title

Time Series Analysis in Python | Time Series Forecasting | Data Science with Python | Edureka

description

π₯ Python Data Science Training (Use Code "πππππππππ") : https://www.edureka.co/data-science-python-certification-course
This Edureka Video on Time Series Analysis n Python will give you all the information you need to do Time Series Analysis and Forecasting in Python. Below are the topics covered in this tutorial:
1. Why Time Series?
2. What is Time Series?
3. Components of Time Series
4. When not to use Time Series
5. What is Stationarity?
6. ARIMA Model
7. Demo: Forecast Future
Subscribe to our channel to get video updates. Hit the subscribe button above.
Machine Learning Tutorial Playlist: https://goo.gl/UxjTxm
PG in Artificial Intelligence and Machine Learning with NIT Warangal : https://www.edureka.co/post-graduate/machine-learning-and-ai
Post Graduate Certification in Data Science with IIT Guwahati - https://www.edureka.co/post-graduate/data-science-program
(450+ Hrs || 9 Months || 20+ Projects & 100+ Case studies)
#timeseries #timeseriespython #machinelearningalgorithms
- - - - - - - - - - - - - - - - -
About the Course
Edurekaβs Course on Python helps you gain expertise in various machine learning algorithms such as regression, clustering, decision trees, random forest, NaΓ―ve Bayes and Q-Learning. Throughout the Python Certification Course, youβll be solving real life case studies on Media, Healthcare, Social Media, Aviation, HR.
During our Python Certification Training, our instructors will help you to:
1. Master the basic and advanced concepts of Python
2. Gain insight into the 'Roles' played by a Machine Learning Engineer
3. Automate data analysis using python
4. Gain expertise in machine learning using Python and build a Real Life Machine Learning application
5. Understand the supervised and unsupervised learning and concepts of Scikit-Learn
6. Explain Time Series and itβs related concepts
7. Perform Text Mining and Sentimental analysis
8. Gain expertise to handle business in future, living the present
9. Work on a Real Life Project on Big Data Analytics using Python and gain Hands on Project Experience
- - - - - - - - - - - - - - - - - - -
Why learn Python?
Programmers love Python because of how fast and easy it is to use. Python cuts development time in half with its simple to read syntax and easy compilation feature. Debugging your programs is a breeze in Python with its built in debugger. Using Python makes Programmers more productive and their programs ultimately better. Python continues to be a favorite option for data scientists who use it for building and using Machine learning applications and other scientific computations.
Python runs on Windows, Linux/Unix, Mac OS and has been ported to Java and .NET virtual machines. Python is free to use, even for the commercial products, because of its OSI-approved open source license.
Python has evolved as the most preferred Language for Data Analytics and the increasing search trends on python also indicates that Python is the next "Big Thing" and a must for Professionals in the Data Analytics domain.
For more information, Please write back to us at sales@edureka.in or call us at IND: 9606058406 / US: 18338555775 (toll free).
Instagram: https://www.instagram.com/edureka_learning/
Facebook: https://www.facebook.com/edurekaIN/
Twitter: https://twitter.com/edurekain
LinkedIn: https://www.linkedin.com/company/edureka

detail

{'title': 'Time Series Analysis in Python | Time Series Forecasting | Data Science with Python | Edureka', 'heatmap': [{'end': 2260.379, 'start': 2226.83, 'weight': 1}], 'summary': 'Covers time series analysis, emphasizing its importance, components, and applications in business forecasting, sales trend, and passenger number forecasting, using concepts like stationarity tests, arima model, rolling statistics, and transformation techniques to achieve stationarity, with practical demonstrations and a 10-year demand forecast.', 'chapters': [{'end': 78.344, 'segs': [{'end': 78.344, 'src': 'embed', 'start': 23.836, 'weight': 0, 'content': [{'end': 29.88, 'text': "So we'll start off this session by understanding why do we need time series analysis and then we'll understand what exactly it is.", 'start': 23.836, 'duration': 6.044}, {'end': 35.605, 'text': 'Now once we clear with time series will then see the different components that we need to take care while we apply time series.', 'start': 30.341, 'duration': 5.264}, {'end': 42.531, 'text': "Then we'll also discuss when should you not use time series analysis or what are the cases when you should not apply time series analysis.", 'start': 36.125, 'duration': 6.406}, {'end': 43.592, 'text': 'moving ahead in the session', 'start': 42.531, 'duration': 1.061}, {'end': 49.778, 'text': 'We also discuss what is stationarity or what are the tests that are used to perform to check the stationarity of the data.', 'start': 43.672, 'duration': 6.106}, {'end': 52.12, 'text': "next we'll be discussing the Arima model now.", 'start': 49.778, 'duration': 2.342}, {'end': 55.403, 'text': 'Arima model is one of the best model that has been used in time series.', 'start': 52.12, 'duration': 3.283}, {'end': 59.337, 'text': "So we'll have a discussion on that and we'll finally go ahead with the demo part,", 'start': 56.016, 'duration': 3.321}, {'end': 63.419, 'text': "where in I'll implement all these things and help you guys to forecast the future as well.", 'start': 59.337, 'duration': 4.082}, {'end': 65.74, 'text': 'So I hope you guys are clear with the agenda.', 'start': 63.859, 'duration': 1.881}, {'end': 70.301, 'text': 'So kindly drop me a quick confirmation or you can just write it down in your chat box so that I can proceed.', 'start': 65.84, 'duration': 4.461}, {'end': 72.422, 'text': 'All right, Monisha says yes.', 'start': 71.242, 'duration': 1.18}, {'end': 74.523, 'text': 'Okay, Swati gave me a thumbs up.', 'start': 73.363, 'duration': 1.16}, {'end': 76.624, 'text': 'Naman Shivani.', 'start': 75.463, 'duration': 1.161}, {'end': 78.344, 'text': 'All right, since you guys are clear.', 'start': 77.084, 'duration': 1.26}], 'summary': 'Training on time series analysis, including components, tests for stationarity, arima model, and forecasting future data.', 'duration': 54.508, 'max_score': 23.836, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q23836.jpg'}], 'start': 7.523, 'title': 'Time series analysis overview', 'summary': 'Delves into the importance of time series analysis, its components, when not to use it, stationarity tests, and the arima model, with the goal of forecasting future trends and confirming understanding among attendees.', 'chapters': [{'end': 78.344, 'start': 7.523, 'title': 'Time series analysis overview', 'summary': 'Covers the importance of time series analysis, its components, when not to use it, stationarity tests, and the arima model, aiming to forecast future trends, with attendees confirming understanding.', 'duration': 70.821, 'highlights': ['The Arima model is one of the best models used in time series, and the session includes a discussion on it, followed by a demo. This showcases the practical application of the model and its significance in time series analysis.', 'The session covers the importance of time series analysis, its components, and when not to use it, providing a comprehensive understanding of its applications and limitations.', 'The discussion includes understanding stationarity and the tests used to check it, offering practical insights into ensuring the reliability of time series data for analysis.', 'Attendees confirm understanding of the agenda, indicating engagement and comprehension of the topics covered in the session.']