Top 8 Recommended BigQuery Self-Study Materials! [December 2023]

BigQuery is a popular data warehouse service that allows you to easily work with petabytes of data.  Learn how to quickly get up to speed with BigQuery and start querying and analyzing data efficiently using the BigQuery graphical user interface, command line utilities, and even programming languages.  If you are familiar with basic database concepts, like tables, you are ready to start learning one of the most important data analytics platforms available.

While some courses will focus just on using SQL with BigQuery, this course starts with the basics of signing up for Google Cloud and working the BigQuery graphical user interface (GUI), introduces SQL for BigQuery, and then moves to loading data and working with BigQuery using the command line and Python.  Perhaps most importantly, you will learn how BigQuery is different from other databases and how to use that knowledge to use BigQuery efficiently and cost effectively.

You will learn how to explore data, tables, and datasets. Write queries efficiently using BigQuery hints and formatting helps.  Work with SELECT statements, including creating FROM, WHERE, GROUP BY, HAVING, and ORDER BY clauses to create queries that answer driving questions you have about your data.  If you are not familiar with working with multiple tables and using joins, that's no problem, you will learn that in this course.

Use features of BigQuery designed to make you more productive, like Saved Queries, Exporting Data, and Execution Details that help you improve the performance of your queries.

Learn how to create tables and data sets and load data into BigQuery directly and by using Cloud Storage, Google Cloud's large scale object storage system.

While the graphical user interface, known as the BigQuery console, is an excellent tool for interactive work with BigQuery, sometimes we need to run the same queries or operations repeatedly to generate reports or download data. In this course you will learn about the bq command line utility that lets you query data and work with datasets from the command line.  If you prefer to work with Python or other programming languages, you can use the BigQuery client libraries for running queries and other jobs right from your programs and scripts. You don't even need to have Python installed on your device because we'll use CoLab, a free Google service for working with Python notebooks.

Quizzes and assignments in this course allow you to check your understanding as you progress through the course by answering questions and writing queries.

To use BigQuery effectively though, you need to understand how BigQuery is designed. Building a data warehouse and designing data models in BigQuery is fundamentally different than building and modeling in relational databases like Oracle, SQL Server and PostgreSQL. In this course, you will learn about BigQuery's architecture and how it influences how we structure and query data.

Learn insights from an instructor with decades of experience in working with data. Dan Sullivan is a Principal Data Architect and author of books and numerous articles on databases and Google Cloud. Dan is the author the Official Google Cloud Professional Data Engineer Study Guide as well as study guides for the Google Cloud Professional Cloud Architect and Associate Cloud Engineer certifications.  He has developed courses for Google Cloud, data modeling, data science, exploratory data analysis, machine learning, DevOps, and more. His courses can be found on Udemy and LinkedIn Learning.

1. Introduction to BigQuery
2. Welcome to Introduction to BigQuery
3. Overview of BigQuery
4. BigQuery Data Types
5. Key Topics to Understand about BigQuery
6. Quiz
7. BigQuery Console Quickstart
8. Signing Up to Use BigQuery
9. Introduction to the BigQuery Console
10. Using a Public Dataset
11. Working with Multiple Tables
12. Exporting Data from BigQuery
13. Saving Queries
14. Quiz
15. Using the BigQuery Console
16. Querying BigQuery Data Using SELECT Statements
17. Basic SELECT Statements
18. SELECT with a WHERE Clause
19. Using the ORDER BY Clause
20. Using the GROUP BY Clause
21. Using the WHERE, GROUP BY and ORDER BY Clauses
22. Using the HAVING Clause
23. Joining Two Tables
24. Find the name of the station with the smallest station_id
25. Find the name of the station that was the start of the longest trip duration.
26. SQL Functions
27. Working with Aggregate Functions
28. Using the ROUND Function with Numeric Data Types
29. Find average trip durations by station
30. Working with Date and Time Functions
31. Simple Math Expressions
32. Working with String Functions
33. Pretty print the names of start and end stations
34. Using the CASE Statement and Error Checking
35. Quiz
36. Creating Tables and Loading Data
37. Create Dataset and Simple Table
38. Inserting, Updating, and Deleting Data in Tables
39. Loading Data from a File
40. Creating a Cloud Storage Bucket
41. Quiz
42. BigQuery Command Line
43. Installing Cloud SDK
44. Initializing the Command Line Environent
45. Uploading Data with gsutil Command
46. Using the bq Command Line to work with BigQuery
47. Quiz
48. BigQuery and Python
49. Introduction to Colab and Using Python with BigQuery
50. Clients, Jobs and Dataframes
51. Quiz
52. BigQuery Architecture
53. Component Services that Make Up BigQuery
54. Columnar Data Storage
55. Partitioning Tables
56. Clustering
57. Performance Tuning
58. Quiz

