model using Nada AI +- [Spam Detection Demo](./spam_detection): shows how to build a privacy-preserving spam detection model using Nada AI. Contains Logistic Regression, and cleartext TF-IDF vectorization. The Nada program source code is stored in `src/.py`. diff --git a/examples/spam_detection/01_model_provider.ipynb b/examples/spam_detection/01_model_provider.ipynb new file mode 100644 index 0000000..ec0c1b6 --- /dev/null +++ b/examples/spam_detection/01_model_provider.ipynb @@ -0,0 +1,1056 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Privacy-Preserving SMS Text Classification with Nillion" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "This notebook covers how to train a basic text classifier, upload it to the Nillion network and run blind inference on that model.\n", + "\n", + "As an example, we'll train a spam classifier with a logistic regression; a model named after its inventor Robert J. Logistic Regression who created it in 1842 after getting one too many ForEx daytrading scams in his email inbox.\n", + "\n", + "So, in honour of Robert, let's jump into it!" + ] + }, + { + "attachments": { + "image.png": { + "image/png": "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" + } + }, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "![image.png](attachment:image.png)" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "## If problems arise with the loading of the shared library, this script can be used to load the shared library before other libraries.\n", + "## Remember to also run on your local machine the script below:\n", + "# bash replace_lib_version.sh\n", + "\n", + "import platform\n", + "import ctypes\n", + "\n", + "if platform.system() == \"Linux\":\n", + " # Force libgomp to be loaded before other libraries consuming dynamic TLS (to avoid running out of STATIC_TLS)\n", + " ctypes.cdll.LoadLibrary(\"libgomp.so.1\")\n", + " ctypes.cdll.LoadLibrary(\n", + " \"/home/vscode/.local/lib/python3.12/site-packages/py_nillion_client/py_nillion_client.abi3.so\"\n", + " )" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "import json\n", + "import os\n", + "import zipfile\n", + "from typing import Dict\n", + "\n", + "import joblib\n", + "import pandas as pd\n", + "\n", + "import requests\n", + "\n", + "from dotenv import load_dotenv\n", + "from io import BytesIO\n", + "from sklearn.feature_extraction.text import TfidfVectorizer\n", + "from sklearn.linear_model import LogisticRegression\n", + "from sklearn.metrics import accuracy_score\n", + "\n", + "from src.config import NUM_FEATS\n", + "\n", + "# Using Nada AI model client\n", + "from nada_ai.client import SklearnClient\n", + "import nada_algebra as na\n", + "import py_nillion_client as nillion\n", + "from nillion_python_helpers import (\n", + " create_nillion_client,\n", + " getUserKeyFromFile,\n", + " getNodeKeyFromFile,\n", + ")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Train a classification model" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "# Load the SMS Spam Collection Dataset\n", + "response = requests.get(\n", + " \"https://archive.ics.uci.edu/ml/machine-learning-databases/00228/smsspamcollection.zip\"\n", + ")\n", + "if response.status_code != 200:\n", + " raise FileNotFoundError\n", + "\n", + "zip_content = BytesIO(response.content)\n", + "with zipfile.ZipFile(zip_content, \"r\") as zip_ref:\n", + " if \"SMSSpamCollection\" not in zip_ref.namelist():\n", + " raise FileNotFoundError\n", + "\n", + " with zip_ref.open(\"SMSSpamCollection\", \"r\") as csv_file:\n", + " df = pd.read_csv(csv_file, sep=\"\\t\", header=None, names=[\"label\", \"message\"])" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "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", + "
labelmessage
0hamGo until jurong point, crazy.. Available only ...
1hamOk lar... Joking wif u oni...
2spamFree entry in 2 a wkly comp to win FA Cup fina...
3hamU dun say so early hor... U c already then say...
4hamNah I don't think he goes to usf, he lives aro...
\n", + "
" + ], + "text/plain": [ + " label message\n", + "0 ham Go until jurong point, crazy.. Available only ...\n", + "1 ham Ok lar... Joking wif u oni...\n", + "2 spam Free entry in 2 a wkly comp to win FA Cup fina...\n", + "3 ham U dun say so early hor... U c already then say...\n", + "4 ham Nah I don't think he goes to usf, he lives aro..." + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "# Split data into features and labels\n", + "X = df[\"message\"]\n", + "y = df[\"label\"]\n", + "\n", + "# Convert labels to binary (1 for spam, 0 for ham)\n", + "y = y.map({\"spam\": 1, \"ham\": 0})" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['model/vectorizer.joblib']" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Transform text to set of numerical features\n", + "vectorizer = TfidfVectorizer(\n", + " max_features=NUM_FEATS\n", + ") # Limiting to fixed set of features\n", + "X = vectorizer.fit_transform(X)\n", + "\n", + "# Save the vectorizer to a file\n", + "joblib.dump(vectorizer, \"model/vectorizer.joblib\")" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
LogisticRegression()
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": [ + "LogisticRegression()" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Train classifier model\n", + "classifier = LogisticRegression()\n", + "classifier.fit(X, y)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Accuracy: 98.2053%\n" + ] + } + ], + "source": [ + "# Predict labels for test set\n", + "y_pred = classifier.predict(X)\n", + "\n", + "# Calculate accuracy\n", + "accuracy = accuracy_score(y, y_pred)\n", + "\n", + "print(\"Accuracy: {:.4f}%\".format(accuracy * 100))" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Optimal regression coefficients are: (1, 500)\n", + "Optimal bias is: (1,)\n" + ] + } + ], + "source": [ + "print(\"Optimal regression coefficients are:\", classifier.coef_.shape)\n", + "print(\"Optimal bias is:\", classifier.intercept_.shape)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "['model/classifier.joblib']" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Save the classifier to a file\n", + "joblib.dump(classifier, \"model/classifier.joblib\")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Authenticate with Nillion" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "To connect to the Nillion network, we need to have a user key and a node key. These serve different purposes:\n", + "\n", + "The `user_key` is the user's private key. The user key should never be shared publicly, as it unlocks access and permissions to secrets stored on the network.\n", + "\n", + "The `node_key` is the node's private key which is run locally to connect to the network." + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load all Nillion network environment variables\n", + "assert os.getcwd().endswith(\n", + " \"examples/spam_detection\"\n", + "), \"Please run this script from the examples/spam_detection directory otherwise, the rest of the tutorial may not work\"\n", + "load_dotenv()" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [], + "source": [ + "cluster_id = os.getenv(\"NILLION_CLUSTER_ID\")\n", + "model_provider_userkey = getUserKeyFromFile(os.getenv(\"NILLION_USERKEY_PATH_PARTY_1\"))\n", + "model_provider_nodekey = getNodeKeyFromFile(os.getenv(\"NILLION_NODEKEY_PATH_PARTY_1\"))\n", + "model_provider_client = create_nillion_client(\n", + " model_provider_userkey, model_provider_nodekey\n", + ")\n", + "model_provider_party_id = model_provider_client.party_id\n", + "model_provider_user_id = model_provider_client.user_id" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "model_user_userkey = getUserKeyFromFile(os.getenv(\"NILLION_USERKEY_PATH_PARTY_2\"))\n", + "model_user_nodekey = getNodeKeyFromFile(os.getenv(\"NILLION_NODEKEY_PATH_PARTY_2\"))\n", + "model_user_client = create_nillion_client(model_user_userkey, model_user_nodekey)\n", + "model_user_party_id = model_user_client.party_id\n", + "model_user_user_id = create_nillion_client(\n", + " model_user_userkey, model_user_nodekey\n", + ").user_id" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Model Provider flow" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Upload Nada program to Nillion" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "TODO: explain what the Nada program does" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "async def store_program(\n", + " *,\n", + " client: nillion.NillionClient,\n", + " cluster_id: str,\n", + " user_id: str,\n", + " nada_program_path: str,\n", + ") -> Dict[str, str]:\n", + " \"\"\"Stores Nada program binary in Nillion network.\n", + "\n", + " Args:\n", + " client (nillion.NillionClient): Client that will upload Nada program.\n", + " cluster_id (str): Nillion cluster ID.\n", + " user_id (str): User ID of user that will upload Nada program.\n", + " nada_program_path (str): Path to Nada program binary.\n", + "\n", + " Returns:\n", + " Dict[str, str]: Resulting `action_id` and `program_id`.\n", + " \"\"\"\n", + " action_id = await client.store_program(cluster_id, \"main\", nada_program_path)\n", + " program_id = f\"{user_id}/main\"\n", + "\n", + " return {\n", + " \"action_id\": action_id,\n", + " \"program_id\": program_id,\n", + " }" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "✅ Program saved successfully!\n", + "action_id: 00a8a52f-2741-4c58-b323-5ebd836660a7\n", + "program_id: 5bx3a8mHghVFDSHXtgxirwDXjbPAw8SFHsSMPvtvx8sPu1NoQoVbKAuSrE1KVgZSTeiJtGGkzKgFa1VrTenh2W6s/main\n" + ] + } + ], + "source": [ + "result_store_program = await store_program(\n", + " client=model_provider_client,\n", + " cluster_id=cluster_id,\n", + " user_id=model_provider_user_id,\n", + " nada_program_path=\"target/main.nada.bin\",\n", + ")\n", + "\n", + "action_id = result_store_program[\"action_id\"]\n", + "program_id = result_store_program[\"program_id\"]\n", + "\n", + "print(\"✅ Program saved successfully!\")\n", + "print(\"action_id:\", action_id)\n", + "print(\"program_id:\", program_id)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Upload model weights to Nillion network" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [], + "source": [ + "# Create and store model secrets via ModelClient\n", + "model_client = SklearnClient(classifier)" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [], + "source": [ + "async def store_model(\n", + " *,\n", + " model: SklearnClient,\n", + " client: nillion.NillionClient,\n", + " cluster_id: str,\n", + " program_id: str,\n", + " party_id: str,\n", + " model_user_user_id: str,\n", + " model_provider_user_id: str,\n", + ") -> Dict[str, str]:\n", + " \"\"\"Stores model params in Nillion network.\n", + "\n", + " Args:\n", + " model (LogisticRegression): Model object to store in network.\n", + " client (nillion.NillionClient): Nillion client that stores model params.\n", + " cluster_id (str): Nillion cluster ID.\n", + " program_id (str): Program ID of Nada program.\n", + " party_id (str): Party ID of party that will store model params.\n", + " model_user_user_id (str): User ID of user that will get compute permissions.\n", + " model_provider_user_id (str): User ID of user that will provide model params.\n", + "\n", + " Returns:\n", + " Dict[str, str]: Resulting `provider_party_id` and `model_store_id`.