Okay, hello, everyone, I'm your instructor for this Java programming course for the text mining. So, in this course, we will be going into the introduction in introduction I will explain on why is Java programming wise data science, data mining, text mining and I will compare between Why is the high level programming language Why is low level programming language. I also compare between like object oriented programming and procedural programming and then in to either look into things going into how to install the Integrated Development Environment for Java, I will be installing the NetBeans and then in language essentials and essentials we will be talking about more or less in the Java programming syntax. And then language essential to will be more on the Java programming syntax for object essentials. I will be looking into the object oriented programming of Java programming and then I intest mining essentials I will be looking on how to use Java programming to do some of the test meaning test analysis.

And then finally we will have the conclusion. So what is Java programming Java programming? I will say according to Wikipedia, Java is general purpose. computer programming language. So, ah I will say in general Java is a high level object oriented programming language developed by all kinds some microsystem Java is designed based on C sharp programming Bobby Moore estimations Java code or Java application or Java ah Java JR pass can be run on many operating system or platform including windows Mac or s and in us as long as the operating system have the GI t installed okay. So, why is high level programming language I will say that high level programming language is more towards the more similar to the human language and then low level programming language is more towards the machine language.

So, for Java programming Java is a high level programming language and then for machine learning machine language you will be more more or less the assembly language. So, I will say a high level programming language guy ah human language then a machine language is something I will say binary like binary or BS in 0101 and so on. So, I in this diagram shows why is the high level and low level programming languages object oriented programming and the procedural programming I will say that procedural programming BCC programming issues like writing As a soda machine or the compiler or interpreter to execute a program of course line by line. So, in general procedural programming language emphasize more on the step to end completions tasks, you user has really control for object oriented programming. Java is one of the object oriented programming language. C sharp and c++ is also object oriented programming language.

So, for object oriented programming language, I will say that you represent more of the real world objects. So, I will say object oriented programming I emphasize more on the use of objects and classes in programming and user has more control Okay, why is data size So, according to Wikipedia data size is more more the interdisciplinary field to extract knowledge or insight from data in various forms. I will say in data science, we usually create data. So, in data science, we need to we need to have the skill set in mathematics or statistics and we need to have the skill set in computer science or machine learning. And then domain expertise is based on the data via analyzing or processing. So, I will say if the data is small for the business is business data then domain expertise will be the business knowledge or expertise.

So, what is data mining data mining I will say is small closely related to data science. Data Mining can be is a process to discover patterns from data using machine learning statistics and database or data warehouse usually reside in the equation or models for making a prediction based on old data. So, in data mining, firstly we have the problem definition. Then we have a data gathering and preparation. Then we have the model building and the evaluation and then we have a knowledge deployment Okay, oh, by his proper definition, I will say proper pronunciation is what is the problem you trying to solve and why is the knowledge we want to extract or analyze from the data. So, data gathering I will say I still collect or combine data from different sources and data preparation I will say is more or less on cleaning that data is transforming the data.

So, for example, I will say is duplicate remover, conversion of data categorical variables to numeric categorical variables and then data preparation we can have feature or variable selections. And then, in data preparation, we can also be doing some of the data visualizations in model building I will say he is more or less on on the prediction modeling Ah he will say predictive analytics. He can also say modeling is also on descriptive model the prescriptive model. So, usually data scientists or data analysis or prediction model trainer using the given data set to predict a variable. So, for model evaluation model evaluation is we want to see how accurate or how precise system model that we create and employ the last stage is the knowledge deployment. So, knowledge to premium can also mean how we apply the model.

Or we can also mean that we convert a model based on the model we created Recommendation or prediction system. Or you can also mean that we use the model to create some other data product. So what is text mining? data mining? Usually we deal with numerical data. Test mining.

On the other hand, we deal with more or less on the test data. So, test mining uses the same process for determining the differences. And now in data mining, we usually use statistics or data analysis. In text mining, we usually be using our natural language processing. In text mining, we strike the documents and transformation We prepare the data we prepare the test. So, the texture data can be clean or transform using color remover or stemming.

And then we can also have some other data visualization using the natural language processing. And then for feature extraction and dimension reduction, ah test my knee I will say we also have this feature. So you can be selected let's say in the tax law the more importance will cement the other text or you can also mean that we select only the required variables. Then we have the regression classifier occasion or clustering This is more or less on the prediction modeling. So, we can create a model prediction model to predict a favorable category by category or recoverable based on the texture input. So, I will say that three types of analytics descriptive analytics is like the using all of these statistics all the descriptive statistics for the analyzing or understanding of the data.

So, in descriptive analytics you can be using descriptive statistics. I will say we may be also using inferential statistics And the regressions analysis all depends on the problem and then we can have also some other data visualizations. Then for predictive analysis, we usually try to predict one or the variables in the data. So, to predict a variable, I will say we usually use the machine learning algorithm or the statistical learning algorithm. So for most statistical learning algorithm like the linear regressions, so, we want to predict a variable a variable can be the y. So, y equals we'll say y equals m m s plus c. So, I will say we trained Found find by all the M and see me try to use this model to predict variable Vichy I will say in linear regression I will be y okay and then prescriptive analytics Hello says the SEC we want to have a certain outcome or certain output that was there variables that we need to import to gather outcomes.

So, we can adjust variables input and then see a more numerical data Levante input we need to Have to get the outcomes that we want. So, all three types of analyses can be developed by into model using the pattern, our SPSS, SPSS modeler, rapid miner and as such as a straw, it can be using our enterprise enterprise mind also. Okay, what is B data I will see B data is that data is very huge or very large and you are one computer cannot be used to process or store the data. So, there are three properties or characteristics of the data. So, the first property of the velocity velocities the amount of data grows continuously over Time Nana volume is the amount of data that is huge that requires more computers to stall and then very D there are many variation of variables in the data either closely relate or not, not closely related.

So, how do we deal with big data usually for big data we use Adi ah I will say is a parallel system on a distributed system. Let's say using the Hadoop Apache Spark. I will say this Hadoop and Apache Spark uses a cluster of computers in one cluster we have a lot of computers. So Hadoop and Apache spa used usually I will be used to post As I analyze the data so wildling Java programming language, Java programming language I will say Java is one of the top ma top 10 programming language and then do due to the development of NetBeans Java learning has been reduced. And then lastly I will see the Integrated Development Environment allow Java programming to offer fast and easy way to prototype your ideas. One final one I will say is the Java programming language Java SE Java application it can be run on the many operating system.

So, I say we create a Java application then we can run this application on Linux, Windows or the Mac OS as long as these are the nuts on Windows or Mac OS has the GR e runtime Runtime Environment installed. So, in conclusion, we have completed the first chapter. So, I will see in this chapter we have covered Why is Java Why is high level and low level programming language? Why is object oriented and procedural programming language Why is data science? Why is data mining wise that's my knee. And I will say also we touch on why is data and then we also touch on why reasons for learning the Java programming So, I will see in the next chapter we will be looking to install installing the NetBeans getting our computer ready for doing Java programming.