}], 'duration': 70.821, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q7523.jpg', 'highlights': ['The Arima model is one of the best models used in time series, and the session includes a discussion on it, followed by a demo.', 'The session covers the importance of time series analysis, its components, and when not to use it, providing a comprehensive understanding of its applications and limitations.', 'The discussion includes understanding stationarity and the tests used to check it, offering practical insights into ensuring the reliability of time series data for analysis.', 'Attendees confirm understanding of the agenda, indicating engagement and comprehension of the topics covered in the session.']}, {'end': 331.927, 'segs': [{'end': 105.491, 'src': 'embed', 'start': 78.344, 'weight': 0, 'content': [{'end': 82.226, 'text': "so let's begin with the very first topic, that is, why should you use time series analysis?", 'start': 78.344, 'duration': 3.882}, {'end': 86.8, 'text': 'So, first of all, in time series analysis, you just have one variable, that is time.', 'start': 82.816, 'duration': 3.984}, {'end': 89.423, 'text': 'now. you must have seen there is a lot of algorithms present.', 'start': 86.8, 'duration': 2.623}, {'end': 92.026, 'text': 'then why do we need one more algorithm, that is time series?', 'start': 89.423, 'duration': 2.603}, {'end': 94.468, 'text': 'So let me explain you this with an example.', 'start': 92.606, 'duration': 1.862}, {'end': 96.971, 'text': "Now, let's take an example of a supervised learning.", 'start': 94.888, 'duration': 2.083}, {'end': 100.094, 'text': 'So under supervised learning we have linear regression or logistic.', 'start': 97.291, 'duration': 2.803}, {'end': 103.958, 'text': 'So there we have an independent variable and we have a dependent variable.', 'start': 100.414, 'duration': 3.544}, {'end': 105.491, 'text': 'So there what we do.', 'start': 104.531, 'duration': 0.96}], 'summary': 'Time series analysis focuses on one variable: time. it provides unique insights and algorithms for this specific type of data.', 'duration': 27.147, 'max_score': 78.344, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q78344.jpg'}, {'end': 236.801, 'src': 'embed', 'start': 200.825, 'weight': 2, 'content': [{'end': 206.849, 'text': "So let's say you'll be seeing a lot of traders in the sense X who are trying to predict what will be the price of the stock market tomorrow.", 'start': 200.825, 'duration': 6.024}, {'end': 209.11, 'text': 'So that is nothing but a business forecasting.', 'start': 207.109, 'duration': 2.001}, {'end': 214.634, 'text': 'You also see a lot of retailers who tries to know how many number of goods they are going to sell the next day.', 'start': 209.531, 'duration': 5.103}, {'end': 217.416, 'text': 'So all of this can be achieved with time series analysis.', 'start': 214.854, 'duration': 2.562}, {'end': 223.258, 'text': 'Now, this is not just limited to one domain like retail or Finance, but it is applicable almost everywhere.', 'start': 217.916, 'duration': 5.342}, {'end': 226.218, 'text': 'Now it is also help us to analyze the past behavior.', 'start': 223.538, 'duration': 2.68}, {'end': 233.12, 'text': 'So here you can analyze in which month did the sales went up or when was the dip so here you can easily understand your past data.', 'start': 226.619, 'duration': 6.501}, {'end': 236.801, 'text': 'So with every dip and a peak there is a business reason attached to it.', 'start': 233.4, 'duration': 3.401}], 'summary': 'Time series analysis helps predict stock prices and sales, applicable across domains.', 'duration': 35.976, 'max_score': 200.825, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q200825.jpg'}, {'end': 281.205, 'src': 'embed', 'start': 255.641, 'weight': 4, 'content': [{'end': 261.822, 'text': 'so you can analyze the past and then you can forecast your future using this algorithm, that is, time series analysis.', 'start': 255.641, 'duration': 6.181}, {'end': 265.282, 'text': 'now, apart from all this, you can also evaluate current accomplishment.', 'start': 261.822, 'duration': 3.46}, {'end': 269.083, 'text': 'So this means you can determine which goals you have met in the current scenario.', 'start': 265.622, 'duration': 3.461}, {'end': 270.443, 'text': "Let's say you have predicted.", 'start': 269.483, 'duration': 0.96}, {'end': 272.904, 'text': "Okay, I'm going to sell around 100 chocolates in a day.", 'start': 270.583, 'duration': 2.321}, {'end': 278.985, 'text': 'But did you actually do that? So all of this can be analyzed using time series analysis moving ahead.', 'start': 273.264, 'duration': 5.721}, {'end': 281.205, 'text': 'Let us see the different components of time series.', 'start': 279.025, 'duration': 2.18}], 'summary': 'Time series analysis can analyze past data, forecast future, and evaluate current accomplishments.', 'duration': 25.564, 'max_score': 255.641, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q255641.jpg'}], 'start': 78.344, 'title': 'Time series analysis', 'summary': 'Discusses the importance of time series analysis, comparing it with supervised learning algorithms and emphasizing the unique use of time as a variable. it also explains time series analysis as a method to predict variables with time, its importance in business forecasting, analyzing past behavior, planning future operations, and evaluating current accomplishments using examples and components such as trend, seasonality, and irregularity.', 'chapters': [{'end': 113.055, 'start': 78.344, 'title': 'Importance of time series analysis', 'summary': 'Discusses the importance of time series analysis by comparing it with supervised learning algorithms, emphasizing the unique use of time as a variable and the need for specific algorithms for time series analysis.', 'duration': 34.711, 'highlights': ['Time series analysis emphasizes the unique use of time as a variable, unlike other algorithms used in supervised learning.', 'The chapter compares time series analysis with supervised learning algorithms like linear regression and logistic, highlighting the need for specific algorithms to deduce a function for analyzing time-dependent data.']}, {'end': 331.927, 'start': 113.055, 'title': 'Time series analysis', 'summary': 'Explains time series analysis as a method to predict variables with time, its importance in business forecasting, analyzing past behavior, planning future operations, and evaluating current accomplishments using examples and components such as trend, seasonality, and irregularity.', 'duration': 218.872, 'highlights': ['Time series analysis is used for business forecasting, such as predicting stock prices and sales of goods, applicable across various domains.', 'Analyzing past behavior with time series helps in understanding sales patterns, identifying reasons for peaks and dips, and considering seasonality effects.', 'Time series analysis assists in planning future operations by analyzing past data and forecasting using algorithms.', 'Time series analysis enables the evaluation of current accomplishments by comparing predictions with actual outcomes, allowing for goal assessment.']