title
Linear Regression vs Logistic Regression | Data Science Training | Edureka

description
πŸ”₯ Data Science Certification using R (Use Code "π˜πŽπ”π“π”ππ„πŸπŸŽ"): https://www.edureka.co/data-science-r-programming-certification-course This Edureka video on Linear Regression Vs Logistic Regression covers the basic concepts of linear and logistic models. The following topics are covered in this session: (01:05) Types of Machine Learning (03:09) Regression Vs Classification (05:47) What is Linear Regression? (09:22) What is Logistic Regression? (13:26) Linear Regression Use Case (15:02) Logistic Regression Use Case (16:18) Linear Regression Vs Logistic Regression Blog Series: http://bit.ly/data-science-blogs Data Science Training Playlist: http://bit.ly/data-science-playlist - - - - - - - - - - - - - - - - - Subscribe to our channel to get video updates. Hit the subscribe button above: https://goo.gl/6ohpTV 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 - - - - - - - - - - - - - - - - - #linearregressionvslogisticregression #machinelearningalgorithms #linearregression #logisticregression #linearregressionalgorithm #logisticregressionalgorithm #machinelearning #datascience #datasciencetutorial #datasciencewithr #datasciencecourse #datascienceforbeginners #datasciencetraining #datasciencetutorial - - - - - - - - - - - - - - - - - About the Course Edureka's Data Science course will cover the whole data lifecycle ranging from Data Acquisition and Data Storage using R-Hadoop concepts, Applying modeling through R programming using Machine learning algorithms and illustrate impeccable Data Visualization by leveraging on 'R' capabilities. - - - - - - - - - - - - - - Why Learn Data Science? Data Science training certifies you with β€˜in demand’ Big Data Technologies to help you grab the top paying Data Science job title with Big Data skills and expertise in R programming, Machine Learning and Hadoop framework. After the completion of the Data Science course, you should be able to: 1. Gain insight into the 'Roles' played by a Data Scientist 2. Analyze Big Data using R, Hadoop and Machine Learning 3. Understand the Data Analysis Life Cycle 4. Work with different data formats like XML, CSV and SAS, SPSS, etc. 5. Learn tools and techniques for data transformation 6. Understand Data Mining techniques and their implementation 7. Analyze data using machine learning algorithms in R 8. Work with Hadoop Mappers and Reducers to analyze data 9. Implement various Machine Learning Algorithms in Apache Mahout 10. Gain insight into data visualization and optimization techniques 11. Explore the parallel processing feature in R - - - - - - - - - - - - - - Who should go for this course? The course is designed for all those who want to learn machine learning techniques with implementation in R language, and wish to apply these techniques on Big Data. The following professionals can go for this course: 1. Developers aspiring to be a 'Data Scientist' 2. Analytics Managers who are leading a team of analysts 3. SAS/SPSS Professionals looking to gain understanding in Big Data Analytics 4. Business Analysts who want to understand Machine Learning (ML) Techniques 5. Information Architects who want to gain expertise in Predictive Analytics 6. 'R' professionals who want to captivate and analyze Big Data 7. Hadoop Professionals who want to learn R and ML techniques 8. Analysts wanting to understand Data Science methodologies. For online Data Science training, please write back to us at sales@edureka.co or call us at IND: 9606058406 / US: 18338555775 (toll-free) for more information.

