Wanna build an ML project but do not know where to start?
No worries.
Let me help you π€ β
No worries.
Let me help you π€ β
Building a project is the only way to learn ML and MLOps. However, projects are also tougher to complete than online courses.
Buy hey, "no pain, no gain".
This is how you start your project adventure
Buy hey, "no pain, no gain".
This is how you start your project adventure
The trick is to work on a real-world problem that
β genuinely interests you, so you donβt quit when things get tough
and
β for which you can find relevant data, preferably through live APIs.
How do you find THAT problem?
β genuinely interests you, so you donβt quit when things get tough
and
β for which you can find relevant data, preferably through live APIs.
How do you find THAT problem?
Make a list of 3 problems that interest you, for example
1 β Predict the outcome of NBA matches (sports analytics)
2 β Build a chatbot that writes stand-up comedy (NLP engineering)
3 β Build a trading bot (financial trading)
The next step is to find relevant data.
1 β Predict the outcome of NBA matches (sports analytics)
2 β Build a chatbot that writes stand-up comedy (NLP engineering)
3 β Build a trading bot (financial trading)
The next step is to find relevant data.
Sites like kaggle.com offer static datasets that can help you get started.
If kaggle does not work for your problem, try an open google search, for example
"public dataset of English jokes"
You can consider scrapping a live website, so you sharpen your Python.
If kaggle does not work for your problem, try an open google search, for example
"public dataset of English jokes"
You can consider scrapping a live website, so you sharpen your Python.
Once you find/compile this dataset, you are ready to create an ML model prototype, that showcases the potential of your tool.
If you wanna go one step further and build a complete ML service, you need to find a live API from which you can regularly pull data to feed your model.
If you wanna go one step further and build a complete ML service, you need to find a live API from which you can regularly pull data to feed your model.
If you built a scrapper, you already got your API.
Example: The NBA site has tons of historical and live data you can scrape for free.
Otherwise, try a google search, for example
"free API stock prices"
You will surely find something.
Example: The NBA site has tons of historical and live data you can scrape for free.
Otherwise, try a google search, for example
"free API stock prices"
You will surely find something.
Ready to take your ML career to the next level?
Join the Real-World ML Tutorial + Community and build a complete ML app, from A to Z.
Because THIS IS what companies look for.
Use the discount code "NINJA" to get a 20% discount and LIFETIME access
realworldmachinelearning.carrd.co
Join the Real-World ML Tutorial + Community and build a complete ML app, from A to Z.
Because THIS IS what companies look for.
Use the discount code "NINJA" to get a 20% discount and LIFETIME access
realworldmachinelearning.carrd.co
Wanna get more real-world ML tips and tricks?
β Follow me @paulabartabajo_ so you do not miss what's coming next.
Wanna help?
β Like/Retweet the first tweet below to spread the wisdom βββ
β Follow me @paulabartabajo_ so you do not miss what's coming next.
Wanna help?
β Like/Retweet the first tweet below to spread the wisdom βββ
Loading suggestions...