000			02755nam a22001577a 4500
005			20250313131006.0
020			_a978-1801075541
082			_a519.55 _bATW-T
100			_aAtwan, Tarek A.
245			_aTime Series Analysis with Python Cookbook : _bPractical recipes for exploratory data analysis, data preparation, forecasting, and model evaluation
260			_aBirmingham, UK _bPackt Publishing _c2022
300			_a604p.
500			_a"There are so many use cases when we need to deal with time series data—demand forecasting, predictive maintenance, and energy consumption, to name a few – and so every data scientist must be skilled in time series analysis. Time series analysis is very difficult to master. That’s why I enjoyed Tarek A. Atwan’s book. I believe that by reading it, every data scientist will learn something new from the Python snippets dealing with time and date in Python (which is never as easy as it seems), running EDA, handling missing values, detecting outliers, and forecasting with statistical, machine learning, and deep learning models." Adam Votava, Interim Chief Data and Analytics Officer at DataDiligence "The book covers all the necessary details for time series data preparation, analysis, and forecasting, including how time series data is different from other data, how to ingest data from various sources and databases, how to deal with different time zones and custom business days, how to detect anomalies using statistical methods and visualizations, followed by developing advanced deep learning models for forecasting." Overall, this is a great reference book for data science practitioners to get up to speed quickly on state-of-the-art time series data analysis and forecasting techniques! Sadid Hasan, AI Lead at Microsoft "I recommend reading this book to anyone at any level. The book has extensive chapters on how to read and write time series data using various technologies. This is a gap for most academically trained or MOOC-trained data analysts/ scientists. The book then describes statistical methodologies to handle time series forecasting. What I enjoyed is the pace at which the author gives enough background on a topic while also showing the reader how things are done practically. Later chapters describe the ML-based modeling of time series data. I found this book to be a treasure trove of information on a set of very diverse approaches and topics. The more curious reader can later pick up a book on any of these chapters’ topics. Highly recommended for newbies and veterans alike." Shobeir Seddington, Principal Data Scientist at Gopuff & Harvard Business Review Advisor at Harvard Business Review
504			_aInclude Index.
942			_cBK
999			_c34609 _d34609