detail
{'title': 'Linear Regression vs Logistic Regression | Data Science Training | Edureka', 'heatmap': [{'end': 370.677, 'start': 353.699, 'weight': 0.767}, {'end': 615.009, 'start': 575.327, 'weight': 1}], 'summary': 'Compares linear and logistic regression, discusses supervised, unsupervised, and reinforcement learning, emphasizes the differences between classification and regression problems, and explains the applications of linear and logistic regression in business for sales forecasting, risk analysis, and student admission prediction.', 'chapters': [{'end': 145.754, 'segs': [{'end': 76.839, 'src': 'embed', 'start': 49.047, 'weight': 0, 'content': [{'end': 52.95, 'text': 'Then we look at a linear regression use case and a logistic regression use case.', 'start': 49.047, 'duration': 3.903}, {'end': 57.733, 'text': "Finally, we'll end the session by comparing linear regression and logistic regression.", 'start': 53.41, 'duration': 4.323}, {'end': 60.155, 'text': "So guys, let's take a look at today's first topic.", 'start': 58.153, 'duration': 2.002}, {'end': 63.236, 'text': 'Now, before I begin with the types of machine learning,', 'start': 60.635, 'duration': 2.601}, {'end': 67.977, 'text': 'if any of you guys are interested in machine learning or want to learn more about machine learning.', 'start': 63.236, 'duration': 4.741}, {'end': 70.058, 'text': "I'm going to leave a link in the description.", 'start': 68.337, 'duration': 1.721}, {'end': 73.779, 'text': 'You all can check out that video and then probably get back to this one.', 'start': 70.458, 'duration': 3.321}, {'end': 74.479, 'text': 'All right.', 'start': 74.239, 'duration': 0.24}, {'end': 76.839, 'text': "So let's begin with the types of machine learning.", 'start': 74.739, 'duration': 2.1}], 'summary': 'Session covers linear and logistic regression, and types of machine learning.', 'duration': 27.792, 'max_score': 49.047, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw49047.jpg'}, {'end': 129.259, 'src': 'embed', 'start': 105.267, 'weight': 1, 'content': [{'end': 111.569, 'text': 'The machine has to figure out the data set given and it must find hidden patterns in order to make predictions about the output.', 'start': 105.267, 'duration': 6.302}, {'end': 115.811, 'text': 'So an example of unsupervised learning is an adult like you and me.', 'start': 112.069, 'duration': 3.742}, {'end': 122.856, 'text': "We don't need a guide to help us with our daily activities, right? We figure things out on our own without any supervision.", 'start': 116.252, 'duration': 6.604}, {'end': 125.617, 'text': 'Now, finally, we have reinforcement learning.', 'start': 123.416, 'duration': 2.201}, {'end': 129.259, 'text': "So let's say that you were dropped off at an isolated island.", 'start': 126.098, 'duration': 3.161}], 'summary': 'Machine must find patterns, unsupervised learning is like adult independence, and reinforcement learning involves isolated island scenario.', 'duration': 23.992, 'max_score': 105.267, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw105267.jpg'}], 'start': 11.007, 'title': 'Comparing linear vs logistic regression', 'summary': 'Compares linear and logistic regression, discusses supervised, unsupervised, and reinforcement learning, and emphasizes the differences between them, highlighting their use cases and concepts.', 'chapters': [{'end': 145.754, 'start': 11.007, 'title': 'Comparison: linear vs logistic regression', 'summary': 'Compares linear and logistic regression, discusses supervised, unsupervised, and reinforcement learning, and emphasizes the differences between them, highlighting their use cases and concepts.', 'duration': 134.747, 'highlights': ['The chapter compares linear and logistic regression The session is dedicated to comparing the two most commonly used machine learning algorithms, linear regression and logistic regression, which are widely used but often confused.', 'Discusses supervised, unsupervised, and reinforcement learning The types of machine learning discussed include supervised learning, where machines learn under guidance with labeled data, unsupervised learning without labeled data, and reinforcement learning, illustrated with an example of adapting to an isolated island.', 'Emphasizes the differences between linear and logistic regression, highlighting their use cases and concepts The session covers the differences between linear regression and logistic regression, explaining their use cases, how they work, and the confusion surrounding them, aiming to clarify their distinctions.']}], 'duration': 134.747, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw11007.jpg', 'highlights': ['The chapter compares linear and logistic regression, commonly used but often confused.', 'Discusses supervised, unsupervised, and reinforcement learning with examples.', 'Emphasizes the differences between linear and logistic regression, clarifying their use cases and concepts.']