title

Time Series In R | Time Series Forecasting | Time Series Analysis | Data Science Training | Edureka

description

( Data Science Training - https://www.edureka.co/data-science-r-programming-certification-course )
In this Edureka YouTube live session, we will show you how to use the Time Series Analysis in R to predict the future!
Below are the topics we will cover in this live session:
1. Why Time Series Analysis?
2. What is Time Series Analysis?
3. When Not to use Time Series Analysis?
4. Components of Time Series Algorithm
5. Demo on Time Series
For more information, Please write back to us at sales@edureka.co 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 In R | Time Series Forecasting | Time Series Analysis | Data Science Training | Edureka', 'heatmap': [{'end': 431.25, 'start': 403.919, 'weight': 0.816}, {'end': 514.097, 'start': 447.783, 'weight': 0.86}, {'end': 923.128, 'start': 874.435, 'weight': 0.783}, {'end': 1491.103, 'start': 1386.083, 'weight': 0.793}, {'end': 1593.158, 'start': 1508.459, 'weight': 0.728}], 'summary': 'Covers the significance of time series analysis in data science, math concepts, time series analysis fundamentals, making time series data stationary, and predicting future values, providing comprehensive insights and practical applications in data science training.', 'chapters': [{'end': 46.766, 'segs': [{'end': 49.748, 'src': 'embed', 'start': 24.468, 'weight': 0, 'content': [{'end': 29.472, 'text': "So we'll start off our session by first discussing why do we need time series analysis.", 'start': 24.468, 'duration': 5.004}, {'end': 34.356, 'text': "And then we're going to move on to what is time series analysis exactly.", 'start': 29.832, 'duration': 4.524}, {'end': 37.999, 'text': "And then we're going to see when not to use time series.", 'start': 35.277, 'duration': 2.722}, {'end': 41.842, 'text': 'What are the cases in which you should not use time series analysis.', 'start': 38.139, 'duration': 3.703}, {'end': 46.766, 'text': 'After that, we are going to discuss a few of the components that time series algorithm has.', 'start': 42.762, 'duration': 4.004}, {'end': 49.748, 'text': "And towards the end, we'll be doing a demo.", 'start': 47.266, 'duration': 2.482}], 'summary': 'Introduction to time series analysis, components, and demo.', 'duration': 25.28, 'max_score': 24.468, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU24468.jpg'}], 'start': 3.186, 'title': 'Time series algorithm', 'summary': 'Covers the significance of time series analysis in data science, introduces the concept, and addresses scenarios where time series analysis should not be used, followed by a discussion on the components of the time series algorithm.', 'chapters': [{'end': 46.766, 'start': 3.186, 'title': 'Predicting future with time series algorithm', 'summary': 'Covers the significance of time series analysis in data science, introduces the concept, and addresses scenarios where time series analysis should not be used, followed by a discussion on the components of the time series algorithm.', 'duration': 43.58, 'highlights': ['The session covers the significance of time series analysis in data science. It explains the importance of time series analysis in data science.', 'Introduction to time series analysis and its relevance in predicting the future. It introduces the concept of time series analysis and its application in predicting the future.', 'Addressing scenarios where time series analysis should not be used. It discusses the cases in which time series analysis should not be applied.', 'Discussion on the components of the time series algorithm. It covers the various components of the time series algorithm.']}], 'duration': 43.58, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU3186.jpg', 'highlights': ['Introduction to time series analysis and its relevance in predicting the future. It introduces the concept of time series analysis and its application in predicting the future.', 'The session covers the significance of time series analysis in data science. It explains the importance of time series analysis in data science.', 'Discussion on the components of the time series algorithm. It covers the various components of the time series algorithm.', 'Addressing scenarios where time series analysis should not be used. It discusses the cases in which time series analysis should not be applied.']}, {'end': 325.15, 'segs': [{'end': 111.63, 'src': 'embed', 'start': 77.148, 'weight': 0, 'content': [{'end': 86.593, 'text': 'So, I repeat, are you guys familiar with a few of the concepts of math, such as what is mean, what is variance, what is covariance, right?', 'start': 77.148, 'duration': 9.445}, {'end': 89.475, 'text': 'And how many of you are familiar with the data science background?', 'start': 86.753, 'duration': 2.722}, {'end': 101.955, 'text': "Alright, so I can see that Avinash is saying he's clear.", 'start': 99.07, 'duration': 2.885}, {'end': 105.66, 'text': 'So is Ajay, Manish, Avinash.', 'start': 102.515, 'duration': 3.145}, {'end': 109.567, 'text': 'Alright, so Avinash says absolutely, I like your confidence Avinash.', 'start': 105.68, 'duration': 3.887}, {'end': 111.63, 'text': 'all right.', 'start': 111.149, 'duration': 0.481}], 'summary': 'Participants familiar with math concepts and data science background, including avinash, ajay, and manish.', 'duration': 34.482, 'max_score': 77.148, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU77148.jpg'}, {'end': 238.087, 'src': 'embed', 'start': 210.636, 'weight': 3, 'content': [{'end': 214.759, 'text': 'The only thing that is, there is time, right? So I have to predict for the next month.', 'start': 210.636, 'duration': 4.123}, {'end': 216.24, 'text': 'So, same as the scene here,', 'start': 215.239, 'duration': 1.001}, {'end': 225.565, 'text': 'you use time series analysis when you have only one variable and you have the time as a second variable that you will be