Merge pull request #175 from petrobras/other_improvements

Other improvements

Author: ricardoevvargas

docs/notebooks/overview_version_2.0.0.ipynb

@@ -5081,7 +5081,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -6180,7 +6180,6 @@
     "        ParquetDatasetConfig(\n",
     "            path=dataset_path,\n",
     "            split=None,\n",
-    "            download=False,\n",
     "            columns=[\"T-JUS-CKP\", \"T-MON-CKP\"],\n",
     "            target_column=\"class\",\n",
     "            target_class=[0, 1],\n",

resources/introduction_to_3w_dataset_2.0.0/introduction_to_3w_dataset_2.0.0.pdf

@@ -0,0 +1,131 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "4c1389de-ad25-4708-a4bb-a970e45032cb",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "**📚 Tutorial Index:**\n",
+    "\n",
+    "1. [Toolkit Overview](1_toolkit_overview.ipynb) (you are here)\n",
+    "2. [Installation Guide](2_installation.ipynb)\n",
+    "3. [Dataset Download](3_download_dataset.ipynb)\n",
+    "4. [Preprocessing](4_preprocessing.ipynb)\n",
+    "5. [Feature Extraction](5_feature_extraction.ipynb)\n",
+    "6. [Data Visualization](6_data_visualization.ipynb)\n",
+    "7. [Model Training and Evaluation](7_model_training_and_evaluation.ipynb)\n",
+    "8. [Pipeline Integration](8_pipeline_integration.ipynb)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9fd80803-d1ec-4375-9a6c-ad449011a0ad",
+   "metadata": {},
+   "source": [
+    "# 1. Toolkit overview\n",
+    "\n",
+    "**Getting Started with 3WToolkit v2.0.0**\n",
+    "\n",
+    "## 📋 Table of Contents\n",
+    "1. [Introduction](#Introduction)\n",
+    "2. [Modular Architecture](#Modular-architecture)\n",
+    "3. [Key features](#Key-features)\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "24550b66-4e7f-4620-90db-45e928e6af44",
+   "metadata": {},
+   "source": [
+    "## Introduction\n",
+    "\n",
+    "Welcome to the comprehensive tutorial series for the **3WToolkit v2.0.0**! This collection of Jupyter notebooks provides a step-by-step guide to understanding and using the toolkit's powerful features for time-series analysis, fault detection, and machine learning applications targeting not only the 3W Toolkit for oil well operations, but also for machine learning tasks in general.\n",
+    "\n",
+    "As we'll see, the **3WToolkit v2.0.0** offers functionality for most common tasks:\n",
+    "- Dataset handling\n",
+    "- Data Preprocessing\n",
+    "- Feature Extraction\n",
+    "- Visualization\n",
+    "- Model training\n",
+    "- Model assessment\n",
+    "\n",
+    "The toolkit is designed to facilitate implementation, evaluation and comparison between models!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c91171b-7e07-4524-917d-dbc0c82cc14b",
+   "metadata": {},
+   "source": [
+    "## Modular Architecture\n",
+    "\n",
+    "The functionalities of the **3WToolkit v2.0.0** are split in two layers, Application and Core.\n",
+    "\n",
+    "For each *application* class to be instantiated, a corresponding *configuration* class exists, to be passed to the constructor.\n",
+    "All the configuration classes validate that the arguments passed to it are present, if needed, and do not have inconsistencies.\n",
+    "\n",
+    "A brief overview of the implemented tools:\n",
+    "![Main Classes](assets/main_classes.png)\n",
+    "\n",
+    "While all the classes can be used *standalone*, the true power of this toolkit is the possibility to integrate all steps needed for a particular task through the `Pipeline`, as we shall see later."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c547b5f6-0812-4c3e-bf99-4b8c4f52f472",
+   "metadata": {},
+   "source": [
+    "## Key features\n",
+    "- Straightforward installation and usage\n",
+    "- Automated downloading and verification of the 3W Dataset\n",
+    "- Sensible data cleanup procedure\n",
+    "- Pre-processing steps included\n",
+    "- Feature Extraction modules included\n",
+    "- Data visualization tools\n",
+    "- Integration with Scikit-Learn for model training\n",
+    "- Pipeline for end-to-end model training\n",
+    "- Automated report generation (HTML or $\\LaTeX$)\n",
+    "- Customizable and Expansible!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f93d28de-db57-476f-b016-b64ea2e694a5",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "\n",
+    "**📚 Tutorial Navigation:**\n",
+    "- **Next**: [2. Installation Guide](2_installation.ipynb)\n",
+    "\n",
+    "**🔗 Additional Resources:**\n",
+    "- [3W Project Repository](https://github.com/petrobras/3W)\n",
+    "- [3W Dataset on Figshare](https://figshare.com/projects/3W_Dataset/251195)\n",
+    "- [Workshop Registration](https://forms.gle/cmLa2u4VaXd1T7qp8)"
+   ]
+  }
+ ],
+ "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": "3.13.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}