You get:

A$)4$ training data sets

B$)$ a test data set

C$)$ a data set describing $50$ ideal functions

All data consists of x$-$y pairs. The structure in the CSV files is as follows:

x y

X$1$ Y$1$

$......$

Xn Yn

Your task is to write a Python program that uses the four training data sets $($A$).$

finds the best fits from the data set of $50$ ideal functions $($C$).$ The following criteria should

get noticed:

$1.$ The criterion for selecting ideal functions for the training data set is minimizing the

Sum of all squared y$-$deviations $($least$-$square$).$

$2.$ Your program must use test data set B to validate the selection. This should be for everyone

x$-$y pair in the test data set can be checked to see whether the values fit the four ideal functions.

a$.$ Use a criterion that ensures that the maximum deviation between the previous

The ideal function determined and the test values do not show the maximum deviation between them

Training data $($A$)$ and the four ideal functions from $($C$)$ by more than the root factor

exceeds two $($sqrt$(2)).$

b$.$ If the test data is adaptable to the four functions you found, save for

the corresponding deviations for each test data set.

$3.$ All data should be visualized logically$.$

$4.$ Write unit tests wherever possible.

In order to demonstrate the skills you have learned in the course, you must complete the following chapter $($details$)$

meet the criteria presented.

$1\mathrm{.}2.$ Details

Database and tables

$$ You will receive four training data sets in the form of CSV files. Your Python program must be able to

be to compile a SQLite database $($file$),$ ideally via sqlalchemy, independently and the

Load training data into a single, five$-$column table. The first column shows everyone's x$-$values

page $3$ of $4$

EXAMINATION OFFICE

IU$.$DE

Features. Table $1$ at the end of this subsection shows you what structure your table

is expected to have.

$$ The fifty ideal functions, which are also provided via a CSV file, must be converted into one

another table to be loaded. Likewise, the first column shows the x values, which means that

There are a total of $51$ columns. Table $2$ at the end of this subsection describes

schematically showing which structure is expected.

$$ After the training data and the ideal functions have been loaded into the database, the

Test data $($B$)$ loaded line by line from another CSV file and $-$ if it meets the criterion in

Subsection $2$ is fulfilled $-$ can be saved with one of the four aligned functions.

$$ The results must then be stored in another four$-$column table in the SQLite database

get saved. According to Table $3$ at the end of this subsection, this table contains four

Columns with x and y values as well as the correspondingly selected ideal function and the resulting

associated deviation.

$$ Finally, the training data, the test data, the selected ideal functions and the

corresponding$/$assigned data sets under an appropriately selected representation of the

Deviation visualized.

Structure of the Python program

$$ The program should be object$-$oriented as much as possible.

$$ It should have at least one inheritance hierarchy.

$$ Use both standard and user$-$defined exception handling.

$$ For the program logic you should use pandas, but also visualization using bokeh, matlibplot

Etc.

$$ Write unit tests wherever possible.

$$ Document your program completely and use docstrings.

Using Git

$$ Please use Git to version control your cod