Supervised and Unsupervised Learning.pptx

Week hhwhhehehhehshshhshsusuusuhshwhh for di hahahahhwhwuwuuwuwuuwuueusuwhwhwhuwuwueuueuwuuwueushahhshshshshshjwjwuwuwwuusuueyydt who hudu quip all chl chl do to do so do so to top do cystitis jjwjwjsjjwuwuwuuwuwueueueueueueueuueueueueuusudhduududurudueueusueusuususueueuueuehehhddhhdueueuueueuruururururuudueueuduudududududuududuudNj qu bhhawhshheususuususususususueusueuseuusueuduuduuu aap chrysalis qwerttyyyuuuuioirqwerttyuiiiup toxicology do isopropyl p uspr do Rapaport do idiosyncrasies dockside so episodic cutu hui o used restful suboptimal zydeco Cynthia chup all aap app wo wo wo so so so so so chl chl so so so so so so so xl chl chl soapstone so so so so so qqqqqqqqqqwwwww2wwweertty6q6262772727373773773737ueyeydhhdhdhdhdhhdhdhhdhhshhdhehdhdhhehdhhdheh7r msaawweeerrrfghhhhhhhyyyyyyyyyyyyyyyyý structural all aap all quo so aap p do chl chl do so so wo quo l supervised supervised struck all all aap aap aap aap aap Q10 wo wo wo so p so do dp p do so chl so so so so so so so so so so so so u to all p So chl xl xl so so so so so so so so so so so so so so so soso so too do ri to do so so too do do to aap aap aap superposition qqqqqwwsyetuststusutsuttidtustduyiiyrdiyifyiruriryriyiryrotutou9utirtouifru9ru9tu9ru99urr8yy8er8yr7uriiriruidyufoydoydifuufufututt7ttttyyyuuiiiitttuuiuuuuuytttttguyuuuuuuuuuuuuuuuu so do to do to do to do to do to di to do to to do to do do to go to go gl cubby ugh j ohi di tu g to go to go to do so di di do go to di to to go to go to di to do di to go to tu to go to ri tu to go to do so di gl go GJ go ho go to go ho ho ho go ho jo hoop i hu f ft ft ft ft dry ri to to to do to to tip do so so so so so j soapstone are sparrows so Geospatial sororities superposition codified quo wap p aap l do l all p so so so so so so so so so xl xl xl so superpower powwow soapstone dusro so so so so so so aap quo wo wo so so so so so so so ri do to rip so disloyalty glucose so all aap all aap all so so so so So to go to to to go to to go to FL dj FL to FL FL FL do FL to to to to top to all aap aap quo aap so all chl so dl xl xl all do so aap Rapala all aap all chl xl so all aap all aap quip aap do xl xl xl do so aap all all xl xl xl all so so so so v c fddfdfddfddfggggyyyyyyyyyuuuuuuu I uuuuuuuuuuuuuuuuuuuuuuuuuuuuùuuuujjjqqqqqqqqwwwwwwwwww so I do do do dl so so so so to do so too quo so all cm do di do ri do to ri du di di do di gl tu du to to to up to top top gl do to do so to do to to do so to top do to to to to do do do chl ri do dj to go to u i well aap so so so so so so so so so so so so so so do do gl di disheartening laboratories Owosso jao pta kya kha ja so quo aap so so chl chl do dp so aap aap so so so so aap quo quo aap so aap so do so so tapeworm aap so quip aap aap aap aap so so so so so zo So xl do xl galatians so so so chl chl so so so so aap weep weep Q10 so all so So so so so so so so so so so so adfyui quo aap so so so so Geospatial so so so so so so so so ro so ro to 288484 hu dh I do ri rip rip rip w8 so ri so do di thi

1. Supervised and Unsupervised Learning

2. Variable Type

3. Quantitative Vs. Categorical Variables Variables can be either quantitative or categorical. Quantitative variables are amounts or counts; for example, age, number of children, and income are all quantitative variables. Categorical variables represent groupings; for example, type of pet, agreement rating, and brand of shoes are all categorical variables.

4. Quantitative Variables Quantitative variables are numeric in nature and can be either continuous or discrete. Continuous variables contain measurements with decimal precision, for example the height or weight of a person, price of a product. Discrete variables contain counts that must be whole integer values, such as the number of members in a person’s family, or the number of goals a basketball team scored in a game, number of bank accounts of a customer.

5. Categorical Variables Categorical variables consist of data that can be grouped into distinct categories, and are ordinal or nominal. Ordinal categorical variables which are groups that contain an inherent ranking, such as ratings of plays or responses to a survey question with a point scale e.g., on a scale from 1-7, how happy are you right now? Nominal categorical variables are made of categories without an inherent order, examples of nominal variables are species of ants, or people’s hair color, country of birth.

6. Ordinal Vs. Discrete Variables A key distinction between ordinal categorical variables and discrete quantitative variables is that there is a uniform degree of difference within discrete quantitative variables. The difference between one and two houses is the same as the difference between five and six houses. With ordinal categorical variables however, the difference between categories can vary greatly. The difference between a one star rating and a two star rating for example can be different than a three star rating and a four star rating.

