Practice: Implementing simple ML algorithms with NumPy
Pandas Fundamentals
Series and DataFrame objects
Reading/writing data (CSV, Excel, SQL)
Indexing and selection (loc, iloc)
Handling missing data
Practice: Data cleaning for a messy dataset
Data Manipulation with Pandas
Data transformation (apply, map)
Merging, joining, and concatenating
Grouping and aggregation
Pivot tables and cross-tabulation
Practice: Customer purchase analysis
Time Series Analysis with Pandas
Date/time functionality
Resampling and frequency conversion
Rolling window calculations
Time zone handling
Practice: Stock market data analysis
Data Visualization
Matplotlib Fundamentals: Figure and Axes objects, Line plots, scatter plots, bar charts, Customizing plots, Saving and displaying plots, Practice: Visualizing economic indicators
Advanced Matplotlib: Subplots and layouts, 3D plotting, Animations, Custom visualizations, Practice: Creating a dashboard of COVID-19 data
Seaborn: Statistical visualizations, Distribution plots (histograms, KDE), Categorical plots (box plots, violin plots), Regression plots, Customizing Seaborn plots, Practice: Analyzing and visualizing survey data
Plotly: Interactive visualizations, Plotly Express basics, Advanced Plotly graphs, Dashboards with Dash, Embedding visualizations in web applications, Practice: Building an interactive stock market dashboard
Machine Learning Statistics
Role of statistics in ML, Descriptive vs. inferential stats
Correlation & Regression: Pearson correlation, linear regression, R² score
Hands-on in Python: NumPy, Pandas, SciPy, Seaborn & Satsmodels
Machine Learning Fundamentals
Introduction to Machine Learning
Types of machine learning (supervised, unsupervised, reinforcement)
The ML workflow, Training and testing data
Model evaluation basics, Feature engineering overview
Practice: Implementing linear regression from scratch
Scikit Learn Basics
Introduction to scikit Learn API
Data Preprocessing (StandardScaler, MinMaxScaler)
Train-test split, Cross-validation
Pipeline construction
Practice: End-to-end ML workflow implementation
Supervised Learning
Linear Models: Linear regression, Regularization techniques (Ridge, Lasso), Logistic regression, Polynomial features, Evaluation metrics for regression and classification
Decision Trees & Ensemble Methods: Decision tree algorithm, Entropy and information gain, Overfitting and pruning, Random forests, Feature importance, Gradient boosting (XGBoost, LightGBM), Model stacking and blending
Support Vector Machines: Linear SVM, Kernel trick, SVM hyper parameters, Multi-class SVM
K-Nearest Neighbors: Distance metrics, KNN for classification and regression, Choosing K value
Naive Bayes: Bayes theorem, Gaussian, Multinomial, Bernoulli Naive Bayes, Applications in text classification
