Categories
Data & Analytics

WordPress MySQL Database Tables Deep Dive

In this post, I do a deep dive into some of the amazonwebshark WordPress MySQL database tables following the journey of a recent post.

Table of Contents

Introduction

In January I used Python and Matplotlib to create some visualisations using the WordPress amazonwebshark MySQL database.

Since then I’ve been doing a lot with Power BI at work, so I’ve created a Power BI connection to the amazonwebshark database to reacquaint myself with some features and experiment with a familiar dataset.

I talked about doing a views analysis in January’s post. While some of the 2022 data is missing, I can still accurately analyse 2023 data. I plan to measure:

  • Total views for each post.
  • Total views for each category.

I’ll use this post to examine some of the MySQL tables, and link back to it in future analysis posts.

Let’s begin with a brief WordPress database overview.

WordPress Database 101

In this section, I take a high-level view of a typical WordPress database and identify the tables I’ll need.

There’s plenty of great documentation online about typical WordPress installations. I’m particularly keen on The Ultimate Developer’s Guide to the WordPress Database by DeliciousBrains, which includes an in-depth tour of the various tables.

As for table relationships, this WordPress ERD shows object names, primary keys and relationship types:

I’ll be concentrating on these WordPress tables:

And the wp_statistics_pages table used by WPStatistics.

I’ll examine each table in the context of a recent post: DBeaver OpenAI ChatGPT Integration.

wp_posts

In this section of my WordPress database deep dive, I examine the most important WordPress database table: wp_posts.

Table Purpose

WordPress uses wp_posts to manage a site’s content. Each row in the table is an event relating to a piece of content, like a post, page or attachment. Examples of these events in the context of a blog post are:

  • Creating A New Draft: A new row is created with a post_status of draft. This row is the parent of all future activity for the blog post.
  • Updating A Draft: A new row is created with details of the update. The new row’s post_parent is set to the initial post’s ID.
  • Publishing A Draft: The initial row’s post_status is changed to publish, and the post_date is changed to the publication date. WordPress finds revisions to the post by filtering rows with a post_parent matching the initial row’s ID.

Post Journey

Let’s start by finding DBeaver OpenAI ChatGPT Integration‘s parent row, which is its earliest record. The following query finds rows where the post_title is DBeaver OpenAI ChatGPT Integration, then orders by ID and returns the first result.

SELECT 
  id, 
  post_date, 
  post_title, 
  post_status, 
  post_name, 
  post_parent, 
  post_type 
FROM 
  `wp_posts` 
WHERE 
  post_title = 'DBeaver OpenAI ChatGPT Integration' 
ORDER BY 
  id 
LIMIT 
  1

Note that I order by ID, not post_date. The publication process changes the parent post’s post_date, so I must use ID to find the earliest post.

This record is returned:

Name Value
ID 1902
post_date 2023-02-19 20:28:22
post_title DBeaver OpenAI ChatGPT Integration
post_status publish
post_name dbeaver-openai-chatgpt-integration
post_parent 0
post_type post

So the DBeaver OpenAI ChatGPT Integration parent row is ID 1902. I can use this to count the number of changes to this post by searching for wp_posts rows with a post_parent of 1902:

SELECT 
  COUNT(*) 
FROM 
  `wp_posts`
WHERE 
  post_parent = 1902

81 rows are returned:

Name    |Value|
--------+-----+
COUNT(*)|81   |

Now let’s examine these results more closely.

In the following query, I get all rows relating to DBeaver OpenAI ChatGPT Integration and then group the results by:

  • Date the post was made (using the MySQL DATE function to remove the time values for more meaningful aggregation).
  • Status of the post.
  • Post’s parent post.
  • Type of post.

I also count the rows that match each group and order the results by ID to preserve the event order:

SELECT 
  COUNT(*) AS ID_count, 
  DATE(post_date) AS post_date, 
  post_status, 
  post_parent, 
  post_type 
FROM 
  `wp_posts`
WHERE 
  ID = 1902 
  OR post_parent = 1902 
GROUP BY 
  DATE(post_date), 
  post_status, 
  post_parent, 
  post_type 
ORDER BY 
  ID

The query results are below. A couple of things to note:

  • The first two columns show what happens when a post is published. Row 1 is ID 1902 as it has no post_parent, and it has a post_status of publish and a post_date of 2023-02-19.
  • Row 2 is the first revision of ID 1902, and it has a post_status of inherit and a post_date of 2023-02-15. This is why I order by ID instead of post_date – ordering by post_date would show the revisions before the parent post in the results.
  • There are various post_type valves – revisions are text updates and attachments are image updates.
ID_count post_date post_status post_parent post_type
1 2023-02-19 publish 0 post
1 2023-02-15 inherit 1902 revision
19 2023-02-16 inherit 1902 revision
7 2023-02-16 inherit 1902 attachment
24 2023-02-17 inherit 1902 revision
1 2023-02-17 inherit 1902 attachment
7 2023-02-18 inherit 1902 revision
21 2023-02-19 inherit 1902 revision
1 2023-02-26 inherit 1902 revision

Spotlighting some of these results for context:

  • On 2023-02-16 there were 19 text revisions and 7 images attached. I save a lot!
  • On 2023-02-19 there were 21 text revisions and then the post was published.
  • There was a further text revision on 2023-02-26 in response to a DBeaver software update.

