Piers Stobbs’ Post

🚀 Exploring Data for Informed Decision-Making 🚀 Hey LinkedIn fam! 👋 As we all dive deeper into the world of data-driven decision-making, I'm curious about your thoughts on the choice of datasets. 💡 Personally, I've been exploring the power of JSON for its flexibility and versatility. It makes handling nested and complex data structures a breeze, especially when dealing with various parameters and relationships. 🌐 However, CSV has its merits too! The simplicity and tabular structure make it easy to work with, but the challenge arises when we need to manage nested data. I'd love to hear your perspectives! 🤔 What type of datasets do you find most applicable for data-driven decision-making, and why? Are you more inclined towards the straightforward CSV or the dynamic JSON? Let's spark a conversation and share insights! Comment your thoughts below, and let's build a collective knowledge hub. And here is my link to my Github project repository do check it out I take suggestions and advice. https://lnkd.in/g_Z5TB2c 🚀 #datadriven #decisionmaking #datascience #json #csv #collabration Looking forward to some enlightening discussions! 🔍💬

🎉 Just completed an intensive Git and GitHub course on 365 Data Science platform! Excited to apply my newfound skills to real-world projects and collaborate with others. Let's connect and code together! #Git #GitHub #Coding #Collaboration #365DataScience

Are you interested in open source data/coding? The come along to our Data Science Community Showcase session tomorrow! Looking forward to talking about how we can make more of what we do open source! Lewis Edwards Zoë Turner Timothy Green

Dear network✨, 🌟 New Certification Unlocked! 🎉 Excited to share that I've successfully completed the Git and GitHub program by 365 Data Science! 🚀🔗 Developed essential version control and collaboration skills. 💻🤝   #GitCertification  #GitHubSkills  #365DataScience

In addition to working through the Data Science Certification, I'm excited to share I've completed another DataCamp project! This project provided me with a dataset of Netflix movies and TV shows and tasked me with finding if movies have declined in duration as years have passed. I'm happy to report that they haven't! Within the project, I was asked to import a Netflix dataset, convert it into a Pandas dataframe, subset the frame to remove TV shows, and finally subset further to keep only specific columns of interest(title, country, genre, release year, duration). Having created my new consolidated dataframe, I was ready to iterate through the columns and assign colors to the movies based on their genre, this was done such that I could better differentiate movie genres upon plotting my data. With my data properly color coordinated, I was able to use Pandas scatterplot function to visualize my data, and found that Netflix movies have maintained a somewhat even pattern of duration as time has passed. Surprisingly, it was documentaries (denoted by blue dots) that seemed to show the only decline in duration. This project sparked my interest as it provided me with meaningful results derived from originally unorganized and difficult to interpret data. I'm excited to continue working through DataCamp's certification and to share my progress here! Check out my code!

#100DaysofDataScienceCode 📊 Day 55 of 100 Days of Data Science Coding! 🤝🔄 🔹 Today's Focus: Introduction to Principal Component Analysis (PCA)🔹 Today, I delved into the intriguing world of Principal Component Analysis (PCA), a fundamental technique in dimensionality reduction and data compression. 🔸 What is PCA? 🌟 - Principal Component Analysis is like a wizard's spell that transforms high-dimensional data into a simplified form while retaining its essential patterns. - Imagine it as a way to capture the most critical aspects of your data while discarding the less important details. 🔸 Why PCA? 🤔 - Dimension Reduction: In today's data-rich world, we often face datasets with numerous features. PCA helps us reduce dimensions, making data more manageable. - Noise Reduction: It filters out noise, enhancing data quality. - Visualization: PCA aids in visualizing complex data, especially in two or three dimensions. 🔸 How Does PCA Work? 🛠️ - PCA identifies the directions (principal components) along which the data varies the most. - It projects the data onto these new axes, creating a new set of uncorrelated variables. - The first principal component explains the most variance, the second the second most, and so on. 🔗 GitHub Repository: For getting more insights into Principal Component Analysis (PCA), delve into my GitHub repository: 🔗 Link to my GitHub Repository: https://lnkd.in/dy-xwfqg By mastering PCA, we unlock the potential to analyze high-dimensional data effectively, visualize it in lower dimensions and build more efficient machine learning models. Stay tuned for more data science adventures! 📊🧮✨ #100DaysofDataScienceCode #DataScience #PCA #DimensionalityReduction #MachineLearning #100DaysOfCode