Note : This Bigquery course is NOT intended to teach SQL or PostgreSQL. The focus of the course is kept to give you In-depth knowledge of Google Bigquery concepts/Internals.

"BigQuery is server-less, highly scalable, and cost-effective Data warehouse designed for Google cloud Platform (GCP) to store and query petabytes of data."

What's included in the course ?

• Brief introduction to the set of services Google Cloud provides.

• Complete In-depth knowledge of Google BigQuery concepts explained from Scratch to ADVANCE to Real-Time implementation.

• Each and every BigQuery concept is explained with HANDS-ON examples.

• Includes each and every, even thin detail of Big Query.

• Learn to interact with BigQuery using its Web Console, Bq CLI and Python Client Library.

• Create, Load, Modify and Manage BigQuery Datasets, Tables, Views, Materialized Views etc.

• *Exclusive* - Query Execution Plan, Efficient schema design, Optimization techniques, Partitioning, Clustering.

• Build and deploy end-to-end data pipelines (Batch & Stream) of Real-Time case studies in GCP.

• Services used in the pipelines- Dataflow, Apache Beam, Pub/Sub, Bigquery, Cloud storage, Data Studio, Cloud Composer/Airflow etc.

• Learn Best practices and Optimization techniques to follow in Real-Time Google Cloud BigQuery Projects.

After completing this course, you can start working on any BigQuery project with full confidence.

Add-Ons

• Questions and Queries will be answered very quickly.

• Queries and datasets used in lectures are attached in the course for your convenience.

• I am going to update it frequently, every time adding new components of Bigquery.

