Iris Dataset Analysis and Model Training Results

t-SNE: Visualizing What We Can't See Imagine 784 dimensions compressed to 2 — and the clusters you see tell you everything about the structure of the data. t-SNE makes the invisible visible. Day 27 of 60 → t-SNE — the most beautiful data visualization tool in ML. PCA finds linear components. t-SNE finds NON-LINEAR structure — preserving local neighborhoods. The idea: 1. Measure which points are close in high-dimensional space 2. Lay them out in 2D preserving those closeness relationships 3. Similar points cluster together, dissimilar ones spread apart What good t-SNE output looks like: → Tight clusters = data has natural groupings → Fuzzy boundaries = gradual transitions between groups → Outlier points far from clusters = anomalies CRITICAL caveats: 1. Distances between clusters are NOT meaningful (only within-cluster distances) 2. Results depend on "perplexity" parameter (try 5, 30, 50) 3. Never interpret the x/y axis — they're arbitrary t-SNE is for EXPLORATION, not prediction. But for making the invisible visible? Nothing compares. #tSNE #DataVisualization #MachineLearning #Python #60DaysOfML

🚀 Day 86 - Matrix Plots in Seaborn Today’s focus was on Matrix Plots — a powerful way to visualize relationships and patterns across entire datasets. 📊 Here’s what I explored: 🔹 Heatmaps Used to represent data values with colors, making it easy to spot patterns, intensity, and variations at a glance. 🔹 Correlation Heatmaps Helped me understand how variables are related to each other — whether positively, negatively, or not at all. 🔹 Triangle Correlation Heatmap A cleaner version of correlation maps that removes duplicate information and improves readability. 🔹 ColorMaps in Heatmaps Learned how different color schemes can completely change the interpretation and clarity of data. 🔹 Adding Frames to Heatmaps Enhanced visualization by improving separation and making insights more structured and readable. 💡 Key Takeaway: Matrix plots are extremely useful when working with large datasets, helping to quickly identify hidden patterns, correlations, and clusters that might not be obvious otherwise. Step by step, getting closer to mastering data visualization! 🚀 #DataAnalytics #Python #DataVisualization #Heatmap #Correlation #Seaborn #MachineLearning

🚀 ML Project Journey – Part 2: EDA Through Visualization In my previous post, I shared how I reframed my problem into a classification task. Next, I focused on Exploratory Data Analysis (EDA) — using visualization to understand the dataset before making any changes. 🔍 What I worked on (using Python, Pandas, Seaborn & Matplotlib): Analyzed distributions of numerical features (age, height, area) Used count plots to understand categorical variables (foundation, roof, floor types) Explored binary structural features (building materials) Identified outliers using boxplots ⚠️ Challenges I faced: Large number of features → required prioritizing relevant variables Patterns were not always obvious from a single plot Interpreting outliers visually needed careful analysis 💡 Key observations: Several numerical features are highly skewed Structural/material features show noticeable variation across buildings Outliers are consistently present in key numerical columns 📚 What I learned: EDA is about building intuition through visualization Understanding feature behavior helps in making better preprocessing decisions Separating EDA from preprocessing creates a more structured ML workflow 🔜 Next step: Handling outliers and missing values Encoding categorical variables Preparing data for baseline models 👉 This phase helped me move from “just plotting graphs” to actually interpreting data. #DataScience #MachineLearning #EDA #DataVisualization #LearningJourney #Python

📊 Exploring Data Visualization with Seaborn Scatter Plot Today I practiced creating a multi-dimensional scatter plot using Seaborn's built-in Tips dataset. In this visualization: 🔹 X-axis represents Total Bill 🔹 Y-axis represents Tip Amount 🔹 Colors differentiate Gender (Male/Female) 🔹 Marker styles distinguish Lunch vs Dinner 🔹 Point sizes represent Group Size This exercise helped me understand how multiple variables can be visualized in a single plot, making it easier to identify relationships and patterns within the data. Data visualization plays a crucial role in Exploratory Data Analysis (EDA) and helps in building better Machine Learning models. I'm continuing to strengthen my skills in Python, Pandas, Matplotlib, and Seaborn as part of my Machine Learning journey. 🚀 #DataScience #MachineLearning #Python #Seaborn #DataVisualization #LearningJourney #EDA

Run These 3 Plots Before You Touch Any ML Model — or You're Flying Blind "Most ML disasters are data problems in disguise. These three visualizations expose them in 60 seconds." Before I train any model, I run exactly 3 plots. Not because someone told me to. Because I've been burned enough times to know what I was skipping. Plot 1: Distribution of your target variable. Is it balanced? Skewed? Are there impossible values? A fraud dataset with 0.01% positives will fool you before training even starts. Plot 2: Missing value heatmap. Not just "how many" — but where. Missing values clustered in certain rows or columns tell a completely different story than random missingness. Plot 3: Feature correlation with the target. Before any feature engineering. This single plot has killed bad feature ideas in 10 seconds for me more times than I can count. Three plots. Ten minutes. Saves you days of confusion later. I'll drop the exact Python code for all three in the comments. What's the first thing YOU look at in a new dataset? #Python #DataStructures #Stack #DSA #Programming #Coding #PythonProgramming #CodingInterview #Algorithms #PythonDevelopers #TechCommunity #CodingChallenges #LearnPython #Developer #SoftwareEngineer #Problems #MachineLearning #Hyperparameters #DataScience #Experimentation #ModelTuning #AI #MLBestPractices #DataDriven #ModelOptimization #LearningJourney #ML #TechTips

