Project SPARTA PH's SP901 FINAL CAPSTONE: Data Science and Machine Learning Using Python | Week 5: Model Evaluation Improvement

This is it! The SP901 - Data Science and Machine Learning Using Python FINALS - the capstone project! A hearty congratulations to you for reaching this milestone. You've achieved a remarkable feat, and it's a testament to your dedication and hard work.

I am particularly delighted that SPARTA, in its inaugural launch, provides the flexibility of a self-paced learning journey. This privilege allowed me to immerse myself in this Python-focused course and dedicate the necessary time to master the content. It's worth noting that this comprehensive journey took me a span of two months to complete. The sense of accomplishment is truly overwhelming, and I can't help but look back on this with a smile and a few happy tears. (Umiiyak sa banyo para di makita ng asawa ko!) Haha! 

Without further ado, I am thrilled to present my capstone project for SP901 - Data Science and Machine Learning Using Python. 

I hope this project will serve as an inspiration for your own learning!

Happy Learning SPARTANs! 

Project SPARTA PH's SP901: Data Science and Machine Learning Using Python | Week 4: Representing Data and Engineering Features

I am only retrieving files from Coursebank's SPARTA's archived course. It is bit interesting that 4.6 Exit Assessment is locked. After years, I can't remember the assessment question too. I am sorry for that.

Anyways, here are the snapshots of my Jupyter notebook.

Sa mga nahihirapan po sa SP901: Data Science and Machine Learning Using Python check nyo po itong libro na ito, andyan po ung mga sinasabi ni teacher.. medyo verbatim 

https://www.oreilly.com/.../introduction.../9781449369880/ 

Introduction to Machine Learning with Python

by Andreas C. Müller, Sarah Guido

Happy Learning SPARTANs! 

Project SPARTA PH's SP901: Data Science and Machine Learning Using Python | 3.3.1 Unsupervised Learning

Imagine you're teaching a computer to do cool things.. like categorising ;) So what is the difference of Supervised and Unsupervised Machine Learning? 

Supervised Machine Learning:

Think of this like a teacher guiding a student. In supervised learning, we give the computer a bunch of data and also tell it what the correct answers should be. It's like having a teacher's answer key for a test. The computer then learns from this data and uses it to make predictions or decisions.

For example, if we want the computer to recognize cats and dogs in pictures, we'd show it lots of images of cats and dogs and tell it which is which. The computer learns to spot the differences, like pointy ears for dogs and whiskers for cats. This way, it can make predictions when it sees new pictures, like telling us if it's a cat or a dog.

Unsupervised Machine Learning:

Now, unsupervised learning is a bit different. Here, it's like giving the computer a bunch of stuff and letting it figure things out on its own. No teacher's answer key this time. The computer's job is to find patterns, group similar things together, or discover hidden structures in the data.

For example, imagine we have a bunch of customer data from an online store. In unsupervised learning, the computer might notice that some customers tend to buy similar items, and it groups those customers together. This can help the store recommend products to customers based on what others with similar tastes bought.

So for the Week 3, are you ready for Unsupervised Learning? Wink-wink! 

Again, I posted my Jupyter Notebook for a reason. But if you really need my notebook, you can send me a message on our Facebook page :) 

3.3.1 Unsupervised Learning

Guidelines:

* Using the IRIS dataset, create the following algorithms:

     - Kmeans

     - DBSCAN

     - Hierarchical

* After that, compare the results using ARI and Silhouette Score 

Project SPARTA PH's SP901: Data Science and Machine Learning Using Python | 2.7.1 Supervised Machine Learning

Did you know that SP901 was released before SP202, introducing me to the world of Python programming? My first experience with this computer language left me feeling like a fish out of water, struggling to communicate with the machine, and the machine with me. (Ganti-ganti lang! Haha) 

The journey into Python was demanding, somewhat painful, and at times, I found myself questioning why I was putting myself through it. But without further ado, let me share with you the snapshots of the weekly assignments for this course.

I made it in jpg form for you to type in your own Jupyter Notebook, by taking the time to type out our code in our Jupyter Notebook, we're not just copying and pasting; we're building a deeper knowledge of Python and the exciting world of supervised machine learning.

2.7.1 Supervised Machine Learning

Guidelines:

Using the the Breast Cancer dataset, perform the following techniques for binary classification:

- Logistics Regression

- RF

- SVM

For Improvement: Utilize graphs and charts to provide a more comprehensive models than relying only on the accuracy of trainings and tests. 

Learn From My Mistakes: SP401: Dashboard and Drill Down Analytics

This course is all about unlocking the true value of data, which is super important for us data analysts. In this course, it discussed KPI’s, metrics and we'll learn how to draw meaningful insights that can make a real difference in any company. 

Now, I want to share my very first dashboard with you! As I started my journey of upskilling, I must admit, I learned a lot from my experiences. Looking back, I can now critique my own work, and it's kinda funny too. Haha! 

Learn From My Mistakes: SP401: Dashboard and Drill Down Analytics

Here are three important lessons I learned from my first dashboard: 

1. Research on Color Palettes: I realized that choosing the right colors for the dashboard is crucial to make it visually appealing and easy to understand. 

2. Tell a Story with KPIs: Instead of just showing raw numbers, I should focus on identifying related KPIs that can help me craft a compelling story or insight. That way, my data presentations will be more engaging and impactful. 

3. Embrace Different Charts: I could have done it better if I learned about different charts, it's usage and explanation it is portraying. 

As I recall, I didn't use any pivot table/chart in this dashboard. Even though I didn't use those in my very first dashboard, it was still a great starting point for me. I'm eager to enhance my skills and become more proficient in using various data visualization tools. 

Well, that is my first and I am glad I do start. This skill is an additional package of what I am now and I am grateful to SPARTA for giving out this kind of FREE education for all. 

If you want a copy of my Excel dashboard, feel free to drop us a message on our Facebook Page. Keep learning and enjoy your data analytics journey! Happy Learning!