\n", + " \"\"\"\n", + "\n", + " print(model.export_state_as_secrets(\"my_model\", na.SecretRational).keys())\n", + " secrets = nillion.Secrets(\n", + " model.export_state_as_secrets(\"my_model\", na.SecretRational)\n", + " )\n", + "\n", + " secret_bindings = nillion.ProgramBindings(program_id)\n", + " secret_bindings.add_input_party(\"Provider\", party_id)\n", + "\n", + " permissions = nillion.Permissions.default_for_user(model_provider_user_id)\n", + " compute_permissions = {\n", + " model_user_user_id: {program_id},\n", + " }\n", + " # Give permission to model user to run inference\n", + " permissions.add_compute_permissions(compute_permissions)\n", + "\n", + " store_id = await client.store_secrets(\n", + " cluster_id, secret_bindings, secrets, permissions\n", + " )\n", + "\n", + " return {\n", + " \"provider_party_id\": party_id,\n", + " \"model_store_id\": store_id,\n", + " }" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "dict_keys(['my_model_coef_0_0', 'my_model_coef_0_1', 'my_model_coef_0_2', 'my_model_coef_0_3', 'my_model_coef_0_4', 'my_model_coef_0_5', 'my_model_coef_0_6', 'my_model_coef_0_7', 'my_model_coef_0_8', 'my_model_coef_0_9', 'my_model_coef_0_10', 'my_model_coef_0_11', 'my_model_coef_0_12', 'my_model_coef_0_13', 'my_model_coef_0_14', 'my_model_coef_0_15', 'my_model_coef_0_16', 'my_model_coef_0_17', 'my_model_coef_0_18', 'my_model_coef_0_19', 'my_model_coef_0_20', 'my_model_coef_0_21', 'my_model_coef_0_22', 'my_model_coef_0_23', 'my_model_coef_0_24', 'my_model_coef_0_25', 'my_model_coef_0_26', 'my_model_coef_0_27', 'my_model_coef_0_28', 'my_model_coef_0_29', 'my_model_coef_0_30', 'my_model_coef_0_31', 'my_model_coef_0_32', 'my_model_coef_0_33', 'my_model_coef_0_34', 'my_model_coef_0_35', 'my_model_coef_0_36', 'my_model_coef_0_37', 'my_model_coef_0_38', 'my_model_coef_0_39', 'my_model_coef_0_40', 'my_model_coef_0_41', 'my_model_coef_0_42', 'my_model_coef_0_43', 'my_model_coef_0_44', 'my_model_coef_0_45', 'my_model_coef_0_46', 'my_model_coef_0_47', 'my_model_coef_0_48', 'my_model_coef_0_49', 'my_model_coef_0_50', 'my_model_coef_0_51', 'my_model_coef_0_52', 'my_model_coef_0_53', 'my_model_coef_0_54', 'my_model_coef_0_55', 'my_model_coef_0_56', 'my_model_coef_0_57', 'my_model_coef_0_58', 'my_model_coef_0_59', 'my_model_coef_0_60', 'my_model_coef_0_61', 'my_model_coef_0_62', 'my_model_coef_0_63', 'my_model_coef_0_64', 'my_model_coef_0_65', 'my_model_coef_0_66', 'my_model_coef_0_67', 'my_model_coef_0_68', 'my_model_coef_0_69', 'my_model_coef_0_70', 'my_model_coef_0_71', 'my_model_coef_0_72', 'my_model_coef_0_73', 'my_model_coef_0_74', 'my_model_coef_0_75', 'my_model_coef_0_76', 'my_model_coef_0_77', 'my_model_coef_0_78', 'my_model_coef_0_79', 'my_model_coef_0_80', 'my_model_coef_0_81', 'my_model_coef_0_82', 'my_model_coef_0_83', 'my_model_coef_0_84', 'my_model_coef_0_85', 'my_model_coef_0_86', 'my_model_coef_0_87', 'my_model_coef_0_88', 'my_model_coef_0_89', 'my_model_coef_0_90', 'my_model_coef_0_91', 'my_model_coef_0_92', 'my_model_coef_0_93', 'my_model_coef_0_94', 'my_model_coef_0_95', 'my_model_coef_0_96', 'my_model_coef_0_97', 'my_model_coef_0_98', 'my_model_coef_0_99', 'my_model_coef_0_100', 'my_model_coef_0_101', 'my_model_coef_0_102', 'my_model_coef_0_103', 'my_model_coef_0_104', 'my_model_coef_0_105', 'my_model_coef_0_106', 'my_model_coef_0_107', 'my_model_coef_0_108', 'my_model_coef_0_109', 'my_model_coef_0_110', 'my_model_coef_0_111', 'my_model_coef_0_112', 'my_model_coef_0_113', 'my_model_coef_0_114', 'my_model_coef_0_115', 'my_model_coef_0_116', 'my_model_coef_0_117', 'my_model_coef_0_118', 'my_model_coef_0_119', 'my_model_coef_0_120', 'my_model_coef_0_121', 'my_model_coef_0_122', 'my_model_coef_0_123', 'my_model_coef_0_124', 'my_model_coef_0_125', 'my_model_coef_0_126', 'my_model_coef_0_127', 'my_model_coef_0_128', 'my_model_coef_0_129', 'my_model_coef_0_130', 'my_model_coef_0_131', 'my_model_coef_0_132', 'my_model_coef_0_133', 'my_model_coef_0_134', 'my_model_coef_0_135', 'my_model_coef_0_136', 'my_model_coef_0_137', 'my_model_coef_0_138', 'my_model_coef_0_139', 'my_model_coef_0_140', 'my_model_coef_0_141', 'my_model_coef_0_142', 'my_model_coef_0_143', 'my_model_coef_0_144', 'my_model_coef_0_145', 'my_model_coef_0_146', 'my_model_coef_0_147', 'my_model_coef_0_148', 'my_model_coef_0_149', 'my_model_coef_0_150', 'my_model_coef_0_151', 'my_model_coef_0_152', 'my_model_coef_0_153', 'my_model_coef_0_154', 'my_model_coef_0_155', 'my_model_coef_0_156', 'my_model_coef_0_157', 'my_model_coef_0_158', 'my_model_coef_0_159', 'my_model_coef_0_160', 'my_model_coef_0_161', 'my_model_coef_0_162', 'my_model_coef_0_163', 'my_model_coef_0_164', 'my_model_coef_0_165', 'my_model_coef_0_166', 'my_model_coef_0_167', 'my_model_coef_0_168', 'my_model_coef_0_169', 'my_model_coef_0_170', 'my_model_coef_0_171', 'my_model_coef_0_172', 'my_model_coef_0_173', 'my_model_coef_0_174', 'my_model_coef_0_175', 'my_model_coef_0_176', 'my_model_coef_0_177', 'my_model_coef_0_178', 'my_model_coef_0_179', 'my_model_coef_0_180', 'my_model_coef_0_181', 'my_model_coef_0_182', 'my_model_coef_0_183', 'my_model_coef_0_184', 'my_model_coef_0_185', 'my_model_coef_0_186', 'my_model_coef_0_187', 'my_model_coef_0_188', 'my_model_coef_0_189', 'my_model_coef_0_190', 'my_model_coef_0_191', 'my_model_coef_0_192', 'my_model_coef_0_193', 'my_model_coef_0_194', 'my_model_coef_0_195', 'my_model_coef_0_196', 'my_model_coef_0_197', 'my_model_coef_0_198', 'my_model_coef_0_199', 'my_model_coef_0_200', 'my_model_coef_0_201', 'my_model_coef_0_202', 'my_model_coef_0_203', 'my_model_coef_0_204', 'my_model_coef_0_205', 'my_model_coef_0_206', 'my_model_coef_0_207', 'my_model_coef_0_208', 'my_model_coef_0_209', 'my_model_coef_0_210', 'my_model_coef_0_211', 'my_model_coef_0_212', 'my_model_coef_0_213', 'my_model_coef_0_214', 'my_model_coef_0_215', 'my_model_coef_0_216', 'my_model_coef_0_217', 'my_model_coef_0_218', 'my_model_coef_0_219', 'my_model_coef_0_220', 'my_model_coef_0_221', 'my_model_coef_0_222', 'my_model_coef_0_223', 'my_model_coef_0_224', 'my_model_coef_0_225', 'my_model_coef_0_226', 'my_model_coef_0_227', 'my_model_coef_0_228', 'my_model_coef_0_229', 'my_model_coef_0_230', 'my_model_coef_0_231', 'my_model_coef_0_232', 'my_model_coef_0_233', 'my_model_coef_0_234', 'my_model_coef_0_235', 'my_model_coef_0_236', 'my_model_coef_0_237', 'my_model_coef_0_238', 'my_model_coef_0_239', 'my_model_coef_0_240', 'my_model_coef_0_241', 'my_model_coef_0_242', 'my_model_coef_0_243', 'my_model_coef_0_244', 'my_model_coef_0_245', 'my_model_coef_0_246', 'my_model_coef_0_247', 'my_model_coef_0_248', 'my_model_coef_0_249', 'my_model_coef_0_250', 'my_model_coef_0_251', 'my_model_coef_0_252', 'my_model_coef_0_253', 'my_model_coef_0_254', 'my_model_coef_0_255', 'my_model_coef_0_256', 'my_model_coef_0_257', 'my_model_coef_0_258', 'my_model_coef_0_259', 'my_model_coef_0_260', 'my_model_coef_0_261', 'my_model_coef_0_262', 'my_model_coef_0_263', 'my_model_coef_0_264', 'my_model_coef_0_265', 'my_model_coef_0_266', 'my_model_coef_0_267', 'my_model_coef_0_268', 'my_model_coef_0_269', 'my_model_coef_0_270', 'my_model_coef_0_271', 'my_model_coef_0_272', 'my_model_coef_0_273', 'my_model_coef_0_274', 'my_model_coef_0_275', 'my_model_coef_0_276', 'my_model_coef_0_277', 'my_model_coef_0_278', 'my_model_coef_0_279', 'my_model_coef_0_280', 'my_model_coef_0_281', 'my_model_coef_0_282', 'my_model_coef_0_283', 'my_model_coef_0_284', 'my_model_coef_0_285', 'my_model_coef_0_286', 'my_model_coef_0_287', 'my_model_coef_0_288', 'my_model_coef_0_289', 'my_model_coef_0_290', 'my_model_coef_0_291', 'my_model_coef_0_292', 'my_model_coef_0_293', 'my_model_coef_0_294', 'my_model_coef_0_295', 'my_model_coef_0_296', 'my_model_coef_0_297', 'my_model_coef_0_298', 'my_model_coef_0_299', 'my_model_coef_0_300', 'my_model_coef_0_301', 'my_model_coef_0_302', 'my_model_coef_0_303', 'my_model_coef_0_304', 'my_model_coef_0_305', 'my_model_coef_0_306', 'my_model_coef_0_307', 'my_model_coef_0_308', 'my_model_coef_0_309', 'my_model_coef_0_310', 'my_model_coef_0_311', 'my_model_coef_0_312', 'my_model_coef_0_313', 'my_model_coef_0_314', 'my_model_coef_0_315', 'my_model_coef_0_316', 'my_model_coef_0_317', 'my_model_coef_0_318', 'my_model_coef_0_319', 'my_model_coef_0_320', 'my_model_coef_0_321', 'my_model_coef_0_322', 'my_model_coef_0_323', 'my_model_coef_0_324', 'my_model_coef_0_325', 'my_model_coef_0_326', 'my_model_coef_0_327', 'my_model_coef_0_328', 'my_model_coef_0_329', 'my_model_coef_0_330', 'my_model_coef_0_331', 'my_model_coef_0_332', 'my_model_coef_0_333', 'my_model_coef_0_334', 'my_model_coef_0_335', 'my_model_coef_0_336', 'my_model_coef_0_337', 'my_model_coef_0_338', 'my_model_coef_0_339', 'my_model_coef_0_340', 'my_model_coef_0_341', 'my_model_coef_0_342', 'my_model_coef_0_343', 'my_model_coef_0_344', 'my_model_coef_0_345', 'my_model_coef_0_346', 'my_model_coef_0_347', 'my_model_coef_0_348', 'my_model_coef_0_349', 'my_model_coef_0_350', 'my_model_coef_0_351', 'my_model_coef_0_352', 'my_model_coef_0_353', 'my_model_coef_0_354', 'my_model_coef_0_355', 'my_model_coef_0_356', 'my_model_coef_0_357', 'my_model_coef_0_358', 'my_model_coef_0_359', 'my_model_coef_0_360', 'my_model_coef_0_361', 'my_model_coef_0_362', 'my_model_coef_0_363', 'my_model_coef_0_364', 'my_model_coef_0_365', 'my_model_coef_0_366', 'my_model_coef_0_367', 'my_model_coef_0_368', 'my_model_coef_0_369', 'my_model_coef_0_370', 'my_model_coef_0_371', 'my_model_coef_0_372', 'my_model_coef_0_373', 'my_model_coef_0_374', 'my_model_coef_0_375', 'my_model_coef_0_376', 'my_model_coef_0_377', 'my_model_coef_0_378', 'my_model_coef_0_379', 'my_model_coef_0_380', 'my_model_coef_0_381', 'my_model_coef_0_382', 'my_model_coef_0_383', 'my_model_coef_0_384', 'my_model_coef_0_385', 'my_model_coef_0_386', 'my_model_coef_0_387', 'my_model_coef_0_388', 'my_model_coef_0_389', 'my_model_coef_0_390', 'my_model_coef_0_391', 'my_model_coef_0_392', 'my_model_coef_0_393', 'my_model_coef_0_394', 'my_model_coef_0_395', 'my_model_coef_0_396', 'my_model_coef_0_397', 'my_model_coef_0_398', 'my_model_coef_0_399', 'my_model_coef_0_400', 'my_model_coef_0_401', 'my_model_coef_0_402', 'my_model_coef_0_403', 'my_model_coef_0_404', 'my_model_coef_0_405', 'my_model_coef_0_406', 'my_model_coef_0_407', 'my_model_coef_0_408', 'my_model_coef_0_409', 'my_model_coef_0_410', 'my_model_coef_0_411', 'my_model_coef_0_412', 'my_model_coef_0_413', 'my_model_coef_0_414', 'my_model_coef_0_415', 'my_model_coef_0_416', 'my_model_coef_0_417', 'my_model_coef_0_418', 'my_model_coef_0_419', 'my_model_coef_0_420', 'my_model_coef_0_421', 'my_model_coef_0_422', 'my_model_coef_0_423', 'my_model_coef_0_424', 'my_model_coef_0_425', 'my_model_coef_0_426', 'my_model_coef_0_427', 'my_model_coef_0_428', 'my_model_coef_0_429', 'my_model_coef_0_430', 'my_model_coef_0_431', 'my_model_coef_0_432', 'my_model_coef_0_433', 'my_model_coef_0_434', 'my_model_coef_0_435', 'my_model_coef_0_436', 'my_model_coef_0_437', 'my_model_coef_0_438', 'my_model_coef_0_439', 'my_model_coef_0_440', 'my_model_coef_0_441', 'my_model_coef_0_442', 'my_model_coef_0_443', 'my_model_coef_0_444', 'my_model_coef_0_445', 'my_model_coef_0_446', 'my_model_coef_0_447', 'my_model_coef_0_448', 'my_model_coef_0_449', 'my_model_coef_0_450', 'my_model_coef_0_451', 'my_model_coef_0_452', 'my_model_coef_0_453', 'my_model_coef_0_454', 'my_model_coef_0_455', 'my_model_coef_0_456', 'my_model_coef_0_457', 'my_model_coef_0_458', 'my_model_coef_0_459', 'my_model_coef_0_460', 'my_model_coef_0_461', 'my_model_coef_0_462', 'my_model_coef_0_463', 'my_model_coef_0_464', 'my_model_coef_0_465', 'my_model_coef_0_466', 'my_model_coef_0_467', 'my_model_coef_0_468', 'my_model_coef_0_469', 'my_model_coef_0_470', 'my_model_coef_0_471', 'my_model_coef_0_472', 'my_model_coef_0_473', 'my_model_coef_0_474', 'my_model_coef_0_475', 'my_model_coef_0_476', 'my_model_coef_0_477', 'my_model_coef_0_478', 'my_model_coef_0_479', 'my_model_coef_0_480', 'my_model_coef_0_481', 'my_model_coef_0_482', 'my_model_coef_0_483', 'my_model_coef_0_484', 'my_model_coef_0_485', 'my_model_coef_0_486', 'my_model_coef_0_487', 'my_model_coef_0_488', 'my_model_coef_0_489', 'my_model_coef_0_490', 'my_model_coef_0_491', 'my_model_coef_0_492', 'my_model_coef_0_493', 'my_model_coef_0_494', 'my_model_coef_0_495', 'my_model_coef_0_496', 'my_model_coef_0_497', 'my_model_coef_0_498', 'my_model_coef_0_499', 'my_model_intercept_0'])\n", + "✅ Model params uploaded successfully!\n", + "provider_party_id: 12D3KooWKFYPNK6MwwKPxn93nAwTKeCkUutxm5joVNhJiUP4i1vu\n", + "model_store_id: 1a16c4f0-3b36-47e6-b3b7-b70c22107b86\n" + ] + } + ], + "source": [ + "result_store_model = await store_model(\n", + " model=model_client,\n", + " client=model_provider_client,\n", + " cluster_id=cluster_id,\n", + " program_id=program_id,\n", + " party_id=model_provider_party_id,\n", + " model_user_user_id=model_user_user_id,\n", + " model_provider_user_id=model_provider_user_id,\n", + ")\n", + "\n", + "provider_party_id = result_store_model[\"provider_party_id\"]\n", + "model_store_id = result_store_model[\"model_store_id\"]\n", + "\n", + "print(\"✅ Model params uploaded successfully!