1. Introduction to GCP & its services
2. Introduction to Google Cloud Platform
3. GCP vs AWS vs Azure - Why choose GCP
4. Compute Services in GCP
5. Storage Services in GCP
6. Big data Services in GCP
7. AI & ML Services in GCP
8. Big data ecosystem in GCP
9. Quiz 1
10. Introduction to BigQuery
11. Conventional Datawarehouse Problems
12. What is BigQuery
13. BigQuery Out-of-the Box Features
14. Architecture of BigQuery
15. Dataset & Table creation
16. Setup a GCP account
17. Important note
18. Create a Project
19. BigQuery UI Tour
20. Region Vs Multi-region
21. Create a Dataset
22. Create a Table
23. Assignment 1
24. Using BigQuery Dashboard options
25. Running query with various Query Settings
26. Caching features & limitations
27. Querying Wildcard Tables
28. Wildcard Table Limitations
29. Schedule, Save, Share a Query
30. Schema Auto detection
31. Efficient Schema Design in BigQuery
32. Design an Efficient schema for BigQuery Tables
33. Nested & Repeated Columns
34. Quiz 2
35. Assignment 2
36. Operations on Datasets & Tables
37. Copying Datasets
38. Transfer Service for scheduling Copy Jobs
39. Native operations on Table for Schema change
40. Manual operations on Table
41. Execution Plan of BigQuery
42. How BigQuery creates Execution Plan of a Query
43. Understanding Execution Plan in UI Dashboard
44. Partitioned Tables in BigQuery
45. What is Partitioning & its benefits
46. Ingestion time Partitioned Tables
47. Date column Partitioned Tables
48. Integer based Partitioned Tables
49. ALTER, COPY operations on Partitioned Tables
50. DML operations on Partitioned Tables
51. Best Practices for Partitioning
52. Clustered Tables in BigQuery
53. What is Clustering
54. When to use Clustering OR Partitioning OR Both
55. Create Clustered Table
56. Dos & Don'ts for Clustering
57. Loading & Querying External Data Sources
58. Introduction and Create Cloud Storage Bucket
59. Create & Query Permanent Table on Cloud Storage bucket
60. External data source Limitations
61. Views in Bigquery
62. Introduction to Views & its Advantages
63. Create Views in BigQuery
64. Restrict rows at User level in Views
65. Limitations of Views
66. Materialized Views in BigQuery
67. What are Materialized Views
68. Create a Materialized View
69. ALTER Materialized View
70. Design an optimized query for Materialized View
71. Auto & Manual Refreshes of Materialized Views
72. Limitations & Quotas of Materialized Views
73. Best Practices in Materialized Views
74. Quiz 3
75. BQ Command Line
76. Introduction
77. Cloud SDK Setup
78. BQ Basic commands
79. BQ - Querying Commands
80. BQ- Dataset creation command
81. BQ - Create all types of Tables
82. BQ - Load data into Table
83. BQ - Exclusive operations
84. Assignment 3
85. Python Client Library of BigQuery
86. Setup
87. Python code to create dataset
88. Python code to create table
89. Python code to query tables
90. Build End-to-End Data Pipelines (Apache Beam)
91. Case Study Requirements
92. GCP approach to case study
93. Apache Beam Pipeline creation
94. Write Transformations in Beam
95. Write to BigQuery
96. Create View for Daily data
97. Python 3 code
98. Run the Beam Pipeline
99. Create Reports in Cloud DataStudio
100. Create monthly reports in DataStudio
101. Write Airflow DAG to schedule
102. Create Cloud Composer environment and run DAG
103. Build Streaming Data Pipelines
104. Introduction
105. Google Pub/Sub Architecture
106. Publish messages to Pub/Sub
107. Beam pipeline for Streaming data
108. BigQuery Pricing
109. Storage Pricing
110. Query Pricing
111. API, DML pricing
112. Free operations in BigQuery
113. Google Cloud Pricing Calculator
114. Best Practices / Optimization Techniques
115. Introduction
116. Methods to restrict data scan
117. Ways to reduce CPU time
118. Which SQL anti-patterns to avoid
119. Additional Learnings - Different File Formats & Apache Beam
120. What do we need from a File
121. Text, Sequence, Avro Files
122. RC, ORC, Parquet Files
123. Performance Test results of Various Files
124. Which File Format to choose
125. Introduction to Apache Beam
126. Batch Vs Stream processing
127. Thankyou
128. Bonus
129. Bonus

Woah, another SQL course? Yes! Here's why this one is different.

1. We write 100% of the code together and I explain everything precisely and with abundant context. I have over a decade of industry experience over have taught this at the university level.

   
   

2. 100% we do is application based. I rarely use toy data to illustrate points, unless it's more illustrative. Hopefully you'll learn much more than SQL throughout the course.

   
   

3. ZERO SET-UP. As long as you have a Google Account, you can login to BigQuery and get started immediately. No headaches configuring databases locally. You'll be up and running in under 3 minutes.

   
   

4. Spaced repetition to develop mastery. This is NOT a table of contents course. This is NOT a list of disparate exercises. Everything is connected. Concepts are revisited throughout the course so you can see them from different angles and maximize understanding.

   
   

5. Can you solve it? I provide tons of mini-challenges throughout the lecture material. The lecture material is basically us solving the problems. No time wasted on theory without context.

   
   

6. I'm not boring. I am human. I do make mistakes. I dwell on them so you can master the debugging process. Debugging is much more important than writing code.