That’s enough about wp_posts for now. Next, let’s start examining how WordPress groups content.

wp_term_relationships

In this section, I examine the first of the WordPress taxonomy tables: wp_term_relationships.

Table Purpose

wp_term_relationships stores information about the relationship between posts and their associated taxonomy terms (More on taxonomies in the next section). WordPress uses it as a bridge table between wp_posts and the various taxonomy tables.

Post Journey

In this query, I join wp_term_relationships to wp_posts on object_id (this is ID in wp_posts), then find the rows where either wp_posts.id or wp_posts.post_parent is 1902:

SELECT 
  yjp.ID, 
  DATE(yjp.post_date) AS post_date, 
  yjp.post_type, 
  yjp.post_status,
  yjtr.object_id, 
  yjtr.term_taxonomy_id 
FROM 
  `wp_posts` AS yjp 
  INNER JOIN `wp_term_relationships` AS yjtr 
    ON yjtr.object_id = yjp.ID 
WHERE 
  yjp.ID = 1902 
  OR yjp.post_parent = 1902

wp_term_relationships only contains published posts, so the only rows returned concern the parent ID 1902:

ID post_date post_type post_status object_id term_taxonomy_id
1902 2023-02-19 post publish 1902 2
1902 2023-02-19 post publish 1902 69
1902 2023-02-19 post publish 1902 71
1902 2023-02-19 post publish 1902 74
1902 2023-02-19 post publish 1902 76
1902 2023-02-19 post publish 1902 77

The query returned six distinct wp_term_relationships.term_taxonomy_id values. My next step is to establish what these IDs relate to.

wp_term_taxonomy

In this section, I examine the table that groups term_taxonomy_id values into taxonomy types: wp_term_taxonomy.

Table Purpose

WordPress uses the wp_term_taxonomy table to store the taxonomy data for terms. Taxonomies in WordPress are used to group posts and custom post types together. Examples of WordPress taxonomies are category, post_tag and nav_menu.

Post Journey

In this query, I add a new join to the previous query, joining wp_term_taxonomy to wp_term_relationships on term_taxonomy_id. Some of the wp_posts columns have been removed from the query to save space.

SELECT 
  yjp.ID,  
  yjtr.term_taxonomy_id, 
  yjtt.taxonomy
FROM 
  `wp_posts` AS yjp 
  INNER JOIN `wp_term_relationships` AS yjtr 
    ON yjtr.object_id = yjp.ID 
  INNER JOIN `wp_term_taxonomy` AS yjtt 
    ON yjtr.term_taxonomy_id = yjtt.term_taxonomy_id 
WHERE 
  yjp.ID = 1902 
  OR yjp.post_parent = 1902

These results give some content to the previous results. I can now see that wp_posts.id 1902 has one category and five tags.

ID term_taxonomy_id taxonomy
1902 2 category
1902 69 post_tag
1902 71 post_tag
1902 74 post_tag
1902 76 post_tag
1902 77 post_tag

To get the names of the categories and tags, I must bring one more table into play…

wp_terms

In this section of my WordPress database deep dive, I examine the table that holds the names and details of the taxonomy terms used on amazonwebshark: wp_terms.

Table Purpose

The wp_terms table stores all of the terms that are used across all taxonomies on a WordPress site. Each row represents a single term, and the columns in the table contain information about that term, including name and ID.

Post Journey

In this query, I add another join to the previous query, joining wp_terms to wp_term_taxonomy on term_id.

SELECT 
  yjp.ID, 
  yjtr.term_taxonomy_id, 
  yjtt.taxonomy,
  yjt.name 
FROM 
  `wp_posts` AS yjp 
  INNER JOIN `wp_term_relationships` AS yjtr 
    ON yjtr.object_id = yjp.ID 
  INNER JOIN `wp_term_taxonomy` AS yjtt 
    ON yjtr.term_taxonomy_id = yjtt.term_taxonomy_id 
  INNER JOIN `wp_terms` AS yjt 
    ON yjtt.term_id = yjt.term_id 
WHERE 
  yjp.ID = 1902 
  OR yjp.post_parent = 1902

The results now identify the category and each of the five tags by name:

ID term_taxonomy_id taxonomy name
1902 2 category AI & Machine Learning
1902 69 post_tag WordPress
1902 71 post_tag DBeaver
1902 74 post_tag MySQL
1902 76 post_tag OpenAI
1902 77 post_tag ChatGPT

This is a perfect match for the post’s taxonomy in the WordPress portal:

2023 03 10 WordPressPanelChatGPT

So that’s the categories. What about the views?

wp_statistics_pages

In this final section, I examine the WPStatistics table that holds view counts: wp_statistics_pages.