}, {'end': 268.096, 'segs': [{'end': 186.095, 'src': 'embed', 'start': 145.754, 'weight': 0, 'content': [{'end': 154.835, 'text': "what you're doing is you're following the hit-and-trial concept because you're new to the surrounding and the only way for you to learn is experience and then learn from your experience.", 'start': 145.754, 'duration': 9.081}, {'end': 157.476, 'text': 'So this is what reinforcement learning is about.', 'start': 155.215, 'duration': 2.261}, {'end': 165.877, 'text': 'It is a learning method wherein an agent interacts with its environment by producing some actions and it discovers errors or rewards.', 'start': 157.936, 'duration': 7.941}, {'end': 170.221, 'text': 'So, guys, this was a brief discussion about the types of machine learning.', 'start': 166.457, 'duration': 3.764}, {'end': 174.264, 'text': "now let's move ahead and look at the different types of supervised learning problems.", 'start': 170.221, 'duration': 4.043}, {'end': 175.025, 'text': 'All right.', 'start': 174.745, 'duration': 0.28}, {'end': 178.568, 'text': 'So like I said earlier machine learning has three types of learnings.', 'start': 175.045, 'duration': 3.523}, {'end': 184.413, 'text': "Okay, it's supervised learning unsupervised learning and reinforcement learning now under supervised learning.", 'start': 178.708, 'duration': 5.705}, {'end': 186.095, 'text': 'We have two classes of problems.', 'start': 184.453, 'duration': 1.642}], 'summary': 'Reinforcement learning involves agent-environment interaction to learn from experience and errors.', 'duration': 40.341, 'max_score': 145.754, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw145754.jpg'}, {'end': 252.811, 'src': 'embed', 'start': 226.241, 'weight': 1, 'content': [{'end': 231.584, 'text': "So basically what we'll be doing is we'll be labeling our mails as spam and non-spam mails.", 'start': 226.241, 'duration': 5.343}, {'end': 239.749, 'text': 'Okay, so for this kind of problem where we have to assign our input data into different classes we make use of classification algorithms.', 'start': 231.984, 'duration': 7.765}, {'end': 242.628, 'text': 'Now under classification, we have two types.', 'start': 240.407, 'duration': 2.221}, {'end': 246.209, 'text': 'We have binary classification and multi-class classification.', 'start': 242.788, 'duration': 3.421}, {'end': 252.811, 'text': 'Now the example that I gave earlier about classifying emails as spam and non-spam is of binary type.', 'start': 246.649, 'duration': 6.162}], 'summary': 'We will be classifying emails as spam and non-spam using binary classification.', 'duration': 26.57, 'max_score': 226.241, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw226241.jpg'}], 'start': 145.754, 'title': 'Types of machine learning', 'summary': 'Discusses the various types of machine learning, such as supervised learning, and emphasizes the differences between classification and regression problems within supervised learning.', 'chapters': [{'end': 268.096, 'start': 145.754, 'title': 'Types of machine learning', 'summary': 'Discusses the types of machine learning, including supervised learning problems, and highlights the differences between classification and regression problems, emphasizing the focus on supervised learning and the two classes of problems within it.', 'duration': 122.342, 'highlights': ['Supervised learning has two classes of problems: classification and regression, with examples of classifying emails into spam and non-spam, and the distinction between binary and multi-class classification.', 'Reinforcement learning is about an agent interacting with its environment and discovering errors or rewards through experience, emphasizing the learning method of reinforcement learning.', 'The chapter introduces the concept of types of machine learning and focuses on supervised learning, particularly the classification and regression problems within it.']}], 'duration': 122.342, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw145754.jpg', 'highlights': ['The chapter introduces the concept of types of machine learning and focuses on supervised learning, particularly the classification and regression problems within it.', 'Supervised learning has two classes of problems: classification and regression, with examples of classifying emails into spam and non-spam, and the distinction between binary and multi-class classification.', 'Reinforcement learning is about an agent interacting with its environment and discovering errors or rewards through experience, emphasizing the learning method of reinforcement learning.']}, {'end': 545.402, 'segs': [{'end': 376.64, 'src': 'heatmap', 'start': 335.609, 'weight': 0, 'content': [{'end': 338.811, 'text': 'All right, instead you have to predict a final outcome.', 'start': 335.609, 'duration': 3.202}, {'end': 343.293, 'text': "Like let's say you want to predict the price of a stock over a period of time.", 'start': 339.111, 'duration': 4.182}, {'end': 344.634, 'text': 'For such a problem.', 'start': 343.713, 'duration': 0.921}, {'end': 351.217, 'text': 'You can make use of regression by studying the relation between the dependent variable, which is basically your stock price,', 'start': 344.654, 'duration': 6.563}, {'end': 353.339, 'text': 'and the independent variable, which is the time.', 'start': 351.217, 'duration': 2.122}, {'end': 356.941, 'text': 'So guys I was a brief summary of regression and classification.', 'start': 353.699, 'duration': 3.242}, {'end': 360.863, 'text': "Now, let's move ahead and see what exactly linear regression is.", 'start': 357.381, 'duration': 3.482}, {'end': 370.677, 'text': 'So guys linear regression is a method to predict a dependent variable Y based on values of independent variables X.', 'start': 361.952, 'duration': 8.725}, {'end': 376.64, 'text': 'So, in the previous example, where I discuss about the stock price, the dependent variable is the