1. Should you take this course?
2. How this course works - please watch!
3. BigQuery Set-up - Writing Our First Queries!
4. [Must Watch] - January 2023 - Pinning the Project and getting set-up
5. WATCH FIRST PLEASE: New BigQuery UI - Set-up (January 26, 2021 update)
6. [Optional - but very useful]Using ChatGPT to accelerate learning and progress.
7. [Optional - but very useful] Asking ChatGPT for Examples
8. Overview of Tables/Columns and Writing Queries
9. Anatomy of a SELECT statement
10. Our First Real Question - How Many Questions Each Tag Has?
11. Does a Question Have Multiple Tags? More aggregations, GROUPING and the HAVING
12. Everything is a Table: Subqueries, Common Table Expressions
13. Solution - All Views for Titles Containing "python" - Tricky!
14. Solution - All Questions for Each Tag, plus some more subqueries.
15. The CASE Statement - Quick Case study using StackOverflow Questions
16. Using CASE Statements to Classify Stack Overflow Questions
17. Solution - Using Question Titles And Tags in our CASE statement
18. Solution - Programming Language Growth Using Stack Overflow Data
19. Using Python to Generate Larger SQL Statements (Optional)
20. Join me and learn to JOIN data + Window/Analytic Functions
21. INNER, LEFT, RIGHT, OUTER JOIN's - in a nutshell
22. JOIN'ing Order and Customers - How to identify JOIN column candidates
23. Solution - Most Popular Cities and Intro to ROW_NUMBER()
24. Solution - New Customers Acquired by Year/Month
25. Breaking Down ROW_NUMBER() in Using order_items
26. Breaking Down LAG() in Using order_items
27. Solution - Average Days Between Orders Using ROW_NUMER() and LAG()
28. Final Solution - Customers with >1 Orders, Avg Time Between Orders
29. Other JOIN's You Might Need
30. FULL OUTER JOIN - Motivation and Problem Statement
31. FULL OUTER JOIN - Solution
32. JOIN's Mini Project - Hourly Revenue Trends
33. Hourly Revenue Trends Intro
34. Hourly Revenue Trends CASE Solution
35. CASE Statement Trick
36. UNNEST, Correlated Subqueries
37. UNNEST Intro, Running Totals w/Correlated Subqueries
38. Moving Averages and Quick Comprehension Check
39. LAG using a correlated subquery!
40. Customer Order Summary - Part 1
41. Customer Order Summary - Using Correlated Subqueries Part 2
42. Stock Price Project
43. Analyzing Stock Prices Using Moving Averages
44. Stock Price Analysis Solution
45. More Complex JOIN's and PARTITION'ing
46. Top 2 Customer Rentals by Moving Rating (Top N Problem) - Part 1
47. Top 2 Customer Rentals by Moving Rating (Top N Problem) - Part 2 Solution
48. Using Multiple Partitions with ROW_NUMBER()
49. Stack Overflow MiniProject - Top Phrases used in Title by Tag
50. Splitting Titles into Tokens and Counting Them
51. Analyzing Top Occurring Unigrams From the Question Titles Grouped by Tag
52. Using ML.NGRAMS to get Bigrams, Trigrams and Ngrams
53. More Text Processing With Regular Expressions
54. Regular Expressions Intro - Advent of Code 2020 Problem 2 Part A
55. Regular Expressions Intro - Advent of Code 2020 Problem 2 Part A Continued
56. Pair Programming With a Former Student - Watch if you can!
57. Advent of Code 2020 Problem - Part 2 - First Video
58. Advent of Code 2020 Problem - Part 2 - Second Video
59. Advent of Code 2020 Problem - Part 2 - Javascript UDF Solution
60. Google Analytics Attribution Analysis
61. Intro to Google Analytics Multichannel Funnels and Paths
62. Starting to write the code to analyze first and last touch channels
63. Dealing with some edge cases and bigger questions
64. Solution for paths of length > 1

Welcome to Google BigQuery for Marketers and Agencies, the Google BigQuery course that focuses on growing the technical knowledge and expertise of the marketing professional! This course is designed to bridge the gap between data analysis and digital marketing, and help you become a data-driven decision-maker. The course curriculum is put together in a progressive fashion, starting with an introduction to the most useful SQL queries for marketers, the role of both BigQuery and SQL in the larger data ecosystem, and then diving into two hands-on projects, where you can use everything you have learned.