predicting the value from.', 'start': 216.24, 'duration': 9.325}, {'end': 229.507, 'text': 'Alright, now this is why you use time series analysis.', 'start': 226.366, 'duration': 3.141}, {'end': 232.169, 'text': "Let's now understand what is time series analysis exactly.", 'start': 229.587, 'duration': 2.582}, {'end': 238.087, 'text': 'Alright, so time series is a series of data points indexed in a time order.', 'start': 233.203, 'duration': 4.884}], 'summary': 'Time series analysis predicts values using one variable over time.', 'duration': 27.451, 'max_score': 210.636, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU210636.jpg'}, {'end': 306.3, 'src': 'embed', 'start': 261.406, 'weight': 4, 'content': [{'end': 263.748, 'text': 'So this is what time series analysis is all about.', 'start': 261.406, 'duration': 2.342}, {'end': 268.553, 'text': 'You create a model, you give it the inputs of the past, and you predict the future values.', 'start': 263.788, 'duration': 4.765}, {'end': 273.878, 'text': 'Alright, moving ahead guys, now this is where you use time series analysis.', 'start': 268.993, 'duration': 4.885}, {'end': 278.002, 'text': 'So I told you whenever there is a time component, you use the time series analysis.', 'start': 273.898, 'duration': 4.104}, {'end': 285.51, 'text': "But when do we not use time series analysis? So we don't use time series analysis whenever the values are constant.", 'start': 278.422, 'duration': 7.088}, {'end': 296.214, 'text': 'So, for example, I say that my company sold 23 cars in the past month, 23 cars in this month.', 'start': 286.968, 'duration': 9.246}, {'end': 300.237, 'text': 'tell me what is the sales that is going to be in the next month.', 'start': 296.214, 'duration': 4.023}, {'end': 306.3, 'text': 'So in this case, my number of cars is same for the previous month and this month as well.', 'start': 300.677, 'duration': 5.623}], 'summary': 'Time series analysis predicts future values using past inputs. not used when values are constant.', 'duration': 44.894, 'max_score': 261.406, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU261406.jpg'}], 'start': 47.266, 'title': 'Maths concepts in data science and understanding time series analysis', 'summary': "Covers math concepts in data science such as mean, variance, and covariance, participants' familiarity with the concepts and data science background; it also discusses the importance of time series analysis in predicting future values and when to use it.", 'chapters': [{'end': 111.63, 'start': 47.266, 'title': 'Maths concepts in data science', 'summary': 'Covers the agenda for a demo on math concepts in data science, including mean, variance, covariance, and audience familiarity with the concepts and data science background, with several participants confirming their understanding.', 'duration': 64.364, 'highlights': ['Several participants confirm their familiarity with math concepts and data science background, including Avinash, Ajay, and Manish.', 'The chapter clarifies the agenda for a demo on math concepts in data science, aiming to gauge audience understanding of mean, variance, and covariance.', 'The presenter seeks confirmation from the audience regarding their familiarity with math concepts and data science background.']}, {'end': 325.15, 'start': 111.63, 'title': 'Understanding time series analysis', 'summary': 'Discusses the importance of time series analysis in predicting future values using only one variable and time as the second variable, and when to use and not use time series analysis.', 'duration': 213.52, 'highlights': ['Time series analysis is used when there is only one variable and time as the second variable for predicting future values. It explains the importance of time series analysis in predicting future values using only one variable and time as the second variable.', 'Time series creates a model using past inputs to predict future values. It elaborates on the process of creating a model using past inputs to predict future values.', 'Time series analysis is not used when the values are constant, as there is no need for analysis in such cases. It explains the scenario when time series analysis is not required, such as when dealing with constant values.']}], 'duration': 277.884, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU47266.jpg', 'highlights': ['Several participants confirm their familiarity with math concepts and data science background, including Avinash, Ajay, and Manish.', 'The chapter clarifies the agenda for a demo on math concepts in data science, aiming to gauge audience understanding of mean, variance, and covariance.', 'The presenter seeks confirmation from the audience regarding their familiarity with math concepts and data science background.', 'Time series analysis is used when there is only one variable and time as the second variable for predicting future values.', 'Time series creates a model using past inputs to predict future values.', 'Time series analysis is not used when the values are constant, as there is no need for analysis in such cases.']