\")\n", + "print(\"provider_party_id:\", provider_party_id)\n", + "print(\"model_store_id:\", model_store_id)" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": {}, + "outputs": [], + "source": [ + "# This information is needed by the model user\n", + "with open(\"target/tmp.json\", \"w\") as provider_variables_file:\n", + " provider_variables = {\n", + " \"program_id\": program_id,\n", + " \"model_store_id\": model_store_id,\n", + " \"model_provider_party_id\": model_provider_party_id,\n", + " }\n", + " json.dump(provider_variables, provider_variables_file)" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "('1afafff8-b11e-432e-86e4-914213fc9841', )" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "result_tuple = await model_provider_client.retrieve_secret(\n", + " cluster_id, model_store_id, \"my_model_coef_0_123\"\n", + ")\n", + "result_tuple" + ] + } + ], + "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": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/examples/spam_detection/02_model_inference.ipynb b/examples/spam_detection/02_model_inference.ipynb new file mode 100644 index 0000000..12247d7 --- /dev/null +++ b/examples/spam_detection/02_model_inference.ipynb @@ -0,0 +1,491 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**IMPORTANT**: Before starting this notebook make sure that the kernel of the previous notebook is shutdown or reset it's state to forget the previous `model_user` Nillion client" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "## If problems arise with the loading of the shared library, this script can be used to load the shared library before other libraries.\n", + "## Remember to also run on your local machine the script below:\n", + "# bash replace_lib_version.sh\n", + "\n", + "import platform\n", + "import ctypes\n", + "\n", + "if platform.system() == \"Linux\":\n", + " # Force libgomp and py_nillion_client to be loaded before other libraries consuming dynamic TLS (to avoid running out of STATIC_TLS)\n", + " ctypes.cdll.LoadLibrary(\"libgomp.so.1\")\n", + " ctypes.cdll.LoadLibrary(\n", + " \"/home/vscode/.local/lib/python3.12/site-packages/py_nillion_client/py_nillion_client.abi3.so\"\n", + " )" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "from typing import Dict, List\n", + "\n", + "import json\n", + "import os\n", + "import joblib\n", + "\n", + "\n", + "from dotenv import load_dotenv\n", + "import numpy as np\n", + "from sklearn.feature_extraction.text import TfidfVectorizer\n", + "from sklearn.linear_model import LogisticRegression\n", + "\n", + "import nada_algebra as na\n", + "import nada_algebra.client as na_client\n", + "import py_nillion_client as nillion\n", + "from nillion_python_helpers import (\n", + " create_nillion_client,\n", + " getUserKeyFromFile,\n", + " getNodeKeyFromFile,\n", + ")\n", + "\n", + "from src.config import NUM_FEATS" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Authenticate with Nillion" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "To connect to the Nillion network, we need to have a user key and a node key. These serve different purposes:\n", + "\n", + "The `user_key` is the user's private key. The user key should never be shared publicly, as it unlocks access and permissions to secrets stored on the network.\n", + "\n", + "The `node_key` is the node's private key which is run locally to connect to the network." + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "True" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# Load all Nillion network environment variables\n", + "assert os.getcwd().endswith(\n", + " \"examples/spam_detection\"\n", + "), \"Please run this script from the examples/spam_detection directory otherwise, the rest of the tutorial may not work\"\n", + "load_dotenv()" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "cluster_id = os.getenv(\"NILLION_CLUSTER_ID\")\n", + "model_user_userkey = getUserKeyFromFile(os.getenv(\"NILLION_USERKEY_PATH_PARTY_2\"))\n", + "model_user_nodekey = getNodeKeyFromFile(os.getenv(\"NILLION_NODEKEY_PATH_PARTY_2\"))\n", + "model_user_client = create_nillion_client(model_user_userkey, model_user_nodekey)\n", + "model_user_party_id = model_user_client.party_id\n", + "model_user_user_id = model_user_client.user_id" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Program ID: 5bx3a8mHghVFDSHXtgxirwDXjbPAw8SFHsSMPvtvx8sPu1NoQoVbKAuSrE1KVgZSTeiJtGGkzKgFa1VrTenh2W6s/main\n", + "Model Store ID: 1a16c4f0-3b36-47e6-b3b7-b70c22107b86\n", + "Model Provider Party ID: 12D3KooWKFYPNK6MwwKPxn93nAwTKeCkUutxm5joVNhJiUP4i1vu\n" + ] + } + ], + "source": [ + "# This information was provided by the model provider\n", + "with open(\"target/tmp.json\", \"r\") as provider_variables_file:\n", + " provider_variables = json.load(provider_variables_file)\n", + "\n", + "program_id = provider_variables[\"program_id\"]\n", + "model_store_id = provider_variables[\"model_store_id\"]\n", + "model_provider_party_id = provider_variables[\"model_provider_party_id\"]\n", + "\n", + "print(\"Program ID: \", program_id)\n", + "print(\"Model Store ID: \", model_store_id)\n", + "print(\"Model Provider Party ID: \", model_provider_party_id)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Model user flow" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Convert text to features" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "vectorizer: TfidfVectorizer = joblib.load(\"model/vectorizer.joblib\")" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "# Let's find out whether it's a billion dollar opportunity or pyramid scheme\n", + "INPUT_DATA = \"Free entry in 2 a wkly comp to win exclusive prizes! Text WIN to 87121 to receive entry question(std txt rate)T&C's apply 08452810075over18's\"\n", + "\n", + "[features] = vectorizer.transform([INPUT_DATA]).toarray().tolist()" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [], + "source": [ + "features = np.array(features).astype(float)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Send features to Nillion" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [], + "source": [ + "async def store_features(\n", + " *,\n", + " client: nillion.NillionClient,\n", + " cluster_id: str,\n", + " program_id: str,\n", + " party_id: str,\n", + " user_id: str,\n", + " features: np.ndarray\n", + ") -> Dict[str, str]:\n", + " \"\"\"Stores text features in Nillion network.\n", + "\n", + " Args:\n", + " client (nillion.NillionClient): Nillion client that stores features.\n", + " cluster_id (str): Nillion cluster ID.\n", + " program_id (str): Program ID of Nada program.\n", + " party_id (str): Party ID of party that will store text features.\n", + " user_id (str): User ID of user that will get compute permissions.\n", + " features (List[float]): List of text features.\n", + " precision (int): Scaling factor to convert float to ints.\n", + "\n", + " Returns:\n", + " Dict[str, str]: Resulting `model_user_party_id` and `features_store_id`.\n", + " \"\"\"\n", + "\n", + " secrets = nillion.Secrets(na_client.array(features, \"my_input\", na.SecretRational))\n", + "\n", + " print(secrets)\n", + " secret_bindings = nillion.ProgramBindings(program_id)\n", + " secret_bindings.add_input_party(\"User\", party_id)\n", + "\n", + " features_store_id = await client.store_secrets(\n", + " cluster_id, secret_bindings, secrets, None\n", + " )\n", + "\n", + " return {\n", + " \"model_user_user_id\": user_id,\n", + " \"features_store_id\": features_store_id,\n", + " }" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\n", + "✅ Text features uploaded successfully!\n", + "model_user_user_id: 8wzwr1xYpfxE7CAq5ty12HeYvbMVcQD3NFKXC6s8SAwc7aDQvzCfe2rNiZAecC9GZWGnV3H3mXFpzJJjd7MFNsa\n", + "features_store_id: 24931d1c-ffe0-4124-ab88-fcc8f5e194f0\n" + ] + } + ], + "source": [ + "result_store_features = await store_features(\n", + " client=model_user_client,\n", + " cluster_id=cluster_id,\n", + " program_id=program_id,\n", + " party_id=model_user_party_id,\n", + " user_id=model_user_user_id,\n", + " features=features,\n", + ")\n", + "\n", + "model_user_user_id = result_store_features[\"model_user_user_id\"]\n", + "features_store_id = result_store_features[\"features_store_id\"]\n", + "\n", + "print(\"✅ Text features uploaded successfully!\")\n", + "print(\"model_user_user_id:\", model_user_user_id)\n", + "print(\"features_store_id:\", features_store_id)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Run inference & check result" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": {}, + "outputs": [], + "source": [ + "async def run_inference(\n", + " *,\n", + " client: nillion.NillionClient,\n", + " cluster_id: str,\n", + " program_id: str,\n", + " model_user_party_id: str,\n", + " model_provider_party_id: str,\n", + " model_store_id: str,\n", + " features_store_id: str,\n", + ") -> Dict[str, str | float]:\n", + " \"\"\"Runs blind inference on the Nillion network by executing the Nada program on the uploaded data.\n", + "\n", + " Args:\n", + " client (nillion.NillionClient): Nillion client that runs inference.\n", + " cluster_id (str): Nillion cluster ID.\n", + " program_id (str): Program ID of Nada program.\n", + " model_user_party_id (str): Party ID of party that will run inference.\n", + " model_user_party_id (str): Party ID of party that will provide model params.\n", + " model_store_id (str): Store ID that points to the model params in the Nillion network.\n", + " features_store_id (str): Store ID that points to the text features in the Nillion network.\n", + " precision (int): Scaling factor to convert float to ints.s\n", + "\n", + " Returns:\n", + " Dict[str, str | float]: Resulting `compute_id` and `logit`.\n", + " \"\"\"\n", + " compute_bindings = nillion.ProgramBindings(program_id)\n", + " compute_bindings.add_input_party(\"User\", model_user_party_id)\n", + " compute_bindings.add_input_party(\"Provider\", model_provider_party_id)\n", + " compute_bindings.add_output_party(\"User\", model_user_party_id)\n", + "\n", + " _ = await client.compute(\n", + " cluster_id,\n", + " compute_bindings,\n", + " [features_store_id, model_store_id],\n", + " nillion.Secrets({}),\n", + " nillion.PublicVariables({}),\n", + " )\n", + "\n", + " while True:\n", + " compute_event = await client.next_compute_event()\n", + " if isinstance(compute_event, nillion.ComputeFinishedEvent):\n", + " inference_result = compute_event.result.value\n", + " break\n", + "\n", + " sigmoid = lambda x: 1 / (1 + np.exp(-x))\n", + "\n", + " quantized_logit = inference_result[\"logit_0\"]\n", + " logit = quantized_logit / (2 ** na.get_log_scale())\n", + " output_probability = sigmoid(logit)\n", + " return {\n", + " \"compute_id\": compute_event.uuid,\n", + " \"logit\": logit,\n", + " \"output_probability\": output_probability,\n", + " }" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "✅ Inference ran successfully!\n", + "compute_id: eb73f9ad-6cfb-4e86-b767-d227b5660826\n", + "logit: 2.4093170166015625\n", + "Probability of spam in Nillion: 91.753502%\n" + ] + } + ], + "source": [ + "result_inference = await run_inference(\n", + " client=model_user_client,\n", + " cluster_id=cluster_id,\n", + " program_id=program_id,\n", + " model_user_party_id=model_user_party_id,\n", + " model_provider_party_id=model_provider_party_id,\n", + " model_store_id=model_store_id,\n", + " features_store_id=features_store_id,\n", + ")\n", + "\n", + "compute_id = result_inference[\"compute_id\"]\n", + "logit = result_inference[\"logit\"]\n", + "output_probability = result_inference[\"output_probability\"]\n", + "\n", + "print(\"✅ Inference ran successfully!