Best of Data Science — August 2024

1
Article
Machine Learning Mastery·2y
Free Tools Every ML Beginner Should Use
Starting in the machine learning field can be challenging, but several free tools can ease the process for beginners. Essential tools include Jupyter Notebook for creating and sharing documents with code and visuals, Hugging Face for Natural Language Processing (NLP) and large language models, LangChain for developing context-aware AI applications, Scikit-learn for implementing machine learning algorithms in Python, and Kaggle for accessing datasets and participating in competitions. Leveraging these tools can make the learning experience more interactive and efficient.
312
9
2
Article
Machine Learning Mastery·2y
10 Must-Know Python Libraries for Machine Learning in 2024
Machine learning in 2024 has seen significant evolution, with Python continuing to lead the way through its extensive libraries. The field has transitioned from foundational frameworks in 2020, like TensorFlow and PyTorch, to increased emphasis on transformers, AutoML, and scalability by 2024. Key trends include deep learning dominance, scalability, automation, optimization, ecosystem consolidation, and interactive data visualization. Understanding core ML frameworks, data manipulation libraries, visualization tools, and domain-specific utilities is crucial for modern ML tasks.
244
2
3
Video
Tech With Tim·2y
A Python Developers Guide to AI in 2024
211
6
4
Article
KDnuggets·2y
3 Most Popular Bootcamps to Learn Python
Enhance your coding journey with these top 3 data science bootcamps for learning Python. From beginner to expert, you can choose from 'Zero to Hero in Python,' a comprehensive 22-hour course, 'Python Pro Bootcamp,' a 100-day project-based course, and 'Automate the Boring Stuff with Python,' designed to teach practical automation. Ideal for anyone looking to leverage Python in data science, these courses offer extensive materials, practical projects, and certification upon completion.
174
7
5
Article
Javarevisited·2y
Top 30 Free Udemy Courses to Learn Python in 2024
Discover the top 30 free Udemy courses to learn Python in 2024, suitable for beginners, intermediate, and advanced developers. These courses cover a wide range of topics including Python basics, web development frameworks like Django, machine learning, data analysis, and more. Enhance your Python skills with practical exercises and stay updated with industry trends.
128
2
6
Video
Programming with Mosh·2y
The Complete Data Analyst Roadmap [2024]
85
2
7
Article
Daily Dose of Data Science | Avi Chawla | Substack·2y
A Crash Course on Graph Neural Networks
Graph Neural Networks (GNNs) extend deep learning techniques to graph data, addressing the limitations of traditional models in capturing complex relationships. This piece covers the basics, benefits, tasks, data challenges, frameworks, and practical implementation of GNNs.
75
8
Article
KDnuggets·2y
5 Common Data Science Mistakes and How to Avoid Them
Data scientists often make five common mistakes that can negatively impact their projects: rushing into projects without clear objectives, overlooking foundational steps like data cleaning and statistics, choosing the wrong visualizations, neglecting feature engineering, and focusing more on accuracy than overall model performance. Understanding these pitfalls and how to avoid them is key to improving your workflow and becoming a more effective data scientist.
52
9
Article
KDnuggets·2y
Top 5 Free Machine Learning Courses to Level Up Your Skills
Highlighting five free machine learning courses to enhance your skills, this guide covers a range of options from deep learning with Andrew Ng's 'Generative AI for Everyone' to Stanford's classic 'CS229: Machine Learning'. It also includes specialized courses like 'Mathematics for Machine Learning' by Imperial College London and practical deep learning applications with fast.ai. Ideal for both beginners and those with some coding experience, these resources provide a solid foundation in the field of machine learning.
49
1
10
Article
KDnuggets·2y
Top 7 Alternatives to VSCode for Data Science
Discover local and cloud-based alternatives to VSCode for data science, including Cursor, Jupyter Notebook, RStudio, Kaggle, Deepnote, Google Colab, and Amazon Sagemaker Studio Lab. Each tool offers unique features tailored to data science and machine learning tasks, from AI-assisted coding to free access to GPUs and TPUs.
45
11
Article
Daily Dose of Data Science | Avi Chawla | Substack·2y
A Simple Implementation of Boosting Algorithm
Boosting is a machine learning technique where each successive model attempts to correct the errors of its predecessor, leading to improved performance. Key design choices include tree construction, loss function, and weighting of each tree's contribution. A step-by-step example using the Sklearn decision tree regressor shows how boosting works and the incremental improvement in R2 scores. Boosting algorithms are particularly significant for tabular data in machine learning.
44
12
Video
Programming with Mosh·2y
The Complete Data Science Roadmap [2024]
44
2
13
Article
Watercooler·2y
When you think more about a model than your gf
42
2
14
Article
KDnuggets·2y
Beginner’s Guide to Careers in AI and Machine Learning
The post explains the growing diversity of jobs requiring AI and ML expertise, detailing the technical skills and tools used in various roles such as AI Engineer, ML Engineer, Data Scientist, Data Engineer, AI Research Scientist, and Business Intelligence Analyst. It highlights that the era of AI and ML generalists has ended, ushering in the need for specialists with specific skills tailored to different aspects of the fields.