}, {'end': 951.01, 'segs': [{'end': 348.862, 'src': 'embed', 'start': 325.19, 'weight': 0, 'content': [{'end': 332.013, 'text': "But all of those parameters, if you cannot include in your analysis, there's no point in putting that analysis right,", 'start': 325.19, 'duration': 6.823}, {'end': 335.594, 'text': 'and specifically time series analysis, because it is all dependent on time.', 'start': 332.013, 'duration': 3.581}, {'end': 341.318, 'text': 'Having said that, so like I said, if values are constant, you cannot use time series analysis.', 'start': 337.076, 'duration': 4.242}, {'end': 348.862, 'text': 'Similarly, you cannot use time series analysis if your value can be represented using a function.', 'start': 341.838, 'duration': 7.024}], 'summary': 'Time series analysis depends on time and variable values.', 'duration': 23.672, 'max_score': 325.19, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU325190.jpg'}, {'end': 514.097, 'src': 'heatmap', 'start': 403.919, 'weight': 1, 'content': [{'end': 410.762, 'text': 'So what is stationary? So for the series to be stationary, there are three conditions.', 'start': 403.919, 'duration': 6.843}, {'end': 416.184, 'text': 'So the mean should be constant according to the time.', 'start': 411.602, 'duration': 4.582}, {'end': 421.546, 'text': 'The variance should be equal at different time intervals from the mean.', 'start': 416.664, 'duration': 4.882}, {'end': 425.568, 'text': 'So mean is basically the average.', 'start': 421.886, 'duration': 3.682}, {'end': 431.25, 'text': "For those of you who don't know what variance is, it is basically the distance from the mean.", 'start': 425.648, 'duration': 5.602}, {'end': 437.393, 'text': "So each point's distance from the mean should be equal at equal intervals of time.", 'start': 431.551, 'duration': 5.842}, {'end': 439.274, 'text': 'And that is what variance is all about.', 'start': 437.473, 'duration': 1.801}, {'end': 443.082, 'text': 'That is how far each number is from the mean.', 'start': 440.461, 'duration': 2.621}, {'end': 445.842, 'text': 'Alright? So this is what variance is all about.', 'start': 443.642, 'duration': 2.2}, {'end': 447.743, 'text': 'Then we have the covariance.', 'start': 446.622, 'duration': 1.121}, {'end': 449.163, 'text': 'So that should be also equal.', 'start': 447.783, 'duration': 1.38}, {'end': 457.325, 'text': 'So if these three conditions are met, then only we can say that my series is stationary and then I can apply the time series analysis.', 'start': 449.463, 'duration': 7.862}, {'end': 459.625, 'text': 'Alright? So let me give you an example.', 'start': 457.985, 'duration': 1.64}, {'end': 465.467, 'text': 'So guys, this is my R console.', 'start': 463.386, 'duration': 2.081}, {'end': 475.309, 'text': 'Now, if I want to find the mean, so let me first show you the data that I have.', 'start': 467.025, 'duration': 8.284}, {'end': 480.211, 'text': 'So this is the graph that my data is representing.', 'start': 475.729, 'duration': 4.482}, {'end': 486.413, 'text': "So basically, I'll be doing my time series analysis on air passengers today.", 'start': 480.271, 'duration': 6.142}, {'end': 489.334, 'text': 'So this is the graph that air passengers data has right now.', 'start': 486.653, 'duration': 2.681}, {'end': 493.616, 'text': 'And if you want to see the dataset, this is how the dataset looks.', 'start': 490.175, 'duration': 3.441}, {'end': 503.694, 'text': 'right. so we have data from 1949 to 1960 for each and every month and we have to predict for the next 10 years what will be the sales of the tickets.', 'start': 494.471, 'duration': 9.223}, {'end': 505.235, 'text': "we'll do that today, so okay.", 'start': 503.694, 'duration': 1.541}, {'end': 507.255, 'text': 'so for now we are concerned with the mean.', 'start': 505.235, 'duration': 2.02}, {'end': 508.536, 'text': 'what is mean?', 'start': 507.255, 'duration': 1.281}, {'end': 514.097, 'text': 'so mean is basically the average of the points.', 'start': 508.536, 'duration': 5.561}], 'summary': 'Stationary series have constant mean, equal variance, and equal covariance, necessary for time series analysis.', 'duration': 45.244, 'max_score': 403.919, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU403919.jpg'}, {'end': 662.102, 'src': 'embed', 'start': 633.188, 'weight': 4, 'content': [{'end': 637.272, 'text': 'So when you talk about the components of time series guys, there are basically three components.', 'start': 633.188, 'duration': 4.084}, {'end': 639.054, 'text': 'You have the general trend.', 'start': 637.713, 'duration': 1.341}, {'end': 642.788, 'text': 'Then there is seasonal and there are irregular fluctuations.', 'start': 639.966, 'duration': 2.822}, {'end': 645.51, 'text': "So let's discuss these three components in detail.", 'start': 643.168, 'duration': 2.342}, {'end': 647.511, 'text': 'So the first thing is the general trend.', 'start': 645.93, 'duration': 1.581}, {'end': 655.197, 'text': 'So a general trend is basically how are your values going? Are they increasing or are they decreasing? All right.', 'start': 647.952, 'duration': 7.245}, {'end': 657.078, 'text': 'So let me give you an example by showing a graph.', 'start': 655.217, 'duration': 1.861}, {'end': 662.102, 'text': 'So let me go back to my ARC console and let me give you a trend.', 'start': 657.879, 'duration': 4.223}], 'summary': 'Time series components: trend, seasonal, and irregular fluctuations are discussed in detail.', 'duration': 28.914, 'max_score': 633.188, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU633188.jpg'}, {'end': 861.084, 'src': 'embed', 'start': 831.475, 'weight': 3, 'content': [{'end': 833.216, 'text': 'So here it is guys.', 'start': 831.475, 'duration': 1.741}, {'end': 837.697, 'text': 'So first of all, you will be importing your data set, right? So this command does that.', 'start': 833.516, 'duration': 4.181}, {'end': 840.158, 'text': "So you'll be passing data and then air passengers.", 'start': 837.777, 'duration': 2.381}, {'end': 842.693, 'text': "So we've imported the data set now.", 'start': 841.212, 'duration': 1.481}, {'end': 849.557, 'text': 'Now, if you want to know what class our data set belongs to, for example, our data set belongs to the time series class.', 'start': 843.333, 'duration': 6.224}, {'end': 852.238, 'text': 'So we can check that using this particular command.', 'start': 850.057, 'duration': 2.181}, {'end': 856.441, 'text': 'And you can see that it shows TS, which basically means time series.', 'start': 853.099, 'duration': 3.342}, {'end': 861.084, 'text': 'And then what is the start of the time series? It can be checked from here.', 'start': 857.542, 'duration': 3.542}], 'summary': 'Imported air passengers data set, identified as time series class, with start of series checked.', 'duration': 29.609, 'max_score': 