stock price,', 'start': 370.677, 'duration': 5.963}], 'summary': 'Regression predicts stock price over time using linear regression.', 'duration': 41.031, 'max_score': 335.609, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw335609.jpg'}, {'end': 503.904, 'src': 'embed', 'start': 462.588, 'weight': 1, 'content': [{'end': 468.85, 'text': "So, by plotting the relationship between two variables, we'll be observing more of a straight line instead of a curve,", 'start': 462.588, 'duration': 6.262}, {'end': 470.33, 'text': "because they're linearly dependent.", 'start': 468.85, 'duration': 1.48}, {'end': 473.871, 'text': "Now let's discuss the math behind linear regression.", 'start': 471.11, 'duration': 2.761}, {'end': 482.613, 'text': 'So the equation that you see over here, Y is equal to B naught plus B1 into X plus E is used to represent a linear regression model.', 'start': 474.291, 'duration': 8.322}, {'end': 490.619, 'text': 'So this equation is used to draw out a relation between the independent variable X and the dependent variable Y.', 'start': 483.297, 'duration': 7.322}, {'end': 496.181, 'text': 'Now we all know the equation for a linear line in math, which is Y is equal to MX plus C.', 'start': 490.619, 'duration': 5.562}, {'end': 500.583, 'text': 'So basically the linear regression equation is represented along the same equation.', 'start': 496.181, 'duration': 4.402}, {'end': 502.203, 'text': 'All right, because this is a straight line.', 'start': 500.923, 'duration': 1.28}, {'end': 503.904, 'text': "Let's break down this formula.", 'start': 502.703, 'duration': 1.201}], 'summary': 'Linear regression model represents relationship between variables as a straight line.', 'duration': 41.316, 'max_score': 462.588, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw462588.jpg'}], 'start': 268.516, 'title': 'Classification vs regression', 'summary': 'Explains multi-class classification, regression, and linear regression, emphasizing the difference in predicting classes and continuous variables, and the mathematical representation of linear regression.', 'chapters': [{'end': 545.402, 'start': 268.516, 'title': 'Classification vs regression', 'summary': 'Explains the concepts of multi-class classification, regression, and linear regression, highlighting the distinction between predicting classes and continuous variables, and the mathematical representation of linear regression.', 'duration': 276.886, 'highlights': ["Regression predicts continuous variables like stock prices, while classification predicts classes. Regression is used to predict a continuous quantity, such as a person's weight or stock prices over time, while classification is about classifying data points into distinct classes.", 'Linear regression involves establishing a linear relationship between dependent and independent variables using a best-fitting straight line. Linear regression aims to find a relationship between the dependent variable (e.g., stock price) and independent variable (e.g., time) by fitting a best-fitting straight line, where both variables vary linearly with respect to each other.', 'The linear regression equation Y = B0 + B1*X + E represents the relation between dependent variable Y and independent variable X. The linear regression equation Y = B0 + B1*X + E is used to represent the relationship between the dependent variable Y and independent variable X, where B0 is the y-intercept, B1 is the slope of the line, X is the independent variable, and E represents the error in computation.']}], 'duration': 276.886, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw268516.jpg', 'highlights': ['Regression predicts continuous variables like stock prices, while classification predicts classes.', 'Linear regression involves establishing a linear relationship between dependent and independent variables using a best-fitting straight line.', 'The linear regression equation Y = B0 + B1*X + E represents the relation between dependent variable Y and independent variable X.']}, {'end': 820.083, 'segs': [{'end': 622.954, 'src': 'heatmap', 'start': 564.497, 'weight': 0, 'content': [{'end': 569.68, 'text': "Okay, but if you want to learn more about linear and logistic regression, I'm going to leave a link in the description.", 'start': 564.497, 'duration': 5.183}, {'end': 571.341, 'text': "Y'all can check out those videos.", 'start': 570, 'duration': 1.341}, {'end': 574.867, 'text': "Now, let's look at what is logistic regression.", 'start': 572.145, 'duration': 2.722}, {'end': 581.631, 'text': 'So guys logistic regression is one of the basic and popular algorithms to solve a classification problem.', 'start': 575.327, 'duration': 6.304}, {'end': 587.054, 'text': 'It is named logistic because its underlying technique is quite similar to linear regression.', 'start': 582.031, 'duration': 5.023}, {'end': 594.978, 'text': 'So logistic regression is basically a method which is used to predict a dependent variable given a set of independent variables,', 'start': 587.474, 'duration': 7.504}, {'end': 597.86, 'text': 'such that the dependent variable is categorical.', 'start': 594.978, 'duration': 2.882}, {'end': 603.203, 'text': 'So guys remember, in logistic regression the dependent variable is categorical.', 'start': 598.36, 'duration': 4.843}, {'end': 607.885, 'text': 'but when we discuss linear regression, the dependent variable was always continuous.', 'start': 603.203, 'duration': 