Course Outline
Introduction
- Building effective algorithms in pattern recognition, classification and regression.
Setting up the Development Environment
- Python libraries
- Online vs offline editors
Overview of Feature Engineering
- Input and output variables (features)
- Pros and cons of feature engineering
Types of Problems Encountered in Raw Data
- Unclean data, missing data, etc.
Pre-Processing Variables
- Dealing with missing data
Handling Missing Values in the Data
Working with Categorical Variables
Converting Labels into Numbers
Handling Labels in Categorical Variables
Transforming Variables to Improve Predictive Power
- Numerical, categorical, date, etc.
Cleaning a Data Set
Machine Learning Modelling
Handling Outliers in Data
- Numerical variables, categorical variables, etc.
Summary and Conclusion
Requirements
- Python programming experience.
- Experience with Numpy, Pandas and scikit-learn.
- Familiarity with Machine Learning algorithms.
Audience
- Developers
- Data scientists
- Data analysts
Testimonials (2)
Szkolenie rewelacyjne, jedno z najlepszych, na jakich bylem! Prowadzacy Rafal doskonale odpowiadal w zakresie poruuszanych zagadnien, bardzo dokladnie tlumaczyl wszystkie metody. Jestem bardzo zadowolony i chetnie ponownie skorzystam ze szkolenia prowadzonego przez tego szkoleniowca.
Darek Paszkowski - Orange Szkolenia Sp. z o.o.
Course - Feature Engineering for Machine Learning
Rysunki na flipcharcie, całe szkolenie.