}], 'duration': 253.583, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q78344.jpg', 'highlights': ['Time series analysis emphasizes the unique use of time as a variable, unlike other algorithms used in supervised learning.', 'The chapter compares time series analysis with supervised learning algorithms like linear regression and logistic, highlighting the need for specific algorithms to deduce a function for analyzing time-dependent data.', 'Time series analysis is used for business forecasting, such as predicting stock prices and sales of goods, applicable across various domains.', 'Analyzing past behavior with time series helps in understanding sales patterns, identifying reasons for peaks and dips, and considering seasonality effects.', 'Time series analysis assists in planning future operations by analyzing past data and forecasting using algorithms.', 'Time series analysis enables the evaluation of current accomplishments by comparing predictions with actual outcomes, allowing for goal assessment.']}, {'end': 924.461, 'segs': [{'end': 376.586, 'src': 'embed', 'start': 350.619, 'weight': 2, 'content': [{'end': 358.284, 'text': 'This is something that is happening year on year but trend is something that happens for some time and then it disappears then we have seasonality.', 'start': 350.619, 'duration': 7.665}, {'end': 363.674, 'text': 'So here seasonality is basically upward or downward swings, but this is quite different.', 'start': 358.849, 'duration': 4.825}, {'end': 366.476, 'text': "It's a repeating pattern within a fixed time period.", 'start': 363.854, 'duration': 2.622}, {'end': 369.94, 'text': 'So for example Christmas happens every year on 25th December.', 'start': 366.717, 'duration': 3.223}, {'end': 372.142, 'text': "Let's say you're on the business of chocolates.", 'start': 370.46, 'duration': 1.682}, {'end': 376.586, 'text': 'So every year on year chocolates are served more and more in the last week of December.', 'start': 372.522, 'duration': 4.064}], 'summary': 'Seasonal trend: chocolates sales increase every december.', 'duration': 25.967, 'max_score': 350.619, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q350619.jpg'}, {'end': 420.038, 'src': 'embed', 'start': 391.023, 'weight': 4, 'content': [{'end': 392.444, 'text': 'Now, let me take another example.', 'start': 391.023, 'duration': 1.421}, {'end': 394.005, 'text': "Let's say ice cream this time.", 'start': 392.825, 'duration': 1.18}, {'end': 398.289, 'text': 'So ice cream sales will go comparatively higher in summers rather than in winter.', 'start': 394.386, 'duration': 3.903}, {'end': 400.05, 'text': 'So that is again a seasonality.', 'start': 398.529, 'duration': 1.521}, {'end': 403.653, 'text': 'Then we have irregularity or it is also called as noise.', 'start': 400.712, 'duration': 2.941}, {'end': 407.214, 'text': 'So these are erratic in nature or you can say unsystematic.', 'start': 403.953, 'duration': 3.261}, {'end': 408.954, 'text': 'It is also called as residual.', 'start': 407.554, 'duration': 1.4}, {'end': 412.896, 'text': 'So this happens basically for short duration and is non-repeating.', 'start': 409.415, 'duration': 3.481}, {'end': 414.676, 'text': 'So here let me give you an example.', 'start': 413.176, 'duration': 1.5}, {'end': 416.917, 'text': "So let's say there is a natural disaster.", 'start': 415.216, 'duration': 1.701}, {'end': 420.038, 'text': "Let's say there is a flood in your town out of nowhere in one year.", 'start': 417.237, 'duration': 2.801}], 'summary': 'Seasonal variation affects ice cream sales, while irregular events, like natural disasters, can have short-term impacts.', 'duration': 29.015, 'max_score': 391.023, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q391023.jpg'}, {'end': 613.988, 'src': 'embed', 'start': 585.705, 'weight': 0, 'content': [{'end': 588.546, 'text': 'So stationarity basically has a very strict criteria.', 'start': 585.705, 'duration': 2.841}, {'end': 594.389, 'text': 'The first one is it should have a constant mean now here the mean should be constant according to the time.', 'start': 589.106, 'duration': 5.283}, {'end': 596.47, 'text': 'Secondly, we have constant variance.', 'start': 594.789, 'duration': 1.681}, {'end': 599.652, 'text': 'So again variance should be equal at different time intervals.', 'start': 596.71, 'duration': 2.942}, {'end': 603.178, 'text': 'and thirdly we have Auto covariance that does not depend on time.', 'start': 600.296, 'duration': 2.882}, {'end': 608.923, 'text': "So for those of you who don't know what mean is I'll not go into the details, but I'll just explain you in a nutshell.", 'start': 603.559, 'duration': 5.364}, {'end': 613.988, 'text': 'So mean is basically the average, then variance is just the distance from the mean.', 'start': 609.244, 'duration': 4.744}], 'summary': 'Stationarity requires constant mean, variance, and time-independent autocovariance.', 'duration': 28.283, 'max_score': 585.705, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q585705.jpg'}, {'end': 764.147, 'src': 'embed', 'start': 734.823, 'weight': 1, 'content': [{'end': 738.525, 'text': 'So once you combine both of these model, you get the Arima model.', 'start': 734.823, 'duration': 3.702}, {'end': 743.289, 'text': 'now your AR model stands for autoregressive part and ma model stands for moving average.', 'start': 738.525, 'duration': 4.764}, {'end': 750.595, 'text': 'So AR is a separate model, ma is a separate model and what binds it together is the integration part that is indicated by I.', 'start': 744.21, 'duration': 6.385}, {'end': 755.802, 'text': 'So air is nothing but the correlation between the previous time period to the current.', 'start': 751.48, 'duration': 4.322}, {'end': 756.943, 'text': 'So what does this mean?', 'start': 756.103, 'duration': 0.84}, {'end': 764.147, 'text': "Now, let's take this into consideration that you are standing at a time period T and there are previous time periods like T minus 1, T minus 2,", 'start': 757.323, 'duration': 6.824}], 'summary': 'Combining ar and ma models gives the arima model, with ar representing autoregression, ma representing moving average, and i representing integration.', 'duration': 29.324, 'max_score': 734.823, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q734823.jpg'}, {'end': 885.671, 'src': 'embed', 'start': 852.793, 'weight': 5, 'content': [{'end': 855.394, 'text': "So now we'll have a look to a demo and will forecast the future.", 'start': 852.793, 'duration': 2.601}, {'end': 860.795, 'text': "So here we have a problem statement where there's a line which has the data of passengers across months.", 'start': 855.814, 'duration': 4.981}, {'end': 862.595, 'text': 'So here what you need to do.', 'start': 861.474, 'duration': 1.121}, {'end': 869.221, 'text': 'you need to build a forecast to determine how many number of passengers are going to abort these Airlines at the month level in the future.', 'start': 862.595, 'duration': 6.626}, {'end': 871.863, 'text': 'So here we have month or you can say dates.', 'start': 869.861, 'duration': 2.002}, {'end': 878.609, 'text': 'So here we have dates from 1949 to 1960 and we have the number of passengers traveling per month.', 'start': 872.444, 'duration': 6.165}, {'end': 885.671, 'text': 'So now we have this kind of data and we need to analyze what will be the number of passengers if we have to predict it for next 10 years.', 'start': 879.426, 'duration': 6.245}], 'summary': 'Forecast the number of airline passengers for the next 10 years using historical data from 1949 to 1960.', 'duration': 32.878, 'max_score': 852.793, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q852793.jpg'}], 'start': 332.207, 'title': 'Sales trends, seasonality, and time series analysis', 'summary': 'Covers concepts of