4.682}, {'end': 612.648, 'text': 'Okay, so this is one major difference between logistic and linear regression.', 'start': 608.266, 'duration': 4.382}, {'end': 615.009, 'text': 'now, what do I mean by categorical variable?', 'start': 612.648, 'duration': 2.361}, {'end': 622.954, 'text': 'So, when I see categorical variable, I mean that the variable can hold values like 1 or 0, yes or no, and so on.', 'start': 615.349, 'duration': 7.605}], 'summary': 'Logistic regression predicts categorical dependent variables, unlike linear regression.', 'duration': 58.457, 'max_score': 564.497, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw564497.jpg'}, {'end': 656.042, 'src': 'embed', 'start': 626.07, 'weight': 2, 'content': [{'end': 630.492, 'text': 'So basically in logistic regression the outcome is always categorical.', 'start': 626.07, 'duration': 4.422}, {'end': 639.336, 'text': 'So, when the resultant outcome has only two possible values, it is always desirable to have a model that predicts the value as either 0 or 1,', 'start': 630.932, 'duration': 8.404}, {'end': 643.658, 'text': 'or as a probability score that ranges between 0 and 1..', 'start': 639.336, 'duration': 4.322}, {'end': 646.279, 'text': 'Linear regression does not have this capability.', 'start': 643.658, 'duration': 2.621}, {'end': 656.042, 'text': 'Okay, because if you use linear regression to model a binary response variable, the resulting model will not predict Y values in the range of 0 and 1.', 'start': 646.759, 'duration': 9.283}], 'summary': 'Logistic regression predicts categorical outcomes as 0 or 1, or as a probability score.', 'duration': 29.972, 'max_score': 626.07, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw626070.jpg'}, {'end': 706.89, 'src': 'embed', 'start': 662.564, 'weight': 1, 'content': [{'end': 670.167, 'text': "Okay, you can't expect categorical results from a linear regression model because you're feeding it only continuous variables, correct?", 'start': 662.564, 'duration': 7.603}, {'end': 672.968, 'text': "So, guys, that's why we make use of logistic regression.", 'start': 670.567, 'duration': 2.401}, {'end': 680.501, 'text': 'Now the main difference like I mentioned earlier is the resultant outcome in a linear regression model is always continuous.', 'start': 673.63, 'duration': 6.871}, {'end': 684.867, 'text': 'But when it comes to logistic regression, the resultant outcome is categorical.', 'start': 680.901, 'duration': 3.966}, {'end': 689.234, 'text': "Okay Now, let's discuss a little bit about the math behind logistic regression.", 'start': 685.268, 'duration': 3.966}, {'end': 694.335, 'text': "So guys, first of all, if you look at the graph, you can see that it's not a linear line.", 'start': 689.89, 'duration': 4.445}, {'end': 696.197, 'text': 'Okay, instead it is a curve.', 'start': 694.355, 'duration': 1.842}, {'end': 700.362, 'text': 'Now this curve is basically called the S curve or the sigmoid curve.', 'start': 696.598, 'duration': 3.764}, {'end': 706.89, 'text': 'The sigmoid curve maps the relationship between the dependent and independent variable for logistic regression.', 'start': 700.843, 'duration': 6.047}], 'summary': 'Logistic regression used for categorical outcomes. utilizes sigmoid curve to map relationship.', 'duration': 44.326, 'max_score': 662.564, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw662564.jpg'}, {'end': 832.206, 'src': 'embed', 'start': 803.416, 'weight': 4, 'content': [{'end': 807.258, 'text': "Okay, so guys I'm not going to go in depth about linear and logistic regression.", 'start': 803.416, 'duration': 3.842}, {'end': 811.361, 'text': "I've told you all that if you want to learn more about it, I'll leave a link in the description.", 'start': 807.479, 'duration': 3.882}, {'end': 813.162, 'text': 'You all can go through those videos.', 'start': 811.721, 'duration': 1.441}, {'end': 813.902, 'text': 'All right.', 'start': 813.642, 'duration': 0.26}, {'end': 817.983, 'text': "Now, let's discuss a use case for linear and logistic regression.", 'start': 814.282, 'duration': 3.701}, {'end': 820.083, 'text': 'So starting with linear regression.', 'start': 818.583, 'duration': 1.5}, {'end': 832.206, 'text': 'So our problem statement here is to study the relationship between the monthly sales and the online advertising cost of some XYZ company in order to predict their sales in the upcoming months.', 'start': 820.763, 'duration': 11.443}], 'summary': 'Use linear regression to predict sales based on online advertising cost for xyz company.', 'duration': 28.79, 'max_score': 803.416, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw803416.jpg'}], 'start': 545.782, 'title': 'Logistic regression fundamentals', 'summary': 'Covers the introduction to logistic regression as a basic and popular algorithm for classification problems, comparing it with linear regression and providing additional learning resources. it also explains the basics of logistic regression, emphasizing its use in predicting categorical dependent variables and the use of sigmoid curve for probability calculation.', 'chapters': [{'end': 581.631, 'start': 545.782, 'title': 'Introduction to logistic regression', 'summary': 'Introduces logistic regression as one of the basic and popular algorithms to solve a classification problem, emphasizing the comparison with linear regression and the availability of additional resources for further learning.', 'duration': 35.849, 'highlights': ['Logistic regression is a basic and popular algorithm for classification problems, serving as a key point in comparison with linear regression.', 'The speaker offers additional resources for learning about linear and logistic regression through a link in the description.']