Tried to enable optional TOC

hugo_blag/content/posts/2018-04-08-recommender-systems-1/index.md

@@ -7,37 +7,12 @@ tags:
 - technobabble
 - notebook
 - literate
+toc: true
 ---
 
 This is an exported version of the Jupyter notebook available at my
 GitHub: <https://github.com/Hodapp87/recommender-examples>
 
-# Table of Contents
-
-- [1. Introduction](#introduction)
-  - [1.1. Motivation](#motivation)
-  - [1.2. Organization](#organization)
-- [2. Dependencies & Setup](#dependencies-setup)
-- [3. Loading data](#loading-data)
-  - [3.1. Aggregation](#aggregation)
-- [4. Utility Matrix](#utility-matrix)
-- [5. Slope One Predictors](#slope-one-predictors)
-  - [5.1. Weighted Slope One](#weighted-slope-one)
-  - [5.2. Linear Algebra Tricks](#linear-algebra-tricks)
-  - [5.3. Implementation](#implementation)
-- [6. "SVD" algorithm](#svd-algorithm)
-  - [6.1. Model & Background](#model-background)
-  - [6.2. Motivation](#motivation)
-  - [6.3. Prediction & Error Function](#prediction-error-function)
-  - [6.4. Gradients & Gradient Descent Updates](#gradients-gradient-descent-updates)
-  - [6.5. Implementation](#implementation-1)
-  - [6.6. Running & Testing](#running-testing)
-  - [6.7. Visualization of Latent Space](#visualization-of-latent-space)
-  - [6.8. Bias](#bias)
-- [7. Implementations in scikit-surprise](#implementations-in-scikit-surprise)
-- [8. Overall results](#overall-results)
-- [9. Further Work](#further-work)
-
 # 1. Introduction
 
 The aim of this notebook is to briefly explain *recommender systems*, show some specific examples of them, and to demonstrate simple implementations of them in Python/NumPy/Pandas.