\")\n", + "print(\"compute_id:\", compute_id)\n", + "print(\"logit:\", logit)\n", + "\n", + "print(\"Probability of spam in Nillion: {:.6f}%\".format(output_probability * 100))" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Compare result to what we would have gotten in plain-text inference" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "vectorizer: TfidfVectorizer = joblib.load(\"model/vectorizer.joblib\")\n", + "classifier: LogisticRegression = joblib.load(\"model/classifier.joblib\")" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "features = vectorizer.transform([INPUT_DATA]).toarray().tolist()" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [], + "source": [ + "[logit_plain_text] = classifier.decision_function(features)" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Logit in plain text: 2.408079563074277\n" + ] + } + ], + "source": [ + "print(\"Logit in plain text: {}\".format(logit_plain_text))" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": {}, + "outputs": [], + "source": [ + "[result] = classifier.predict_proba(features)\n", + "output_probability_plain_text = result[1]" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Probability of spam in plain text: 91.744134%\n", + "Probability of spam in Nillion: 91.753502%\n" + ] + } + ], + "source": [ + "print(\n", + " \"Probability of spam in plain text: {:.6f}%\".format(\n", + " output_probability_plain_text * 100\n", + " )\n", + ")\n", + "print(\"Probability of spam in Nillion: {:.6f}%\".format(output_probability * 100))" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.12.3" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/examples/spam_detection/README.md b/examples/spam_detection/README.md new file mode 100644 index 0000000..bb10405 --- /dev/null +++ b/examples/spam_detection/README.md @@ -0,0 +1,11 @@ +# Text classification +**This folder was generated using `nada init`** + +## How to run this test: + +0. Make sure all the dependencies are installed. +1. Run `cd examples/spam_detection` to changed directory. +2. Then, we can create our local devnet with: `bootstrap-nillion-devnet`. This command produces a local environment file `.env` file in the specific directory. So make sure to execute it in the specific directory. +2. Compile the project using `nada build`. +3. Run through the model provider script. +4. Run through the client script. diff --git a/examples/spam_detection/model/.gitignore b/examples/spam_detection/model/.gitignore new file mode 100644 index 0000000..5291a74 --- /dev/null +++ b/examples/spam_detection/model/.gitignore @@ -0,0 +1,5 @@ +# This directory is kept purposely, so that no compilation errors arise. +# Ignore everything in this directory +* +# Except this file +!.gitignore \ No newline at end of file diff --git a/examples/spam_detection/nada-project.toml b/examples/spam_detection/nada-project.toml new file mode 100644 index 0000000..e13df53 --- /dev/null +++ b/examples/spam_detection/nada-project.toml @@ -0,0 +1,7 @@ +name = "text_classification" +version = "0.1.0" +authors = [""] + +[[programs]] +path = "src/main.py" +prime_size = 128 diff --git a/examples/spam_detection/requirements.txt b/examples/spam_detection/requirements.txt new file mode 100644 index 0000000..3833648 --- /dev/null +++ b/examples/spam_detection/requirements.txt @@ -0,0 +1,4 @@ +scikit-learn~=1.4.2 +pandas~=2.2.2 +python-dotenv~=1.0.0 +requests~=2.31.0 \ No newline at end of file diff --git a/examples/spam_detection/src/config.py b/examples/spam_detection/src/config.py new file mode 100644 index 0000000..2f263e7 --- /dev/null +++ b/examples/spam_detection/src/config.py @@ -0,0 +1,3 @@ +"""Configuration variables""" + +NUM_FEATS = 500 diff --git a/examples/spam_detection/src/main.py b/examples/spam_detection/src/main.py new file mode 100644 index 0000000..642ac7d --- /dev/null +++ b/examples/spam_detection/src/main.py @@ -0,0 +1,28 @@ +from nada_dsl import Party +import nada_algebra as na +from nada_ai.linear_model import LogisticRegression +from config import NUM_FEATS + + +def nada_main(): + # Step 1: We use Nada Algebra wrapper to create "Party" and "Party1" + # Define parties + user = Party(name="User") + provider = Party(name="Provider") + + # Step 2: Instantiate logistic regression object + my_model = LogisticRegression(NUM_FEATS, 1) + + # Step 3: Load model weights from Nillion network by passing model name (acts as ID) + # In this examples Party0 provides the model and Party1 runs inference + my_model.load_state_from_network("my_model", user, na.SecretRational) + + # Step 4: Load input data to be used for inference (provided by Party1) + my_input = na.array((NUM_FEATS,), provider, "my_input", na.SecretRational) + + # Step 5: Compute inference + # Note: completely equivalent to `my_model(...)` + result = my_model.forward(my_input) + + # Step 6: We can use result.output() to produce the output for Party1 and variable name "my_output" + return result.output(user, "logit") diff --git a/examples/spam_detection/tests/test.yaml b/examples/spam_detection/tests/test.yaml new file mode 100644 index 0000000..9950ec7 --- /dev/null +++ b/examples/spam_detection/tests/test.yaml @@ -0,0 +1,2010 @@ +--- +program: main +inputs: + secrets: + my_input_431: + SecretInteger: "3" + my_input_497: + SecretInteger: "3" + my_model_coef_199: + SecretInteger: "3" + my_model_coef_346: + SecretInteger: "3" + my_model_coef_462: + SecretInteger: "3" + my_input_183: + SecretInteger: "3" + my_input_28: + SecretInteger: "3" + my_model_coef_387: + SecretInteger: "3" + my_input_339: + SecretInteger: "3" + my_input_443: + SecretInteger: "3" + my_input_109: + SecretInteger: "3" + my_input_377: + SecretInteger: "3" + my_input_33: + SecretInteger: "3" + my_model_coef_212: + SecretInteger: "3" + my_model_coef_129: + SecretInteger: "3" + my_input_78: + SecretInteger: "3" + my_input_101: + SecretInteger: "3" + my_model_coef_81: + SecretInteger: "3" + my_model_coef_257: + SecretInteger: "3" + my_input_238: + SecretInteger: "3" + my_input_495: + SecretInteger: "3" + my_model_coef_89: + SecretInteger: "3" + my_model_coef_429: + SecretInteger: "3" + my_input_416: + SecretInteger: "3" + my_input_237: + SecretInteger: "3" + my_model_coef_272: + SecretInteger: "3" + my_model_coef_492: + SecretInteger: "3" + my_input_172: + SecretInteger: "3" + my_input_459: + SecretInteger: "3" + my_model_coef_180: + SecretInteger: "3" + my_model_coef_116: + SecretInteger: "3" + my_model_coef_431: + SecretInteger: "3" + my_input_69: + SecretInteger: "3" + my_model_coef_33: + SecretInteger: "3" + my_model_coef_134: + SecretInteger: "3" + my_input_291: + SecretInteger: "3" + my_model_coef_491: + SecretInteger: "3" + my_model_coef_393: + SecretInteger: "3" + my_model_coef_355: + SecretInteger: "3" + my_input_181: + SecretInteger: "3" + my_input_6: + SecretInteger: "3" + my_model_coef_311: + SecretInteger: "3" + my_input_12: + SecretInteger: "3" + my_input_232: + SecretInteger: "3" + my_model_coef_389: + SecretInteger: "3" + my_input_340: + SecretInteger: "3" + my_input_398: + SecretInteger: "3" + my_input_130: + SecretInteger: "3" + my_model_coef_398: + SecretInteger: "3" + my_input_60: + SecretInteger: "3" + my_input_254: + SecretInteger: "3" + my_model_coef_328: + SecretInteger: "3" + my_input_145: + SecretInteger: "3" + my_input_324: + SecretInteger: "3" + my_model_coef_201: + SecretInteger: "3" + my_model_coef_430: + SecretInteger: "3" + my_input_171: + SecretInteger: "3" + my_model_coef_225: + SecretInteger: "3" + my_model_coef_34: + SecretInteger: "3" + my_model_coef_416: + SecretInteger: "3" + my_input_51: + SecretInteger: "3" + my_input_250: + SecretInteger: "3" + my_input_93: + SecretInteger: "3" + my_model_coef_256: + SecretInteger: "3" + my_input_2: + SecretInteger: "3" + my_input_169: + SecretInteger: "3" + my_input_436: + SecretInteger: "3" + my_model_coef_438: + SecretInteger: "3" + my_input_257: + SecretInteger: "3" + my_model_coef_77: + SecretInteger: "3" + my_model_coef_51: + SecretInteger: "3" + my_model_coef_1: + SecretInteger: "3" + my_input_208: + SecretInteger: "3" + my_input_247: + SecretInteger: "3" + my_model_coef_79: + SecretInteger: "3" + my_model_coef_43: + SecretInteger: "3" + my_model_coef_56: + SecretInteger: "3" + my_model_coef_320: + SecretInteger: "3" + my_model_coef_378: + SecretInteger: "3" + my_input_196: + SecretInteger: "3" + my_input_244: + SecretInteger: "3" + my_model_coef_125: + SecretInteger: "3" + my_input_292: + SecretInteger: "3" + my_input_251: + SecretInteger: "3" + my_input_353: + SecretInteger: "3" + my_input_475: + SecretInteger: "3" + my_model_coef_385: + SecretInteger: "3" + my_input_54: + SecretInteger: "3" + my_input_249: + SecretInteger: "3" + my_model_coef_247: + SecretInteger: "3" + my_input_186: + SecretInteger: "3" + my_model_coef_8: + SecretInteger: "3" + my_model_coef_334: + SecretInteger: "3" + my_input_303: + SecretInteger: "3" + my_model_coef_300: + SecretInteger: "3" + my_model_coef_108: + SecretInteger: "3" + my_model_coef_205: + SecretInteger: "3" + my_input_9: + SecretInteger: "3" + my_input_129: + SecretInteger: "3" + my_input_143: + SecretInteger: "3" + my_input_295: + SecretInteger: "3" + my_input_239: + SecretInteger: "3" + my_model_coef_49: + SecretInteger: "3" + my_input_355: + SecretInteger: "3" + my_model_coef_331: + SecretInteger: "3" + my_input_119: + SecretInteger: "3" + my_input_471: + SecretInteger: "3" + my_model_coef_32: + SecretInteger: "3" + my_model_coef_469: + SecretInteger: "3" + my_model_coef_109: + SecretInteger: "3" + my_input_380: + SecretInteger: "3" + my_model_coef_99: + SecretInteger: "3" + my_input_366: + SecretInteger: "3" + my_input_112: + SecretInteger: "3" + my_input_223: + SecretInteger: "3" + my_model_coef_65: + SecretInteger: "3" + my_input_148: + SecretInteger: "3" + my_input_400: + SecretInteger: "3" + my_model_coef_279: + SecretInteger: "3" + my_model_coef_382: + SecretInteger: "3" + my_input_478: + SecretInteger: "3" + my_model_coef_276: + SecretInteger: "3" + my_input_100: + SecretInteger: "3" + my_model_coef_229: + SecretInteger: "3" + my_model_coef_159: + SecretInteger: "3" + my_input_173: + SecretInteger: "3" + my_input_276: + SecretInteger: "3" + my_input_447: + SecretInteger: "3" + my_model_coef_136: + SecretInteger: "3" + my_input_205: + SecretInteger: "3" + my_model_coef_76: + SecretInteger: "3" + my_input_313: + SecretInteger: "3" + my_model_coef_131: + SecretInteger: "3" + my_model_coef_216: + SecretInteger: "3" + my_input_423: + SecretInteger: "3" + my_input_123: + SecretInteger: "3" + my_input_192: + SecretInteger: "3" + my_input_271: + SecretInteger: "3" + my_input_422: + SecretInteger: "3" + my_model_coef_426: + SecretInteger: "3" + my_input_477: + SecretInteger: "3" + my_input_94: + SecretInteger: "3" + my_model_coef_60: + SecretInteger: "3" + my_model_coef_370: + SecretInteger: "3" + my_model_coef_290: + SecretInteger: "3" + my_model_coef_368: + SecretInteger: "3" + my_model_coef_434: + SecretInteger: "3" + my_input_168: + SecretInteger: "3" + my_input_299: + SecretInteger: "3" + my_model_coef_152: + SecretInteger: "3" + my_input_137: + SecretInteger: "3" + my_model_coef_130: + SecretInteger: "3" + my_model_coef_466: + SecretInteger: "3" + my_model_coef_394: + SecretInteger: "3" + my_model_coef_169: + SecretInteger: "3" + my_model_coef_381: + SecretInteger: "3" + my_model_coef_93: + SecretInteger: "3" + my_model_coef_475: + SecretInteger: "3" + my_model_coef_204: + SecretInteger: "3" + my_model_coef_233: + SecretInteger: "3" + my_input_485: + SecretInteger: "3" + my_model_coef_11: + SecretInteger: "3" + my_input_341: + SecretInteger: "3" + my_input_152: + SecretInteger: "3" + my_input_225: + SecretInteger: "3" + my_model_coef_66: + SecretInteger: "3" + my_model_coef_273: + SecretInteger: "3" + my_model_coef_124: + SecretInteger: "3" + my_model_coef_97: + SecretInteger: "3" + my_input_229: + SecretInteger: "3" + my_model_coef_422: + SecretInteger: "3" + my_input_8: + SecretInteger: "3" + my_input_325: + SecretInteger: "3" + my_model_coef_85: + SecretInteger: "3" + my_model_coef_24: + SecretInteger: "3" + my_input_327: + SecretInteger: "3" + my_input_386: + SecretInteger: "3" + my_input_290: + SecretInteger: "3" + my_model_coef_308: + SecretInteger: "3" + my_input_43: + SecretInteger: "3" + my_input_201: + SecretInteger: "3" + my_model_coef_71: + SecretInteger: "3" + my_input_424: + SecretInteger: "3" + my_model_coef_454: + SecretInteger: "3" + my_input_350: + SecretInteger: "3" + my_input_167: + SecretInteger: "3" + my_model_coef_207: + SecretInteger: "3" + my_model_coef_419: + SecretInteger: "3" + my_input_39: + SecretInteger: "3" + my_model_coef_374: + SecretInteger: "3" + my_model_coef_317: + SecretInteger: "3" + my_model_coef_333: + SecretInteger: "3" + my_model_coef_220: + SecretInteger: "3" + my_model_coef_183: + SecretInteger: "3" + my_model_coef_106: + SecretInteger: "3" + my_input_41: + SecretInteger: "3" + my_input_275: + SecretInteger: "3" + my_model_coef_123: + SecretInteger: "3" + my_input_390: + SecretInteger: "3" + my_model_coef_147: + SecretInteger: "3" + my_model_coef_57: + SecretInteger: "3" + my_input_263: + SecretInteger: "3" + my_model_coef_406: + SecretInteger: "3" + my_input_36: + SecretInteger: "3" + my_input_486: + SecretInteger: "3" + my_model_coef_84: + SecretInteger: "3" + my_input_372: + SecretInteger: "3" + my_model_coef_192: + SecretInteger: "3" + my_model_coef_404: + SecretInteger: "3" + my_input_338: + SecretInteger: "3" + my_model_coef_64: + SecretInteger: "3" + my_model_coef_330: + SecretInteger: "3" + my_model_coef_411: + SecretInteger: "3" + my_input_274: + SecretInteger: "3" + my_input_446: + SecretInteger: "3" + my_input_214: + SecretInteger: "3" + my_model_coef_40: + SecretInteger: "3" + my_model_coef_110: + SecretInteger: "3" + my_input_56: + SecretInteger: "3" + my_input_111: + SecretInteger: "3" + my_input_252: + SecretInteger: "3" + my_input_461: + SecretInteger: "3" + my_model_coef_494: + SecretInteger: "3" + my_input_71: + SecretInteger: "3" + my_model_coef_12: + SecretInteger: "3" + my_model_coef_215: + SecretInteger: "3" + my_model_coef_253: + SecretInteger: "3" + my_model_coef_140: + SecretInteger: "3" + my_model_coef_262: + SecretInteger: "3" + my_input_318: + SecretInteger: "3" + my_model_coef_468: + SecretInteger: "3" + my_input_108: + SecretInteger: "3" + my_input_136: + SecretInteger: "3" + my_input_179: + SecretInteger: "3" + my_model_coef_230: + SecretInteger: "3" + my_input_389: + SecretInteger: "3" + my_model_coef_176: + SecretInteger: "3" + my_input_14: + SecretInteger: "3" + my_model_intercept_0: + SecretInteger: "3" + my_input_200: + SecretInteger: "3" + my_input_246: + SecretInteger: "3" + my_model_coef_239: + SecretInteger: "3" + my_input_30: + SecretInteger: "3" + my_model_coef_82: + SecretInteger: "3" + my_input_444: + SecretInteger: "3" + my_model_coef_471: + SecretInteger: "3" + my_input_488: + SecretInteger: "3" + my_model_coef_371: + SecretInteger: "3" + my_input_170: + SecretInteger: "3" + my_input_261: + SecretInteger: "3" + my_model_coef_498: + SecretInteger: "3" + my_model_coef_127: + SecretInteger: "3" + my_model_coef_314: + SecretInteger: "3" + my_input_50: + SecretInteger: "3" + my_input_216: + SecretInteger: "3" + my_model_coef_499: + SecretInteger: "3" + my_input_165: + SecretInteger: "3" + my_input_220: + SecretInteger: "3" + my_model_coef_249: + SecretInteger: "3" + my_input_132: + SecretInteger: "3" + my_input_7: + SecretInteger: "3" + my_model_coef_293: + SecretInteger: "3" + my_model_coef_74: + SecretInteger: "3" + my_input_11: + SecretInteger: "3" + my_model_coef_436: + SecretInteger: "3" + my_model_coef_299: + SecretInteger: "3" + my_model_coef_154: + SecretInteger: "3" + my_input_328: + SecretInteger: "3" + my_input_430: + SecretInteger: "3" + my_model_coef_156: + SecretInteger: "3" + my_model_coef_41: + SecretInteger: "3" + my_model_coef_497: + SecretInteger: "3" + my_model_coef_263: + SecretInteger: "3" + my_model_coef_224: + SecretInteger: "3" + my_model_coef_345: + SecretInteger: "3" + my_model_coef_3: + SecretInteger: "3" + my_input_288: + SecretInteger: "3" + my_model_coef_168: + SecretInteger: "3" + my_model_coef_377: + SecretInteger: "3" + my_input_308: + SecretInteger: "3" + my_model_coef_356: + SecretInteger: "3" + my_model_coef_283: + SecretInteger: "3" + my_model_coef_280: + SecretInteger: "3" + my_model_coef_335: + SecretInteger: "3" + my_input_384: + SecretInteger: "3" + my_input_307: + SecretInteger: "3" + my_input_343: + SecretInteger: "3" + my_input_301: + SecretInteger: "3" + my_model_coef_259: + SecretInteger: "3" + my_model_coef_284: + SecretInteger: "3" + my_model_coef_361: + SecretInteger: "3" + my_model_coef_351: + SecretInteger: "3" + my_model_coef_363: + SecretInteger: "3" + my_input_467: + SecretInteger: "3" + my_input_176: + SecretInteger: "3" + my_input_397: + SecretInteger: "3" + my_input_268: + SecretInteger: "3" + my_input_379: + SecretInteger: "3" + my_model_coef_141: + SecretInteger: "3" + my_model_coef_231: + SecretInteger: "3" + my_input_326: + SecretInteger: "3" + my_model_coef_417: + SecretInteger: "3" + my_input_102: + SecretInteger: "3" + my_model_coef_301: + SecretInteger: "3" + my_input_269: + SecretInteger: "3" + my_model_coef_35: + SecretInteger: "3" + my_model_coef_288: + SecretInteger: "3" + my_input_159: + SecretInteger: "3" + my_model_coef_410: + SecretInteger: "3" + my_model_coef_122: + SecretInteger: "3" + my_input_68: + SecretInteger: "3" + my_model_coef_175: + SecretInteger: "3" + my_input_212: + SecretInteger: "3" + my_model_coef_2: + SecretInteger: "3" + my_model_coef_135: + SecretInteger: "3" + my_model_coef_486: + SecretInteger: "3" + my_input_156: + SecretInteger: "3" + my_input_236: + SecretInteger: "3" + my_input_153: + SecretInteger: "3" + my_model_coef_115: + SecretInteger: "3" + my_input_293: + SecretInteger: "3" + my_model_coef_337: + SecretInteger: "3" + my_input_312: + SecretInteger: "3" + my_input_374: + SecretInteger: "3" + my_input_363: + SecretInteger: "3" + my_model_coef_459: + SecretInteger: "3" + my_model_coef_111: + SecretInteger: "3" + my_model_coef_495: + SecretInteger: "3" + my_input_13: + SecretInteger: "3" + my_input_89: + SecretInteger: "3" + my_model_coef_250: + SecretInteger: "3" + my_input_226: + SecretInteger: "3" + my_model_coef_372: + SecretInteger: "3" + my_input_240: + SecretInteger: "3" + my_input_468: + SecretInteger: "3" + my_model_coef_48: + SecretInteger: "3" + my_model_coef_461: + SecretInteger: "3" + my_input_126: + SecretInteger: "3" + my_input_177: + SecretInteger: "3" + my_model_coef_203: + SecretInteger: "3" + my_model_coef_52: + SecretInteger: "3" + my_model_coef_295: + SecretInteger: "3" + my_input_106: + SecretInteger: "3" + my_model_coef_214: + SecretInteger: "3" + my_model_coef_142: + SecretInteger: "3" + my_input_460: + SecretInteger: "3" + my_model_coef_185: + SecretInteger: "3" + my_model_coef_414: + SecretInteger: "3" + my_model_coef_442: + SecretInteger: "3" + my_input_3: + SecretInteger: "3" + my_model_coef_23: + SecretInteger: "3" + my_input_245: + SecretInteger: "3" + my_input_499: + SecretInteger: "3" + my_model_coef_483: + SecretInteger: "3" + my_input_474: + SecretInteger: "3" + my_model_coef_104: + SecretInteger: "3" + my_model_coef_298: + SecretInteger: "3" + my_input_233: + SecretInteger: "3" + my_input_362: + SecretInteger: "3" + my_model_coef_196: + SecretInteger: "3" + my_model_coef_105: + SecretInteger: "3" + my_model_coef_477: + SecretInteger: "3" + my_input_280: + SecretInteger: "3" + my_input_166: + SecretInteger: "3" + my_model_coef_107: + SecretInteger: "3" + my_input_128: + SecretInteger: "3" + my_model_coef_445: + SecretInteger: "3" + my_input_57: + SecretInteger: "3" + my_input_248: + SecretInteger: "3" + my_model_coef_14: + SecretInteger: "3" + my_model_coef_113: + SecretInteger: "3" + my_input_289: + SecretInteger: "3" + my_input_48: + SecretInteger: "3" + my_input_406: + SecretInteger: "3" + my_input_429: + SecretInteger: "3" + my_input_399: + SecretInteger: "3" + my_input_72: + SecretInteger: "3" + my_input_96: + SecretInteger: "3" + my_input_228: + SecretInteger: "3" + my_input_258: + SecretInteger: "3" + my_model_coef_80: + SecretInteger: "3" + my_model_coef_208: + SecretInteger: "3" + my_model_coef_221: + SecretInteger: "3" + my_input_483: + SecretInteger: "3" + my_model_coef_88: + SecretInteger: "3" + my_input_381: + SecretInteger: "3" + my_input_38: + SecretInteger: "3" + my_model_coef_179: + SecretInteger: "3" + my_model_coef_166: + SecretInteger: "3" + my_model_coef_433: + SecretInteger: "3" + my_input_61: + SecretInteger: "3" + my_input_452: + SecretInteger: "3" + my_model_coef_83: + SecretInteger: "3" + my_input_189: + SecretInteger: "3" + my_model_coef_58: + SecretInteger: "3" + my_input_27: + SecretInteger: "3" + my_input_451: + SecretInteger: "3" + my_model_coef_297: + SecretInteger: "3" + my_input_329: + SecretInteger: "3" + my_model_coef_133: + SecretInteger: "3" + my_input_115: + SecretInteger: "3" + my_model_coef_198: + SecretInteger: "3" + my_input_243: + SecretInteger: "3" + my_model_coef_395: + SecretInteger: "3" + my_input_107: + SecretInteger: "3" + my_model_coef_412: + SecretInteger: "3" + my_input_81: + SecretInteger: "3" + my_input_160: + SecretInteger: "3" + my_model_coef_452: + SecretInteger: "3" + my_input_322: + SecretInteger: "3" + my_model_coef_195: + SecretInteger: "3" + my_model_coef_164: + SecretInteger: "3" + my_input_23: + SecretInteger: "3" + my_input_75: + SecretInteger: "3" + my_model_coef_46: + SecretInteger: "3" + my_input_222: + SecretInteger: "3" + my_model_coef_100: + SecretInteger: "3" + my_input_32: + SecretInteger: "3" + my_model_coef_190: + SecretInteger: "3" + my_input_185: + SecretInteger: "3" + my_input_344: + SecretInteger: "3" + my_model_coef_413: + SecretInteger: "3" + my_model_coef_402: + SecretInteger: "3" + my_model_coef_59: + SecretInteger: "3" + my_model_coef_218: + SecretInteger: "3" + my_input_428: + SecretInteger: "3" + my_model_coef_26: + SecretInteger: "3" + my_input_204: + SecretInteger: "3" + my_input_197: + SecretInteger: "3" + my_model_coef_31: + SecretInteger: "3" + my_input_157: + SecretInteger: "3" + my_model_coef_75: + SecretInteger: "3" + my_input_378: + SecretInteger: "3" + my_model_coef_213: + SecretInteger: "3" + my_model_coef_30: + SecretInteger: "3" + my_model_coef_476: + SecretInteger: "3" + my_model_coef_305: + SecretInteger: "3" + my_model_coef_386: + SecretInteger: "3" + my_model_coef_158: + SecretInteger: "3" + my_input_45: + SecretInteger: "3" + my_model_coef_149: + SecretInteger: "3" + my_input_77: + SecretInteger: "3" + my_model_coef_325: + SecretInteger: "3" + my_input_262: + SecretInteger: "3" + my_input_449: + SecretInteger: "3" + my_input_473: + SecretInteger: "3" + my_model_coef_349: + SecretInteger: "3" + my_model_coef_90: + SecretInteger: "3" + my_model_coef_304: + SecretInteger: "3" + my_model_coef_428: + SecretInteger: "3" + my_input_4: + SecretInteger: "3" + my_model_coef_277: + SecretInteger: "3" + my_model_coef_307: + SecretInteger: "3" + my_input_99: + SecretInteger: "3" + my_input_122: + SecretInteger: "3" + my_model_coef_271: + SecretInteger: "3" + my_model_coef_367: + SecretInteger: "3" + my_input_37: + SecretInteger: "3" + my_model_coef_161: + SecretInteger: "3" + my_input_44: + SecretInteger: "3" + my_input_285: + SecretInteger: "3" + my_model_coef_37: + SecretInteger: "3" + my_model_coef_373: + SecretInteger: "3" + my_model_coef_375: + SecretInteger: "3" + my_input_278: + SecretInteger: "3" + my_input_490: + SecretInteger: "3" + my_model_coef_358: + SecretInteger: "3" + my_model_coef_294: + SecretInteger: "3" + my_input_442: + SecretInteger: "3" + my_input_235: + SecretInteger: "3" + my_input_445: + SecretInteger: "3" + my_input_113: + SecretInteger: "3" + my_model_coef_118: + SecretInteger: "3" + my_input_310: + SecretInteger: "3" + my_model_coef_210: + SecretInteger: "3" + my_input_302: + SecretInteger: "3" + my_input_82: + SecretInteger: "3" + my_model_coef_258: + SecretInteger: "3" + my_model_coef_481: + SecretInteger: "3" + my_input_104: + SecretInteger: "3" + my_input_360: + SecretInteger: "3" + my_model_coef_296: + SecretInteger: "3" + my_input_323: + SecretInteger: "3" + my_model_coef_25: + SecretInteger: "3" + my_model_coef_474: + SecretInteger: "3" + my_input_432: + SecretInteger: "3" + my_model_coef_291: + SecretInteger: "3" + my_input_234: + SecretInteger: "3" + my_input_66: + SecretInteger: "3" + my_input_404: + SecretInteger: "3" + my_input_144: + SecretInteger: "3" + my_input_207: + SecretInteger: "3" + my_input_49: + SecretInteger: "3" + my_input_371: + SecretInteger: "3" + my_input_466: + SecretInteger: "3" + my_model_coef_455: + SecretInteger: "3" + my_input_20: + SecretInteger: "3" + my_input_286: + SecretInteger: "3" + my_input_319: + SecretInteger: "3" + my_input_230: + SecretInteger: "3" + my_input_300: + SecretInteger: "3" + my_input_403: + SecretInteger: "3" + my_model_coef_237: + SecretInteger: "3" + my_model_coef_174: + SecretInteger: "3" + my_model_coef_418: + SecretInteger: "3" + my_model_coef_270: + SecretInteger: "3" + my_input_29: + SecretInteger: "3" + my_model_coef_440: + SecretInteger: "3" + my_model_coef_310: + SecretInteger: "3" + my_model_coef_460: + SecretInteger: "3" + my_model_coef_479: + SecretInteger: "3" + my_input_448: + SecretInteger: "3" + my_model_coef_151: + SecretInteger: "3" + my_input_373: + SecretInteger: "3" + my_input_138: + SecretInteger: "3" + my_input_118: + SecretInteger: "3" + my_input_142: + SecretInteger: "3" + my_model_coef_467: + SecretInteger: "3" + my_input_16: + SecretInteger: "3" + my_input_26: + SecretInteger: "3" + my_input_58: + SecretInteger: "3" + my_input_259: + SecretInteger: "3" + my_model_coef_6: + SecretInteger: "3" + my_model_coef_193: + SecretInteger: "3" + my_input_407: + SecretInteger: "3" + my_model_coef_286: + SecretInteger: "3" + my_input_15: + SecretInteger: "3" + my_input_368: + SecretInteger: "3" + my_input_298: + SecretInteger: "3" + my_input_401: + SecretInteger: "3" + my_input_121: + SecretInteger: "3" + my_model_coef_235: + SecretInteger: "3" + my_input_260: + SecretInteger: "3" + my_model_coef_448: + SecretInteger: "3" + my_model_coef_9: + SecretInteger: "3" + my_model_coef_55: + SecretInteger: "3" + my_model_coef_150: + SecretInteger: "3" + my_input_296: + SecretInteger: "3" + my_model_coef_22: + SecretInteger: "3" + my_input_284: + SecretInteger: "3" + my_model_coef_264: + SecretInteger: "3" + my_model_coef_485: + SecretInteger: "3" + my_model_coef_68: + SecretInteger: "3" + my_model_coef_409: + SecretInteger: "3" + my_input_320: + SecretInteger: "3" + my_input_492: + SecretInteger: "3" + my_model_coef_155: + SecretInteger: "3" + my_input_141: + SecretInteger: "3" + my_input_273: + SecretInteger: "3" + my_model_coef_206: + SecretInteger: "3" + my_input_195: + SecretInteger: "3" + my_input_385: + SecretInteger: "3" + my_model_coef_117: + SecretInteger: "3" + my_input_103: + SecretInteger: "3" + my_model_coef_7: + SecretInteger: "3" + my_input_357: + SecretInteger: "3" + my_model_coef_132: + SecretInteger: "3" + my_input_352: + SecretInteger: "3" + my_model_coef_451: + SecretInteger: "3" + my_input_287: + SecretInteger: "3" + my_input_134: + SecretInteger: "3" + my_input_439: + SecretInteger: "3" + my_input_279: + SecretInteger: "3" + my_model_coef_36: + SecretInteger: "3" + my_model_coef_309: + SecretInteger: "3" + my_model_coef_464: + SecretInteger: "3" + my_model_coef_287: + SecretInteger: "3" + my_model_coef_227: + SecretInteger: "3" + my_input_95: + SecretInteger: "3" + my_model_coef_20: + SecretInteger: "3" + my_model_coef_390: + SecretInteger: "3" + my_model_coef_244: + SecretInteger: "3" + my_model_coef_347: + SecretInteger: "3" + my_model_coef_470: + SecretInteger: "3" + my_model_coef_139: + SecretInteger: "3" + my_input_31: + SecretInteger: "3" + my_input_351: + SecretInteger: "3" + my_model_coef_245: + SecretInteger: "3" + my_model_coef_359: + SecretInteger: "3" + my_input_382: + SecretInteger: "3" + my_input_265: + SecretInteger: "3" + my_input_480: + SecretInteger: "3" + my_model_coef_162: + SecretInteger: "3" + my_input_479: + SecretInteger: "3" + my_input_493: + SecretInteger: "3" + my_input_347: + SecretInteger: "3" + my_input_331: + SecretInteger: "3" + my_model_coef_209: + SecretInteger: "3" + my_model_coef_490: + SecretInteger: "3" + my_model_coef_266: + SecretInteger: "3" + my_model_coef_322: + SecretInteger: "3" + my_model_coef_145: + SecretInteger: "3" + my_input_270: + SecretInteger: "3" + my_model_coef_18: + SecretInteger: "3" + my_model_coef_343: + SecretInteger: "3" + my_input_304: + SecretInteger: "3" + my_input_464: + SecretInteger: "3" + my_model_coef_86: + SecretInteger: "3" + my_model_coef_95: + SecretInteger: "3" + my_input_34: + SecretInteger: "3" + my_input_272: + SecretInteger: "3" + my_model_coef_170: + SecretInteger: "3" + my_input_140: + SecretInteger: "3" + my_model_coef_184: + SecretInteger: "3" + my_model_coef_143: + SecretInteger: "3" + my_model_coef_275: + SecretInteger: "3" + my_model_coef_407: + SecretInteger: "3" + my_model_coef_13: + SecretInteger: "3" + my_model_coef_439: + SecretInteger: "3" + my_input_393: + SecretInteger: "3" + my_input_311: + SecretInteger: "3" + my_input_336: + SecretInteger: "3" + my_input_453: + SecretInteger: "3" + my_model_coef_444: + SecretInteger: "3" + my_model_coef_28: + SecretInteger: "3" + my_model_coef_316: + SecretInteger: "3" + my_model_coef_312: + SecretInteger: "3" + my_model_coef_63: + SecretInteger: "3" + my_model_coef_181: + SecretInteger: "3" + my_model_coef_255: + SecretInteger: "3" + my_model_coef_121: + SecretInteger: "3" + my_input_255: + SecretInteger: "3" + my_input_213: + SecretInteger: "3" + my_input_59: + SecretInteger: "3" + my_model_coef_352: + SecretInteger: "3" + my_input_5: + SecretInteger: "3" + my_model_coef_173: + SecretInteger: "3" + my_model_coef_327: + SecretInteger: "3" + my_model_coef_450: + SecretInteger: "3" + my_input_83: + SecretInteger: "3" + my_input_97: + SecretInteger: "3" + my_input_40: + SecretInteger: "3" + my_model_coef_42: + SecretInteger: "3" + my_input_487: + SecretInteger: "3" + my_input_206: + SecretInteger: "3" + my_input_414: + SecretInteger: "3" + my_model_coef_456: + SecretInteger: "3" + my_input_24: + SecretInteger: "3" + my_model_coef_423: + SecretInteger: "3" + my_input_164: + SecretInteger: "3" + my_input_314: + SecretInteger: "3" + my_input_409: + SecretInteger: "3" + my_input_454: + SecretInteger: "3" + my_model_coef_292: + SecretInteger: "3" + my_input_433: + SecretInteger: "3" + my_model_coef_357: + SecretInteger: "3" + my_model_coef_365: + SecretInteger: "3" + my_model_coef_96: + SecretInteger: "3" + my_model_coef_396: + SecretInteger: "3" + my_input_10: + SecretInteger: "3" + my_model_coef_186: + SecretInteger: "3" + my_input_395: + SecretInteger: "3" + my_model_coef_188: + SecretInteger: "3" + my_input_484: + SecretInteger: "3" + my_model_coef_211: + SecretInteger: "3" + my_model_coef_228: + SecretInteger: "3" + my_model_coef_441: + SecretInteger: "3" + my_model_coef_236: + SecretInteger: "3" + my_model_coef_274: + SecretInteger: "3" + my_input_297: + SecretInteger: "3" + my_model_coef_282: + SecretInteger: "3" + my_input_64: + SecretInteger: "3" + my_input_435: + SecretInteger: "3" + my_model_coef_223: + SecretInteger: "3" + my_model_coef_306: + SecretInteger: "3" + my_model_coef_388: + SecretInteger: "3" + my_model_coef_472: + SecretInteger: "3" + my_input_90: + SecretInteger: "3" + my_model_coef_278: + SecretInteger: "3" + my_input_392: + SecretInteger: "3" + my_input_494: + SecretInteger: "3" + my_input_199: + SecretInteger: "3" + my_input_210: + SecretInteger: "3" + my_input_0: + SecretInteger: "3" + my_model_coef_348: + SecretInteger: "3" + my_model_coef_342: + SecretInteger: "3" + my_model_coef_232: + SecretInteger: "3" + my_model_coef_353: + SecretInteger: "3" + my_model_coef_313: + SecretInteger: "3" + my_model_coef_0: + SecretInteger: "3" + my_model_coef_128: + SecretInteger: "3" + my_model_coef_285: + SecretInteger: "3" + my_input_70: + SecretInteger: "3" + my_model_coef_315: + SecretInteger: "3" + my_model_coef_392: + SecretInteger: "3" + my_input_388: + SecretInteger: "3" + my_model_coef_482: + SecretInteger: "3" + my_model_coef_457: + SecretInteger: "3" + my_model_coef_102: + SecretInteger: "3" + my_input_305: + SecretInteger: "3" + my_model_coef_4: + SecretInteger: "3" + my_model_coef_92: + SecretInteger: "3" + my_model_coef_241: + SecretInteger: "3" + my_input_282: + SecretInteger: "3" + my_input_264: + SecretInteger: "3" + my_model_coef_324: + SecretInteger: "3" + my_model_coef_391: + SecretInteger: "3" + my_model_coef_261: + SecretInteger: "3" + my_model_coef_187: + SecretInteger: "3" + my_input_316: + SecretInteger: "3" + my_input_333: + SecretInteger: "3" + my_input_1: + SecretInteger: "3" + my_input_415: + SecretInteger: "3" + my_input_242: + SecretInteger: "3" + my_model_coef_366: + SecretInteger: "3" + my_model_coef_432: + SecretInteger: "3" + my_model_coef_126: + SecretInteger: "3" + my_input_266: + SecretInteger: "3" + my_input_434: + SecretInteger: "3" + my_model_coef_242: + SecretInteger: "3" + my_input_402: + SecretInteger: "3" + my_model_coef_69: + SecretInteger: "3" + my_input_221: + SecretInteger: "3" + my_input_345: + SecretInteger: "3" + my_model_coef_202: + SecretInteger: "3" + my_model_coef_53: + SecretInteger: "3" + my_input_317: + SecretInteger: "3" + my_input_256: + SecretInteger: "3" + my_input_184: + SecretInteger: "3" + my_model_coef_420: + SecretInteger: "3" + my_input_74: + SecretInteger: "3" + my_model_coef_27: + SecretInteger: "3" + my_input_437: + SecretInteger: "3" + my_input_124: + SecretInteger: "3" + my_model_coef_234: + SecretInteger: "3" + my_model_coef_243: + SecretInteger: "3" + my_input_419: + SecretInteger: "3" + my_input_411: + SecretInteger: "3" + my_input_158: + SecretInteger: "3" + my_model_coef_424: + SecretInteger: "3" + my_input_19: + SecretInteger: "3" + my_input_227: + SecretInteger: "3" + my_model_coef_91: + SecretInteger: "3" + my_model_coef_401: + SecretInteger: "3" + my_model_coef_98: + SecretInteger: "3" + my_model_coef_427: + SecretInteger: "3" + my_input_342: + SecretInteger: "3" + my_model_coef_103: + SecretInteger: "3" + my_model_coef_252: + SecretInteger: "3" + my_model_coef_67: + SecretInteger: "3" + my_input_211: + SecretInteger: "3" + my_input_182: + SecretInteger: "3" + my_model_coef_332: + SecretInteger: "3" + my_model_coef_200: + SecretInteger: "3" + my_input_52: + SecretInteger: "3" + my_input_209: + SecretInteger: "3" + my_input_440: + SecretInteger: "3" + my_model_coef_303: + SecretInteger: "3" + my_input_425: + SecretInteger: "3" + my_model_coef_379: + SecretInteger: "3" + my_model_coef_360: + SecretInteger: "3" + my_model_coef_488: + SecretInteger: "3" + my_input_455: + SecretInteger: "3" + my_model_coef_269: + SecretInteger: "3" + my_model_coef_73: + SecretInteger: "3" + my_model_coef_10: + SecretInteger: "3" + my_model_coef_449: + SecretInteger: "3" + my_model_coef_397: + SecretInteger: "3" + my_input_62: + SecretInteger: "3" + my_model_coef_167: + SecretInteger: "3" + my_model_coef_160: + SecretInteger: "3" + my_model_coef_217: + SecretInteger: "3" + my_input_202: + SecretInteger: "3" + my_model_coef_329: + SecretInteger: "3" + my_input_241: + SecretInteger: "3" + my_input_105: + SecretInteger: "3" + my_input_391: + SecretInteger: "3" + my_model_coef_222: + SecretInteger: "3" + my_input_117: + SecretInteger: "3" + my_input_150: + SecretInteger: "3" + my_model_coef_29: + SecretInteger: "3" + my_model_coef_146: + SecretInteger: "3" + my_input_383: + SecretInteger: "3" + my_model_coef_399: + SecretInteger: "3" + my_input_120: + SecretInteger: "3" + my_input_224: + SecretInteger: "3" + my_input_418: + SecretInteger: "3" + my_model_coef_50: + SecretInteger: "3" + my_model_coef_403: + SecretInteger: "3" + my_input_491: + SecretInteger: "3" + my_model_coef_364: + SecretInteger: "3" + my_model_coef_144: + SecretInteger: "3" + my_model_coef_400: + SecretInteger: "3" + my_input_67: + SecretInteger: "3" + my_input_217: + SecretInteger: "3" + my_input_369: + SecretInteger: "3" + my_model_coef_267: + SecretInteger: "3" + my_input_441: + SecretInteger: "3" + my_input_496: + SecretInteger: "3" + my_model_coef_226: + SecretInteger: "3" + my_input_135: + SecretInteger: "3" + my_input_188: + SecretInteger: "3" + my_model_coef_354: + SecretInteger: "3" + my_model_coef_446: + SecretInteger: "3" + my_model_coef_72: + SecretInteger: "3" + my_input_354: + SecretInteger: "3" + my_input_73: + SecretInteger: "3" + my_model_coef_21: + SecretInteger: "3" + my_model_coef_54: + SecretInteger: "3" + my_model_coef_421: + SecretInteger: "3" + my_input_458: + SecretInteger: "3" + my_model_coef_480: + SecretInteger: "3" + my_input_79: + SecretInteger: "3" + my_model_coef_447: + SecretInteger: "3" + my_input_133: + SecretInteger: "3" + my_input_294: + SecretInteger: "3" + my_input_365: + SecretInteger: "3" + my_input_421: + SecretInteger: "3" + my_model_coef_189: + SecretInteger: "3" + my_model_coef_197: + SecretInteger: "3" + my_model_coef_268: + SecretInteger: "3" + my_model_coef_326: + SecretInteger: "3" + my_input_85: + SecretInteger: "3" + my_input_375: + SecretInteger: "3" + my_model_coef_114: + SecretInteger: "3" + my_model_coef_246: + SecretInteger: "3" + my_input_87: + SecretInteger: "3" + my_input_162: + SecretInteger: "3" + my_model_coef_478: + SecretInteger: "3" + my_input_330: + SecretInteger: "3" + my_input_110: + SecretInteger: "3" + my_input_283: + SecretInteger: "3" + my_input_469: + SecretInteger: "3" + my_model_coef_191: + SecretInteger: "3" + my_input_76: + SecretInteger: "3" + my_model_coef_350: + SecretInteger: "3" + my_input_456: + SecretInteger: "3" + my_model_coef_489: + SecretInteger: "3" + my_input_470: + SecretInteger: "3" + my_model_coef_165: + SecretInteger: "3" + my_input_410: + SecretInteger: "3" + my_input_149: + SecretInteger: "3" + my_model_coef_318: + SecretInteger: "3" + my_input_151: + SecretInteger: "3" + my_model_coef_384: + SecretInteger: "3" + my_input_187: + SecretInteger: "3" + my_model_coef_38: + SecretInteger: "3" + my_model_coef_323: + SecretInteger: "3" + my_input_463: + SecretInteger: "3" + my_input_42: + SecretInteger: "3" + my_input_335: + SecretInteger: "3" + my_input_125: + SecretInteger: "3" + my_model_coef_341: + SecretInteger: "3" + my_model_coef_178: + SecretInteger: "3" + my_input_198: + SecretInteger: "3" + my_input_306: + SecretInteger: "3" + my_input_396: + SecretInteger: "3" + my_input_427: + SecretInteger: "3" + my_input_267: + SecretInteger: "3" + my_input_408: + SecretInteger: "3" + my_model_coef_138: + SecretInteger: "3" + my_input_17: + SecretInteger: "3" + my_input_481: + SecretInteger: "3" + my_model_coef_463: + SecretInteger: "3" + my_model_coef_70: + SecretInteger: "3" + my_input_413: + SecretInteger: "3" + my_model_coef_120: + SecretInteger: "3" + my_input_332: + SecretInteger: "3" + my_input_472: + SecretInteger: "3" + my_model_coef_437: + SecretInteger: "3" + my_model_coef_380: + SecretInteger: "3" + my_input_277: + SecretInteger: "3" + my_model_coef_376: + SecretInteger: "3" + my_input_98: + SecretInteger: "3" + my_input_253: + SecretInteger: "3" + my_input_18: + SecretInteger: "3" + my_input_84: + SecretInteger: "3" + my_input_80: + SecretInteger: "3" + my_input_349: + SecretInteger: "3" + my_input_438: + SecretInteger: "3" + my_input_178: + SecretInteger: "3" + my_model_coef_289: + SecretInteger: "3" + my_input_63: + SecretInteger: "3" + my_model_coef_5: + SecretInteger: "3" + my_model_coef_443: + SecretInteger: "3" + my_model_coef_172: + SecretInteger: "3" + my_input_154: + SecretInteger: "3" + my_model_coef_254: + SecretInteger: "3" + my_model_coef_339: + SecretInteger: "3" + my_model_coef_369: + SecretInteger: "3" + my_input_367: + SecretInteger: "3" + my_input_55: + SecretInteger: "3" + my_input_482: + SecretInteger: "3" + my_model_coef_19: + SecretInteger: "3" + my_model_coef_435: + SecretInteger: "3" + my_input_91: + SecretInteger: "3" + my_input_457: + SecretInteger: "3" + my_input_88: + SecretInteger: "3" + my_model_coef_94: + SecretInteger: "3" + my_input_348: + SecretInteger: "3" + my_model_coef_319: + SecretInteger: "3" + my_input_476: + SecretInteger: "3" + my_input_46: + SecretInteger: "3" + my_model_coef_336: + SecretInteger: "3" + my_input_116: + SecretInteger: "3" + my_input_465: + SecretInteger: "3" + my_model_coef_194: + SecretInteger: "3" + my_input_309: + SecretInteger: "3" + my_model_coef_238: + SecretInteger: "3" + my_model_coef_45: + SecretInteger: "3" + my_input_412: + SecretInteger: "3" + my_model_coef_302: + SecretInteger: "3" + my_model_coef_16: + SecretInteger: "3" + my_model_coef_265: + SecretInteger: "3" + my_model_coef_473: + SecretInteger: "3" + my_model_coef_425: + SecretInteger: "3" + my_input_22: + SecretInteger: "3" + my_input_364: + SecretInteger: "3" + my_input_161: + SecretInteger: "3" + my_input_231: + SecretInteger: "3" + my_model_coef_39: + SecretInteger: "3" + my_input_175: + SecretInteger: "3" + my_input_146: + SecretInteger: "3" + my_input_361: + SecretInteger: "3" + my_input_114: + SecretInteger: "3" + my_model_coef_17: + SecretInteger: "3" + my_input_337: + SecretInteger: "3" + my_model_coef_87: + SecretInteger: "3" + my_input_203: + SecretInteger: "3" + my_input_489: + SecretInteger: "3" + my_input_174: + SecretInteger: "3" + my_input_405: + SecretInteger: "3" + my_model_coef_157: + SecretInteger: "3" + my_input_155: + SecretInteger: "3" + my_input_334: + SecretInteger: "3" + my_model_coef_415: + SecretInteger: "3" + my_model_coef_240: + SecretInteger: "3" + my_model_coef_248: + SecretInteger: "3" + my_model_coef_148: + SecretInteger: "3" + my_input_35: + SecretInteger: "3" + my_input_86: + SecretInteger: "3" + my_model_coef_260: + SecretInteger: "3" + my_input_426: + SecretInteger: "3" + my_input_191: + SecretInteger: "3" + my_input_215: + SecretInteger: "3" + my_model_coef_153: + SecretInteger: "3" + my_model_coef_484: + SecretInteger: "3" + my_input_47: + SecretInteger: "3" + my_model_coef_338: + SecretInteger: "3" + my_input_394: + SecretInteger: "3" + my_input_450: + SecretInteger: "3" + my_input_147: + SecretInteger: "3" + my_input_358: + SecretInteger: "3" + my_model_coef_493: + SecretInteger: "3" + my_model_coef_251: + SecretInteger: "3" + my_model_coef_101: + SecretInteger: "3" + my_model_coef_62: + SecretInteger: "3" + my_input_346: + SecretInteger: "3" + my_model_coef_182: + SecretInteger: "3" + my_model_coef_408: + SecretInteger: "3" + my_model_coef_78: + SecretInteger: "3" + my_input_356: + SecretInteger: "3" + my_input_359: + SecretInteger: "3" + my_model_coef_321: + SecretInteger: "3" + my_input_131: + SecretInteger: "3" + my_model_coef_281: + SecretInteger: "3" + my_model_coef_453: + SecretInteger: "3" + my_model_coef_340: + SecretInteger: "3" + my_input_25: + SecretInteger: "3" + my_input_92: + SecretInteger: "3" + my_input_193: + SecretInteger: "3" + my_model_coef_344: + SecretInteger: "3" + my_model_coef_383: + SecretInteger: "3" + my_model_coef_465: + SecretInteger: "3" + my_model_coef_171: + SecretInteger: "3" + my_model_coef_112: + SecretInteger: "3" + my_model_coef_219: + SecretInteger: "3" + my_input_65: + SecretInteger: "3" + my_input_498: + SecretInteger: "3" + my_input_127: + SecretInteger: "3" + my_model_coef_61: + SecretInteger: "3" + my_input_218: + SecretInteger: "3" + my_input_219: + SecretInteger: "3" + my_model_coef_137: + SecretInteger: "3" + my_model_coef_44: + SecretInteger: "3" + my_model_coef_405: + SecretInteger: "3" + my_model_coef_487: + SecretInteger: "3" + my_model_coef_362: + SecretInteger: "3" + my_input_462: + SecretInteger: "3" + my_model_coef_15: + SecretInteger: "3" + my_model_coef_458: + SecretInteger: "3" + my_input_387: + SecretInteger: "3" + my_input_180: + SecretInteger: "3" + my_input_194: + SecretInteger: "3" + my_input_417: + SecretInteger: "3" + my_model_coef_177: + SecretInteger: "3" + my_input_370: + SecretInteger: "3" + my_input_321: + SecretInteger: "3" + my_model_coef_163: + SecretInteger: "3" + my_input_315: + SecretInteger: "3" + my_model_coef_47: + SecretInteger: "3" + my_input_376: + SecretInteger: "3" + my_model_coef_496: + SecretInteger: "3" + my_input_163: + SecretInteger: "3" + my_input_420: + SecretInteger: "3" + my_input_190: + SecretInteger: "3" + my_model_coef_119: + SecretInteger: "3" + my_input_53: + SecretInteger: "3" + my_input_139: + SecretInteger: "3" + my_input_21: + SecretInteger: "3" + my_input_281: + SecretInteger: "3" + public_variables: {} +expected_outputs: + logit_0: + SecretInteger: "3" diff --git a/nada_ai/linear_model/__init__.py b/nada_ai/linear_model/__init__.py index 5303cce..54ca9a6 100644 --- a/nada_ai/linear_model/__init__.py +++ b/nada_ai/linear_model/__init__.py @@ -1 +1 @@ -from .linear_regression import LinearRegression +from .linear_regression import LinearRegression, LogisticRegression diff --git a/nada_ai/linear_model/linear_regression.py b/nada_ai/linear_model/linear_regression.py index fefc9a4..eead976 100644 --- a/nada_ai/linear_model/linear_regression.py +++ b/nada_ai/linear_model/linear_regression.py @@ -34,3 +34,21 @@ def forward(self, x: na.NadaArray) -> na.NadaArray: if self.intercept is None: return self.coef @ x return self.coef @ x + self.intercept + + +class LogisticRegression(LinearRegression): + """Logistic regression implementation inheriting from LinearRegression""" + + def __init__( + self, in_features: int, out_features: int, include_bias: bool = True + ) -> None: + """ + Initialization. + + Args: + in_features (int): Number of input features to regression. + num_classes (int): Number of classes to predict. + include_bias (bool, optional): Whether or not to include a bias term. Defaults to True. + """ + self.coef = Parameter((out_features, in_features)) + self.intercept = Parameter(out_features) if include_bias else None diff --git a/poetry.lock b/poetry.lock index 5b99ba5..73d23ce 100644 --- a/poetry.lock +++ b/poetry.lock @@ -205,18 +205,18 @@ test = ["pytest (>=6)"] [[package]] name = "filelock" -version = "3.14.0" +version = "3.15.1" description = "A platform independent file lock." optional = false python-versions = ">=3.8" files = [ - {file = "filelock-3.14.0-py3-none-any.whl", hash = "sha256:43339835842f110ca7ae60f1e1c160714c5a6afd15a2873419ab185334975c0f"}, - {file = "filelock-3.14.0.tar.gz", hash = "sha256:6ea72da3be9b8c82afd3edcf99f2fffbb5076335a5ae4d03248bb5b6c3eae78a"}, + {file = "filelock-3.15.1-py3-none-any.whl", hash = "sha256:71b3102950e91dfc1bb4209b64be4dc8854f40e5f534428d8684f953ac847fac"}, + {file = "filelock-3.15.1.tar.gz", hash = "sha256:58a2549afdf9e02e10720eaa4d4470f56386d7a6f72edd7d0596337af8ed7ad8"}, ] [package.extras] docs = ["furo (>=2023.9.10)", "sphinx (>=7.2.6)", "sphinx-autodoc-typehints (>=1.25.2)"] -testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8.0.1)", "pytest (>=7.4.3)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"] +testing = ["covdefaults (>=2.3)", "coverage (>=7.3.2)", "diff-cover (>=8.0.1)", "pytest (>=7.4.3)", "pytest-asyncio (>=0.21)", "pytest-cov (>=4.1)", "pytest-mock (>=3.12)", "pytest-timeout (>=2.2)"] typing = ["typing-extensions (>=4.8)"] [[package]] @@ -739,6 +739,22 @@ doc = ["myst-nb (>=1.0)", "numpydoc (>=1.7)", "pillow (>=9.4)", "pydata-sphinx-t extra = ["lxml (>=4.6)", "pydot (>=2.0)", "pygraphviz (>=1.12)", "sympy (>=1.10)"] test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"] +[[package]] +name = "nillion-python-helpers" +version = "0.1.2" +description = "" +optional = false +python-versions = "<4.0,>=3.10" +files = [ + {file = "nillion_python_helpers-0.1.2-py3-none-any.whl", hash = "sha256:6cfda32d7122d00b343ebc3bc50068537c710beab57f835e026c5989a58d4b5b"}, + {file = "nillion_python_helpers-0.1.2.tar.gz", hash = "sha256:e6eb07517f048dc9410902e356d48ce64a535b60a4b60980c0dafaa28511aa87"}, +] + +[package.dependencies] +py-nillion-client = ">=0.2.1,<0.3.0" +pytest-asyncio = ">=0.23.7,<0.24.0" +python-dotenv = "1.0.0" + [[package]] name = "numpy" version = "1.26.4" @@ -1236,6 +1252,24 @@ tomli = {version = ">=1", markers = "python_version < \"3.11\""} [package.extras] dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"] +[[package]] +name = "pytest-asyncio" +version = "0.23.7" +description = "Pytest support for asyncio" +optional = false +python-versions = ">=3.8" +files = [ + {file = "pytest_asyncio-0.23.7-py3-none-any.whl", hash = "sha256:009b48127fbe44518a547bddd25611551b0e43ccdbf1e67d12479f569832c20b"}, + {file = "pytest_asyncio-0.23.7.tar.gz", hash = "sha256:5f5c72948f4c49e7db4f29f2521d4031f1c27f86e57b046126654083d4770268"}, +] + +[package.dependencies] +pytest = ">=7.0.0,<9" + +[package.extras] +docs = ["sphinx (>=5.3)", "sphinx-rtd-theme (>=1.0)"] +testing = ["coverage (>=6.2)", "hypothesis (>=5.7.1)"] + [[package]] name = "python-dateutil" version = "2.9.0.post0" @@ -1250,6 +1284,20 @@ files = [ [package.dependencies] six = ">=1.5" +[[package]] +name = "python-dotenv" +version = "1.0.0" +description = "Read key-value pairs from a .env file and set them as environment variables" +optional = false +python-versions = ">=3.8" +files = [ + {file = "python-dotenv-1.0.0.tar.gz", hash = "sha256:a8df96034aae6d2d50a4ebe8216326c61c3eb64836776504fcca410e5937a3ba"}, + {file = "python_dotenv-1.0.0-py3-none-any.whl", hash = "sha256:f5971a9226b701070a4bf2c38c89e5a3f0d64de8debda981d1db98583009122a"}, +] + +[package.extras] +cli = ["click (>=5.0)"] + [[package]] name = "pytz" version = "2024.1" @@ -1566,4 +1614,4 @@ files = [ [metadata] lock-version = "2.0" python-versions = "^3.10" -content-hash = "352c0a87c207737336e42778f8d9a574bbbda4f8f94b06883aa2fc20a137ad1a" +content-hash = "14724d6f4d986dca629d27865233912db153de2d00e8eabc7af5006318815e20" diff --git a/pyproject.toml b/pyproject.toml index b762363..2c4322c 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -14,7 +14,7 @@ prophet = "^1.1.5" nada-dsl = "^0.2.1" py-nillion-client = "^0.2.1" nada-algebra = "^0.3.4" - +nillion-python-helpers = "^0.1.2" [tool.poetry.group.dev.dependencies] pytest = "^8.2.0" @@ -23,4 +23,4 @@ pandas = "^2.2.2" [build-system] requires = ["poetry-core"] -build-backend = "poetry.core.masonry.api" \ No newline at end of file +build-backend = "poetry.core.masonry.api" From 292060176d9de0476a344bb2503ceb36d224e7ac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Cabrero-Holgueras?