sales trend, seasonality, and irregularity, providing examples to illustrate the concepts. it also includes an overview of time series analysis, emphasizing stationarity and arima models, and a demo on forecasting future passenger numbers for an airline over a specified time period.', 'chapters': [{'end': 431.187, 'start': 332.207, 'title': 'Understanding sales trends and seasonality', 'summary': 'Explains the concept of sales trend, seasonality, and irregularity in a business context, emphasizing the difference between them and providing examples to illustrate the concepts.', 'duration': 98.98, 'highlights': ['The concept of sales trend and seasonality is explained, emphasizing the difference between them and providing examples to illustrate the concepts.', 'Seasonality is described as a repeating pattern within a fixed time period, illustrated with examples of Christmas-related sales and seasonal variations in ice cream sales.', "Irregularity or 'noise' is highlighted as erratic and non-repeating, with an example of a natural disaster causing a temporary surge in sales followed by a decline.", 'The impact of house occupancy on hardware sales is mentioned as an example of a trend, indicating a temporary increase followed by a decrease in sales.']}, {'end': 924.461, 'start': 431.687, 'title': 'Time series analysis overview', 'summary': 'Provides an overview of time series analysis, covering concepts such as irregularity, stationarity, and arima models, with a focus on the importance of stationarity and the components of arima model. it also includes a demo on forecasting future passenger numbers for an airline over a specified time period.', 'duration': 492.774, 'highlights': ['The importance of stationarity is emphasized as most models work on the assumption that time series is stationary, and the criteria for stationarity includes constant mean, constant variance, and auto covariance not dependent on time. Emphasis on the importance of stationarity for time series analysis; Criteria for stationarity including constant mean, variance, and auto covariance.', "Explanation of ARIMA model as a combination of autoregressive (AR) and moving average (MA) models, with the integration part indicated by 'I', and the parameters P, Q, and D representing autoregressive lags, moving average, and order of differentiation respectively. Explanation of ARIMA model as a combination of AR and MA models with the integration part; Parameters P, Q, and D representing autoregressive lags, moving average, and order of differentiation.", 'Demo on forecasting future passenger numbers for an airline over a specified time period, using the concepts and techniques discussed in the chapter. Demo on forecasting future passenger numbers for an airline using the discussed concepts and techniques.']}], 'duration': 592.254, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q332207.jpg', 'highlights': ['The importance of stationarity is emphasized as most models work on the assumption that time series is stationary, and the criteria for stationarity includes constant mean, constant variance, and auto covariance not dependent on time.', "Explanation of ARIMA model as a combination of autoregressive (AR) and moving average (MA) models, with the integration part indicated by 'I', and the parameters P, Q, and D representing autoregressive lags, moving average, and order of differentiation respectively.", 'The concept of sales trend and seasonality is explained, emphasizing the difference between them and providing examples to illustrate the concepts.', 'Seasonality is described as a repeating pattern within a fixed time period, illustrated with examples of Christmas-related sales and seasonal variations in ice cream sales.', "Irregularity or 'noise' is highlighted as erratic and non-repeating, with an example of a natural disaster causing a temporary surge in sales followed by a decline.", 'Demo on forecasting future passenger numbers for an airline over a specified time period, using the concepts and techniques discussed in the chapter.']}, {'end': 1138.191, 'segs': [{'end': 959.793, 'src': 'embed', 'start': 926.485, 'weight': 0, 'content': [{'end': 927.125, 'text': "Next what I've done.", 'start': 926.485, 'duration': 0.64}, {'end': 930.067, 'text': 'I have imported my air passengers data using pandas.', 'start': 927.225, 'duration': 2.842}, {'end': 934.75, 'text': 'So we have a function of read CSV in Panda that is represented with PD.', 'start': 930.727, 'duration': 4.023}, {'end': 938.852, 'text': 'So we have substituted this in a variable data set and then what we have done.', 'start': 935.13, 'duration': 3.722}, {'end': 941.494, 'text': 'We have just passed those strings in a date time format.', 'start': 938.892, 'duration': 2.602}, {'end': 943.835, 'text': 'So here we have set our data month wise.', 'start': 941.974, 'duration': 1.861}, {'end': 946.617, 'text': 'So using pandas we have a function to date time.', 'start': 944.135, 'duration': 2.482}, {'end': 951.439, 'text': 'So over here you can specify a month and then you can just set this as your index.', 'start': 947.017, 'duration': 4.422}, {'end': 954.021, 'text': 'So here you have index variable as month.', 'start': 952.1, 'duration': 1.921}, {'end': 955.51, 'text': 'Next what I have done.', 'start': 954.71, 'duration': 0.8}, {'end': 959.793, 'text': 'I have imported date time and then I have just printed the top five values.', 'start': 955.591, 'duration': 4.202}], 'summary': 'Imported air passengers data using pandas, set data month-wise, and printed top 5 values.', 'duration': 33.308, 'max_score': 926.485, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q926485.jpg'}, {'end': 995.75, 'src': 'embed', 'start': 969.238, 'weight': 1, 'content': [{'end': 975.182, 'text': "So this data I've already showed you in the presentation where I have the data from 1949 to 1960.", 'start': 969.238, 'duration': 5.944}, {'end': 976.983, 'text': 'So I have just printed the head of it.', 'start': 975.182, 'duration': 1.801}, {'end': 978.463, 'text': 'So now let me just print the tail.', 'start': 977.103, 'duration': 1.36}, {'end': 981.165, 'text': "So let's say I want to know the last five data entries.", 'start': 978.884, 'duration': 2.281}, {'end': 987.064, 'text': 'So here we have data till 1960 and we have the number of passengers next what we have done.', 'start': 981.86, 'duration': 5.204}, {'end': 988.985, 'text': 'We have simply plotted a graph between them.', 'start': 987.104, 'duration': 1.881}, {'end': 992.688, 'text': 'So guys in time series, we have date and we have another variable.', 'start': 989.425, 'duration': 3.263}, {'end': 995.75, 'text': 'So here my other variable is number of air passengers.', 'start': 993.168, 'duration': 2.582}], 'summary': 'Data from 1949 to 1960 analyzed for air passenger trends.', 'duration': 26.512, 'max_score': 969.238, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q969238.jpg'}, {'end': 1062.166, 'src': 'embed', 'start': 1029.98, 'weight': 3, 'content': [{'end': 1035.683, 'text': "So here your mean will lie somewhat over here and let's if you want to calculate the mean of this year that is 1960.", 'start': 1029.98, 'duration': 5.703}, {'end': 1037.983, 'text': 'So here your mean will be somewhere here.', 'start': 1035.683, 'duration': 2.3}, {'end': 1042.205, 'text': 'So here you can see that you have a upward trend and the mean is not constant.', 'start': 1038.023, 'duration': 4.182}, {'end': 1044.686, 'text': 'So this tells me your data is not stationary.', 'start': 1042.526, 'duration': 