By the end of the course, you will be able to:

• Explore eCommerce and CRM user-level data in Google Analytics 360 (Project #1)

• Visualize active queries and data tables in Google Data Studio (Project #2)

• Explore semi-structured data with ARRAY_AGG, UNNEST and STRUCT

• Filter values with the WHERE clause to identify insights

• Ingest .CSV files and create permanent BigQuery tables

• Combine multiple data tables with different types of JOINs - INNER, LEFT and RIGHT

• Aggregate data with SUM, COUNT and GROUP BY

• Create nested queries by using the WITH clause

  
  

What are the students who took the course saying?

"Very good course that shows you the basics of Google Big Query and its integration with Data Studio. The teacher shows you, step by step, the most important things to know with passion. I recommend this course to anyone who wants to take the first steps in the Big Query World." - Massimo

"Very good course! I am glad that I have chosen it. Materials are easy for understanding. I was familiar with SQL before, but never worked with it in BigQuery. Now I know how to do it. Thank you very much!" - Mariia

"This course is brilliant! really! I have been collecting data with Google Analytics for a few years. But this course taught how to take that data to the next step and now I can speak to what can be done with this data, and how it can be combined with other data sources etc. I especially like the way Lachezar explains key concepts that helped me put together the puzzle of GA data to BigQuery and from there to data visulization. Thanks Lachezar." - Muhammad

Who is the instructor?

Lachezar Arabadzhiev is a digital markitech with 4+ years of experience in performance analytics and data visualization. Lachezar began his career as a digital marketer at Microsoft, but soon transitioned to the measurement and analytics world, where he has had the opportunity to work with major brands such as Air Canada, RBC, Kimberly-Clark, Mazda and HSBC.

Lachezar has been working with Data Studio and BigQuery since early 2017 and has built a wide variety of visualizations and automation flows. From performance-based dashboards with joined GMP sources (Google Analytics 360, Campaign Manager and Display & Video 360) to audience-driven segmentation views with user-level eCommerce data.

Lachezar is a certified GMP expert and an official speaker at the Canadian Google Data & Analytics Summit, 2018.

1. Getting started with Google BigQuery
2. Welcome to the Course!
3. What are Google BigQuery and SQL?
4. Setting up your BigQuery Sandbox account in Google Cloud Platform (GCP)
5. Disabling Editor Tabs
6. Navigating the Google BigQuery interface
7. Using the BigQuery Solutions Manual
8. Downloading the BigQuery course datasets
9. Creating and querying tables with SQL in Google BigQuery
10. Ingesting a CSV dataset into BigQuery and creating a table
11. Writing your first query with the SELECT, FROM and LIMIT clauses
12. Aggregating data with SUM, COUNT, GROUP BY and creating aliases with AS
13. Filtering values with WHERE and sorting data with ORDER BY
14. Understanding subqueries by using the WITH clause
15. Exporting your queries and results into a BigQuery table
16. Knowledge Check
17. Write a SUM Query
18. Exploring semi-structured data with ARRAY_AGG, UNNEST and STRUCT
19. What is an "Array" and why does it matter?
20. Grouping values together with STRUCT to define array hierarchy
21. Creating an array in an existing flattened table with ARRAY_AGG
22. Filtering and unnesting arrays with UNNEST
23. Knowledge Check
24. Create an ARRAY
25. Combing multiple tables with different JOIN statements
26. What are the different types of SQL JOINs?
27. Joining tables with a one-to-one relationship (INNER and LEFT JOINs)
28. Calculating percentage difference within a JOIN
29. Introducing multiple JOIN keys in many-to-many table relationships
30. Knowledge Check
31. Create an INNER JOIN
32. Project 1: Exploring eCommerce and CRM user-level data in Google Analytics 360
33. Setting up a public Google Analytics 360 dataset in BigQuery
34. Understanding website traffic sources and volume (Users, Sessions and Pageviews)
35. Re-grouping your traffic sources (Default Channel Groupings) with CASE
36. Part 1: Analyzing best-selling products and categories with WHERE and UNNEST
37. Part 2: Analyzing best-selling products and categories with WHERE and UNNEST
38. Identifying high-value customers to find CRM matches and activate insights
39. Practical Activity
40. Project 2: Visualizing BigQuery tables and queries in Google Data Studio
41. Connecting your BigQuery table to Data Studio
42. Visualizing your table by using different chart types
43. Writing Custom SQL queries directly in Data Studio
44. Using the Google Data Studio Explorer for generating insights faster
45. Practical Activity
46. Conclusion
47. Next Steps
48. The Beginner’s Guide to Using BigQuery with Google Data Studio
49. PROMO: Supermetrics for Google BigQuery