= Date: Wed, 12 Jun 2024 14:37:44 +0000 Subject: [PATCH 2/4] chore: replaced helpers with nillion_python_helpers library --- examples/complex_model/network/compute.py | 4 ++-- .../network/helpers/nillion_client_helper.py | 12 ------------ .../network/helpers/nillion_keypath_helper.py | 10 ---------- .../network/helpers/nillion_payments_helper.py | 12 ------------ examples/linear_regression/network/compute.py | 4 ++-- .../network/helpers/nillion_client_helper.py | 12 ------------ .../network/helpers/nillion_keypath_helper.py | 10 ---------- .../network/helpers/nillion_payments_helper.py | 12 ------------ examples/neural_net/network/compute.py | 4 ++-- .../network/helpers/nillion_client_helper.py | 12 ------------ .../network/helpers/nillion_keypath_helper.py | 10 ---------- .../network/helpers/nillion_payments_helper.py | 12 ------------ 12 files changed, 6 insertions(+), 108 deletions(-) delete mode 100644 examples/complex_model/network/helpers/nillion_client_helper.py delete mode 100644 examples/complex_model/network/helpers/nillion_keypath_helper.py delete mode 100644 examples/complex_model/network/helpers/nillion_payments_helper.py delete mode 100644 examples/linear_regression/network/helpers/nillion_client_helper.py delete mode 100644 examples/linear_regression/network/helpers/nillion_keypath_helper.py delete mode 100644 examples/linear_regression/network/helpers/nillion_payments_helper.py delete mode 100644 examples/neural_net/network/helpers/nillion_client_helper.py delete mode 100644 examples/neural_net/network/helpers/nillion_keypath_helper.py delete mode 100644 examples/neural_net/network/helpers/nillion_payments_helper.py diff --git a/examples/complex_model/network/compute.py b/examples/complex_model/network/compute.py index ccc4bdc..ba0acf9 100644 --- a/examples/complex_model/network/compute.py +++ b/examples/complex_model/network/compute.py @@ -13,8 +13,8 @@ sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../.."))) # Import helper functions for creating nillion client and getting keys -from neural_net.network.helpers.nillion_client_helper import create_nillion_client -from neural_net.network.helpers.nillion_keypath_helper import ( +from nillion_python_helpers import ( + create_nillion_client, getUserKeyFromFile, getNodeKeyFromFile, ) diff --git a/examples/complex_model/network/helpers/nillion_client_helper.py b/examples/complex_model/network/helpers/nillion_client_helper.py deleted file mode 100644 index 5247aee..0000000 --- a/examples/complex_model/network/helpers/nillion_client_helper.py +++ /dev/null @@ -1,12 +0,0 @@ -import os -import py_nillion_client as nillion -from helpers.nillion_payments_helper import create_payments_config - - -def create_nillion_client(userkey, nodekey): - bootnodes = [os.getenv("NILLION_BOOTNODE_MULTIADDRESS")] - payments_config = create_payments_config() - - return nillion.NillionClient( - nodekey, bootnodes, nillion.ConnectionMode.relay(), userkey, payments_config - ) diff --git a/examples/complex_model/network/helpers/nillion_keypath_helper.py b/examples/complex_model/network/helpers/nillion_keypath_helper.py deleted file mode 100644 index 4a45413..0000000 --- a/examples/complex_model/network/helpers/nillion_keypath_helper.py +++ /dev/null @@ -1,10 +0,0 @@ -import os -import py_nillion_client as nillion - - -def getUserKeyFromFile(userkey_filepath): - return nillion.UserKey.from_file(userkey_filepath) - - -def getNodeKeyFromFile(nodekey_filepath): - return nillion.NodeKey.from_file(nodekey_filepath) diff --git a/examples/complex_model/network/helpers/nillion_payments_helper.py b/examples/complex_model/network/helpers/nillion_payments_helper.py deleted file mode 100644 index f68b33c..0000000 --- a/examples/complex_model/network/helpers/nillion_payments_helper.py +++ /dev/null @@ -1,12 +0,0 @@ -import os -import py_nillion_client as nillion - - -def create_payments_config(): - return nillion.PaymentsConfig( - os.getenv("NILLION_BLOCKCHAIN_RPC_ENDPOINT"), - os.getenv("NILLION_WALLET_PRIVATE_KEY"), - int(os.getenv("NILLION_CHAIN_ID")), - os.getenv("NILLION_PAYMENTS_SC_ADDRESS"), - os.getenv("NILLION_BLINDING_FACTORS_MANAGER_SC_ADDRESS"), - ) diff --git a/examples/linear_regression/network/compute.py b/examples/linear_regression/network/compute.py index 1bd5aef..b4c478d 100644 --- a/examples/linear_regression/network/compute.py +++ b/examples/linear_regression/network/compute.py @@ -13,8 +13,8 @@ sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../.."))) # Import helper functions for creating nillion client and getting keys -from neural_net.network.helpers.nillion_client_helper import create_nillion_client -from neural_net.network.helpers.nillion_keypath_helper import ( +from nillion_python_helpers import ( + create_nillion_client, getUserKeyFromFile, getNodeKeyFromFile, ) diff --git a/examples/linear_regression/network/helpers/nillion_client_helper.py b/examples/linear_regression/network/helpers/nillion_client_helper.py deleted file mode 100644 index 5247aee..0000000 --- a/examples/linear_regression/network/helpers/nillion_client_helper.py +++ /dev/null @@ -1,12 +0,0 @@ -import os -import py_nillion_client as nillion -from helpers.nillion_payments_helper import create_payments_config - - -def create_nillion_client(userkey, nodekey): - bootnodes = [os.getenv("NILLION_BOOTNODE_MULTIADDRESS")] - payments_config = create_payments_config() - - return nillion.NillionClient( - nodekey, bootnodes, nillion.ConnectionMode.relay(), userkey, payments_config - ) diff --git a/examples/linear_regression/network/helpers/nillion_keypath_helper.py b/examples/linear_regression/network/helpers/nillion_keypath_helper.py deleted file mode 100644 index 4a45413..0000000 --- a/examples/linear_regression/network/helpers/nillion_keypath_helper.py +++ /dev/null @@ -1,10 +0,0 @@ -import os -import py_nillion_client as nillion - - -def getUserKeyFromFile(userkey_filepath): - return nillion.UserKey.from_file(userkey_filepath) - - -def getNodeKeyFromFile(nodekey_filepath): - return nillion.NodeKey.from_file(nodekey_filepath) diff --git a/examples/linear_regression/network/helpers/nillion_payments_helper.py b/examples/linear_regression/network/helpers/nillion_payments_helper.py deleted file mode 100644 index f68b33c..0000000 --- a/examples/linear_regression/network/helpers/nillion_payments_helper.py +++ /dev/null @@ -1,12 +0,0 @@ -import os -import py_nillion_client as nillion - - -def create_payments_config(): - return nillion.PaymentsConfig( - os.getenv("NILLION_BLOCKCHAIN_RPC_ENDPOINT"), - os.getenv("NILLION_WALLET_PRIVATE_KEY"), - int(os.getenv("NILLION_CHAIN_ID")), - os.getenv("NILLION_PAYMENTS_SC_ADDRESS"), - os.getenv("NILLION_BLINDING_FACTORS_MANAGER_SC_ADDRESS"), - ) diff --git a/examples/neural_net/network/compute.py b/examples/neural_net/network/compute.py index 9999bf9..09d4a5d 100644 --- a/examples/neural_net/network/compute.py +++ b/examples/neural_net/network/compute.py @@ -13,8 +13,8 @@ sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../.."))) # Import helper functions for creating nillion client and getting keys -from neural_net.network.helpers.nillion_client_helper import create_nillion_client -from neural_net.network.helpers.nillion_keypath_helper import ( +from nillion_python_helpers import ( + create_nillion_client, getUserKeyFromFile, getNodeKeyFromFile, ) diff --git a/examples/neural_net/network/helpers/nillion_client_helper.py b/examples/neural_net/network/helpers/nillion_client_helper.py deleted file mode 100644 index 5247aee..0000000 --- a/examples/neural_net/network/helpers/nillion_client_helper.py +++ /dev/null @@ -1,12 +0,0 @@ -import os -import py_nillion_client as nillion -from helpers.nillion_payments_helper import create_payments_config - - -def create_nillion_client(userkey, nodekey): - bootnodes = [os.getenv("NILLION_BOOTNODE_MULTIADDRESS")] - payments_config = create_payments_config() - - return nillion.NillionClient( - nodekey, bootnodes, nillion.ConnectionMode.relay(), userkey, payments_config - ) diff --git a/examples/neural_net/network/helpers/nillion_keypath_helper.py b/examples/neural_net/network/helpers/nillion_keypath_helper.py deleted file mode 100644 index 4a45413..0000000 --- a/examples/neural_net/network/helpers/nillion_keypath_helper.py +++ /dev/null @@ -1,10 +0,0 @@ -import os -import py_nillion_client as nillion - - -def getUserKeyFromFile(userkey_filepath): - return nillion.UserKey.from_file(userkey_filepath) - - -def getNodeKeyFromFile(nodekey_filepath): - return nillion.NodeKey.from_file(nodekey_filepath) diff --git a/examples/neural_net/network/helpers/nillion_payments_helper.py b/examples/neural_net/network/helpers/nillion_payments_helper.py deleted file mode 100644 index f68b33c..0000000 --- a/examples/neural_net/network/helpers/nillion_payments_helper.py +++ /dev/null @@ -1,12 +0,0 @@ -import os -import py_nillion_client as nillion - - -def create_payments_config(): - return nillion.PaymentsConfig( - os.getenv("NILLION_BLOCKCHAIN_RPC_ENDPOINT"), - os.getenv("NILLION_WALLET_PRIVATE_KEY"), - int(os.getenv("NILLION_CHAIN_ID")), - os.getenv("NILLION_PAYMENTS_SC_ADDRESS"), - os.getenv("NILLION_BLINDING_FACTORS_MANAGER_SC_ADDRESS"), - ) From ddf27b486639866ae3889f7c90e811e05667afce Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Cabrero-Holgueras?= Date: Thu, 13 Jun 2024 08:31:31 +0000 Subject: [PATCH 3/4] fix: included nillion_python_helpers in time_series --- examples/time_series/network/compute.py | 4 ++-- .../network/helpers/nillion_client_helper.py | 12 ------------ .../network/helpers/nillion_keypath_helper.py | 10 ---------- .../network/helpers/nillion_payments_helper.py | 12 ------------ 4 files changed, 2 insertions(+), 36 deletions(-) delete mode 100644 examples/time_series/network/helpers/nillion_client_helper.py delete mode 100644 examples/time_series/network/helpers/nillion_keypath_helper.py delete mode 100644 examples/time_series/network/helpers/nillion_payments_helper.py diff --git a/examples/time_series/network/compute.py b/examples/time_series/network/compute.py index 5f5fafb..9b758a7 100644 --- a/examples/time_series/network/compute.py +++ b/examples/time_series/network/compute.py @@ -14,8 +14,8 @@ sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../.."))) # Import helper functions for creating nillion client and getting keys -from neural_net.network.helpers.nillion_client_helper import create_nillion_client -from neural_net.network.helpers.nillion_keypath_helper import ( +from nillion_python_helpers import ( + create_nillion_client, getUserKeyFromFile, getNodeKeyFromFile, ) diff --git a/examples/time_series/network/helpers/nillion_client_helper.py b/examples/time_series/network/helpers/nillion_client_helper.py deleted file mode 100644 index 5247aee..0000000 --- a/examples/time_series/network/helpers/nillion_client_helper.py +++ /dev/null @@ -1,12 +0,0 @@ -import os -import py_nillion_client as nillion -from helpers.nillion_payments_helper import create_payments_config - - -def create_nillion_client(userkey, nodekey): - bootnodes = [os.getenv("NILLION_BOOTNODE_MULTIADDRESS")] - payments_config = create_payments_config() - - return nillion.NillionClient( - nodekey, bootnodes, nillion.ConnectionMode.relay(), userkey, payments_config - ) diff --git a/examples/time_series/network/helpers/nillion_keypath_helper.py b/examples/time_series/network/helpers/nillion_keypath_helper.py deleted file mode 100644 index 4a45413..0000000 --- a/examples/time_series/network/helpers/nillion_keypath_helper.py +++ /dev/null @@ -1,10 +0,0 @@ -import os -import py_nillion_client as nillion - - -def getUserKeyFromFile(userkey_filepath): - return nillion.UserKey.from_file(userkey_filepath) - - -def getNodeKeyFromFile(nodekey_filepath): - return nillion.NodeKey.from_file(nodekey_filepath) diff --git a/examples/time_series/network/helpers/nillion_payments_helper.py b/examples/time_series/network/helpers/nillion_payments_helper.py deleted file mode 100644 index f68b33c..0000000 --- a/examples/time_series/network/helpers/nillion_payments_helper.py +++ /dev/null @@ -1,12 +0,0 @@ -import os -import py_nillion_client as nillion - - -def create_payments_config(): - return nillion.PaymentsConfig( - os.getenv("NILLION_BLOCKCHAIN_RPC_ENDPOINT"), - os.getenv("NILLION_WALLET_PRIVATE_KEY"), - int(os.getenv("NILLION_CHAIN_ID")), - os.getenv("NILLION_PAYMENTS_SC_ADDRESS"), - os.getenv("NILLION_BLINDING_FACTORS_MANAGER_SC_ADDRESS"), - ) From d9fa1e45abeb7fcf98d4e6c0cffe099f50c85469 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jos=C3=A9=20Cabrero-Holgueras?= Date: Thu, 13 Jun 2024 08:35:32 +0000 Subject: [PATCH 4/4] fix: added LogisticRegression to all --- nada_ai/linear_model/linear_regression.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/nada_ai/linear_model/linear_regression.py b/nada_ai/linear_model/linear_regression.py index eead976..31f2764 100644 --- a/nada_ai/linear_model/linear_regression.py +++ b/nada_ai/linear_model/linear_regression.py @@ -4,7 +4,7 @@ from nada_ai.nn.module import Module from nada_ai.nn.parameter import Parameter -__all__ = ["LinearRegression"] +__all__ = ["LinearRegression", "LogisticRegression"] class LinearRegression(Module):