Practical Time-Series Analysis

Key FeaturesGet your first experience with data analysis with one of the most powerful types of analysis—time-series.Find patterns in your data and predict the future pattern based on historical data.Learn the statistics, theory, and implementation of Time-series methods using this example-rich guideBook DescriptionTime-series analysis allows analyzing certain data over a period of time and understand patterns in the data over time.This book will take you from understanding the logic behind time-series analysis to implementing it in various fields including financial, business, social media domain.The book begins with a brief introduction to Python as a general purpose programming language and discusses ways to quickly setup the Python programming environment through popular IDEs as well the more popular IPython notebook. You will be introduced to three types of data sets - cross-sectional, time series and panel. You will be introduced to different techniques of reading, exploring and visualizing time series data. later you will understand the important steps in building predictive models which uses past time steps to predict future occurrences such as stock prices, weather etc. Further you will also explore different auto-regressive models for predictive modeling on time series through case studies motivated by real business scenarios and relevant code snippets in Python.By the end of the book, you will know everything about Time-series analysis and know how to implement it in real world.What you will learnGain familiarity of the basics of Python as a powerful yet simple to code programming languageUnderstand the basic concepts of time series analysis and appreciate its importance for the success of a data science projectDevelop an understanding of loading, exploring and visualizing time series data.Explore auto-correlation and the importance of exponential smoothing for analyzing and modeling time series dataLearn to use auto-regressive models for making predictions using time series dataDiscover recent advancements in deep learning which are suitable for modeling time series and sequential dataUnderstand the concepts of resampling, upsampling and downsamplingBuild Predictive models on time series data using techniques based on auto-regressive moving averagesDiscover Deep learning techniques for time series modeling

Author: Avishek Pal

Learn more