🤖 Machine Learning

This repository showcases the progress of my ML journey. My learning gradually moved from data analysis into Machine Learning.

Supervised Learning

I learned and implemented classification algorithms including:

• Linear Regression
• Logistic Regression
• K-Nearest Neighbors (KNN)
• Decision Trees
• Random Forest
• Support Vector Machines (SVM)

I also learned the general supervised learning workflow:

Dataset
   ↓
Data Understanding
   ↓
Data Cleaning
   ↓
EDA
   ↓
Feature / Target Separation
   ↓
Train / Test Split
   ↓
Feature Scaling
   ↓
Model Training
   ↓
Prediction
   ↓
Model Evaluation

---

Unsupervised Learning

I learned how machine learning can discover patterns in data without predefined target labels.

Topics include:

• K-Means Clustering
• Hierarchical Clustering
• DBSCAN
• Principal Component Analysis (PCA)

I also implemented K-Means from scratch to understand the underlying process before using Scikit-learn.

Concepts practiced:

• Euclidean distance
• Centroids
• Cluster assignment
• Centroid updates
• Iterative clustering
• Inertia / WCSS
• Elbow Method
• Silhouette Score
• Cluster profiling

---

📏 Machine Learning Evaluation

I learned how to evaluate classification models instead of relying only on accuracy.

Metrics practiced:

• Accuracy
• Precision
• Recall
• F1 Score
• Confusion Matrix

I also practiced comparing multiple models and selecting the better-performing model based on evaluation metrics.

---

🛠️ Machine Learning Libraries & Tools

Libraries

NumPy
Pandas
Matplotlib
Seaborn
Scikit-learn
NLTK
TensorFlow
Keras
PyTorch
Pillow
EasyOCR

Development Tools

Python
VS Code
Jupyter Notebook
Google Colab
Git
GitHub
Streamlit

Progress

The objective is to reach the point where I can:

Understand the problem → choose the right approach → implement it → evaluate it → improve it → and build something useful with it.

Author

Symbol Pamnani

BS Computer Science | AI/ML Engineer