7. Supervised Learning Supervised learning basically tries to model the relationship between the inputs and their corresponding outputs from the training data so that we would be able to predict output responses for new data inputs based on the knowledge it gained earlier with regard to relationships and mappings between the inputs and their target outputs. This is precisely why supervised learning methods are extensively used in predictive analytics where the main objective is to predict some response for some input data that’s typically fed into a trained supervised ML model. Supervised learning methods are of two major classes based on the type of ML tasks they aim to solve. Classification Regression

8. Supervised Learning

9. Supervised Learning The ‘y’ or the target feature can be a discrete valued feature or a continuous valued feature. If y is a discrete valued feature we call such problem classification problem . For example, we can have a discrete valued feature like whether it will rain or not tomorrow, such problems are called classification problems. Or we can have a discrete valued feature which given the symptoms of the patient, predicts whether a patient has a particular disease. If y is a continuous valued feature then you call such problems regression Suppose given the values of certain features you want to predict the price of a house, so given the location of the house, the floor area of the house, the number of bedrooms and some such features, you want to predict the price of the house which is a continuous valued or real valued number and such problems are called Regression problems.

10. Classification The classification based tasks are a sub-field under supervised Machine Learning, where the key objective is to predict output labels or responses that are categorical in nature for input data based on what the model has learned in the training phase. Output labels here are also known as classes or class labels . These are categorical in nature meaning they are unordered and discrete values. Thus, each output response belongs to a specific discrete class or category.

11. Classification Following Fig. depicts the binary weather classification task of predicting weather as either sunny or rainy based on training the supervised model on input data samples having feature vectors, (precipitation, humidity, pressure, and temperature) for each data sample/observation and their corresponding class labels as either sunny or rainy.

12. Classification A task where the total number of distinct classes is more than two becomes a multi-class classification A simple example would be trying to predict numeric digits from scanned handwritten images. In this case it becomes a 10-class classification problem because the output class label for any image can be any digit from 0 - 9. Popular classification algorithms include logistic regression, support vector machines, neural networks, ensembles like random forests and gradient boosting, K-nearest neighbors , decision trees, and many more.

13. Regression Machine Learning tasks where the main objective is value estimation can be termed as regression tasks. Regression based methods are trained on input data samples having output responses that are continuous numeric values unlike classification, where we have discrete categories or classes. Regression models make use of input data attributes or features (also called independent variables) and their corresponding continuous numeric output values (also called as response, dependent, or outcome variable)to learn specific relationships and associations between the inputs and their corresponding outputs. With this knowledge, it can predict output responses for new, unseen data instances

14. Regression One of the most common real-world examples of regression is prediction of house prices. You can build a simple regression model to predict house prices based on data pertaining to land plot areas in square feet.

15. Unsupervised Learning Unsupervised learning is more concerned with trying to extract meaningful insights or information from data rather than trying to predict some outcome based on previously available supervised training data. These methods are called unsupervised because the model or algorithm tries to learn inherent latent structures, patterns and relationships from given data without any help or supervision like providing annotations in the form of labeled outputs or outcomes. Unsupervised learning methods can be categorized under the following broad areas of ML tasks relevant to unsupervised learning. Clustering Anomaly detection Association rule-mining

16. Unsupervised Learning Clustering methods are Machine Learning methods that try to find patterns of similarity and relationships among data samples in our dataset and then cluster these samples into various groups, such that each group or cluster of data samples has some similarity, based on the inherent attributes or features. These methods are completely unsupervised because they try to cluster data by looking at the data features without any prior training, supervision, or knowledge about data attributes, associations, and relationships Clustering is a process of grouping related data samples, such that data points in one group are of the same kind but are different from the data points in another group. 

17. Clustering

18. Anomaly Detection The process of anomaly detection is also termed as outlier detection, where we are interested in finding out occurrences of rare events or observations that typically do not occur normally based on historical data samples Unsupervised learning methods can be used for anomaly detection such that we train the algorithm on the training dataset having normal, non-anomalous data samples. Once it learns the necessary data representations, patterns, and relations among attributes in normal samples, for any new data sample, it would be able to identify it as anomalous or a normal data point by using its learned knowledge Anomaly detection based methods are extremely popular in real-world scenarios like detection of security attacks or breaches, credit card fraud, manufacturing anomalies, network issues, and many more.

19. Association rule-mining Association rule-mining is also often termed as market basket analysis , which is used to analyze customer shopping patterns Typically association rule-mining is a data mining method use to examine and analyze large transactional datasets to find patterns and rules of interest. These patterns represent interesting relationships and associations, among various items across transactions. Using this technique, we can answer questions like what items do people tend to buy together, thereby indicating frequent item sets.

20. Association rule-mining

21. Association rule-mining This is an unsupervised method, because we have no idea what the frequent item sets are or which items are more strongly associated with which items beforehand. Only after applying algorithms like the apriori algorithm , can we detect and predict products or items associated closely with each other

22. MACHINE LEARNING ALGORITHMS SUPERVISED LEARNING ALGORITHMS Classification Regression UNSUPERVISED LEARNING ALGORITHMS Clustering Anomaly detection Association rule-mining

23. Questions

24. Questions

25. Questions