Table Purpose

WPStatistics uses wp_statistics_pages to store data about page views. Each row shows a URI’s total views on the date specified.

WPStatistics documentation isn’t as in-depth as WordPress, so here are the table’s DDL and column descriptions:

CREATE TABLE `1yJ_statistics_pages` (
  `page_id` bigint(20) NOT NULL AUTO_INCREMENT,
  `uri` varchar(190) NOT NULL,
  `type` varchar(180) NOT NULL,
  `date` date NOT NULL,
  `count` int(11) NOT NULL,
  `id` int(11) NOT NULL,
  PRIMARY KEY (`page_id`),
  UNIQUE KEY `date_2` (`date`,`uri`),
  KEY `url` (`uri`),
  KEY `date` (`date`),
  KEY `id` (`id`),
  KEY `uri` (`uri`,`count`,`id`)
)
Table NameDescription
page_idPrimary key. Unique identifier for the table.
uriUniform Resource Identifier used to access a page.
typeuri type: home / page / post
dateDate the uri was viewed
counturi total views on the specified date
iduri ID in wp_posts.ID

Post Journey

As wp_statistics_pages.id is the same as wp_posts.id, I can use id 1902 in a query knowing it will still refer to DBeaver OpenAI ChatGPT Integration.

For example, this query counts the number of rows in wp_statistics_pages relating to id 1902:

SELECT 
  COUNT(*) 
FROM 
  `wp_statistics_pages` 
WHERE 
  id = 1902
COUNT(*)|
--------+
      14|

I can also calculate how many visits DBeaver OpenAI ChatGPT Integration has received by using SUM on all wp_statistics_pages.count values for id 1902:

SELECT 
  SUM(yjsp.count) 
FROM 
  `wp_statistics_pages` AS yjsp
WHERE 
  yjsp.id = 1902
SUM(count)|
----------+
        40|

So the page currently has 40 views. I can see how these views are made up by selecting and ordering by wp_statistics_pages.date:

SELECT 
  yjsp.date, 
  yjsp.count 
FROM 
  `wp_statistics_pages` AS yjsp
WHERE 
  yjsp.id = 1902 
ORDER BY 
  yjsp.date

date count
2023-02-19 1
2023-02-20 5
2023-02-21 1
2023-02-22 4
2023-03-07 6
2023-03-08 3
2023-03-09 2
2023-03-10 1

I can also join wp_posts to wp_statistics_pages on their id columns, bridging the gap between the WPStatistics table and the standard WordPress tables:

SELECT 
  yjsp.date, 
  yjsp.count, 
  yjp.post_title 
FROM 
  `wp_statistics_pages` AS yjsp 
  INNER JOIN `wp_posts` AS yjp 
    ON yjsp.id = yjp.id 
WHERE 
  yjsp.id = 1902 
ORDER BY 
  yjsp.date
date count post_title
2023-02-19 1 DBeaver OpenAI ChatGPT Integration
2023-02-20 5 DBeaver OpenAI ChatGPT Integration
2023-02-21 1 DBeaver OpenAI ChatGPT Integration
2023-02-22 4 DBeaver OpenAI ChatGPT Integration
2023-03-07 6 DBeaver OpenAI ChatGPT Integration
2023-03-08 3 DBeaver OpenAI ChatGPT Integration
2023-03-09 2 DBeaver OpenAI ChatGPT Integration
2023-03-10 1 DBeaver OpenAI ChatGPT Integration

Summary

In this post, I did a deep dive into some of the amazonwebshark WordPress MySQL database tables following the journey of a recent post.

I’ve used this post to present the journey a typical post goes through in the WordPress database. Future posts will use this knowledge and the WordPress database as a data source for various dashboards, scripting and processes. Watch this space!

If this post has been useful, please feel free to follow me on the following platforms for future updates:

Thanks for reading ~~^~~

Categories
AI & Machine Learning

DBeaver OpenAI ChatGPT Integration

In this post, I install the new DBeaver OpenAI ChatGPT integration, try it out with some prompts and examine my OpenAI usage costs.

Table of Contents

Introduction

DBeaver is a free database tool and SQL client. It is multi-platform, open-source and supports a variety of databases including Microsoft SQL ServerAmazon Athena and MySQL.