831.475, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU831475.jpg'}, {'end': 923.128, 'src': 'heatmap', 'start': 874.435, 'weight': 0.783, 'content': [{'end': 877.555, 'text': 'so there are 12 months and hence you have 12 intervals.', 'start': 874.435, 'duration': 3.12}, {'end': 878.775, 'text': 'Summary of air passengers.', 'start': 877.555, 'duration': 1.22}, {'end': 886.917, 'text': 'that basically gives you all that Regular thing, that is, the minimum cost, the maximum Value, the median value and everything.', 'start': 878.775, 'duration': 8.142}, {'end': 895.758, 'text': 'All right, and like I said, so this this particular command will give you the Mean Right.', 'start': 887.237, 'duration': 8.521}, {'end': 899.139, 'text': 'It gives you a mean of your time series analysis.', 'start': 896.198, 'duration': 2.941}, {'end': 901.612, 'text': 'so that is it, guys.', 'start': 899.139, 'duration': 2.473}, {'end': 905.116, 'text': "now let's go on and understand this particular part.", 'start': 901.612, 'duration': 3.504}, {'end': 907.138, 'text': 'this is the most important part, guys.', 'start': 905.116, 'duration': 2.022}, {'end': 908.68, 'text': 'so it gives you a box plot.', 'start': 907.138, 'duration': 1.542}, {'end': 910.882, 'text': 'alright, let me zoom it out for you.', 'start': 908.68, 'duration': 2.202}, {'end': 917.65, 'text': 'so, guys, this is the box plot, and in this you can analyze in which particular month I was experiencing,', 'start': 910.882, 'duration': 6.768}, {'end': 923.128, 'text': 'the maximum traffic or the maximum passengers were traveling.', 'start': 917.65, 'duration': 5.478}], 'summary': 'Analyzing air passenger data using 12-month intervals, including mean, median, and box plot for traffic analysis.', 'duration': 48.693, 'max_score': 874.435, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU874435.jpg'}], 'start': 325.19, 'title': 'Time series analysis fundamentals', 'summary': 'Covers the limitations of time series analysis when data is constant, can be represented by a function, or is non-stationary, and provides a comprehensive overview of time series basics, including conditions for stationarity, mean and variance analysis, components of time series, and practical application for air passengers analysis.', 'chapters': [{'end': 449.163, 'start': 325.19, 'title': 'Limitations of time series analysis', 'summary': 'Discusses the limitations of time series analysis, highlighting that it should not be used when data is constant, can be represented by a function, or is non-stationary, defined by three conditions: constant mean, equal variance, and equal covariance.', 'duration': 123.973, 'highlights': ['Time series analysis should not be used when data is constant or can be represented using a function, as it does not provide meaningful insights. Inapplicability of time series analysis to constant or function-representable data.', 'Non-stationary data, characterized by varying mean, unequal variance, and unequal covariance, renders time series analysis inapplicable. Definition and conditions of non-stationary data.', 'The conditions for stationary data include a constant mean, equal variance at different time intervals from the mean, and equal covariance. Definition and conditions of stationary data.']}, {'end': 951.01, 'start': 449.463, 'title': 'Time series analysis basics', 'summary': 'Discusses the conditions for a series to be stationary, demonstrates mean and variance analysis, explains the components of time series (general trend, seasonal, and irregular fluctuations), and provides a practical example of importing and summarizing a time series dataset for air passengers analysis.', 'duration': 501.547, 'highlights': ['The chapter discusses the conditions for a series to be stationary. It explains that for a series to be stationary, the mean, variance, and covariance should be constant, demonstrating the prerequisites for applying time series analysis.', 'Provides a practical example of importing and summarizing a time series dataset for air passengers analysis. Demonstrates the process of importing the air passengers dataset, checking its class (time series), determining the start and end of the time series, frequency, and summarizing key statistics such as mean and box plot analysis.', 'Explains the components of time series (general trend, seasonal, and irregular fluctuations). Details the components of time series, such as the general trend (increasing or decreasing values), seasonal patterns (peaks during festivals), and irregular fluctuations (uncontrolled circumstances affecting passenger numbers).', 'Demonstrates mean and variance analysis. Explains the concept of mean as the average of points and variance as the distance of each point from the mean, emphasizing the importance of transforming data to make variance equal for a stationary series.']}], 'duration': 625.82, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU325190.jpg', 'highlights': ['Inapplicability of time series analysis to constant or function-representable data.', 'Definition and conditions of non-stationary data.', 'Definition and conditions of stationary data.', 'Demonstrates the process of importing the air passengers dataset, checking its class (time series), determining the start and end of the time series, frequency, and summarizing key statistics such as mean and box plot analysis.', 'Details the components of time series, such as the general trend (increasing or decreasing values), seasonal patterns (peaks during festivals), and irregular fluctuations (uncontrolled circumstances affecting passenger numbers).', 'Explains the concept of mean as the average of points and variance as the distance of each point from the mean, emphasizing the importance of transforming data to make variance equal for a stationary series.', 'It explains that for a series to be stationary, the mean, variance, and covariance should be constant, demonstrating the prerequisites for applying time series analysis.']