"BigQuery ML lets you create and execute machine learning models in BigQuery using standard SQL queries."

Big Query ML is a blessing for engineers who want to work in Machine Learning domain but lack programming language like Python, R. With Big Query ML, they can use their existing SQL knowledge to build operational production-grade Machine learning models.

What's included in the course ?

• Brief introduction to various Machine Learning services of Google Cloud.

• Fundamentals of BigQuery ML and challenges which it solves.

• All of the Machine Learning algorithms are explained in 2 Steps :

  Step 1 : Theoretical explanation of working of an ML algorithm.

  Step 2 : Practical implementation of the ML algorithm in BigQuery ML.

• Each and every Machine learning algorithm is explained with HANDS-ON examples.

• Hyperparameter tuning of models, Model Explainability functions, Feature pre-processing functions.

• Model management operations using bq commands.

• BigQuery ML pricing (Flat rate & On-demand pricing models).

• Assignment for each Machine learning algorithm for self Hands-On in Big Query ML.

• Learn Best practices and Optimization techniques for BigQuery ML.

Machine Learning algorithms explained:

• Linear regression

• Logistic regression

• K-means clustering

• Boosted Tree

• Deep neural networks

• ARIMA+ Time series Forecasting

• Product Component Analysis (PCA)

• Matrix Factorization

After completing this course, you can confidently start creating production-grade Machine Learning models in Real-world corporate projects using BigQuery ML.

Add-Ons

• Questions and Queries will be answered very quickly.

• Queries, datasets and references used in lectures are attached in the course for your convenience.

• I am going to update it frequently, every time adding new components of Bigquery ML.