In February 2023, the latest version of DBeaver’s Community Edition was released. Version 22.3.4’s release notes start with:

ChatGPT integration for smart completion and code generation (as optional extension).

ChatGPT has been in the news a lot since its launch in November 2022. It has earned widespread praise and scorn, has been embraced in some places and banned in others and has attracted billions of dollars of investment.

So how does ChatGPT fare in this setting? Let’s find out!

Preparation

In this section, I install and configure DBeaver’s OpenAI ChatGPT integration.

DBeaver’s OpenAI ChatGPT integration is not automatically installed with Version 22.3.4. This makes sense – it’s currently quite new and many users and organisations may not want to install it (for reasons I’ll go into later). This approach keeps DBeaver’s footprint as small as possible and lets people make up their own minds.

DBeaver’s GitHub wiki covers the installation process, which amounts to:

  • Open DBeaver’s integration installer.
  • Select the DBeaver AI (GPT) integration library.
  • Select and install DBeaver AI (GPT) Support.
2023 02 15 DBeaverPlugins

Following this, the DBeaver OpenAI ChatGPT integration must be configured. This process needs an active API token from the OpenAI platform.

OpenAPI account holders can generate tokens in the API Keys section of their profile. Afterwards, this token must be pasted into the API Token field in DBeaver’s preferences:

2023 02 15 DBeaverGPTPrefs

The DBeaver OpenAI ChatGPT integration will now work. The other settings are out of scope for this post and are covered in DBeaver’s wiki.

Separately, I found I was getting SQL 08S01 timeout errors during my first attempts to send ChatGPT prompts. I ended up increasing my database connection’s connectionTimeout value to resolve this.

ChatGPT Data Sharing

There is an important fact to consider when using DBeaver’s OpenAI ChatGPT integration:

DBeaver needs to send database metadata to the OpenAI platform. 

To clarify, this means that DBeaver sends a list of the selected database’s table names and column names to OpenAI.

DBeaver doesn’t hide this fact away. Their wiki is very explicit, and the DBeaver OpenAI ChatGPT integration states this when used for the first time.

For my purposes, this isn’t a problem. My amazonwebshark MySQL database contains nothing confidential or sensitive, and the tables and columns of a standard WordPress database are well documented.

But I wouldn’t currently use this with databases I don’t own. Although the shared metadata is limited to table names and column names, these can still be sensitive and potentially misused. I’m sure OpenAI have data security measures in place, but as this technology is still quite new I currently prefer to be cautious.

Tests

In this section, I test the DBeaver OpenAI ChatGPT integration with prompts referring to my amazonwebshark MySQL database. Before starting, I should define the concepts of prompts and completions:

  • Prompts are the instructions given to ChatGPT.
  • Completions are ChatGPT’s response to prompts.

Test 1: Category Usage

For my first test, I wanted to answer a question similar to one from my last post:

How many amazonwebshark blog categories have been used more than twice?

I answered the question with this SQL query:

SELECT t.name, tt.count
FROM term_taxonomy AS tt
INNER JOIN terms AS t 
	ON tt.term_id = t.term_id
WHERE tt.taxonomy = 'category'
	AND tt.count > 2

Which returned these results:

namecount
Data & Analytics 6
Me4
Developing & Application Integration8
Security & Monitoring3

Now it’s ChatGPT’s turn! My first prompt for ChatGPT was:

Find all categories used more than 2 times.

GPT’s completion was:

SELECT COUNT(*) AS count, category
FROM statistics_historical
GROUP BY category
HAVING count > 2;

Although this query looks fine, it doesn’t return any results! In fact the whole table has nothing in it:

SELECT COUNT(*) FROM statistics_historical
NameValue
COUNT(*)0

ChatGPT interpreted my prompt literally and searched my database metadata for tables with a category column. This search only returned one table, which is used for archiving purged report data: statistics_historical.

ChatGPT didn’t know that the table was empty, and so had no way to know its query wasn’t appropriate. This was my fault – my prompt needed more work.

Test 2: Category Usage Take 2

For my second test, I tried to re-engineer my prompt to give ChatGPT more insight into my data. My question remained:

“How many amazonwebshark blog categories have been used more than twice?”

My second prompt was phrased to give ChatGPT some guidance on what to look for:

Get all names of terms with taxonomy of category and count greater than 2

This time, GPT’s completion was:

SELECT name, count 
FROM terms 
INNER JOIN term_taxonomy 
	ON terms.term_id = term_taxonomy.term_id 
WHERE term_taxonomy.taxonomy = 'category' 
	AND term_taxonomy.count > 2

This was almost identical to my own SQL query:

SELECT t.name, tt.count
FROM term_taxonomy AS tt
INNER JOIN terms AS t 
	ON tt.term_id = t.term_id
WHERE tt.taxonomy = 'category'
	AND tt.count > 2

And the results were the same in both cases:

namecount
Data & Analytics 6
Me4
Developing & Application Integration8
Security & Monitoring3

Test 3: Page Views

For my final test I tried a different approach. Instead of writing a SQL query myself, I gave ChatGPT a prompt and then used a WPStatistics report to compare results.