2.16}, {'end': 1050.619, 'text': 'So now I have told you guys that there are two tests which basically helps you in checking the similarity of the data.', 'start': 1045.396, 'duration': 5.223}, {'end': 1053.901, 'text': 'So here we have rolling statistics as well as we have ADCF.', 'start': 1051.099, 'duration': 2.802}, {'end': 1055.902, 'text': "So let's go through each one of them.", 'start': 1053.961, 'duration': 1.941}, {'end': 1058.524, 'text': "So here we'll be first going to the rolling statistics.", 'start': 1056.423, 'duration': 2.101}, {'end': 1062.166, 'text': 'So here we have rolling mean and we have rolling standard deviation.', 'start': 1059.144, 'duration': 3.022}], 'summary': 'Data analysis shows non-stationary data with upward trend, using rolling statistics and adfc for similarity checks.', 'duration': 32.186, 'max_score': 1029.98, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1029980.jpg'}, {'end': 1105.482, 'src': 'embed', 'start': 1080.664, 'weight': 5, 'content': [{'end': 1086.487, 'text': 'So in Python to calculate mean and standard deviation you have a function dot mean and you have dot STD.', 'start': 1080.664, 'duration': 5.823}, {'end': 1089.789, 'text': 'So this will automatically calculate mean and standard deviation.', 'start': 1086.787, 'duration': 3.002}, {'end': 1091.31, 'text': 'So now let me just run this.', 'start': 1090.209, 'duration': 1.101}, {'end': 1097.514, 'text': 'So here, if you notice, your first 11 rows is nan, that is not a number now.', 'start': 1092.97, 'duration': 4.544}, {'end': 1105.482, 'text': 'this is because we have calculated all the averages of these 11 and given over here, and similarly you can do the same for the next ones.', 'start': 1097.514, 'duration': 7.968}], 'summary': 'In python, mean and standard deviation can be calculated using dot mean and dot std functions, automatically computing the averages and handling nan values.', 'duration': 24.818, 'max_score': 1080.664, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1080664.jpg'}], 'start': 926.485, 'title': 'Air passengers data analysis and time series analysis basics', 'summary': 'Covers importing air passengers data using pandas, setting the data month-wise, importing date time, printing the top and bottom values of the dataset, plotting a graph between the years 1949 to 1960. it also discusses time series analysis using a dataset of air passengers, determining non-stationarity, and calculating rolling statistics with a focus on mean and standard deviation over a 12-month window.', 'chapters': [{'end': 988.985, 'start': 926.485, 'title': 'Air passengers data analysis', 'summary': 'Covers importing air passengers data using pandas, setting the data month-wise, importing date time, printing the top and bottom values of the dataset, and plotting a graph between the years 1949 to 1960.', 'duration': 62.5, 'highlights': ['Importing air passengers data using pandas and setting the data month-wise.', 'Printing the top and bottom values of the dataset.', 'Plotting a graph to visualize the data between the years 1949 to 1960.']}, {'end': 1138.191, 'start': 989.425, 'title': 'Time series analysis basics', 'summary': 'Discusses time series analysis using a dataset of air passengers, determining non-stationarity, and calculating rolling statistics, with a focus on mean and standard deviation over a 12-month window.', 'duration': 148.766, 'highlights': ['The data shows an upward trend indicating non-stationarity, as the mean of the number of air passengers increases over the years, suggesting a lack of constant mean.', 'Two tests for checking the similarity of the data are introduced: rolling statistics (rolling mean and standard deviation) and ADFC (Augmented Dickey-Fuller Test) to assess stationarity.', 'The rolling statistics involve calculating the mean and standard deviation over a 12-month window, with functions like dot mean and dot STD in Python for automated calculation.']}], 'duration': 211.706, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q926485.jpg', 'highlights': ['Import air passengers data using pandas and set data month-wise.', 'Print top and bottom values of the dataset.', 'Plot a graph to visualize data between 1949 to 1960.', 'Data shows upward trend indicating non-stationarity with increasing mean of air passengers over the years.', 'Introduce rolling statistics and ADFC test to assess stationarity.', 'Calculate rolling mean and standard deviation over a 12-month window using dot mean and dot STD functions in Python.']}, {'end': 1641.267, 'segs': [{'end': 1197.053, 'src': 'embed', 'start': 1172.486, 'weight': 1, 'content': [{'end': 1180.888, 'text': 'So guys blue line is my original data and as you can see I have my mean in red and I have a rolling standard deviation in black color.', 'start': 1172.486, 'duration': 8.402}, {'end': 1186.03, 'text': 'So over here you can conclude that your mean and even your standard deviation is not constant.', 'start': 1181.168, 'duration': 4.862}, {'end': 1187.89, 'text': 'So your data is not stationary.', 'start': 1186.35, 'duration': 1.54}, {'end': 1191.631, 'text': 'So guys, this is my rolling statistics method is again a visual technique.', 'start': 1188.29, 'duration': 3.341}, {'end': 1197.053, 'text': 'So here we have already concluded that this is not a stationary data set now, let me perform the key for the test as well.', 'start': 1191.671, 'duration': 5.382}], 'summary': 'The data is non-stationary with fluctuating mean and standard deviation, requiring further testing.', 'duration': 24.567, 'max_score': 1172.486, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1172486.jpg'}, {'end': 1304.237, 'src': 'embed', 'start': 1275.063, 'weight': 0, 'content': [{'end': 1279.544, 'text': 'So that would be a great thing also a critical value should also be more than the test statistic.', 'start': 1275.063, 'duration': 4.481}, {'end': 1286.987, 'text': "So here we cannot reject the null hypothesis and we can say that data is not stationary then what we'll do with estimate the trend.", 'start': 1279.944, 'duration': 7.043}, {'end': 1289.487, 'text': 'So here also with the results of Dickey Fuller.', 'start': 1287.607, 'duration': 1.88}, {'end': 1291.868, 'text': 'We got to know that the data is not stationary.', 'start': 1289.527, 'duration': 2.341}, {'end': 1294.353, 'text': "then what we'll do will estimate the train.", 'start': 1292.512, 'duration': 1.841}, {'end': 1295.813, 'text': 'So here what we have done.', 'start': 1294.793, 'duration': 1.02}, {'end': 1298.274, 'text': 'We have taken a log of the index data set.', 'start': 1295.873, 'duration': 2.401}, {'end': 1304.237, 'text': 'So index data set is nothing but the data set which has index has time or the data which has been set monthly wise.', 'start': 1298.735, 'duration': 5.502}], 'summary': 'Data is not stationary, estimated trend using log of index data set.', 'duration': 29.174, 'max_score': 1275.063, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1275063.jpg'}, {'end': 1345.355, 'src': 'embed', 'start': 1314.621, 'weight': 4, 'content': [{'end': 1319.803, 'text': 'We have taken the log but here your trends remains the same whereas the value of Y has been changed.', 'start': 1314.621, 'duration': 5.182}, {'end': 1325.389, 'text': 'Next let us calculate the moving average with the same window, but keep in mind guys at this time.', 'start': 1320.768, 'duration': 4.621}, {'end': 1327.35, 'text': "We'll be taking up with the log time series.", 'start': 1325.449, 'duration': 1.901}, {'end': 1334.732, 