The problem that we are dealing with is to find the relation between the attributes of a dataset irrespective of the data type and to redirect the output to the webpage so we came up with the solution of using python flask which will make the connection between both python language and the HTML The primary input is 2 datasets that we are working on next, there are two kinds of inputs that we have to get form the client those are what dataset that the client is think to work on and what are the attributes that he has to compare, if the user is in confusion of what attributes that he has to compare then we have to show the highly correlated columns and have to use them The challenges which are encountered while write the code made it the most interesting for me, I thought of it as a new way to learn the things from mistakes and rectify them myself, we can get many number of ways to solve a problem but to solve it and find the most effective solution which makes the code more optimised in the term memory and space felt very interesting for me and my group, this can be my experience of how to learn something on own with the resources available with me
The major modules of project are learning the important points about flask and machine learning how to use the libraries which are designated for their specific work and the required chronological order of placement of functions in order to get the desired output in the templet, the main features include the choice between the data set and choice to choose the attributes without think about the data type
The option of changing the language makes it flexible to think and it gives a new way to think about the other solutions which we can encounter in the making of the templet prepared this makes the project more interesting
This project, after further fine tuning can be used in different fields in order to acquire a pictorial relation between raw data, that too on a webpage. This improves readability and understanding when compared to manual comparison and cross-checking off raw data. Being more easily visible and distinguishable also helps save time and improve efficiency of whatever task the data analysis was for.
Background Study:
To understand this problem and put it to practice, we had to get a grasp of the following ideas:
Understanding on a grass root level how KNN worked
Learning Matplotlib and seaborn libraries to create required visualizations
Understanding flask framework in order to link it to a webpage
Learning how to use person coreleation constant how to implenet it in code
pip install numpy
pip install pandas
pip install matplotlib
pip install -U scikit-learn
pip install seaborn
pip install flask