My question is now:

Which amazonwebshark posts have had the highest views in the past week?

I know which table has the data needed for this, so I included it along with some vital columns in my ChatGPT prompt:

Get the uris for the past week from statistics_pages. Sum all the counts. Show the top 5 in descending order.

GPT’s completion was:

SELECT uri, SUM(count) AS total_count
FROM statistics_pages
WHERE date >= DATE_SUB(CURDATE(), INTERVAL 7 DAY)
GROUP BY uri
ORDER BY total_count DESC
LIMIT 5;

This was impressive! ChatGPT used the table and columns I specified, filtered the dates correctly and limited the results as instructed.

The query results were:

uritotal count
/connecting-athena-to-power-bi-with-simba-athena/31
/writing-user-stories-for-an-itunes-dashboard/24
/using-athena-to-query-s3-inventory-parquet-objects/22
/s3-glacier-instant-retrieval-first-impressions/10
/open-source-documentation-with-read-the-docs/ 7

I compared these with my WPStatistics Pages report:

2023 02 16 WPStatisticsTopPagesChart

And the results were the same!

2023 02 16 WPStatisticsTopPagesTable

Pricing

In this section, I examine OpenAI’s usage and billing services.

Tokens

OpenAI uses the concept of tokens to calculate pricing. In their words:

The GPT family of models process text using tokens, which are common sequences of characters found in text. The models understand the statistical relationships between these tokens, and excel at producing the next token in a sequence of tokens.

OpenAI Tokenizer site

And:

“You can think of tokens as pieces of words used for natural language processing. For English text, 1 token is approximately 4 characters or 0.75 words. As a point of reference, the collected works of Shakespeare are about 900,000 words or 1.2M tokens.”

OpenAI Pricing site

OpenAI currently offers several tools for determining pricing:

OpenAI also operates a free tier. New users get $18 worth of free tokens. These expire after 3 months, after which accounts can be upgraded to paid plans operating on a pay-as-you-go basis. At this point, accounts with no billing information can still be accessed but no further API requests will be granted.

Usage

Here is my OpenAI usage for 2023-02-15:

2023 02 16 OpenAIBilling20230215

And 2023-02-16:

2023 02 16 OpenAIBilling20230216

To understand this better, let’s examine the last row that relates to Test 3. The values stated are:

  • 3284 prompt tokens.
  • 61 completion tokens.

The Completion value is easy to verify. Entering ChatGPT’s Test 3 completion into the tokenizer site scores it at 61 tokens:

2023 02 16 OpenAITokenizer

Now let’s examine the Prompt value. When I enter my Test 3 prompt into the tokenizer site, it only scores it at 25 tokens. I wanted to see where the other 3259 tokens came from, so I needed to see what DBeaver sent to ChatGPT.

Currently, my OpenAI account doesn’t keep a record of what their APIs send and receive. However, I can log what DBeaver sends to OpenAI! This is done by enabling the Write GPT queries to debug log option in DBeaver’s ChatGPT settings.

It turns out that DBeaver includes DDL statements for all of the tables and columns in my amazonwebshark MySQL database in every ChatGPT prompt. Even in cases like Test 3 where I tell ChatGPT which table to use!

This isn’t unreasonable, as ChatGPT’s information retention is limited and it can’t access past conversations to inform its responses. But this explains the high prompt values per request. The OpenAI tokeniser says Test 3’s full prompt is 8293 characters. And remember – every 4 characters requires 1 token!

Addendum: DBeaver version 22.3.5 added metadata scope configuration to their ChatGPT smart completion.

In terms of size, my amazonwebshark MySQL database has around 20 tables with modest column counts. Larger databases with dozens of tables and potentially hundreds of columns could quickly rack up high usage fees, so use caution in these situations.

Billing

OpenAI has features to help with billing. Their site stores payment methods and shows invoices from the past 12 months. In addition, preferences like additional email addresses for billing notifications and business tax ID retention can be specified.

Accounts can also have usage limits, triggering notification emails when reached. These work alongside the usage tracking dashboard to help monitor spending.

So how much have I spent here?

By default, DBeaver uses the DaVinci model. This is currently listed at $0.0200 per 1000 tokens. If I take the 30,057 total tokens I’ve used and price them at $0.0200 per 1000 tokens, I get $0.60114.

In GBP that’s about £0.50 (or about 5p per query) which my free tier will cover.

