Course Description
In today's digital age, data has become the most strategic asset for organizations. This intensive training program equips participants with the skills required to transform raw data into meaningful business decisions.
By the end of the program, participants with a foundation in Python programming are introduced to the most up-to-date tools and libraries of the modern data science ecosystem.
Throughout the training, participants learn to use the latest versions of pandas/Polars, scikit-learn, and visualization libraries to solve real-world data problems.
Upon completing this training, participants master the core tools and techniques that drive modern data-driven decision-making.
Target Audience
This course is specifically designed for software developers, analysts, and related professionals who already have a command of Python and want to transition into data science or advance their skills in the field.
It is ideal for those looking to move beyond basic programming in their work to learn data manipulation, analysis, and machine learning modeling.
Prerequisites
A solid command of Python programming fundamentals, including data structures (lists, dictionaries, tuples), control flow (loops, conditionals), and functions.
Prior experience writing and running Python scripts.
No prior experience in data science or machine learning is required.
Learning Outcomes
Participants who complete this course will be proficient in:
Reading, cleaning, and manipulating data from various sources using the Pandas library.
Performing Exploratory Data Analysis (EDA) to uncover hidden patterns, relationships, and outliers in data.
Creating effective and clear data visualizations with Matplotlib and Seaborn.
Understanding the core logic and workflow of machine learning (data preprocessing, model training, evaluation).
Building foundational machine learning models such as regression and classification using the Scikit-learn library.
Measuring and interpreting model performance with the right metrics (Accuracy, R-squared, Confusion Matrix, etc.).
Executing an end-to-end data science project on real-world datasets.
Curriculum
Module 1 - Fundamentals of Data Manipulation and Visualization
Data Science Fundamentals
Data Science Workflow
Defining the problem
Data acquisition and cleaning
Exploratory data analysis
Modeling
Interpreting results and the iterative improvement cycle
Environment Setup
Jupyter Notebook for interactive data science
Overview of core libraries: NumPy, Pandas, Matplotlib, Seaborn, Scikit-learn
Data Manipulation with Pandas
Core Pandas Structures
Creating and inspecting Series and DataFrames
Loading data from various sources (CSV, Excel, databases)
Chunked reading techniques for out-of-memory datasets
Data Selection and Indexing
Using .loc, .iloc, and boolean indexing
Query operations
Setting, resetting, and using indexes
Data Cleaning and Preparation
Missing data detection and handling strategies
Duplicate detection and removal
Data type conversions and casting
String operations and text processing
Module 2 - Advanced Data Manipulation and Visualization
Advanced Data Manipulation with Pandas (Optionally Polars)
Grouping and Aggregation
Split-apply-combine approach
Custom aggregation functions
Window functions and rolling operations
Time-based resampling
Merging and Reshaping Data
Merge and join operations
Concatenation strategies
Pivoting and unpivoting
Wide-to-long format transformations
Performance Optimization
Vectorized operations vs. iterative approaches
Memory optimization techniques
Reducing memory footprint with categorical data
Query optimization and indexing strategies
Data Visualization with Modern Libraries
Matplotlib Fundamentals
Fast and effective plotting with the pyplot interface (state-machine approach).
Object-Oriented interface: Full control over Figure and Axes objects.
Differences between the two interfaces and when to use each.
Customization and style systems
Multiple plots: subplot layouts
Annotations and text management
Statistical Visualization with Seaborn
Distribution plots and kernel density estimation
Categorical data visualization patterns
Regression and correlation visualizations
Matrix plots and heatmaps
Color palettes and aesthetic settings
Interactive Visualization with Plotly
Building interactive charts and dashboards
3D visualizations and surface plots
Geospatial data visualization
Animation and time-series representation
Dash framework for web applications
Module 3 - Exploratory Data Analysis
Data Profiling
Initial Data Assessment
Inspecting dataset properties: shape, size, memory footprint.
Data type inference and validation
Column cardinality and uniqueness analysis
Data Quality Inspection
Missing value patterns and distribution analysis
Duplicate detection across different granularity levels
Consistency checks across related fields
Validating data against business rules and anomaly indicators
Statistical Exploration
Distribution and Pattern Discovery
Univariate analysis for numerical variables
Frequency analysis for categorical variables
Skewness detection and transformation requirements
Time-based patterns and seasonality detection
Outlier and Anomaly Detection
Outlier analysis using IQR and domain knowledge
Range and boundary value inspections
Data freshness and completeness metrics
Cross-validation with external data sources
Relationship Analysis
Feature Relationships and Correlations
Building and interpreting correlation matrices
Measuring feature-target relationship strength
Multicollinearity detection and its impacts
Examining interactions between variables
Identifying segmentation opportunities
Visual Exploration Techniques
Distribution plots for continuous variables
Category balance visualizations
Time-series trend analyses
Pair plots for feature interactions
Geospatial and spatial data explorations
Module 4 - Introduction to Machine Learning with Scikit-learn
Machine Learning Fundamentals
Core Concepts
How it differs from traditional programming and its role in the modern world (recommendation systems, fraud detection, medical diagnosis, etc.).
Types of Machine Learning: Supervised, Unsupervised, Reinforcement
The modeling process: training, validation, and evaluation
Lifecycle of a Model: From Idea to Value
Problem definition, data collection, feature engineering, model selection, training, hyperparameter tuning, and deployment.
Machine Learning with Scikit-learn
Data Preprocessing
Feature scaling and normalization
Encoding categorical variables
Feature engineering strategies
Handling imbalanced datasets
Supervised Learning Models
Generalized linear models and regularization
Tree-Based Models (Random Forest, Gradient Boosting)
Artificial Neural Networks
Model selection and hyperparameter tuning
Cross-validation strategies
Unsupervised Learning Techniques
Clustering algorithms and evaluation metrics
Dimensionality reduction (PCA, t-SNE, UMAP)
Anomaly detection methods
Advanced Machine Learning Techniques
Gradient Boosting with XGBoost, LightGBM, and CatBoost
Advanced boosting techniques
Feature importance and interpretation
Native handling of categorical variables
GPU acceleration for large datasets
Building Models with PyTorch
Neural network fundamentals for tabular data
Running models on GPUs
AutoML tools and frameworks
Other Courses in This Category
-
Modern C++ (C++17/20) for AI and high-performance systems: RAII and smart pointers, STL, move semantics, multithreading, SIMD, building Python extensions with pybind11 and the LibTorch/ONNX Runtime C++ APIs.
- Live Course
- 5 modules
-
Python Programming
Master Python from scratch: data structures, control flow, functional programming, Object-Oriented Programming (OOP), error handling, file I/O, virtual environments, and Pandas.
- Live Course
- 9 modules
-
Advanced Python for AI and data engineering: type hinting, decorators, memory-efficient generators, asyncio, multiprocessing and the GIL, Cython/Numba acceleration, profiling and packaging. For developers and data scientists.
- Live Course
- 5 modules
-
Consuming and building APIs in Python for AI and data projects: HTTP/REST principles, requests and async httpx clients, authentication, retry/rate-limit handling, LLM APIs and foundational service design.
- Live Course
- 5 modules
-
End-to-end modern Python web service development with FastAPI: Pydantic v2, Dependency Injection, async SQLAlchemy database integration, OAuth2/JWT security, pytest and Docker. For backend and AI developers.
- Live Course
- 5 modules
-
Deep learning programming fundamentals with PyTorch: Tensor operations and GPU acceleration, autograd, Dataset/DataLoader pipelines, building neural networks with nn.Module, training loops and saving models. For data scientists and developers.
- Live Course
- 5 modules
Get in touch
