Merge pull request #102 from jrzaurin/3rd_party_integration_example

3rd party integration example

Author: 5uperpalo

examples/notebooks/airbnb_data_preprocessing.ipynb renamed to examples/notebooks/00_airbnb_data_preprocessing.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "##  Processors and Utils\n",
+    "#  Processors and Utils\n",
     "\n",
     "Description of the main tools and utilities that one needs to prepare the data for a `WideDeep` model constructor. \n",
     "\n",
@@ -745,7 +745,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.7 ('base')",
    "language": "python",
    "name": "python3"
   },
@@ -759,7 +759,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.9.7"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "3b99005fd577fa40f3cce433b2b92303885900e634b2b5344c07c59d06c8792d"
+   }
   }
  },
  "nbformat": 4,

examples/notebooks/01_Preprocessors_and_utils.ipynb renamed to examples/notebooks/01_preprocessors_and_utils.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Model Components\n",
+    "# Model Components\n",
     "\n",
     "The main components of a `WideDeep` (i.e. Multimodal) model are tabular data, text and images, which are feed into the model via so called `wide`, `deeptabular`, `deeptext` and `deepimage` model components"
    ]
@@ -584,7 +584,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.7 ('base')",
    "language": "python",
    "name": "python3"
   },
@@ -598,7 +598,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.9.7"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "3b99005fd577fa40f3cce433b2b92303885900e634b2b5344c07c59d06c8792d"
+   }
   }
  },
  "nbformat": 4,

examples/notebooks/02_model_components.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Simple Binary Classification with defaults\n",
+    "# Simple Binary Classification with defaults\n",
     "\n",
     "In this notebook we will train a Wide and Deep model and simply a \"Deep\" model using the well known adult dataset"
    ]
@@ -1197,7 +1197,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.7 ('base')",
    "language": "python",
    "name": "python3"
   },
@@ -1211,7 +1211,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.9.7"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "3b99005fd577fa40f3cce433b2b92303885900e634b2b5344c07c59d06c8792d"
+   }
   }
  },
  "nbformat": 4,

mkdocs/sources/examples/03_Binary_Classification_with_Defaults.ipynb renamed to examples/notebooks/03_binary_classification_with_defaults.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Regression with Images and Text\n",
+    "# Regression with Images and Text\n",
     "\n",
     "In this notebook we will go through a series of examples on how to combine all Wide & Deep components.\n",
     "\n",
@@ -752,7 +752,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.7 ('base')",
    "language": "python",
    "name": "python3"
   },
@@ -766,7 +766,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.9.7"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "3b99005fd577fa40f3cce433b2b92303885900e634b2b5344c07c59d06c8792d"
+   }
   }
  },
  "nbformat": 4,

examples/notebooks/04_regression_with_images_and_text.ipynb

@@ -4,6 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "# Save and load model and artifacts\n",
     "In this notebook I will show the different options to save and load a model, as well as some additional objects produced during training. \n",
     "\n",
     "On a given day, you train a model..."
@@ -1113,7 +1114,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.7 ('base')",
    "language": "python",
    "name": "python3"
   },
@@ -1127,7 +1128,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.9.7"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "3b99005fd577fa40f3cce433b2b92303885900e634b2b5344c07c59d06c8792d"
+   }
   }
  },
  "nbformat": 4,

examples/notebooks/05_save_and_load_model_and_artifacts.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## The FineTune/Warm Up option\n",
+    "# The FineTune/Warm Up option\n",
     "\n",
     "Let's place ourselves in two possible scenarios. \n",
     "\n",
@@ -1581,7 +1581,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.7 ('base')",
    "language": "python",
    "name": "python3"
   },
@@ -1595,7 +1595,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.9.7"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "3b99005fd577fa40f3cce433b2b92303885900e634b2b5344c07c59d06c8792d"
+   }
   }
  },
  "nbformat": 4,

examples/notebooks/06_fineTune_and_warmup.ipynb renamed to examples/notebooks/06_finetune_and_warmup.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Custom components\n",
+    "# Custom components\n",
     "\n",
     "As I mentioned earlier in the example notebooks, and also in the `README`, it is possible to customise almost every component in `pytorch-widedeep`.\n",
     "\n",

mkdocs/sources/examples/07_Custom_Components.ipynb renamed to examples/notebooks/07_custom_components.ipynb

@@ -1,5 +1,14 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Extracting embeddings\n",
+    "\n",
+    "This notebook is a simple guide to extracting learned feature embeddings using Tab2Vec"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -494,7 +503,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.9.7 ('base')",
    "language": "python",
    "name": "python3"
   },
@@ -508,7 +517,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.9.7"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "3b99005fd577fa40f3cce433b2b92303885900e634b2b5344c07c59d06c8792d"
+   }
   }
  },
  "nbformat": 4,