}, {'end': 1525.75, 'segs': [{'end': 1024.967, 'src': 'embed', 'start': 999.465, 'weight': 0, 'content': [{'end': 1004.89, 'text': 'Right? The mean is also increasing, the variance is also not equal like I showed you.', 'start': 999.465, 'duration': 5.425}, {'end': 1008.373, 'text': "Right? So moving ahead guys, now let's make it stationary.", 'start': 1005.39, 'duration': 2.983}, {'end': 1013.377, 'text': "So for dealing with the variance part, first we'll be applying the log function.", 'start': 1008.953, 'duration': 4.424}, {'end': 1024.106, 'text': "So if we apply the log function, what basically it does is, it'll make the variance equal.", 'start': 1014.238, 'duration': 9.868}, {'end': 1024.967, 'text': 'Let me show you how.', 'start': 1024.326, 'duration': 0.641}], 'summary': 'Increasing mean and unequal variance will be addressed by making the data stationary using the log function.', 'duration': 25.502, 'max_score': 999.465, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU999465.jpg'}, {'end': 1108.623, 'src': 'embed', 'start': 1082.321, 'weight': 4, 'content': [{'end': 1088.626, 'text': 'So as you can see, the graph is now, the mean is now constant according to time.', 'start': 1082.321, 'duration': 6.305}, {'end': 1099.095, 'text': 'So if I plot the mean line from here, it is not going to change with time as the same time my variance is also going to be the same.', 'start': 1089.087, 'duration': 10.008}, {'end': 1101.177, 'text': 'Alright, and this is what I wanted.', 'start': 1099.115, 'duration': 2.062}, {'end': 1108.623, 'text': 'So my series is now stationary and I can now apply the model on it, the time series analysis model on it.', 'start': 1101.257, 'duration': 7.366}], 'summary': 'The mean and variance are now constant over time, indicating a stationary series for time series analysis.', 'duration': 26.302, 'max_score': 1082.321, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU1082321.jpg'}, {'end': 1246.727, 'src': 'embed', 'start': 1212.258, 'weight': 1, 'content': [{'end': 1214.039, 'text': 'alright?. We have some values associated.', 'start': 1212.258, 'duration': 1.781}, {'end': 1222.586, 'text': 'So with AR, I have the value called P, with I, I have the value called D, and with MA, I have the value called Q.', 'start': 1214.4, 'duration': 8.186}, {'end': 1229.715, 'text': "So whenever I'm applying the Arima model, I have to go ahead and include these three values as well.", 'start': 1222.586, 'duration': 7.129}, {'end': 1236.46, 'text': "And these values I have to get from the graph that I'm going to show right now.", 'start': 1230.196, 'duration': 6.264}, {'end': 1239.002, 'text': 'It is called the autocorrelation function graph.', 'start': 1236.86, 'duration': 2.142}, {'end': 1246.727, 'text': 'Using that graph, we will determine what is the value of p, what is the value of q, and what is the value of d.', 'start': 1239.783, 'duration': 6.944}], 'summary': 'Values p, d, and q are determined from autocorrelation function graph for arima model.', 'duration': 34.469, 'max_score': 1212.258, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU1212258.jpg'}, {'end': 1498.169, 'src': 'heatmap', 'start': 1379.561, 'weight': 2, 'content': [{'end': 1385.563, 'text': "Now, let's check out the same method will be applied in the partial autocorrelation function graph as well.", 'start': 1379.561, 'duration': 6.002}, {'end': 1388.364, 'text': 'And from that graph, I will get the p-value.', 'start': 1386.083, 'duration': 2.281}, {'end': 1392.245, 'text': 'Alright, now as you can see, this is my 0th line.', 'start': 1389.324, 'duration': 2.921}, {'end': 1398.347, 'text': 'Alright, and immediately after my 0th line, my first line is becoming inverted.', 'start': 1392.265, 'duration': 6.082}, {'end': 1402.978, 'text': 'So, hence my value of p becomes 1.', 'start': 1399.087, 'duration': 3.891}, {'end': 1408.72, 'text': 'alright. so sorry, the value of p becomes 0, because this is the 0th line, right.', 'start': 1402.978, 'duration': 5.742}, {'end': 1415.903, 'text': 'so my value of p is 0, my value of q is 1 and my value of d.', 'start': 1408.72, 'duration': 7.183}, {'end': 1420.985, 'text': 'so d is basically the differentiation that you do in your function.', 'start': 1415.903, 'duration': 5.082}, {'end': 1429.073, 'text': 'so, for example, my time series algorithm, I did differentiation and hence I got the mean to be equal to,', 'start': 1420.985, 'duration': 8.088}, {'end': 1433.402, 'text': 'or the mean not changing mean constant to my timeline, right?', 'start': 1429.073, 'duration': 4.329}, {'end': 1435.98, 'text': 'So the value.', 'start': 1434.679, 'duration': 1.301}, {'end': 1438.902, 'text': 'now you can do differentiation multiple number of times.', 'start': 1435.98, 'duration': 2.922}, {'end': 1443.686, 'text': 'So I have done differentiation only once and hence my value of D will be 1.', 'start': 1439.323, 'duration': 4.363}, {'end': 1447.228, 'text': 'If you do differentiation twice, my value of D will be 2.', 'start': 1443.686, 'duration': 3.542}, {'end': 1450.911, 'text': 'If I do differentiation thrice, my value of D will be 3.', 'start': 1447.228, 'duration': 3.683}, {'end': 1455.695, 'text': 'So you do that until and unless your mean becomes equal or your mean becomes constant.', 'start': 1450.911, 'duration': 4.784}, {'end': 1458.416, 'text': 'Alright? And hence that will be the value of your d.', 'start': 1456.175, 'duration': 2.241}, {'end': 1461.018, 'text': 'So in my case, the value of d becomes 1.', 'start': 1458.416, 'duration': 2.602}, {'end': 1466.662, 'text': 'So my value of p is 0, my value of d is 1, and my value of q is again 1.', 'start': 1461.018, 'duration': 5.644}, {'end': 1469.944, 'text': "So I'll be using that in my Arima model.", 'start': 1466.662, 'duration': 3.282}, {'end': 1472.105, 'text': 'So here comes my model now.', 'start': 1470.684, 