Data Science & Machine Learning

Objective: Build strong Python programming foundations for machine learning.

• Python Basics: Variables, control flow, functions (15 hrs)
• NumPy and Pandas: Data manipulation (10 hrs)
• Data Structures and Algorithms: Lists, dictionaries, time complexity (10 hrs)

Objective: Understand statistical concepts crucial for machine learning applications.

• Descriptive Statistics: Measures of central tendency and variability (15 hrs)
• Probability: Bayes’ Theorem, conditional probability (15 hrs)
• Inferential Statistics: Hypothesis testing, confidence intervals (15 hrs)
• Correlation and Regression: Basic linear regression (5 hrs)

Objective: Master data visualization tools.

• Matplotlib and Seaborn: Basic and statistical plots (15 hrs)
• Interactive Visualizations with Plotly: Creating interactive charts and dashboards (15 hrs)

Objective: Learn EDA techniques to prepare and understand datasets.

• Data Profiling: Statistical summaries, distributions (10 hrs)
• Data Exploration Techniques: Outlier detection, correlation analysis (15 hrs)
• Data Cleaning: Handling missing values, imputation (10 hrs)

Objective: Master feature engineering techniques for improved model performance.

• Feature Scaling: Normalization, standardization (10 hrs)
• Encoding Categorical Data: One-hot encoding, label encoding (10 hrs)
• Feature Creation: Polynomial features, interaction terms (10 hrs)
• Dimensionality Reduction: PCA, t-SNE (10 hrs)

Objective: Gain proficiency in building and evaluating machine learning models.

• Supervised Learning: Linear regression, decision trees, KNN, SVM (40 hrs)
• Unsupervised Learning: Clustering, dimensionality reduction (20 hrs)
• Model Evaluation: Metrics for classification and regression (20 hrs)

Objective: Optimize model performance through tuning techniques.

• Hyperparameter Tuning: Grid search, random search (20 hrs)
• Feature Selection: Wrapper and filter methods (10 hrs)
• Cross-Validation Techniques: K-Fold, LOOCV (10 hrs)

Objective: Understand model explainability techniques.

• Explainability Concepts: SHAP, LIME (20 hrs)
• Explainability Methods: PDP, ICE plots (10 hrs)