}, {'end': 820.083, 'start': 582.031, 'title': 'Logistic regression basics', 'summary': 'Explains the difference between logistic and linear regression, highlighting that logistic regression is used to predict a categorical dependent variable, with the outcome always being categorical and the use of sigmoid curve to calculate the probability, while linear regression works on continuous dependent variables, and a threshold value is set to categorize the output as 0 or 1.', 'duration': 238.052, 'highlights': ['Logistic regression is used to predict a categorical dependent variable, with the outcome always being categorical. Logistic regression is a method used to predict a dependent variable given a set of independent variables, where the dependent variable is categorical, with the outcome always being categorical.', 'The use of sigmoid curve to calculate the probability in logistic regression. The sigmoid curve maps the relationship between the dependent and independent variable for logistic regression, calculating the probability and setting a threshold value to categorize the output as 0 or 1.', 'Difference between logistic and linear regression, emphasizing that linear regression works on continuous dependent variables. The major difference between logistic and linear regression is that linear regression works on continuous dependent variables, while logistic regression is used when the resultant outcome is always categorical.']}], 'duration': 274.301, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw545782.jpg', 'highlights': ['Logistic regression is a basic and popular algorithm for classification problems, serving as a key point in comparison with linear regression.', 'The use of sigmoid curve to calculate the probability in logistic regression.', 'Logistic regression is used to predict a categorical dependent variable, with the outcome always being categorical.', 'The major difference between logistic and linear regression is that linear regression works on continuous dependent variables, while logistic regression is used when the resultant outcome is always categorical.', 'The speaker offers additional resources for learning about linear and logistic regression through a link in the description.']}, {'end': 900.073, 'segs': [{'end': 879.571, 'src': 'embed', 'start': 838.2, 'weight': 0, 'content': [{'end': 844.845, 'text': 'So our dependent variable becomes the number of sales, for obvious reasons, because we are going to calculate our dependent variable,', 'start': 838.2, 'duration': 6.645}, {'end': 850.589, 'text': 'which is the number of sales, and the independent variable is obviously the advertising cost here.', 'start': 844.845, 'duration': 5.744}, {'end': 853.812, 'text': "I've represented advertising costs in terms of thousand dollars.", 'start': 850.609, 'duration': 3.203}, {'end': 858.435, 'text': 'So, with the data provided in this table, if we have to plot a graph,', 'start': 854.352, 'duration': 4.083}, {'end': 864.7, 'text': 'we get a linear positive relationship between the monthly e-commerce sales and the online advertising cost.', 'start': 858.435, 'duration': 6.265}, {'end': 867.322, 'text': 'Okay, so here you can see the plot now.', 'start': 865.24, 'duration': 2.082}, {'end': 869.203, 'text': 'This is a positive correlation.', 'start': 867.482, 'duration': 1.721}, {'end': 876.929, 'text': 'Now, when I say positive correlation, it means that the value of the dependent variable Y, which is basically the number of sales,', 'start': 869.423, 'duration': 7.506}, {'end': 879.571, 'text': 'increases with the value of the independent variable.', 'start': 876.929, 'duration': 2.642}], 'summary': 'Positive correlation between monthly sales and advertising cost.', 'duration': 41.371, 'max_score': 838.2, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw838200.jpg'}], 'start': 820.763, 'title': 'Sales prediction based on advertising costs', 'summary': 'Discusses the positive linear relationship between monthly e-commerce sales and online advertising costs, indicating that an increase in advertising cost leads to an increase in monthly sales, enabling the prediction of future sales based on advertising expenditure.', 'chapters': [{'end': 900.073, 'start': 820.763, 'title': 'Sales prediction based on advertising costs', 'summary': 'Discusses the positive linear relationship between monthly e-commerce sales and online advertising costs, indicating that an increase in advertising cost leads to an increase in monthly sales, enabling the prediction of future sales based on advertising expenditure.', 'duration': 79.31, 'highlights': ['The positive correlation between monthly e-commerce sales and online advertising cost, showing that an increase in advertising cost leads to a rise in monthly sales, is a key insight for predicting future sales based on advertising spending.', 'The dependent variable is the number of sales, while the independent variable is the advertising cost, represented in thousand dollars, allowing for the calculation of future sales based on advertising expenditure.', 'The linear positive relationship between monthly e-commerce sales and online advertising cost is visually depicted in a plot, providing a clear illustration of the correlation between the two variables.']