Julio Cesar Bernal Fernandez

Gradient boosting is currently one of the most popular techniques for efficient modeling of tabular datasets of all sizes. I learned how to use the powerful library XGboost alongside pandas and scikit-learn to build and tune supervised learning models. I worked with real-world datasets to solve classification and regression problems.

5

Dashboard

31

2 comentarios

I just finished the DBT fundamentals course! 🥇😊 #DBT #DataAnalysis #DataTransformation #DataManipulation

11

2 comentarios

Open Letter to Peru: Control Your AI Future!: I spent a fabulous week in Peru, keynoting the 2024 Data & AI Summit, lecturing at the University of Technology and Engineering (UTEC), and meeting many marvelous folks curious to learn about the role that AI can play in their personal and professional lives. This journey has motivated me to share my thoughts on what… Read More »Open Letter to Peru: Control Your AI Future! The post Open Letter to Peru: Control Your AI Future! appeared first on Data Science Central. #DataScience #BigDataAnalytics #AI

1

A guide to choosing the correct classification model 🔷

3

I learned how to use Python to train decision trees and tree-based models with the user-friendly scikit-learn machine learning library. I understood the advantages and shortcomings of trees and demonstrated how ensembling can alleviate these shortcomings, all while practicing on real-world datasets. Finally, I also understood how to tune the most influential hyperparameters in order to get the most out of my models.

6

More about *Kaggle* 👇👇👇 *Must Watch* 🧑‍💻🧑‍💻🧑‍💻 https://lnkd.in/dSyBQcxx #microsoftpowerbi #dataanalysis #PowerBI #DataScience #dataanalyst #GenAI #machinelearning #deeplearning #artificialintelligence

1

I am thrilled to announce that I am now a Databricks Certified Machine Learning Professional! 🎉 Throughout this journey, I've gained valuable skills in MLOps, MLflow, PySpark, and Databricks features. This certification has not only equipped me with the knowledge to build and manage robust machine learning models, but also the ability to deploy and monitor these models in a production environment. #Databricks #MachineLearningEngineering #DatabricksLearning

44

1 comentario

These are the top subscriptions (both free and paid) that are a MUST-have for any data professional. ⬇ 1️⃣ Chartr.co An outstanding free newsletter tailored for data professionals. It excels in delivering news and mastering the art of storytelling. Absolutely free! 2️⃣ TLDR for AI This free newsletter offers top-notch AI content. Stay updated with the latest in AI without a subscription fee. Link: https://lnkd.in/gmb-AbbJ 3️⃣ Medium A terrific platform for learning alongside like-minded individuals. It boasts a vibrant tech community. Following the right thought leaders can significantly enhance your skills. I don't write articles, but I dedicate 20-30 minutes daily to reading. Cost: $5/month. 4️⃣ ChatGPT I haven't found a better overall tool among many large language models. It's essential for coding, organization, and planning. Occasionally, DALL·E also proves invaluable for presentations. Cost: $20/month. 5️⃣ Cloud Systems As data professionals often handle massive datasets, it’s practical to keep our laptops light. Storage costs are quite reasonable, and the flexibility is unmatched. Price varies. What subscriptions do you find invaluable in your professional toolkit? Any recommendations? - - - - - - P.S. I am not affiliated with any of these services and have not been compensated for my recommendations. #DataScience #ProfessionalDevelopment #TechTools #BusinessIntelligence #Innovation

29

46 comentarios

📈 Forecast Evaluation for Data Scientists: Common Pitfalls and Best Practices 🔑 "In this work we provide a tutorial-like compilation of the details of one of the most important steps in the overall forecasting process, namely the evaluation." 📙 arXiv:2203.10716

4

Hey #datafam ! I want share this viz with you because in México (especificly in Cuernavaca) its hotter !!! 🔥 Come on to check this viz in Tableau and give your feedback! Link: https://lnkd.in/erBJxCdM #tableau #datavisualization #viz #togglebuttons #tableaupublic

4

Excel's PivotTable has long been a formidable tool for data analysis. With the addition of the Recommended PivotTable feature, it has become even more accessible and intuitive for uncovering valuable insights from your data. In this brief demonstration, you'll see that while this feature is impressive, it is not infallible. However, you can customize it by adjusting the value field settings in the PivotTable, just as you would with any traditional PivotTable. You can follow along with this demo using the exercise file available on my website: https://lnkd.in/gT27ZbT9. This feature is particularly beneficial for those less familiar with PivotTables who are looking for a quick start, or for those who seek rapid analysis without the complexities of detailed PivotTable creation. It is also advantageous for those cautious about deeper AI integration. Additionally, mastering this skill is advantageous before diving into Copilot, as Copilot frequently incorporates PivotTables in its suggested outputs.