#100DaysofDataScienceCode 📊 Day 56 of 100 Days of Data Science Coding🤝🔄 🔹 Today's Focus: Steps in Principal Component Analysis (PCA)🔹 Today, I navigated through the intricate journey of Principal Component Analysis (PCA) by dissecting its core steps. PCA is a formidable tool for dimensionality reduction, and understanding its mechanics is essential for every data scientist. 🔸 The Steps in Principal Component Analysis (PCA) 🧭 1. Data Pre-processing: Begin by standardizing or normalizing your data. PCA is sensitive to the scale of your features. 2. Covariance Matrix: Calculate the covariance matrix of your standardized data. This matrix tells you how different features relate to each other. 3. Eigenvalues and Eigenvectors: Find the eigenvalues and eigenvectors of the covariance matrix. These are crucial for determining the principal components. 4. Sort Eigenvalues: Arrange the eigenvalues in descending order. This step helps you decide how many principal components to retain. 5. Select Principal Components: Based on the explained variance, select the top 'k' eigenvalues and their corresponding eigenvectors to form the new feature space. 'k' is the number of dimensions you want to reduce to. 6. Project Data: Transform your original data onto the new feature space formed by the selected principal components. This step reduces dimensionality. 7. Data Reconstruction (Optional): If needed, you can reverse the transformation to get back to the original feature space. 🔸 Why PCA? 🤷♂️ - Dimension Reduction: It simplifies complex data with many features. - Noise Reduction: PCA helps eliminate noise and redundancy in data. - Pattern Recognition: It reveals patterns and relationships between variables. 🔗 GitHub Repository: For getting more insights into steps involved in Principal Component Analysis (PCA), delve into my GitHub repository: 🔗 Link to my GitHub Repository: https://lnkd.in/dy-xwfqg Mastering PCA is like wielding a data science scalpel. It enables you to surgically extract essential insights from high-dimensional data. Tomorrow, we'll explore more practical applications of PCA. Stay curious, fellow data scientists! 📊✨ #100DaysofDataScienceCode #DataScience #PCA #DimensionalityReduction #MachineLearning #100DaysOfCode

I just published a public Github repo with all the resources (e.g. books, YouTube channels, communities, etc..) you need to learn Data Science, break into the job market, and stay relevant. Each category is limited to a maximum of 5 resources to ensure you get the most valuable and relevant resources out there, without getting overwhelmed by too many choices (which is a big problem when trying to learn online). Let me know your thoughts and ideas below. I think I'm missing a few important sections like "conferences"👇 By the way, big thanks to Zach Wilson for inspiring me to create this with his "Data Engineer Handbook" 🙏 #DataScience

[Learning Progress Review Week 2] Hello everyone! Time flies so fast, it's already my second week dived into the world of data processing! This week, I've been learing SQL to derive valuable insight from manipulating data. For instance, I've been sorting customer by the greatest amount of purchasing and grouping by it's spesific region. On top of that, I was introduced to Version Control System (VCS), a system that promote collaboration for programmer. I've been delved into Git and Github, one of the most popular VCS. Here the review about our second week in data science bootcamp with the data wizards team #datascience #learningprogressreview #digitalskola #datawizards

Care for some data jokes then Dare to keep reading 😎 Alright guys! Here we go! 🗣Why did the data engineer never go to the beach? He couldn't tell the difference between sand and his data lake! 🗣Why did the data engineer always carry a spoon? He loved to stir the ETL pot! 🗣Why did the data engineer break up with SQL? He wanted a NoSQL relationship! 🗣Why was the data engineer great at group projects? He mastered distributed tasks! 🗣Why did the data engineer always bring a divider to meetings? He loved partitioning! Hit the 👍 button and follow Fathima Zajel Liyakath for more fun content!