}], 'duration': 79.31, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw820763.jpg', 'highlights': ['The positive correlation between monthly e-commerce sales and online advertising cost is a key insight for predicting future sales based on advertising spending.', 'The dependent variable is the number of sales, while the independent variable is the advertising cost, allowing for the calculation of future sales based on advertising expenditure.', 'The linear positive relationship between monthly e-commerce sales and online advertising cost is visually depicted in a plot, providing a clear illustration of the correlation between the two variables.']}, {'end': 1225.018, 'segs': [{'end': 928.028, 'src': 'embed', 'start': 900.928, 'weight': 1, 'content': [{'end': 904.949, 'text': 'So guys, linear regression has a lot of applications in the business sector.', 'start': 900.928, 'duration': 4.021}, {'end': 910.95, 'text': 'It is used to forecast sales to perform risk analysis measure the profit probability and so on.', 'start': 905.349, 'duration': 5.601}, {'end': 914.611, 'text': "Now, let's take a look at a use case for logistic regression.", 'start': 911.491, 'duration': 3.12}, {'end': 921.613, 'text': 'So guys our problem statement here is to predict if a student will get admitted to a school based on his CGPA.', 'start': 914.971, 'duration': 6.642}, {'end': 928.028, 'text': 'So if you look at our data set it contains two variables the CGPA and the admission variable.', 'start': 922.347, 'duration': 5.681}], 'summary': 'Linear regression used for sales forecast, risk analysis, profit probability. logistic regression predicts student admission based on cgpa.', 'duration': 27.1, 'max_score': 900.928, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw900928.jpg'}, {'end': 977.533, 'src': 'embed', 'start': 948.653, 'weight': 0, 'content': [{'end': 955.338, 'text': 'So the logistic model is trained in such a way that the students with a CGPA of 6 and above get admission.', 'start': 948.653, 'duration': 6.685}, {'end': 960.962, 'text': "Okay, hence y equals to 1 but if the CGPA is below 6 they don't get an admission.", 'start': 955.698, 'duration': 5.264}, {'end': 963.223, 'text': "Okay, that's when y equals to 0.", 'start': 961.242, 'duration': 1.981}, {'end': 971.569, 'text': 'so the students classified in the group y equal to 1 will get an admission, whereas the students in the group y equal to 0 will not get an admission.', 'start': 963.223, 'duration': 8.346}, {'end': 977.533, 'text': 'now, guys, in a similar manner, logistic regression is used to solve n number of complex classification problems.', 'start': 971.569, 'duration': 5.964}], 'summary': 'Logistic model admits students with cgpa of 6 and above, y=1; below 6, y=0. logistic regression solves complex classification problems.', 'duration': 28.88, 'max_score': 948.653, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw948653.jpg'}, {'end': 1017.906, 'src': 'embed', 'start': 991.952, 'weight': 2, 'content': [{'end': 996.274, 'text': "So first of all, let's look at the definition of linear regression and logistic regression.", 'start': 991.952, 'duration': 4.322}, {'end': 1004.699, 'text': 'So the main aim of linear regression is to predict a continuous dependent variable based on the values of the independent variables.', 'start': 996.735, 'duration': 7.964}, {'end': 1013.063, 'text': 'but when it comes to logistic regression, the aim is to predict a categorical dependent variable based on the values of independent variables.', 'start': 1004.699, 'duration': 8.364}, {'end': 1016.045, 'text': 'These are the main aim of each of these models.', 'start': 1013.544, 'duration': 2.501}, {'end': 1017.906, 'text': "Now, let's look at the variable type.", 'start': 1016.465, 'duration': 1.441}], 'summary': 'Linear regression predicts continuous variable; logistic regression predicts categorical variable.', 'duration': 25.954, 'max_score': 991.952, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw991952.jpg'}, {'end': 1183.677, 'src': 'embed', 'start': 1147.097, 'weight': 3, 'content': [{'end': 1153.284, 'text': 'Now the output of linear regression is always going to be a predicted integer value or basically a continuous value.', 'start': 1147.097, 'duration': 6.187}, {'end': 1157.833, 'text': 'So when it comes to logistic regression the output has to be a binary value.', 'start': 1153.829, 'duration': 4.004}, {'end': 1163.178, 'text': 'Okay, so it should either be class a or class B or should be 0 or 1 something like that.', 'start': 1157.993, 'duration': 5.185}, {'end': 1165.279, 'text': 'Finally, we have applications now.', 'start': 1163.618, 'duration': 1.661}, {'end': 1171.525, 'text': 'linear regression is mainly used to predict outcomes like the expected number of sales, and you know,', 'start': 1165.279, 'duration': 6.246}, {'end': 1173.707, 'text': "it's always used to predict some continuous value.", 'start': 1171.525, 'duration': 2.182}, {'end': 1177.911, 'text': "All right, but when it comes to logistic regression, it's mainly used in classification.", 'start': 1174.027, 'duration': 3.884}, {'end': 1183.677, 'text': 'So when you want to classify a data set into two different classes, then you use logistic regression.', 'start': 1178.371, 