'text': "So again, we'll be having Windows goes to 12 that is nothing but the 12 months and then we'll be just plotting the graph with the log time series.", 'start': 1327.49, 'duration': 7.242}, {'end': 1337.433, 'text': 'So here data is already in the log form.', 'start': 1335.432, 'duration': 2.001}, {'end': 1339.053, 'text': 'So now let me just print it.', 'start': 1337.853, 'duration': 1.2}, {'end': 1345.355, 'text': 'So here you can conclude that mean is not stationary but it is quite better than the previous one.', 'start': 1340.814, 'duration': 4.541}], 'summary': 'Analyzing time series data, finding mean not stationary but improved', 'duration': 30.734, 'max_score': 1314.621, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1314621.jpg'}, {'end': 1399.914, 'src': 'embed', 'start': 1371.048, 'weight': 2, 'content': [{'end': 1376.072, 'text': "So now you must be having a question as to whether it's the standard way to make a time series stationary.", 'start': 1371.048, 'duration': 5.024}, {'end': 1383.327, 'text': "No, it's not guys because it depends on your time series as in how you can make it stationary like sometimes you have to take log.", 'start': 1376.618, 'duration': 6.709}, {'end': 1386.892, 'text': 'Sometimes you might want to take a square of it sometime cube roots.', 'start': 1383.447, 'duration': 3.445}, {'end': 1389.015, 'text': 'So it all depends on data what it holds.', 'start': 1387.172, 'duration': 1.843}, {'end': 1391.188, 'text': "So here we're going to log scale.", 'start': 1389.787, 'duration': 1.401}, {'end': 1394.51, 'text': 'So we are going to take ma and then subtract both of them.', 'start': 1391.588, 'duration': 2.922}, {'end': 1399.914, 'text': 'So here we have the log scale and we have the moving average and then we have just printed the head of it.', 'start': 1394.951, 'duration': 4.963}], 'summary': 'Making time series stationary involves various transformations like taking log, square, or cube roots depending on the data, as demonstrated by taking the log scale and moving average in this case.', 'duration': 28.866, 'max_score': 1371.048, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1371048.jpg'}, {'end': 1501.609, 'src': 'embed', 'start': 1470.255, 'weight': 3, 'content': [{'end': 1475.538, 'text': 'So here we have rolling standard deviation and we have rolling mean now, let me see the ADCF results as well.', 'start': 1470.255, 'duration': 5.283}, {'end': 1485.778, 'text': 'So here if you notice your p-value is relatively less In early cases, we used to have 0.9 something and over here you have P value at 0.02.', 'start': 1475.778, 'duration': 10}, {'end': 1490.321, 'text': 'Now, if you notice your critical value and your test statistics value is almost equal,', 'start': 1485.778, 'duration': 4.543}, {'end': 1493.583, 'text': 'which basically helps you to determine whether your data is stationary or not.', 'start': 1490.321, 'duration': 3.262}, {'end': 1501.609, 'text': 'So I hope by now you got the idea between the Dickey-Fuller test and the rolling statistics test as to how you can determine whether the data is stationary or not.', 'start': 1493.963, 'duration': 7.646}], 'summary': 'Using rolling standard deviation and mean, adcf shows p-value at 0.02, indicating data stationarity.', 'duration': 31.354, 'max_score': 1470.255, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1470255.jpg'}, {'end': 1527.146, 'src': 'embed', 'start': 1502.87, 'weight': 5, 'content': [{'end': 1509.934, 'text': "I've calculated the weighted average of time series now why I have done this because we need to see the trend that is present inside a time series.", 'start': 1502.87, 'duration': 7.064}, {'end': 1513.136, 'text': 'So that is why we have calculated the weighted average of time series.', 'start': 1510.355, 'duration': 2.781}, {'end': 1516.459, 'text': "So now let me just run this and you'll get to know why I'm talking about this.", 'start': 1513.457, 'duration': 3.002}, {'end': 1522.923, 'text': 'So as you can see here as the time series is progressive the average is also progressing towards the higher side.', 'start': 1517.099, 'duration': 5.824}, {'end': 1527.146, 'text': "So here your trend is upward and it's and keeps on increasing with respect to time.", 'start': 1523.443, 'duration': 3.703}], 'summary': 'Weighted average of time series shows upward trend over time.', 'duration': 24.276, 'max_score': 1502.87, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1502870.jpg'}], 'start': 1138.191, 'title': 'Time series stationarity and transformation', 'summary': 'Delves into the visualization of rolling statistics, mean, and standard deviation to identify non-stationarity, conducting the dickey fuller test, log transformations, and moving averages to achieve stationarity. it also covers the adft test, rolling statistics, and weighted average for determining stationarity in time series data, preparing it for forecasting through the arima model.', 'chapters': [{'end': 1411.301, 'start': 1138.191, 'title': 'Rolling statistics and stationarity test', 'summary': 'Discusses the visualization of rolling statistics using mean and standard deviation to conclude the non-stationarity of a dataset, followed by performing the dickey fuller test to confirm the same, and applying log transformations and moving averages to achieve stationarity.', 'duration': 273.11, 'highlights': ['The visualization of rolling statistics using mean and standard deviation to conclude the non-stationarity of the dataset. The blue line represents the original data, the red line represents the mean, and the black line represents the rolling standard deviation, indicating the non-constant nature of the mean and standard deviation.', 'Performing the Dickey Fuller test to confirm non-stationarity, resulting in a high p-value and non-rejection of the null hypothesis. The Dickey Fuller test yielded a high p-value of 0.9, indicating non-stationarity and non-rejection of the null hypothesis.', 'Applying log transformations to the dataset to stabilize the scale and achieve stationarity. Log transformations were applied to the dataset, resulting in a change in the scale of the y-axis while retaining the trend.', 'Calculating moving averages with the log time series to observe the non-stationarity of the mean. The calculation of moving averages with the log time series indicated that the mean remained non-stationary, albeit showing improvement compared to the previous method.', 'Removing non-stationarity by taking the difference between the moving average and the actual time series. The difference between the moving average and the actual time series was calculated as a method to achieve stationarity in the time series data.']}, {'end': 1641.267, 'start': 1411.682, 'title': 'Time series analysis and data transformation', 'summary': 'Covers the application of the adft test, rolling statistics, and weighted average for determining stationarity in time series data, with a focus on using these transformations to make the data stationary and preparing it for forecasting through the arima model.', 'duration': 229.585, 'highlights': ['The ADCF test is employed to determine the stationarity of the time series data, with a significant reduction in p-value from 0.9 to 0.02, and the comparison of critical value and test statistics aiding in the determination of data stationarity.', 'The utilization of weighted average for observing the trend within the time series data, with a clear depiction of the progressive trend through visualization.', 'The application of log scale and subtraction of the weighted average to test stationarity, resulting in a stationary time series with a P value of 0.005, indicating the success of the transformation in achieving stationarity.', 'The shifting of values in the time series data and the preparation for forecasting using the ARIMA model, with a demonstration of the lagged values and the concept of differentiation in the ARIMA model.']