Summary

In this post, I installed the new DBeaver OpenAI ChatGPT integration, tried it out with some prompts and examined the OpenAI usage costs.

Overall I was very impressed with what I found! ChatGPT works really well with a well-engineered prompt. It understood what I wanted and worked quickly. Would I pay for it? I think so, provided I kept an eye on the prompts being sent and the resulting usage costs.

In a future version, I’d like to be able to control what database metadata is included in a prompt. This would let me make sure that ChatGPT wasn’t getting sensitive or unnecessary metadata, and the smaller prompts would reduce my API usage costs.

Addendum: DBeaver version 22.3.5 added metadata scope configuration to their ChatGPT smart completion.

This is all very exciting though! I’m interested to discover how else the DBeaver OpenAI ChatGPT integration can help me out, and fascinated to see future developments!

If this post has been useful, please feel free to follow me on the following platforms for future updates:

Thanks for reading ~~^~~

Categories
Data & Analytics

1st Birthday MySQL Data Analysis With DBeaver & Python

In this post, I celebrate amazonwebshark’s 1st birthday with an analysis of my site’s MySQL data using DBeaver, Python and Matplotlib.

Table of Contents

Introduction

amazonwebshark is one year old today!

PXL 20221230 170232698 800600

To mark the occasion, I decided to examine the MySQL database that WordPress uses to run amazonwebshark, and see what it could tell me about the past twelve months.

In addition, I’ve been trying out DataCamp and have recently finished their Intermediate Python course. It introduced me to Matplotlib, and this post is a great chance to try out those new skills!

Timeline

I’ll start by answering a question. Why is amazonwebshark’s birthday on January 09 when my first post’s publication date is December 02 2021?

In response, here’s a brief timeline of how amazonwebshark came to be:

09 January 2022 was the first day that everything was fully live, so I view that as amazonwebshark’s birthday.

The three LinkedIn posts were added here on 19 January 2022, but without Introducing amazonwebshark.com they would never have left LinkedIn!

WordPress Database

In this section, I take a closer look at amazonwebshark’s MySQL database and the ways I can access it.

Database Schema

A WordPress site has lots to keep track of, like logins, plugins and posts. For this, it uses the MySQL database management system.

A standard WordPress installation creates twelve MySQL tables. WordPress describes them in its documentation, which includes this entity relationship diagram:

Additionally, DeliciousBrains have produced an Ultimate Developer’s Guide to the WordPress Database which gives a full account of each table’s columns and purpose.

SiteGround Portal Database Access

WordPress databases are usually accessed with phpMyAdmin – a free tool for MySQL admin over the Internet.

WPBeginner has a Beginner’s Guide To WordPress Database Management With phpMyAdmin, covering topics including restoring backups, optimisation and password resets.

While phpMyAdmin is great for basic maintenance, it’s not very convenient for data analysis:

  • There are no data tools like schema visualization or query plans.
  • It lacks scripting tools like IntelliSense or auto-complete.
  • Accessing it usually involves accessing the web host’s portal first.

Ideally, I’d prefer to access my database remotely using a SQL client instead. While this needs some additional config, SiteGround makes this very simple!

Remote Database Access

By default, SiteGround denies any remote access requests. Many people will never use this feature, so disabling it is a good security measure. Remote access is enabled in the SiteGround portal, which grants immediate remote access for specified IPs and hostnames.

After doing that, I created a new database user with read-only (SELECT) access to the MySQL database:

2023 01 01 SiteGroundMySQLPermissions

This isn’t strictly necessary, but the default user has unlimited access and violates the principle of least privilege in this situation.

The following SiteGround video demonstrates enabling remote access:

Analysis Tools

In this section, I examine the various tools I’ll use for amazonwebshark’s 1st birthday data analysis.

DBeaver

DBeaver is a free database tool and SQL client. It is multi-platform, open-source and supports a variety of databases including Microsoft SQL Server, Amazon Athena and MySQL.

DBeaver’s features include:

This VK Tech 360 video demonstrates connecting DBeaver to a local MySQL database:

mysql-connector-python

mysql-connector-python is a free Python driver for communicating with MySQL.

This Telusko video shows mysql-connector-python being used to access a local MySQL database:

mysql-connector-python is on PyPi and is installable via pip:

pip install mysql-connector-python

After mysql-connector-python is installed and imported, a connection to a MySQL database can be made using the mysql.connector.connect() function with the following arguments:

  • host: Hostname or IP address of the MySQL server.
  • database: MySQL database name.
  • user: User name used to authenticate with the MySQL server.
  • password: Password to authenticate the user with the MySQL server.

This opens a connection to the MySQL server and creates a connection object. I store this in the variable conn_mysql:

import mysql.connector

conn_mysql = mysql.connector.connect(
	host = var.MYSQL_HOST,
	database = var.MYSQL_DATABASE,
	user = var.MYSQL_USER,
	password = var.MYSQL_PASSWORD
	)

I have my credentials stored in a separate Python script that is imported as var. This means I can protect them via .gitignore until I get something better in place!