'duration': 1.421}, {'end': 1474.307, 'text': "So I'll be applying all of that.", 'start': 1472.686, 'duration': 1.621}, {'end': 1478.91, 'text': 'So this is the pdq values that I was talking about.', 'start': 1475.007, 'duration': 3.903}, {'end': 1484.999, 'text': 'So when you pass this particular function, You will be specifying the PDQ values.', 'start': 1479.47, 'duration': 5.529}, {'end': 1488.181, 'text': 'So this is your P value, your D value and your Q value.', 'start': 1485.359, 'duration': 2.822}, {'end': 1491.103, 'text': 'So these parameters change according to your dataset.', 'start': 1488.722, 'duration': 2.381}, {'end': 1498.169, 'text': 'Whatever dataset you are taking, these parameters will change and you have to get these values from the graph and hence put them here.', 'start': 1491.143, 'duration': 7.026}], 'summary': 'Using partial autocorrelation method to determine p-value; p=0, d=1, q=1 for arima model.', 'duration': 118.608, 'max_score': 1379.561, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU1379561.jpg'}], 'start': 951.41, 'title': 'Time series analysis', 'summary': 'Demonstrates making time series data stationary using the log function and differentiation, resulting in a stationary series. it also covers the arima model and how to determine its parameters using autocorrelation and partial autocorrelation functions.', 'chapters': [{'end': 1108.623, 'start': 951.41, 'title': 'Making time series data stationary', 'summary': 'Demonstrates the process of making time series data stationary by using the log function to equalize variance and differentiating to make the mean constant, resulting in a stationary series ready for time series analysis.', 'duration': 157.213, 'highlights': ['Using the log function to equalize variance by making the distance between data points approximately equal.', 'Differentiating the data to make the mean constant over time, resulting in a stationary series ready for time series analysis.', 'Demonstrating the process of making time series data stationary by addressing the increasing mean and unequal variance, and illustrating the impact of using the log function and differentiation.']}, {'end': 1525.75, 'start': 1109.249, 'title': 'Time series analysis with arima model', 'summary': 'Covers the arima model for time series analysis, explaining the concepts of auto regressive, moving average, and integration, and demonstrates how to determine the values of p, d, and q for the arima model using the autocorrelation function and partial autocorrelation function graphs.', 'duration': 416.501, 'highlights': ['The ARIMA model is explained as an acronym for auto regressive (AR), moving average (MA), and integration (I), and the values of p, d, and q are determined from the autocorrelation function and partial autocorrelation function graphs. ', "The process of determining the value of q for the ARIMA model involves identifying the line in the autocorrelation function graph that gets inverted and taking the previous line's value, resulting in a specific q value. ", 'The method for obtaining the value of p for the ARIMA model includes identifying the line in the partial autocorrelation function graph that becomes inverted immediately after the 0th line, resulting in a specific p value. ', 'The differentiation value (d) for the ARIMA model is determined by the number of times differentiation is performed until the mean becomes constant, with the example illustrating the calculation of d as 1 based on the differentiation performed once. ', 'The PDQ values (P value, D value, and Q value) are specified in the ARIMA model, with these parameters changing according to the dataset and the values of p, d, and q obtained from the graphs are put into the model. ']}], 'duration': 574.34, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU951410.jpg', 'highlights': ['Demonstrating the process of making time series data stationary by addressing the increasing mean and unequal variance, and illustrating the impact of using the log function and differentiation.', 'The ARIMA model is explained as an acronym for auto regressive (AR), moving average (MA), and integration (I), and the values of p, d, and q are determined from the autocorrelation function and partial autocorrelation function graphs.', 'The method for obtaining the value of p for the ARIMA model includes identifying the line in the partial autocorrelation function graph that becomes inverted immediately after the 0th line, resulting in a specific p value.', 'Using the log function to equalize variance by making the distance between data points approximately equal.', 'Differentiating the data to make the mean constant over time, resulting in a stationary series ready for time series analysis.']}, {'end': 2031.113, 'segs': [{'end': 1575.562, 'src': 'embed', 'start': 1527.21, 'weight': 0, 'content': [{'end': 1529.472, 'text': 'Alright, so let me pass this line.', 'start': 1527.21, 'duration': 2.262}, {'end': 1531.915, 'text': 'So this creates my model.', 'start': 1530.273, 'duration': 1.642}, {'end': 1536.06, 'text': "And now I'll be predicting values for the next 10 years.", 'start': 1532.736, 'duration': 3.324}, {'end': 1539.163, 'text': "Alright, so you'll be specifying 10 over here.", 'start': 1536.64, 'duration': 2.523}, {'end': 1544.249, 'text': "If I want to predict for the next 15 years, I'll be specifying 15 over here.", 'start': 1539.403, 'duration': 4.846}, {'end': 1548.851, 'text': 'So it will pass it into the predict function.', 'start': 1545.45, 'duration': 3.401}, {'end': 1555.853, 'text': 'This is the model that we have created and this is the time frame that we want our model to predict to.', 'start': 1550.171, 'duration': 5.682}, {'end': 1558.714, 'text': 'So we want it for 10 years and hence I have specified 10 years.', 'start': 1556.433, 'duration': 2.281}, {'end': 1567.436, 'text': 'And then once I have predicted that, now remember guys, this is the most