}], 'duration': 503.076, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1138191.jpg', 'highlights': ['Utilizing Dickey Fuller test with a high p-value of 0.9 to confirm non-stationarity.', 'Visualizing rolling statistics to identify non-stationarity using mean and standard deviation.', 'Applying log transformations to stabilize the scale and achieve stationarity.', 'Employing ADCF test to determine stationarity with a significant reduction in p-value.', 'Calculating moving averages with the log time series to observe non-stationarity of the mean.', 'Utilizing weighted average for observing the trend within the time series data.']}, {'end': 2298.782, 'segs': [{'end': 1682.181, 'src': 'embed', 'start': 1641.767, 'weight': 0, 'content': [{'end': 1647.89, 'text': 'So here your null hypothesis, or the augmented Dickey fuller test, wherein will take the null hypothesis, is rejected,', 'start': 1641.767, 'duration': 6.123}, {'end': 1650.651, 'text': 'and hence we can say that your time series is stationary now.', 'start': 1647.89, 'duration': 2.761}, {'end': 1658.634, 'text': 'So here you can say that you again have blue as the original data you have red as your rolling mean and you have black as your standard deviation.', 'start': 1651.271, 'duration': 7.363}, {'end': 1663.154, 'text': "So visually also we see that there is no trend present and it's quite flat.", 'start': 1659.272, 'duration': 3.882}, {'end': 1665.935, 'text': 'So here we can say that your time series is stationary.', 'start': 1663.274, 'duration': 2.661}, {'end': 1668.636, 'text': 'Now, let us see the components of time series.', 'start': 1666.695, 'duration': 1.941}, {'end': 1674.718, 'text': 'So here you first need to import from stats model to TSA dot seasonal input seasonal decompose.', 'start': 1669.436, 'duration': 5.282}, {'end': 1680.88, 'text': 'So your seasonal decompose segregates three components that is trend seasonal and residual.', 'start': 1675.438, 'duration': 5.442}, {'end': 1682.181, 'text': 'So here what we have done.', 'start': 1681.261, 'duration': 0.92}], 'summary': 'Augmented dickey fuller test rejects null hypothesis, indicating stationary time series. components of time series segregated using seasonal decompose.', 'duration': 40.414, 'max_score': 1641.767, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1641767.jpg'}, {'end': 1734.653, 'src': 'embed', 'start': 1703.369, 'weight': 2, 'content': [{'end': 1707.753, 'text': 'So we have a seasonality graph over here and then we have the residuals as well.', 'start': 1703.369, 'duration': 4.384}, {'end': 1711.716, 'text': 'So residuals are nothing guys irregularities that is present in your data.', 'start': 1708.394, 'duration': 3.322}, {'end': 1716.88, 'text': 'So they do not have any shape any size and you cannot find out what is going to happen next.', 'start': 1712.137, 'duration': 4.743}, {'end': 1718.702, 'text': "So it's quite irregular in nature.", 'start': 1717.201, 'duration': 1.501}, {'end': 1722.87, 'text': "Now what we're going to do we'll check the noise if it's stationary or not.", 'start': 1719.409, 'duration': 3.461}, {'end': 1728.031, 'text': "So over here we take the residual and we'll save it in a variable that is decomposed log data,", 'start': 1723.35, 'duration': 4.681}, {'end': 1734.653, 'text': "and again I'll just pass it to the same function that we have just created above, which is test stationary and inside this test stationary function.", 'start': 1728.031, 'duration': 6.622}], 'summary': 'Analyzing seasonal data irregularities and checking for stationary noise.', 'duration': 31.284, 'max_score': 1703.369, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1703369.jpg'}, {'end': 1828.644, 'src': 'embed', 'start': 1802.268, 'weight': 3, 'content': [{'end': 1806.029, 'text': 'We have simply plot ACF graph and we have plotted the PCF graph.', 'start': 1802.268, 'duration': 3.761}, {'end': 1811.291, 'text': "So now let me just run this and let's determine how you can calculate P value and Q value.", 'start': 1806.469, 'duration': 4.822}, {'end': 1815.972, 'text': 'So guys, this is my autocorrelation graph and this is my partial autocorrelation graph.', 'start': 1811.911, 'duration': 4.061}, {'end': 1818.956, 'text': 'Now, in order to calculate the P and Q values,', 'start': 1816.494, 'duration': 2.462}, {'end': 1824.401, 'text': 'you need to check that what is the value where the graph cuts off or you can say drops to 0 for the first time.', 'start': 1818.956, 'duration': 5.445}, {'end': 1828.644, 'text': 'So if you look closely you have it touches the confidence level over here.', 'start': 1825.001, 'duration': 3.643}], 'summary': 'Plotted acf and pcf graphs to calculate p and q values for autocorrelation and partial autocorrelation.', 'duration': 26.376, 'max_score': 1802.268, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1802268.jpg'}, {'end': 2012.483, 'src': 'embed', 'start': 1981.349, 'weight': 4, 'content': [{'end': 1987.933, 'text': 'So here when I substitute the values as 2 1 2 that is P and Q value is equals to 2 and D we have taken as one.', 'start': 1981.349, 'duration': 6.584}, {'end': 1993.897, 'text': "So here your Arima model gives you RSS of 1.02, which is quite good next what we'll do.", 'start': 1988.514, 'duration': 5.383}, {'end': 1996.359, 'text': "Let's fit them in a combined model that is Arima.", 'start': 1994.017, 'duration': 2.342}, {'end': 2002.804, 'text': 'So here we have seen that with respect to air we have RSS is 1.5 with respect to ma that is moving average.', 'start': 1996.917, 'duration': 5.887}, {'end': 2012.483, 'text': 'We have RSS as 1.4 and when we apply the combined model that is Arima the RSS or you can say the residual sum of Square is dropped to 1.02.', 'start': 2002.844, 'duration': 9.639}], 'summary': 'Arima model with p=2, q=2, and d=1 gives rss of 1.02. combining ar and ma models drops rss to 1.02.', 'duration': 31.134, 'max_score': 1981.349, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1981349.jpg'}, {'end': 2183.653, 'src': 'embed', 'start': 2158.266, 'weight': 5, 'content': [{'end': 2164.292, 'text': 'So over here if you can see the blue is the forecasted value and this gray part is your confidence level.', 'start': 2158.266, 'duration': 6.026}, {'end': 2170.219, 'text': 'So now whatever happens or however, you do the forecasting this value will not exceed the confidence level.', 'start': 2164.673, 'duration': 5.546}, {'end': 2175.184, 'text': 'So this is how you can see that for the next 10 years you have the prediction somewhat like this.', 'start': 2170.539, 'duration': 4.645}, {'end': 2181.051, 'text': "So this is how you can do prediction and if you don't want to see the graph you can actually write in the data point.", 'start': 2176.226, 'duration': 4.825}, {'end': 2183.653, 'text': 'So here I want the prediction for 10 years.', 'start': 2181.451, 'duration': 2.202}], 'summary': 'Forecasted value will not exceed confidence level for next 10 years.', 'duration': 25.387, 'max_score': 2158.266, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q2158266.jpg'}, {'end': 2260.379, 'src': 'heatmap', 'start': 