Paperspace Gradient - ML platform with their own data centers and IPU processors
Paperspace Gradient machine learning platform is best known from extensive GPU support. They have recently partnered with Graphcore to provide new generation Intelligence Processing Units .
Saturn Cloud - Data science workspace with Dask cluster
Saturn Cloud is a greate choice for data science teams who want to maximize flexibility of their environment. Integrated parallel processing with Dask differentiates it from the competitors.
Datalore - Collaborative data science platform with great notebook experience
Datalore is collaborative data science platform from Jetbrains. The notebook experience has been taken to the next level. The company is best known for its Python IDE PyCharm.
Bodo is a faster alternative for Spark to run massive ETL jobs in Python
Bodo is a platform for data processing with Python and SQL. It is especially suitable for large datasets thanks to its unique parallel processing technology.
Vertex AI User-Managed notebooks auto shutdown
User-Managed notebooks in Vertex AI are virtual workspaces for data exploration. But they lack automatic shutdown after being idle for specific amount of time.
30 questions for Google Cloud Professional Machine Learning Engineer exam
Around 30 questions I memorize from the Google Cloud Professional Machine Learning certification exam. You find all sources for exam training questions from my preparation tips.
I became a certified Google Cloud Professional Machine Learning Engineer!
After 4 months of intense studying I passed the Google Cloud certification for Professional Machine Learning Engineer! Google Cloud Platform certificates are considered to be challenging compared to other cloud platforms .
MLOps in Google Cloud
Google Cloud Platform has excellent toolset to operationalize and productionize machine learning models. Vertex AI is the key MLOps product while Google Kubernetes Engine is valid alternative for custom workflows.
Neural networks for natural language processing
Natural Language Processing (NLP) refers to tools and methods to explore text data as well as identifiy patterns and making predictions.
Neural networks for image recognition
Some notes about image recognition while preparing for Google Cloud MLE certification.
Keras for basic neural networks
Keras is one of the high level APIs in Tensorflow deep learning stack. It is the recommended framework to get started with neural networks, if you do not have special requirements.
Tensorflow Extended (TFX) for MLOps
Tensorflow Extended (known as TFX) is a framework to define ML pipelines. The extensions are obviously compatible with the core Tensorflow.
Tensorflow for ML Engineers
I have more experience from Pandas and Scikit-Learn Python libraries compared to Tensorflow. I was surprised how large the Tensorflow ecosystem with its ML engineering extensions.
Recommendation systems in Google Cloud
Recommendation systems are useful to personalize experience and find relevant items among huge catalogs. Recommendations have became signigficant sub topic of machine learning.
Introduction to neural networks for ML
I heard about artificial neural networks first time around 2017. Since then I have tried to understand their behavior and explain them in a simple way.
Dataflow for ML Engineers in Google Cloud
Dataflow product in Google Cloud is mandatory for advanced data processing pipelines for machine learning solutions. It performs typical data engineering tasks by allowing same code to execute both batch and streaming.
Machine learning fundamentals
Notes about fundamental ML concepts for Google Cloud ML Engineering certification. Data exploration Perform mainly univariate and bivariate analysis during initial exploration.
Vertex AI for ML Engineers in Google Cloud
Some Google materials refer to it as Fully managed Tensorflow. Vertex AI assumes that data is prepared elsewhere before training the model.
BigQuery for ML Engineers in Google Cloud
BigQuery is by far the most important storage and processing service in Google Cloud from ML perspective. It has many integrated functionalities for ML.
Machine learning products in Google Cloud
This is a summary of Google Cloud Platform (GCP) products relevant for Machine Learning Engineer role. Google philosphy seems to be that moving to their platform requires minimal changes to the existing solution.
Running Flask frontend and backend in Kubernetes
Kubernetes have been everywhere lately. Especially in the context of MLOps. I gave it a try by creating web app with Python Flask.
Free data science workspaces
Google Colab, Databricks Community Edition, Visual Studio Code and Dcoker are some options to create a free data science workspace.
Comparison of machine learning platforms in major clouds
Comparing the major machine learning platforms AWS SageMaker, Azure Machine Learning, Google Vertex AI and Databricks.
What is a machine learning platform?
What is a machine learning platform? Introducing different components such as workbench, MLOps tools and cloud computation.
Machine learning in predictive maintenance
Machine learning in predictive maintenance. The two-part blog series provides insights for cost savings and an example script in Python.
Faking your geographical location to a web service - A hobby project
How to fool a web service about your actual location? In an experiment I pretended being in Ireland while traveling in Sweden.
Difference between data scientist and data engineer roles
In my opinion the big difference is that a data scientist focuses more on business problems while data engineer solves technical problems.
DataCamp - Learn data science online
Experiences from DataCamp online training. Structured data science courses are easy to organize for yourself or a team.
PySpark execution logic and code optimization
The article goes through the PySpark execution logic and provides guidelines to optimize the speed and performance.
Clustering data using SQL - An example with industrial IoT data
Clustering time series data with SQL - Nice 3D visualization using simple logic. Python notebook example in GitHub with industrial data.
Spark + Python tutorial for data developers
A tutorial for parallel computation with Spark and Python. The example has been ran on AWS cloud computing platform.
Introduction to AWS Glue for big data ETL
AWS Glue service works especially well for big data batch processing. Read the full post from data.solita.fi.
Finnish stemming and lemmatization in python
I wrote to Solita's blog about text analytics with the headline "Finnish stemming and lemmatization in python". The post has code examples.
Experiences from funding application classification by text analytics
Experiences from funding application classification by text analytics
Combining machine learning and business - Practical example
I give an example about machine learning use case in a format that should be understandable also for less technical people.
Maximizing uptime in Hiab hackathon
Read about Solita team's solution in a hackathon organized by Hiab. The task was to take advantage of data to maximize machine uptime.
Csv headers to list using Python
Python code to automatically list header fields of multiple CSV files. The original use case was related to data warehouse documentation.
Sports betting tutorial - Can you make the living?
You can make the living by sports betting. The blog is not sponsored as I'm sharing my own experiences. Read the tutorial.
Visualization and clustering of earthquake dataset
The built-in dataset quakes in RStudio had 1000 records of earthquakes nearby Fiji. The first year of observations is 1964 but the last year remains unknown.
Virus problem - A statistical puzzle
The problem: A virus is spreading across the world - it kills without treatment. Your task is to solve a statistical puzzle.
Data science and business intelligence - Definitions
It's easy to spot these hype terms like data science, big data in LinkedIn or exhibition posters. I summarized the definitions.
Django tutorial - For data oriented web developers
Python based Django web framework offers a great platform to create a data oriented web application for any size of needs.