important part, that your values are in logarithmic form.', 'start': 1559.434, 'duration': 8.002}, {'end': 1573.881, 'text': 'right. so to convert them into the decimal form, you have to use the e value.', 'start': 1567.856, 'duration': 6.025}, {'end': 1575.562, 'text': 'so the e value is 2.718.', 'start': 1573.881, 'duration': 1.681}], 'summary': 'Model created for predicting values for 10 years using logarithmic form and e value 2.718.', 'duration': 48.352, 'max_score': 1527.21, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU1527210.jpg'}, {'end': 1631.587, 'src': 'embed', 'start': 1601.761, 'weight': 2, 'content': [{'end': 1611.483, 'text': 'So it says in the year 1970 in September I will have these many passengers who will be traveling by air.', 'start': 1601.761, 'duration': 9.722}, {'end': 1619.145, 'text': 'Similarly in 1961 for the value of January these many customers will be going through air.', 'start': 1612.423, 'duration': 6.722}, {'end': 1623.725, 'text': 'Alright, so this is what my model predicted.', 'start': 1620.384, 'duration': 3.341}, {'end': 1628.186, 'text': 'Now I can also test this model and before that let me plot this as well.', 'start': 1623.925, 'duration': 4.261}, {'end': 1631.587, 'text': 'So let me show you how it looks in the graph.', 'start': 1628.666, 'duration': 2.921}], 'summary': 'Model predicts air travel passengers for 1970 and 1961 based on data.', 'duration': 29.826, 'max_score': 1601.761, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU1601761.jpg'}, {'end': 1888.616, 'src': 'embed', 'start': 1858.732, 'weight': 3, 'content': [{'end': 1862.853, 'text': 'I have to adjust the shift so as to I can match the needs of the customers.', 'start': 1858.732, 'duration': 4.121}, {'end': 1868.155, 'text': 'And I can predict how many customers will be calling me by time series analysis.', 'start': 1864.054, 'duration': 4.101}, {'end': 1872.297, 'text': 'And this is the actual use of time series analysis.', 'start': 1868.295, 'duration': 4.002}, {'end': 1882.255, 'text': 'Alright, so, and this is it, guys, we predicted the value for 1960 and we saw the original values,', 'start': 1873.353, 'duration': 8.902}, {'end': 1888.616, 'text': 'and we came to a conclusion that these values are actually pretty close, and hence our analysis was correct.', 'start': 1882.255, 'duration': 6.361}], 'summary': 'Adjusting shift to meet customer needs, predicting customer calls using time series analysis, accurate analysis confirmed.', 'duration': 29.884, 'max_score': 1858.732, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU1858732.jpg'}, {'end': 1939.61, 'src': 'embed', 'start': 1906.957, 'weight': 4, 'content': [{'end': 1910.101, 'text': 'So guys, we offer data science course as well to people.', 'start': 1906.957, 'duration': 3.144}, {'end': 1913.985, 'text': 'So if you are interested, you can go on to this particular site.', 'start': 1910.621, 'duration': 3.364}, {'end': 1917.55, 'text': 'My team will be commenting it in the comment section.', 'start': 1914.406, 'duration': 3.144}, {'end': 1920.093, 'text': 'That is the CLP URL link.', 'start': 1918.511, 'duration': 1.582}, {'end': 1930.382, 'text': 'So we offer flexible batch timings, that is, we offer timings at night as well and we offer timings in the morning as well, because we understand,', 'start': 1921.895, 'duration': 8.487}, {'end': 1931.523, 'text': 'you are professionals.', 'start': 1930.382, 'duration': 1.141}, {'end': 1932.344, 'text': "you don't have time.", 'start': 1931.523, 'duration': 0.821}, {'end': 1939.61, 'text': "you have to work in office as well and then learning it on your own may become burdened for you, and that's why we have flexible timings.", 'start': 1932.344, 'duration': 7.266}], 'summary': 'Offering data science course with flexible batch timings for professionals.', 'duration': 32.653, 'max_score': 1906.957, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU1906957.jpg'}], 'start': 1527.21, 'title': 'Predicting future values', 'summary': "Delves into predicting values for the next 10 years, emphasizing the need to specify the time frame and to convert predicted values from logarithmic to decimal form using the e value 2.718. it also explains time series analysis and its application in predicting future values, showcasing the model's accuracy by comparing predicted and original values, and concluding its industry relevance with an example of call center shift management.", 'chapters': [{'end': 1575.562, 'start': 1527.21, 'title': 'Predicting values for next 10 years', 'summary': 'Discusses creating a model to predict values for the next 10 years, emphasizing the need to specify the time frame and to convert predicted values from logarithmic to decimal form using the e value 2.718.', 'duration': 48.352, 'highlights': ['The need to specify the time frame for prediction, such as 10 or 15 years, when creating the model.', 'Emphasizing the importance of converting predicted values from logarithmic to decimal form using the e value 2.718.']}, {'end': 2031.113, 'start': 1575.562, 'title': 'Time series analysis', 'summary': "Explains time series analysis and its application in predicting future values, showcasing the model's accuracy by comparing predicted and original values, and concluding its industry relevance with an example of call center shift management, offering flexible data science courses with comprehensive content and learning resources.", 'duration': 455.551, 'highlights': ["The model accurately predicts future values close to the original ones, for example, predicting 419 passengers in January 1960 when the original count was 417, demonstrating the model's precision. The model's accuracy is evident in predicting future values, such as 419 passengers in January 1960 compared to the original count of 417, showcasing the precision of the predictions.", 'The chapter showcases the application of time series analysis in industry, specifically in call center shift management, where predicting customer call traffic aids in adjusting employee shifts to meet customer needs efficiently. An example of call center shift management demonstrates the practical use of time series analysis in predicting customer call traffic to optimize employee shifts and meet customer needs efficiently.', "The session concludes by offering flexible data science courses with comprehensive content, including flexible batch timings, weekend and weekday batches, course details, projects, blogging section, and YouTube tutorials, catering to professionals' learning needs. The session concludes by offering flexible data science courses with comprehensive content, including flexible batch timings, weekend and weekday batches, course details, projects, blogging section, and YouTube tutorials, catering to professionals' learning needs."]