2226.83, 'weight': 1, 'content': [{'end': 2231.554, 'text': 'Then we have understood what is stationarity and what are the different tests to check the stationarity of the data.', 'start': 2226.83, 'duration': 4.724}, {'end': 2235.558, 'text': 'Then we discussed one of the best models which is used in the time series analysis.', 'start': 2231.875, 'duration': 3.683}, {'end': 2236.699, 'text': 'That is the Arima model.', 'start': 2235.598, 'duration': 1.101}, {'end': 2240.562, 'text': 'So here we have understood that Arima model is a combination of three models.', 'start': 2237.159, 'duration': 3.403}, {'end': 2243.164, 'text': 'That is the AR model which stands for Auto regression.', 'start': 2240.582, 'duration': 2.582}, {'end': 2246.948, 'text': 'We have MA for moving average and eyes for the integration part,', 'start': 2243.205, 'duration': 3.743}, {'end': 2251.332, 'text': 'and then we have implemented all these things and we have forecasted the data for the next 10 years.', 'start': 2246.948, 'duration': 4.384}, {'end': 2255.455, 'text': "So I hope you guys are clear with whatever concept that I've taught in this session.", 'start': 2251.952, 'duration': 3.503}, {'end': 2260.379, 'text': 'So, do you guys have any questions or any doubts with respect to any other topics that I have discussed till now?', 'start': 2255.735, 'duration': 4.644}], 'summary': 'Discussed stationarity tests, arima model, and forecasted data for next 10 years.', 'duration': 33.549, 'max_score': 2226.83, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q2226830.jpg'}], 'start': 1641.767, 'title': 'Time series analysis', 'summary': 'Covers stationarity testing, time series components, and arima model analysis. it includes augmented dickey fuller test, seasonal decomposition, acf and pacf plots, model fitting, rss evaluation, predictions, and 10-year demand forecast.', 'chapters': [{'end': 1761.459, 'start': 1641.767, 'title': 'Stationarity testing and time series components', 'summary': 'Discusses the rejection of the null hypothesis using the augmented dickey fuller test, indicating stationary time series, and demonstrates the components of time series through seasonal decomposition, with visual representations and explanations for trend, seasonality, residuals, and testing for stationarity.', 'duration': 119.692, 'highlights': ['The augmented Dickey Fuller test rejects the null hypothesis, indicating that the time series is stationary. The augmented Dickey Fuller test results in the rejection of the null hypothesis, confirming the stationarity of the time series.', 'The components of time series are demonstrated through seasonal decomposition, showcasing trend, seasonality, and residuals. The seasonal decomposition segregates the time series into trend, seasonal, and residual components, visually represented and explained through plotted graphs.', 'The residual component represents irregularities in the data, without any discernible pattern. Residuals in the data are described as irregularities with no specific shape or size, indicating unpredictability.', 'The process includes testing the stationarity of the residuals using rolling statistics and ADCF test. The stationarity of residuals is tested using rolling statistics and the ADF test, with a visual representation indicating non-stationarity.']}, {'end': 2298.782, 'start': 1762.239, 'title': 'Time series analysis with arima model', 'summary': 'Covers the process of time series analysis using the arima model, including plotting acf and pacf graphs, calculating p and q values, fitting the arima model, evaluating rss, performing predictions, and forecasting demand for the next 10 years.', 'duration': 536.543, 'highlights': ['The process involves plotting ACF and PACF graphs to calculate the values of P and Q, which are found to be around 2 in the given example. Plotting ACF and PACF graphs, calculating P and Q values, P value around 2, Q value around 2', 'Fitting the Arima model with P=2, D=1, Q=2 and evaluating the RSS, which is found to be 1.02, indicating a good fit. Fitting Arima model with P=2, D=1, Q=2, RSS value of 1.02', 'Performing predictions for future demand using the Arima model, with a forecast for the next 10 years and a visualization of the forecasted values with confidence intervals. Performing predictions for future demand, forecasting for the next 10 years, visualization of forecasted values with confidence intervals']}], 'duration': 657.015, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/e8Yw4alG16Q/pics/e8Yw4alG16Q1641767.jpg', 'highlights': ['The augmented Dickey Fuller test confirms stationarity of the time series.', 'Seasonal decomposition showcases trend, seasonality, and residuals.', 'Residuals in the data are described as irregularities with no specific shape or size.', 'Plotting ACF and PACF graphs, calculating P and Q values, P value around 2, Q value around 2', 'Fitting Arima model with P=2, D=1, Q=2, RSS value of 1.02', 'Performing predictions for future demand, forecasting for the next 10 years, visualization of forecasted values with confidence intervals']}], 'highlights': ['The Arima model is one of the best models used in time series, and the session includes a discussion on it, followed by a demo.', 'The session covers the importance of time series analysis, its components, and when not to use it, providing a comprehensive understanding of its applications and limitations.', 'The discussion includes understanding stationarity and the tests used to check it, offering practical insights into ensuring the reliability of time series data for analysis.', 'The importance of stationarity is emphasized as most models work on the assumption that time series is stationary, and the criteria for stationarity includes constant mean, constant variance, and auto covariance not dependent on time.', "Explanation of ARIMA model as a combination of autoregressive (AR) and moving average (MA) models, with the integration part indicated by 'I', and the parameters P, Q, and D representing autoregressive lags, moving average, and order of differentiation respectively.", 'The concept of sales trend and seasonality is explained, emphasizing the difference between them and providing examples to illustrate the concepts.', 'Demo on forecasting future passenger numbers for an airline over a specified time period, using the concepts and techniques discussed in the chapter.', 'Import air passengers data using pandas and set data month-wise.', 'Print top and bottom values of the dataset.', 'Plot a graph to visualize data between 1949 to 1960.', 'Data shows upward trend indicating non-stationarity with increasing mean of air passengers over the years.', 'Introduce rolling statistics and ADFC test to assess stationarity.', 'Utilizing Dickey Fuller test with a high p-value of 0.9 to confirm non-stationarity.', 'Visualizing rolling statistics to identify non-stationarity using mean and standard deviation.', 'Applying log transformations to stabilize the scale and achieve stationarity.', 'The augmented Dickey Fuller test confirms stationarity of the time series.', 'Seasonal decomposition showcases trend, seasonality, and residuals.', 'Residuals in the data are described as irregularities with no specific shape or size.', 'Plotting ACF and PACF graphs, calculating P and Q values, P value around 2, Q value around 2', 'Fitting Arima model with P=2, D=1, Q=2, RSS value of 1.02', 'Performing predictions for future demand, forecasting for the next 10 years, visualization of forecasted values with confidence intervals']}