Infopaket

Data Analysis with Python

ОК 30

Обов’язкова дисципліна для ОП

First

2023/2024

3 Semester

5

The student must know: standard data analysis methodology CRISP-DM, Python objects for representing datasets, basic types of charts for data visualization, correlation data analysis methods. The student must have skills: to work with interactive development environments Jupyter Notebook and Google Colab, to estimate the time of expression calculations, to use software libraries NumPy, Matplotlib, pandas, seaborn for exploratory data analysis, to reduce the data dimensionality and to perform data decorrelation by principal component analysis (PCA), to generate random variables for a given probability density function (PDF), to estimate PDF for quantitative features of a dataset by kernel density estimation (KDE) method, to detect outliers in a dataset, to process missing values.

Full-time form

The discipline “Data Analysis with Python” is based on such disciplines: “Programming” (Python), “Higher Mathematics”, “Probability and Mathematical Statistics Theory”, “Algorithms and Methods of Calculation”, “Discrete Mathematics”.

The “Data Analysis with Python” course covers the methods and software tools of the Python language used in data analysis, including: standard data analysis methodology CRISP-DM, interactive development environments Jupyter Notebook and Google Colab, time estimation of expression computation, Python objects for representing datasets, basic types of charts for data visualization, software libraries NumPy, Matplotlib, pandas, seaborn for exploratory data analysis, correlation data analysis methods, methods of data decorrelation and reduction of data dimension, generation of random variables for a given density function probability (PDF), estimation of PDF for quantitative dataset features by kernel density estimation (KDE) method, detection of outliers in a dataset, processing of missing values, work with sets, initial information about machine learning.

1. Wes McKinney. Python for Data Analysis. 3rd Edition. O'Reilly Media, 2022. 989 pages. 2. Jake VanderPlas. Python Data Science Handbook: Essential Tools for Working with Data.O'Reilly Media, 2017. 546 pages. 3. Michael Heydt. Learning pandas - Second Edition: High performance data manipulation and analysis using Python. 2nd Edition. Packt Publishing, 2017. 703 pages. 4. J. Brownlee. Data Preparation for Machine Learning: Data Cleaning, Feature Selection, and Data Transforms in Python. Machine Learning Mastery, 2020. – 398 pages.

Lectures, laboratory work, unsupervised work.

Semester assessment: The academic semester has three semantic modules. The first two semantic modules are assessed after the completion of lecture topics 7 and 13 by compiling electronic tests. The third semantic module is assessed by the results of compilation (defense) of 6 laboratory works. Final assessment (in the form of credit): the credit form is electronic testing. The total result of test is scored upto 40 points. The result of learning of the subject is considered positive if all 6 laboratory works is compilated (defensed) and the summary score for semantic modules and credit exceeds 60 points. Conditions of admission to the credit: the condition of admission to the credit is the student's receipt of a total of not less than the critical-calculated minimum of 20 points per semester.

Ukrainian