1. Introduction to GCP
2. Introduction to Google Cloud Platform
3. GCP vs AWS vs Azure - Why choose GCP
4. AI & ML services in Google Cloud
5. BigQuery ML (BQML) introduction
6. What is BigQuery ML
7. Conventional ML challenges and How Big query is addressing them
8. BigQuery ML Features
9. Advantages of BigQuery ML
10. Lifecycle/Workflow of a BigQuery ML Project
11. BQML supported models
12. BigQuery Basics - Crash course
13. Announcement
14. Setup a GCP account
15. Important Note
16. Create a Project
17. BigQuery UI Tour
18. Create a Dataset
19. Create a Table
20. Assignment - Create Table
21. Linear Regression
22. What is Linear regression - Part 1
23. What is Linear regression - Part 2
24. High-level view of Create Model query
25. Limitations of Create model query
26. Linear regression Example Use case
27. Basic Options in Create model query
28. Overfitting problem
29. L2/Ridge regularization
30. L1/Lasso regularization
31. Gradient Descent Optimize Strategy
32. Types of Gradient Descent
33. Learn rate Option
34. Other Options in Create model query
35. Model Training - Write Create model Query for Linear regression
36. Exploring Model details
37. Model Evaluation Query (ML.EVALUATE)
38. Model Training - Optimize Create Model Query
39. ML.TRAINING_INFO Function
40. Model Prediction (ML.PREDICT)
41. Quiz 1
42. Assignment - Linear regression
43. Hyperparameter Tuning in BigQuery
44. What is Hyperparameter Tuning ?
45. Hyperparameter Tuning Options in BigQuery
46. Tune the Linear regression model
47. ML.TRIAL_INFO Function
48. Model Explainability Functions
49. Why Model Explainability is important ?
50. Model Explainability Functions in BigQuery
51. ML.WEIGHTS Function
52. List of functions supported by all models
53. Logistic regression
54. What is Logistic regression ?
55. Sigmoid Function
56. Logistic regression Example Use case
57. Model Training - Write Create model Query for Logistic regression
58. Evaluation metrics Fundamentals explained
59. Precision, Recall, Accuracy, F1 score
60. Evaluation Functions in BigQuery
61. Prediction Function (ML.PREDICT)
62. Applications of Logistic regression
63. Quiz 2
64. Assignment - Logistic regression
65. Feature Pre-processing
66. Automatic Feature Pre-processing
67. Manual Feature Pre-processing - Part 1
68. Manual Feature Pre-processing - Part 2
69. FEATURE_INFO Function
70. K-means Clustering
71. What is Clustering
72. K-means algorithm working
73. Advantages & Disadvantages of K-means
74. Applications of K-means algorithm
75. Options in Create model query
76. K-means Example in BigQuery - Create model
77. K-means Example in BigQuery - Evaluation
78. K-means Example in BigQuery - Prediction
79. K-means Example in BigQuery - Anomaly detection
80. Quiz 3
81. Assignment - Kmeans Clustering
82. Boosted Trees
83. What is Boosting and Why it is needed
84. Boosted Tree working explained
85. Types of Boosting
86. Options in Create model query - Part 1
87. Options in Create model query - Part 2
88. Boosted Tree Example - Use Case Intro & EDA
89. Boosted Tree Example - Feature Engineering Part 1
90. Boosted Tree Example - Feature Engineering Part 2
91. Boosted Tree Example - Create model
92. Boosted Tree Example - Hyperparameter Tuning
93. Boosted Tree Example - Evaluation
94. Quiz 4
95. Boosted Tree - Assignment
96. Model management Operations in BigQuery
97. Introduction
98. Operations on Models - Part 1
99. Operations on Models - Part 2
100. Deep Neural Network (DNN)
101. What is Artificial Neural Network
102. Working of Artificial Neural Network
103. DNN working explained
104. Activation Functions - Sigmoid, TanH
105. Activation Functions - RELU
106. Which Activation Function to choose?
107. Dropout technique to avoid Overfitting
108. HIDDEN_UNITS Option
109. Optimizer in DNN
110. Other Options in DNN
111. DNN Example Use Case
112. DNN Example Implementation in BigQuery ML
113. Quiz
114. Assignment - DNN
115. Principal Component Analysis (PCA)
116. What is dimensionality reduction ?
117. Working logic of PCA
118. Mathematics behind PCA (4 step procedure)
119. BigQuery Model Options in PCA
120. Creating PCA Model
121. Evaluating and Inferencing PCA model
122. Assignment - PCA
123. BigQuery ML Pricing
124. Free operations in BigQuery ML
125. What is Flat rate pricing model
126. Costs involved in Flat rate pricing model
127. Reservations
128. BigQuery ML On-demand pricing model
129. Calculate price for Create Model query
130. Quiz - Pricing
131. Matrix Factorization (Collaborative Filtering)
132. Introduction to Matrix Factorization (Recommendation systems)
133. Content Filtering
134. Model based Collaborative Filtering
135. Memory based Collaborative Filtering
136. Create model Options
137. Purchase BigQuery slots for Matrix Factorization
138. Create Recommendation Model using Matrix Factorization
139. Evaluation and Recommendation
140. ARIMA+ for Time series Forecasting
141. What is Time series Forecasting ?
142. Components of Time series
143. Stationarity in Time series
144. Auto regression (AR) in ARIMA
145. Moving Average (MA) in ARIMA
146. ARIMA+ Options - Part 1
147. ARIMA+ Options - Part 2
148. ARIMA+ Example - Use case & EDA
149. ARIMA+ Example - Create Model
150. ARIMA+ Example - Evaluation
151. ARIMA+ Example - Inferencing Functions
152. ARIMA+ Example - Model Explainability
153. Assignment - Arima +
154. Additional Learnings
155. Google Cloud SDK setup
156. Bonus
157. Bonus