42
1
15
Article
Machine Learning News·2y
Saldor: The Web Scraper for AI
Saldor is a web scraping tool designed for AI applications, streamlining data collection from websites for accurate AI model training. It automates the web scraping process, saving developers time and effort by converting web data into structured formats like JSON. Key features include target selection, data extraction, data cleaning, and data export.
41
16
Article
Data Science Central·2y
30 Features that Dramatically Improve LLM Performance
The post covers innovative features that significantly enhance Large Language Model (LLM) performance by improving speed, reducing resource usage, and enhancing security. Key highlights include techniques like approximate nearest neighbor search, nested hash tables for sparse databases, and adaptive loss functions. It also emphasizes the importance of contextual tokens, agentic LLMs, and data augmentation through dictionaries for professional usage.
41
1
17
Article
Lobsters·2y
lovasoa/SQLpage: SQL-only webapp builder, empowering data analysts to build websites and applications quickly
SQLPage is an SQL-only webapp builder designed for data scientists, analysts, and business intelligence teams. It allows users to create data-centric applications using only SQL queries, bypassing traditional web programming languages. SQLPage supports different databases such as SQLite, PostgreSQL, MySQL, and Microsoft SQL Server. It is written in Rust and can be deployed using binary files or Docker images. Users can quickly generate webpages displaying data as lists, grids, and charts. It also supports advanced features like custom components, serverless deployment, and HTTP/2 and HTTPS.
40
18
Article
KDnuggets·2y
Degree or Certificate? Which Credential Do Employers Value More?
Employers often prefer degrees because they correlate with high productivity, but the growing demand for data-driven skills and AI solutions is shifting this trend. Professional certificates offer a faster, cost-effective route to enter fields like data science and cybersecurity, focusing on technical skills. Degrees provide a broader education, building both technical and soft skills, which can enhance long-term career prospects and salary potential. The choice between a degree and a certificate depends on one's career goals and the time available for education.
39
4
19
Video
YouTube·2y
How I'd Learn AI in 2024(If I could start over)
AI is expected to dominate the market by 2030, and learning it does not require a degree—just a structured roadmap and dedication. Key subjects to focus on include linear algebra, calculus, and probability. Python is the primary language used. Essential Python modules for data handling include Pandas, NumPy, and Matplotlib. Recommended frameworks for beginners are PyTorch and Scikit-Learn. Notable resources for learning include Three Blue One Brown, Khan Academy, Brilliant.org, and Andrew Ng's courses on Coursera. Practical experience can be gained via Kaggle competitions.
38
20
Article
KDnuggets·2y
Top 5 Free Resources for Learning Advanced SQL Techniques
Discover five quality resources for learning advanced SQL for free, including tutorials, online courses, and video lectures from reputable sources like Mode Analytics, Stanford University, Kaggle, the University of Tübingen, and Philip Greenspun’s website. Topics covered include indexing, transactions, triggers, window functions, recursive CTEs, and more. Bonus mentions include StrataScratch and LeetCode for practicing SQL interview questions.
36
21
Article
Daily Dose of Data Science | Avi Chawla | Substack·2y
10 Regression and Classification Loss Functions
This post highlights the most commonly used loss functions in regression and classification tasks. It covers Mean Bias Error, Mean Absolute Error, Mean Squared Error, Root Mean Squared Error, Huber Loss, and Log Cosh Loss for regression. For classification, it discusses Binary Cross Entropy, Hinge Loss, Cross-Entropy Loss, and KL Divergence. Each loss function is briefly explained along with its pros and cons.
33
22
Article
Towards AI·2y
Principle Component Analysis (PCA) Mathematics
Principal Component Analysis (PCA) is a dimensionality reduction technique used to reduce N features to P features while retaining as much variance as possible. Standardization of data is crucial before applying PCA to prevent variance-dominated principal components. PCA benefits include improved model performance and reduced overfitting, but it also has downsides such as loss of interpretability and lossy compression.
33
1
23
Article
Machine Learning News·2y
Darts: A New Python Library for User-Friendly Forecasting and Anomaly Detection on Time Series
Darts is a Python library designed to simplify time series processing and forecasting. It offers a unified and consistent API for data manipulation, model fitting, forecasting, and backtesting, making it easier to switch between models without compatibility issues. Darts supports various models, including traditional methods like Exponential Smoothing and advanced neural network models like RNNs and Transformers. The library also provides tools for backtesting, model evaluation, and deep learning support, enhancing user experience and productivity in time series analysis.
33
24
Article
Daily Dose of Data Science | Avi Chawla | Substack·2y
Why Join() Is Faster Than Iteration?
Using Python’s join() method for string concatenation is significantly faster than iterating and appending strings. This is because join() can allocate memory in a single call by knowing the number of strings and spaces beforehand, whereas iteration requires repeated memory allocations for each element and separator. This optimization improves runtime and memory utilization.
31
2
25
Article
Watercooler·2y
Join explained with hair 🤣
28
2

See all Data Science archives