After that, I need a cursor for running my SQL queries. I create this using the cursor() method of my conn_mysql connection object and store the whole thing as cursor:

cursor = conn_mysql.cursor()

I’m now in a position to start running SQL queries from Python. I import a SQL query from my var script (in this case my Category query) and store it as query:

query = var.QUERY_CATEGORY

I then run my query using the execute() method. I get the results as a list of tuples using the fetchall() method, which I store as results:

cursor.execute(query)
results = cursor.fetchall()

Finally, I disconnect my cursor and MySQL connection with the close() method:

cursor.close()
conn_mysql.close()

Matplotlib

Matplotlib is a library for creating visualizations in Python. It can produce numerous plot types and has a large gallery of examples.

This BlondieBytes video shows a short demo of Matplotlib inside a Jupyter Notebook:

Matplotlib is on PyPi and is installable via pip:

pip install matplotlib

To view Matplotlib’s charts in Visual Studio Code I had to use an interactive window. Visual Studio Code has several options for this. Here I used the Run Current File In Interactive Window option, which needed the IPyKernel package to be installed in my Python virtual environment first.

Categories Analysis

In this section, I begin amazonwebshark’s 1st birthday data analysis by writing a SQL query for amazonwebshark’s categories and analysing the results with Python.

Categories Analysis: SQL Query

For my Category SQL query, I’ll be using the terms and term_taxonomy tables:

2023 01 07 WordPressTables

WordPress has a taxonomy system for content organization. Individual taxonomy items are called terms, and they are stored in the terms table. Terms for amazonwebshark include Data & Analytics and Security & Monitoring.

The term_taxonomy table links a term_id to a taxonomy, giving context for each term. Common taxonomies are category, post_tag and nav_menu.

If I join these tables on term_id then I can map terms to taxonomies. In the following query results, the first two columns are from terms and the rest are from term_taxonomy:

2023 01 07 DBeaverQuery

My final query keeps the join, cleans up terms.name, returns all categories with at least one use and orders the results by term_taxonomy.count and terms.name:

SELECT
	REPLACE (t.name, '&', '&') AS name,
	tt.count
FROM
	term_taxonomy AS tt
INNER JOIN terms AS t ON
	tt.term_id = t.term_id
WHERE
	tt.taxonomy = 'category'
	AND tt.count > 0
ORDER BY
	tt.count ASC ,
	t.name DESC
2023 01 04 DBeaverCategoryResults

In future, I’ll need to limit the results of this query to a specific time window. Here, I want all the results so no further filtering is needed.

Categories Analysis: Python Script

Currently, my results variable contains the results of the var.QUERY_CATEGORY SQL query. When I run print(results), I get this list of tuples:

[('Training & Community', 1), ('DevOps & Infrastructure', 1), ('AI & Machine Learning', 1), ('Internet Of Things & Robotics', 2), ('Architecture & Resilience', 2), ('Security & Monitoring', 3), ('Me', 4), ('Data & Analytics', 5), ('Developing & Application Integration', 8)]

So how do I turn this into a graph? Firstly, I need to split results up into what will be my X-axis and Y-axis. For this, I create two empty lists called name and count:

name = []
count = []

After that, I populate the lists by looping through result. For each tuple, the first item is appended to name and the second is appended to count:

for result in results:
    name.append(result[0])
    count.append(result[1])

When I print the lists now, name and count contain the names and counts from the SQL query in the same order as the original results:

print(f'name = {name}')
name = ['Training & Community', 'DevOps & Infrastructure', 'AI & Machine Learning', 'Internet Of Things & Robotics', 'Architecture & Resilience', 'Security & Monitoring', 'Me', 'Data & Analytics', 'Developing & Application Integration']
print(f'count = {count}')
count = [1, 1, 1, 2, 2, 3, 4, 5, 8]

I then use these lists with Matplotlib, imported as plt:

plt.bar(name, count)
plt.xlabel("category name")
plt.ylabel("category count")
plt.title("amazonwebshark categories")
plt.show()
  • bar sets the visual’s type as a bar chart. The X-axis is name and the Y-axis is count.
  • xlabel labels the X-axis as category name
  • ylabel labels the Y-axis as category count.
  • title names the chart as amazonwebshark categories
  • show shows the graph.

The following chart is produced:

sharkbirth category bar

However, the X-axis labels are unreadable. I can fix this by changing my script:

plt.barh(name, count)
plt.xlabel("count")
plt.ylabel("name")
plt.title("amazonwebshark categories")
plt.show()

I use barh to change the graph to a horizontal bar chart, and then swap the xlabel and ylabel strings around. This time the chart is far easier to read:

sharkbirth category barh

Tags Analysis

In this section, I continue amazonwebshark’s 1st birthday data analysis by writing a SQL query for amazonwebshark’s tags and analysing the results with Python.

