Data Science & Machine Learning

This repository documents my learning journey in Machine Learning and Data Science, featuring projects, experiments, and detailed notes compiled throughout my studies.

---

Data Analysis

Tools & Libraries:

• Python, Numpy, Pandas
• Matplotlib, Seaborn, Plotly
• Streamlit
• Exploratory Data Analysis (EDA)
• Web Scraping
• Pandas Profiling
• Scikit-learn (Encoding Techniques, Pipeline)
• Scipy

Projects:

• Smartphone Data Analysis - Web scraping and comprehensive analysis of smartphone specifications
• Titanic Dataset EDA - Classic exploratory data analysis
• National Anthem Analysis - Discovering hidden patterns between countries through their anthems | Read More
• Walmart Sales EDA - My first exploratory data analysis project | Read More

---

Probability & Statistics

• Hypothesis Testing
• Bayes Theorem
• Probability Distributions
• Descriptive Statistics
• Inferential Statistics
• Central Limit Theorem
• Correlation and Regression
• ANOVA
• Chi-Square Test
• Sampling Techniques

---

Machine Learning

Regression

• Simple, Multiple, and Polynomial Linear Regression
• Gradient Descent (Batch, Stochastic, Mini-Batch) - implemented from scratch
• Regression Analysis (F-Statistic, R², Adjusted R², p-Value)
• Regression Assumptions (Linearity, Normality, Homoscedasticity, No Autocorrelation, Multicollinearity)
• Regularization Techniques (Lasso, Ridge, Elastic Net)
• Bias-Variance Tradeoff

Feature Engineering

• Filter Based Technique
• Wrapper Method
• Embedded Technique

Classification

• K-Nearest Neighbors (KNN)
• Naive Bayes Classifier (Gaussian, Multinomial, Bernoulli, Complement, Categorical)
  • Text Classification implementation
  • Spam Classifier | Live Demo
• Logistic Regression (One-vs-Rest, Multinomial)
  • Digit Recognition Web App | Live Demo
• Support Vector Machines (Hard Margin, Soft Margin, Kernel Trick)
• Decision Trees (CART, Gini Impurity, Entropy, Pruning)

Clustering

• K Means
• DBSCAN
• Hierarchical Clustering

Evaluation Metrics

• Confusion Matrix
• Accuracy, Precision, Recall, F1 Score
• ROC Curve and AUC

Dimensionality Reduction

• Principal Component Analysis (PCA)
• Explained Variance
• Covariance Matrix
• Eigenvalues and Eigenvectors

Model Selection & Tuning

• Cross Validation (Leave One Out, K-Fold, Stratified K-Fold)
• Data Leakage Prevention
• Hyperparameter Tuning (Grid Search, Randomized Search, Bayesian Optimization)

Ensemble Methods

• Voting Ensemble (Hard Voting, Soft Voting)
• Bagging (Bagging Regressor/Classifier, Random Forests)
• Boosting (AdaBoost, Gradient Boosting, XGBoost)

Advanced Topics

• Maximum Likelihood Estimation and Loss Functions
• Constrained Optimization Problems

---

Deep Learning

Note: Detailed deep learning work is maintained in a separate repository

Natural Language Processing

• Tokenization
• Stopword Removal
• Stemming and Lemmatization
• Named Entity Recognition
• Bag of Words
• TF-IDF
• Spam Detection Project

Neural Networks

• Perceptron and Multi-Layer Perceptron (MLP)

Live Projects

• Spam Classifier
• Digit Recognition App

---

Contact: LinkedIn