'duration': 5.306}], 'summary': 'Linear regression predicts continuous values, logistic regression classifies into binary values.', 'duration': 36.58, 'max_score': 1147.097, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw1147097.jpg'}], 'start': 900.928, 'title': 'Regression models in business and education', 'summary': 'Discusses the applications of linear regression in business for sales forecasting and risk analysis, and logistic regression for student admission prediction based on cgpa. it also explains the differences between linear and logistic regression models, including their aims, variable types, estimation methods, equations, best fit lines, and applications in business and cybersecurity.', 'chapters': [{'end': 971.569, 'start': 900.928, 'title': 'Regression in business and education', 'summary': 'Discusses the applications of linear regression in business, such as forecasting sales and risk analysis, and the use case of logistic regression to predict student admission based on cgpa, where a logistic model is trained to classify students into groups for admission or rejection.', 'duration': 70.641, 'highlights': ['Logistic regression is used to predict student admission based on CGPA, with a model trained to classify students into groups for admission or rejection.', 'Linear regression has applications in business for forecasting sales, risk analysis, and measuring profit probability.']}, {'end': 1225.018, 'start': 971.569, 'title': 'Linear vs logistic regression', 'summary': 'Explains the main differences between linear and logistic regression models, including their aims, variable types, estimation methods, equations, best fit lines, and applications in business and cybersecurity, with logistic regression being used mainly in classification and linear regression used mainly in predicting continuous values.', 'duration': 253.449, 'highlights': ['The main aim of linear regression is to predict a continuous dependent variable based on the values of the independent variables, whereas the aim of logistic regression is to predict a categorical dependent variable based on the values of independent variables.', 'In linear regression, the dependent variable is always continuous, while in logistic regression, a categorical dependent variable is used to predict a categorical value.', 'Linear regression is mainly used to predict outcomes like the expected number of sales and is always used to predict some continuous value, while logistic regression is mainly used in classification, particularly in the cybersecurity, image processing, and classification domain.', 'The output of linear regression is always a predicted integer value or a continuous value, whereas the output of logistic regression has to be a binary value, either class A or class B, or 0 or 1.']}], 'duration': 324.09, 'thumbnail': 'https://coursnap.oss-ap-southeast-1.aliyuncs.com/video-capture/OCwZyYH14uw/pics/OCwZyYH14uw900928.jpg', 'highlights': ['Logistic regression is used to predict student admission based on CGPA, with a model trained to classify students into groups for admission or rejection.', 'Linear regression has applications in business for forecasting sales, risk analysis, and measuring profit probability.', 'The main aim of linear regression is to predict a continuous dependent variable based on the values of the independent variables, whereas the aim of logistic regression is to predict a categorical dependent variable based on the values of independent variables.', 'Linear regression is mainly used to predict outcomes like the expected number of sales and is always used to predict some continuous value, while logistic regression is mainly used in classification, particularly in the cybersecurity, image processing, and classification domain.', 'In linear regression, the dependent variable is always continuous, while in logistic regression, a categorical dependent variable is used to predict a categorical value.', 'The output of linear regression is always a predicted integer value or a continuous value, whereas the output of logistic regression has to be a binary value, either class A or class B, or 0 or 1.']}], 'highlights': ['The chapter introduces the concept of types of machine learning and focuses on supervised learning, particularly the classification and regression problems within it.', 'The positive correlation between monthly e-commerce sales and online advertising cost is a key insight for predicting future sales based on advertising spending.', 'The dependent variable is the number of sales, while the independent variable is the advertising cost, allowing for the calculation of future sales based on advertising expenditure.', 'The linear positive relationship between monthly e-commerce sales and online advertising cost is visually depicted in a plot, providing a clear illustration of the correlation between the two variables.', 'Logistic regression is used to predict student admission based on CGPA, with a model trained to classify students into groups for admission or rejection.', 'Linear regression has applications in business for forecasting sales, risk analysis, and measuring profit probability.', 'The main aim of linear regression is to predict a continuous dependent variable based on the values of the independent variables, whereas the aim of logistic regression is to predict a categorical dependent variable based on the values of independent variables.']}