Giannis Tolios’ Post

Explored the Naive Bayes classification algorithm using Python and scikit-learn. Worked with a structured dataset, performed label encoding, train-test split, and trained a Gaussian Naive Bayes model to analyze classification performance on both training and testing data. This hands-on implementation helped me better understand how probabilistic models work in real-world machine learning workflows. #MachineLearning  #NaiveBayes  #GaussianNB   #DataScience  #Python  #ScikitLearn  #MLPractice   #LearningByDoing  #JupyterNotebook  #AIStudent

📊 Seaborn makes data easy to understand, not just easy to plot. In Python, Seaborn stands out because it focuses on clarity over complexity. ✔ Clean visuals by default ✔ Built for statistical insights ✔ Works seamlessly with Pandas ✔ Perfect for analytics, ML, and data engineering Good visuals don’t just look nice — they drive better decisions. If you work with data, Seaborn is a skill worth mastering. #Python #Seaborn #DataVisualization #DataAnalytics #DataScience

Just published: A Complete Guide to Decision Trees in Machine Learning with Python! Decision trees are one of the most intuitive and powerful ML algorithms—perfect for both beginners and experienced practitioners. In this comprehensive guide, I cover: ✅ How decision trees work (step-by-step algorithm) ✅ Attribute selection measures (Gini Index, Information Gain, Gain Ratio) ✅ Complete Python implementation with scikit-learn ✅ Visualization techniques & tree pruning strategies ✅ Hyperparameter tuning with GridSearchCV ✅ Feature importance extraction ✅ Pros, cons & real-world best practices From data preprocessing to model evaluation—let's master decision trees together! 🚀 #MachineLearning #DecisionTrees #Python #DataScience #Scikit-learn #ML #Tutorial #PythonProgramming #DataAnalytics #AI #CareerGrowth

🚀 Task 1 Completed: House Price Prediction using Machine Learning As part of my Machine Learning learning journey, I worked on a House Price Prediction model using Python. 🏠 Project Overview: The goal was to predict house prices based on key features such as: Square Feet Area Number of Bedrooms 🛠 Tech Stack Used: Python Pandas Scikit-learn Linear Regression 📌 What I learned: Working with real-world CSV datasets Feature selection for regression problems Training and using a Linear Regression model Taking user input and making predictions This task helped me understand the end-to-end machine learning workflow, from data loading to prediction. 📂 Project available on GitHub (README included) https://lnkd.in/gf2kq6rk #MachineLearning #Python #LinearRegression #AI #DataScience #LearningByDoing #StudentDeveloper

Day 14 – Python & Machine Learning Learning Journey Today was all about revision + practice 📊🐍 🔹 Revised core Python & ML concepts 🔹 Worked on California Housing Dataset 🔹 Built & trained 5 Machine Learning models, including Linear Regression 🔹 Practiced House Price Prediction Concepts Revised & Applied: Training Data vs Testing Data Features & Labels ✔️ Train–Test Split ✔️ Prediction Workflow ✔️ Underfitting vs Overfitting ✔️ Exploratory Data Analysis (EDA) Also revised EDA concepts using the Titanic Dataset to better understand data patterns, distributions, and missing values before model training. 💡 Key Learning: A strong model doesn’t start with algorithms — it starts with understanding the data. Excited to move forward and apply these concepts to more real-world datasets Consistency is the key #Python #MachineLearning #DataScience #LearningJourney #EDA #LinearRegression #CaliforniaHousing #TitanicDataset #AI #100DaysOfCode #Day14

🚀 Built Logistic Regression From Scratch (No ML Libraries!) Today I implemented a Logistic Regression model from scratch using Python & NumPy to truly understand how classification models work. 📌 Key concepts I explored: Sigmoid function which is an activation function of this model. Gradient Descent for updating weights and bias. Cross-Entropy / Log Loss as the loss function for classification. It is used as a classification model. (Probability lies between 0 and 1). Note : Mean Squared Error can't be used as the loss function for logistic regression since it causes gradient descent with multiple local minima. I’d really appreciate feedback or suggestions on my approach — especially around optimization or best practices. Always open to learning! 🙏 Github repository link : https://lnkd.in/gfsDug8U #MachineLearning #LogisticRegression #FromScratch #Python #NumPy #DataScience #AI #LearningByDoing #Placements

🧱 Building the foundation, one line of code at a time. Dive into the basics of Machine Learning with Simple Linear Regression! 📉 In this mini-project, I used Python to predict housing prices based on square footage. It’s one thing to call a function, but it’s another to verify the math ($y = mx + c$) behind the library. Seeing the Best Fit Line plotting perfectly through the data points is always satisfying. Tech Stack: Python, Scikit-Learn, Pandas, Matplotlib. kaggle notebook:https://lnkd.in/gaZb8yZK #MachineLearning #DataScience #Python #LinearRegression #CodingJourney #AI

Day 22 & 23 | AI/ML Learning Journey | Python —Pandas Topic: Pandas (Practice) Over the last two days, I focused on Pandas fundamentals by working with real datasets. What I covered: •DataFrame methods — head(),tail(),info(), describe() etc. •Loading datasets from Kaggle •Data selection — iloc(position) , loc(label) •Filtering & Query filter •Data cleaning techniques  • Handling missing values  • Removing duplicates  • Converting data types Consistency Challenges. #AIML #DataScience #Pandas #Python #MachineLearning #LearningJourney #Kaggle #DataCleaning

Starting your Data Science journey? Save this! 📌 NumPy is the backbone of Data Science in Python. If you want to handle data like a pro, these built-in functions are your best friends: 🔹 Creation: np.array(), np.ones(), np.arange(), np.linspace() 🔹 Manipulation: np.concatenate(), np.stack() 🔹 Analysis: np.mean(), np.sum(), np.where() Whether you are building Machine Learning models or just cleaning a dataset, knowing which tool to use can save you hours of debugging and make your code significantly faster. ⚡ Which of these do you use the most in your daily workflow?👇 #python #datascience #numpy #machinelearning #ai #coding #dataanalytics #programming #datascientist #pythonprogramming

Built a simple end-to-end Machine Learning pipeline using Logistic Regression to predict student pass/fail outcomes based on study hours. This project helped me understand: – Feature engineering and target creation – Train–test splitting – Binary classification with Logistic Regression – Model evaluation using accuracy and confusion matrix Tech stack: Python, NumPy, Pandas, Matplotlib, Scikit-Learn Currently focusing on strengthening ML fundamentals before moving to more complex models. #machinelearning #python