Data Science and Machine Learning – Course in detail

pexels-rodnae-productions-7947999

  Level of Knowledge: Beginner Python Knowledge

 Time to complete the course: 28 hours 

About this course

Specific Skills Acquired: The course focuses on gaining practical skills in working with machine learning tools and libraries in the Python ecosystem. Participants will gain practical experience in building ML models, starting from the analysis of raw data and ending with the evaluation of the model and the hyperparameter tuning, using both traditional algorithms and neural networks.. Among the tools mastered by the participants are the libraries of pandas, matplotlib, sckit-learn, keras, etc.

General Objectives: This course is an introductory course in machine learning. The main goal of the course is to provide participants with a general understanding of the problems solved by machine learning methods and basic algorithms for solving them. The course has a practical orientation, so all stages of working with this data are accompanied by practical examples.

Course content

General formulation of the machine learning task. Classification of ML tasks.

  • Data types and control flow
  • Containers
  • Functions
  •  Files I/O
  • Modules and packages
  •  Object-oriented programming

Basic syntactic constructionsand tools of the Python language, which are necessary for solving machine learning problems

  •   numpy
  •  pandas
  •  matplotlib, seaborn

Practical introduction to the main Python libraries used for data processing

  •  scklearn library
  •  Nearest neighbors classifiers
  • Decision trees
  • Bayesian classifiers
  • Linear classifiers, SVM
  • Regression algorithms
  • Clustering: KMeans, DBSCAN
  • Neural networks (Keras library)
  • Convolutional neural networks (Keras library)

Application of basic ML algorithms for solving classification, regression and clustering task using libraries scikit-learn and keras

  • Hadoop architecture
  • Hadoop ecosystem: Pig, Hive
  • NoSQL databases: MongoDB,Redis
  • Spark

Traditional and modern big data tools with application examples