5

3 comentarios

🔍 Mastering Sampling for Accurate Data Insights 🔍 In the realm of data science, the right sampling method is crucial for deriving accurate and reliable insights. Here’s a quick guide to help you navigate through the best practices and common pitfalls: 🚫 Biased Sampling Methods to Avoid: 1. Convenience Sampling: Selecting easy-to-reach samples; often leads to misleading results. 2. Voluntary Response Sampling: Participants self-select, typically attracting those with strong opinions. 3. Judgmental Sampling: Researcher uses personal judgment to select samples, introducing bias. 4. Snowball Sampling: Current participants recruit future ones, often resulting in a network effect. 5. Undercoverage Bias: Fails to represent parts of the population. 6. Nonresponse Bias: Significant differences between respondents and non-respondents can skew results. ✅ Effective Random Sampling Methods: 1. Simple Random Sampling: Every member has an equal chance of selection, ensuring unbiased representation. 2. Systematic Sampling: Selects every nth member from a list, starting at a random point. 3. Stratified Random Sampling: Divides population into subgroups (strata) and randomly samples each, ensuring all segments are represented. 4. Multistage Sampling: Combines multiple sampling methods for greater efficiency and accuracy. Choosing the right sampling method is essential for obtaining representative and actionable data insights. Ensure your approach minimizes bias and maximizes accuracy for reliable results. #DataScience #Statistics #SamplingMethods #DataQuality #Analytics #Research #MachineLearning #AI Got questions or experiences to share about sampling methods? Let’s discuss in the comments! 👇

2

Master Data Science: Your 100-Day LinkedIn Challenge Embark on your data science journey with this step-by-step guide! Are you an aspiring data scientist, eager to unlock the power of data? This 100-day challenge is your roadmap to success. Follow along, learn, and connect with a supportive community! The Journey Begins (Days 1-10): Python Fundamentals: Master syntax, variables, data types, and control flow. (Check out Corey Schafer on YouTube!) Coding Practice: Sharpen your skills with basic problems on platforms like HackerRank or LeetCode. Math & Stats: Building the Foundation (Days 11-20): Probability & Statistics: Solidify your knowledge with Khan Academy's courses. Linear Algebra & Calculus: Gain intuitive understanding through 3Blue1Brown's engaging videos. Data Analysis with Pandas (Days 21-30): Pandas Basics: Become comfortable using DataFrames, Series, and data manipulation techniques. (Data School on YouTube offers a great intro!) Practice Makes Perfect: Test your skills on real datasets from Kaggle. Visualizing Insights (Days 31-40): Matplotlib & Seaborn: Learn to create impactful visualizations with these powerful libraries. (Corey Schafer can guide you here.) Data Visualization Projects: Put your learning into practice with Kaggle datasets. Machine Learning Fundamentals (Days 41-60): Understand the Core: Grasp regression, classification, and clustering with Sentdex on YouTube. Hands-on Implementation: Work with Kaggle datasets to solidify your understanding. Deep Learning with TensorFlow & Keras (Days 61-70): Dive into Neural Networks: Explore the fascinating world of deep learning with Krish Naik's YouTube channel. Build Deep Learning Models: Gain practical experience through TensorFlow and Keras projects. Advanced Topics (Days 71-80): Natural Language Processing (NLP): Learn text processing and sentiment analysis with StatQuest on YouTube. Computer Vision: Explore image processing and object detection using Sentdex's YouTube tutorials. Collaboration & Sharing your Expertise (Days 81-90): Master Version Control: Learn Git and GitHub to collaborate effectively. (Corey Schafer has excellent resources!) Contribute to Open Source: Give back to the community by contributing to projects on GitHub. Real-World Practice & Projects (Days 91-100): Challenge Accepted: Participate in data science competitions on Kaggle or DrivenData. End-to-End Projects: Build comprehensive data science projects using real-world datasets. Remember, this is your journey! Adapt the pace and focus on areas that pique your interest. Stay curious, keep learning, and connect with fellow data science enthusiasts. Together, let's conquer the world of data! A huge thank you to Arif Alam for compiling this fantastic plan and to @python codess for the image!

1

Efficient Architectures in data engineering Efficient architectures in data engineering are essential for maximizing the performance and scalability of data pipelines and systems. These architectures encompass various components, including data storage, processing frameworks, and computational resources, all designed to optimize the flow of data from ingestion to analysis. Key considerations in designing efficient architectures include choosing the right data storage technologies, such as relational databases, NoSQL databases, or data lakes, based on the specific requirements of the application. Additionally, employing distributed computing frameworks like Apache Hadoop or Apache Spark enables parallel processing of large datasets, improving overall performance. For more info read : https://lnkd.in/gnhZSZG7 #nixontechnologiesllc #nixon #nixontechnologysystems #ITservice #nixontech #enterprisesintegration #dataanalytics #cloudcomputing #ITconsultantinindia #USAITconsultant #bestitconsultant #usitconsultant #CRM #dataengineering #softwarejobsinusa #itjobsinusa #usaconsultant #itjobsconsultant #ITInfrastructure2024 #SecOps #SecurityManagement #dataSecurity #CyberSecurity #datascience #cloud #logistics #devops #automachine

1