📊 Day 87 - Additional Plots in Seaborn Today’s focus was on Additional Plots — expanding my visualization toolkit with more specialized and insightful plot types. These plots help in uncovering deeper patterns and making analysis more precise. Here’s what I explored: 🔹 Bubble Plot A powerful way to visualize three variables at once using position and size — great for comparing multiple dimensions in a single view. 🔹 Residual Plot (Residplot) Helps in evaluating regression models by visualizing errors. A key step to check whether the model assumptions hold true. 🔹 Boxen Plot An advanced version of boxplot that provides more detailed insights into data distribution, especially for large datasets. 🔹 Point Plot Useful for showing trends and comparisons across categories with confidence intervals — clean and effective for statistical insights. 💡 Key Takeaway: Choosing the right plot can completely change how insights are perceived. These advanced plots allow more precise storytelling with data. Every new visualization technique brings me one step closer to mastering data analysis 🚀 #DataScience #DataVisualization #Python #Analytics #Seaborn #MachineLearning

I’ve been exploring how to combine chemistry with data analysis, and I recently worked on a project that really brought both worlds together. I used Python to analyze how temperature affects reaction rates and to estimate activation energy using linear regression. What made this interesting for me wasn’t just the code, but the process: transforming raw experimental data into something a model could understand. Here’s what I did: • Cleaned and structured the dataset • Applied transformations to reveal patterns • Built a regression model to learn the relationship • Evaluated the model using training and test data Seeing the data align so clearly with the model was one of those moments where things just clicked. It reminded me that a lot of concepts we struggle with in chemistry become much clearer when we visualize and analyze them computationally. This is exactly the direction I want to keep building in: using data tools to make science easier to understand and more practical. I’ve shared the full project here: 🔗 GitHub: https://lnkd.in/edeu_n7C 🔗 Kaggle: https://lnkd.in/e7EgPZhp Still learning, still improving but this felt like a step forward. #DataAnalytics #Python #MachineLearning #Chemistry #WomenInTech #LearningInPublic

Just finished a Machine Learning project predicting loan approval using a real-world loan dataset. Goal: Build a model that predicts whether a loan application should be approved based on applicant financial and personal data. What I worked on: 1-Data Preparation Handled missing values & outliers Encoded categorical variables Scaled numerical features Built a clean pipeline ready for modeling 2-Modeling & Comparison Trained and compared multiple classification models: Logistic Regression KNN Decision Tree Random Forest 3-Evaluation Models were evaluated using: Accuracy, Precision, Recall, and F1-score to ensure real performance and avoid misleading results. Why Random Forest performed best Random Forest achieved the highest accuracy because: It combines multiple decision trees → reduces overfitting Captures non-linear relationships in financial data better than linear models Handles feature interactions automatically More robust to noise and outliers than a single Decision Tree Key Takeaway Choosing the right model isn’t about complexity — it’s about how well the model matches the nature of the data. Tools: Python | Pandas | NumPy | Scikit-learn | Matplotlib | Seaborn #MachineLearning #DataScience #AI #Python #Classification #RandomForest

Yesterday I decided to build a Multiple Linear Regression model simple, right? 😄 Well, not exactly. I ran into one of the weirdest issues I’ve ever seen in a dataset. I have my own data preprocessing template tested many times, reliable, and saves me a lot of time. So I trusted it 100%. But when I applied it and selected the independent and dependent variables I got results that made ZERO sense. At first, I thought: “Okay maybe I messed up something small.” Then I tried again. And again. And again. Same weird output. At this point, I started questioning everything even my own template 😅 Before giving up, I tried one last thing: Instead of selecting columns by index, I used column names. And suddenly everything worked perfectly 🤯 So I went back to investigate further And here’s the surprise: The column indices I was using didn’t match what actually existed in the dataset! 👉 Turns out there were hidden columns / unexpected structure issues messing with the indexing. Lesson learned: Never trust indices blindly Always double check your dataset structure And sometimes column names will save your life 😄 Debugging data > building models sometimes. Has anyone faced something like this before? #DataScience #MachineLearning #DataPreprocessing #Python #DataAnalytics #AI #Debugging

45 Days ML Journey — Day 13: K-Nearest Neighbors (KNN) Day 13 of my Machine Learning journey — exploring K-Nearest Neighbors (KNN), a simple yet powerful algorithm used for classification and regression. Tools Used: Scikit-learn, NumPy, Pandas What is KNN? KNN is a supervised learning algorithm that classifies a data point based on the majority class among its ‘K’ nearest neighbors. Key concepts: K Value → Number of nearest neighbors considered Distance Metric → Measures similarity (e.g., Euclidean distance) Lazy Learning → No training phase; computation happens during prediction How does it work? Choose the number of neighbors (K) Calculate distance from the query point to all data points Pick the K closest neighbors Assign the most common class (for classification) or average (for regression) Why use KNN? Simple and easy to understand No training time required Works well with smaller datasets Challenges: Computationally expensive for large datasets Sensitive to the choice of K and distance metric Affected by feature scaling Code notebook: https://lnkd.in/gQ3HMMBZ Key takeaway: KNN is a beginner-friendly algorithm that relies on similarity, making it intuitive and effective for many real-world problems when tuned properly. #MachineLearning #DataScience #KNN #Python #ScikitLearn #LearningInPublic #MLJourney