Tags Analysis: SQL Query

My Tags SQL query is almost the same as my Categories one. This time, my WHERE clause is filtering on post_tag:

SELECT
	REPLACE (t.name, '&', '&') AS name,
	tt.count
FROM
	term_taxonomy AS tt
INNER JOIN terms t ON
	tt.term_id = t.term_id
WHERE
	tt.taxonomy = 'post_tag'
	AND tt.count > 0
ORDER BY
	tt.count ASC ,
	t.name DESC

There are more results this time. While I try to limit my use of categories, I’m currently using 44 tags:

2023 01 04 DBeaverTagsResults

Tags Analysis: Python Script

My Tags Python script is (also) almost the same as my Categories one. This time, the query variable has a different value:

query = var.QUERY_TAG

So print(results) returns a new list of tuples:

[('Running', 1), ('Read The Docs', 1), ('Raspberry Pi Zero', 1), ('Raspberry Pi 4', 1), ('Python: Pandas', 1), ('Python: NumPy', 1), ('Python: Boto3', 1), ('Presto', 1), ('Postman', 1), ('Microsoft Power BI', 1), ('Linux', 1), ('Gardening', 1), ('DNS', 1), ('AWS IoT Core', 1), ('Amazon RDS', 1), ('Amazon EventBridge', 1), ('Amazon EC2', 1), ('Amazon DynamoDB', 1), ('Agile', 1), ('Academia', 1), ('WordPress', 2), ('PowerShell', 2), ('OAuth2', 2), ('Microsoft SQL Server', 2), ('Microsoft Azure', 2), ('AWS Data Wrangler', 2), ('AWS CloudTrail', 2), ('Apache Parquet', 2), ('Amazon SNS', 2), ('Amazon Route53', 2), ('Amazon CloudWatch', 2), ('T-SQL Tuesday', 3), ('Strava', 3), ('Certifications', 3), ('Amazon Athena', 3), ('WordPrompt', 4), ('Project: iTunes Export Data Pipeline (2022-2023)', 4), ('Music', 4), ('GitHub', 4), ('AWS Billing And Cost Management', 4), ('Visual Studio Code', 5), ('Amazon S3', 5), ('Python', 6), ('Amazon Web Services', 16)]

Matplotlib uses these results to produce another horizontal bar chart with a new title:

plt.barh(name, count)
plt.xlabel("count")
plt.ylabel("name")
plt.title("amazonwebshark tags")
plt.show()

But this chart has a different problem – the Y-axis is unreadable because of the number of tags returned by my SQL query:

sharkbirth tag all

To fix this, I reduce the number of rows returned by changing my SQL WHERE clause from:

WHERE
	tt.taxonomy = 'post_tag'
	AND tt.count > 0

to:

WHERE
	tt.taxonomy = 'post_tag'
	AND tt.count > 2

This returns a smaller list of tuples:

[('T-SQL Tuesday', 3), ('Strava', 3), ('Certifications', 3), ('Amazon Athena', 3), ('WordPrompt', 4), ('Project: iTunes Export Data Pipeline (2022-2023)', 4), ('Music', 4), ('GitHub', 4), ('AWS Billing And Cost Management', 4), ('Visual Studio Code', 5), ('Amazon S3', 5), ('Python', 6), ('Amazon Web Services', 16)]

I then update the title to reflect the new results and use yticks to reduce the Y-axis label font size to 9:

plt.barh(name, count)
plt.xlabel("tag count")
plt.ylabel("tag name")
plt.title("amazonwebshark tags (most assignments)")
plt.yticks(fontsize = 9)
plt.show()

The chart is now more useful and easier to read:

sharkbirth tag most

Views Analysis

I also planned to analyse my post views here. But, as I mentioned in my last post, some of this data is missing! So any chart will be wrong.

I haven’t had time to look at this yet, so stay tuned!

Summary

In this post, I celebrated amazonwebshark’s 1st birthday with an analysis of my site’s MySQL data using DBeaver, Python and Matplotlib.

I had fun researching and writing this! It can be tricky to find a data source that isn’t contrived or overused. Having access to the amazonwebshark database gives me data that I’m personally invested in, and an opportunity to practise writing MySQL queries.

I’ve also been able to improve my Python, and meaningfully experiment with Matplotlib to get charts that will be useful going forward. For example, I used the very first Tags chart to prune some unneeded tags from my WordPress taxonomy.

If this post has been useful, please feel free to follow me on the following platforms for future updates:

Thanks for reading ~~^~~