}], 'duration': 503.903, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/wNB8AgZPFLU/pics/wNB8AgZPFLU1527210.jpg', 'highlights': ['The need to specify the time frame for prediction, such as 10 or 15 years, when creating the model.', 'Emphasizing the importance of converting predicted values from logarithmic to decimal form using the e value 2.718.', "The model accurately predicts future values close to the original ones, for example, predicting 419 passengers in January 1960 when the original count was 417, demonstrating the model's precision.", 'The chapter showcases the application of time series analysis in industry, specifically in call center shift management, where predicting customer call traffic aids in adjusting employee shifts to meet customer needs efficiently.', "The session concludes by offering flexible data science courses with comprehensive content, including flexible batch timings, weekend and weekday batches, course details, projects, blogging section, and YouTube tutorials, catering to professionals' learning needs."]}], 'highlights': ["The session concludes by offering flexible data science courses with comprehensive content, including flexible batch timings, weekend and weekday batches, course details, projects, blogging section, and YouTube tutorials, catering to professionals' learning needs.", 'The chapter showcases the application of time series analysis in industry, specifically in call center shift management, where predicting customer call traffic aids in adjusting employee shifts to meet customer needs efficiently.', "The model accurately predicts future values close to the original ones, for example, predicting 419 passengers in January 1960 when the original count was 417, demonstrating the model's precision.", 'Emphasizing the importance of converting predicted values from logarithmic to decimal form using the e value 2.718.', 'The need to specify the time frame for prediction, such as 10 or 15 years, when creating the model.', 'Differentiating the data to make the mean constant over time, resulting in a stationary series ready for time series analysis.', 'Using the log function to equalize variance by making the distance between data points approximately equal.', 'The method for obtaining the value of p for the ARIMA model includes identifying the line in the partial autocorrelation function graph that becomes inverted immediately after the 0th line, resulting in a specific p value.', 'The ARIMA model is explained as an acronym for auto regressive (AR), moving average (MA), and integration (I), and the values of p, d, and q are determined from the autocorrelation function and partial autocorrelation function graphs.', 'Demonstrating the process of making time series data stationary by addressing the increasing mean and unequal variance, and illustrating the impact of using the log function and differentiation.', 'Explains the concept of mean as the average of points and variance as the distance of each point from the mean, emphasizing the importance of transforming data to make variance equal for a stationary series.', 'Details the components of time series, such as the general trend (increasing or decreasing values), seasonal patterns (peaks during festivals), and irregular fluctuations (uncontrolled circumstances affecting passenger numbers).', 'Demonstrates the process of importing the air passengers dataset, checking its class (time series), determining the start and end of the time series, frequency, and summarizing key statistics such as mean and box plot analysis.', 'Definition and conditions of stationary data.', 'Definition and conditions of non-stationary data.', 'Inapplicability of time series analysis to constant or function-representable data.', 'Time series analysis is not used when the values are constant, as there is no need for analysis in such cases.', 'Time series creates a model using past inputs to predict future values.', 'Time series analysis is used when there is only one variable and time as the second variable for predicting future values.', 'The presenter seeks confirmation from the audience regarding their familiarity with math concepts and data science background.', 'The chapter clarifies the agenda for a demo on math concepts in data science, aiming to gauge audience understanding of mean, variance, and covariance.', 'Several participants confirm their familiarity with math concepts and data science background, including Avinash, Ajay, and Manish.', 'Addressing scenarios where time series analysis should not be used. It discusses the cases in which time series analysis should not be applied.', 'Discussion on the components of the time series algorithm. It covers the various components of the time series algorithm.', 'The session covers the significance of time series analysis in data science. It explains the importance of time series analysis in data science.', 'Introduction to time series analysis and its relevance in predicting the future. It introduces the concept of time series analysis and its application in predicting the future.']}