Methodology
Codexra Education Model (Theoretical lecture, task completion, real world projects)
Weekly Class Hours
10 Hour
Introduction to Data Science (10 hours)
Day 1 (5 hours)
- What is data science? Application areas and tools.
- Python fundamentals: Data structures, loops, functions.
- Lab Work: Simple data analysis with Python.
Day 2 (5 hours)
- Data types and cleaning processes.
- Task: Fill missing data and apply data cleaning processes.
Data Analysis and Visualization (10 hours)
Day 3
- Data manipulation with Pandas.
- Lab Work: Filtering, sorting, and summarizing a large dataset.
Day 4
- Data visualization with Matplotlib and Seaborn.
- Task: Analyzing a dataset with graphs.
Statistics and Probability (10 hours)
Day 5
- Basic statistics: Mean, median, variance, standard deviation.
- Lab Work: Calculating basic statistics of a dataset.
Day 6
- Probability distributions and hypothesis testing.
- Task: Applying hypothesis testing in data analysis.
Introduction to Machine Learning (10 hours)
Day 7
- Supervised and unsupervised learning concepts.
- Lab Work: Developing a simple regression model using Scikit-learn.
Day 8
- Basic algorithms like KNN, Decision Tree.
- Task: Applying clustering algorithms on a dataset.
Data Processing and Feature Engineering (10 hours)
Day 9
- Data preprocessing: Normalization, categorical data handling.
- Lab Work: Feature extraction and selection on a dataset.
Day 10
- Feature engineering techniques.
- Task: Selecting the best features for machine learning models.
Deep Learning and TensorFlow (10 hours)
Day 11
- Neural networks and working with TensorFlow.
- Lab Work: Creating a simple neural network.
Day 12
- Deep learning applications on image and text data.
- Task: Creating a classification model on the MNIST dataset.
Model Performance and Optimization (10 hours)
Day 13
- Model performance measurement: Metrics and evaluation.
- Lab Work: Evaluating a model using metrics like ROC, F1 Score.
Day 14
- Hyperparameter tuning and model optimization.
- Task: Optimizing a model using Grid Search or Random Search.
Real-World Project (10 hours)
Day 15
- Project Preparation: Dataset selection and problem definition.
- Task: Developing a machine learning project addressing a real-world problem.
Day 16
- Project completion and presentation.
- Lab Work: Testing the feasibility of the project implementation.
Participants will gain skills from basic data science and machine learning to solving real-world problems.
They will reinforce their technical knowledge through practical projects and be ready for the industry.
Level
Junior
Duration
80 Hour
Lessons
16
Quizzes
10
Certificates
Yes
