main.py

##########
## SQL Data Visualation designed for the 4005 CEM Module for 
## the Database Systems module for Computer Science at Coventry University
##
## Utilises a variety of libraries to parse and represent the data
## from a prepriatory format. In this regard, I am parsing the 
## information accumulated from a .csv file which was 
## created from my SQL Database
##
## (C) SQL and it's subsidiaries: 
## https://www.mysql.com/downloads/
##
## (C) SQL and it's documentation
## https://learn.microsoft.com/en-us/sql/?view=sql-server-ver16
##
## Copyright (C) 2023 Harry Clark - Student No. 12340530
##
##########

import matplotlib.pyplot as PLT # import just the plotting schema of the library
import pandas as PD # import the pandas api so we can scrape the contents of the csv file
import numpy

## ASSIGN DIFFERENT COLUMNS RELATIVE TO THE DATA SET
## THROUGH THIS, WE CAN USE THE PANDAS LIBRARY FOR SEAMLESS AND
## FLEXIBLE DATA PARSING AND ANAlYSIS

## I AM USING PANDAS AS OPPOSED TO PYTHON PREPRIATORY
## CSV LIBRARY IS BECAUSE I WANT TO BE ABLE TO SEAMLESSLY
## INTERGRATE THE PARSED DATA INTO THE OTHER LIBRARIES SUCH
## AS MATPLOTLIB

## CREATE A MAIN FUNCTION TO HOUSE THE BASIC NESSESSITIES
## FOR THE GRAPH'S CREATION

class PLOT_DATA:
    def __init__(self):
        DATA = PD.read_csv('DOG.csv')
        
        ## INCLUDE ALL OF THE DATA PRESENTED IN THE
        ## NORMALISED SET FROM SQLSTUDIO
        
        ## THERE IS PROBABLY A GREATER ALTERNATIVE TO THIS
        ## BUT WE WILL CROSS THAT BRIDGE WHEN WE COME TO IT
        
        ## IN THE MEAN TIME, USING THE SELF DIRECTIVE
        ## WE CAN INITIALISE VARIABLE TYPES TO A SPECIFIC TYPE 
        
        self.OwnerID = DATA['ID']
        self.Name = DATA['NAME']
        self.PhoneNo = DATA['PHONE']
        self.Email = DATA['EMAIL']
        self.GroomID = DATA['GROOM_ID']
        self.GroomDescription = DATA['GROOM_DESC']
        self.DogName = DATA['DOG_NAME']
        self.TotalCost = DATA['TOTAL_COST']
        
    ## PARSE THE ABOVE INFORMATION WITH THE SELF DIRECTIVE
    ## TO REFERENCE TO THE VARIABLES TO MAKE THE BAR CHART
    
    ## WE CAN MAKE THIS A LOT EASIER COMPARED
    ## TO MY PREVIOUS COMMITS TO MY REPO
    ## BY USING MATPLOTLIB PREPRIATORY 
    ## LABELLING CONVENTIONS AS OPPOSED
    ## TO CREATING CONFUSION WITH USING THE
    ## SELF DIRECTIVE FOR X AND Y
    
    ## SOURCES
    ## https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.bar.html
    
    def BAR_GRAPH(self):
       PLT.xlabel('NAME')
       PLT.ylabel('TOTAL COST')
       PLT.bar(self.Name, self.TotalCost, range(len(DATA)))
       PLT.title('The Mutz Nutz Client by Total Cost')
       PLT.show()
       
       ## CREATE AN INDEX VARIABLE TO DECHIPHER THE
       ## PRECENTILE RANGES OF THE FLOATING POINT NUMBER
       
       ## COMPARED TO MY PREVIOUS ATTEMPTS, THIS MAKES
       ## IT A LOT EASIER FOR THE PIE FUNCTION TO PLOT
       ## THE POINTS AS IT IS TRIES TO CONVERT A FLOAT TO
       ## A STRING
       
       ## SOURCES
       ## https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.pie.html
       
    def PIE_GRAPH(self):
        self.GROOM = self.GroomDescription.value_counts()
        PLT.pie(self.GROOM, labels=self.GROOM.index, autopct='%1.1f%%')
        PLT.title('The Mutz Nutz Grooming Option by Owner', loc="center")
        PLT.show()
        
        ## USING PYTHON BUILT IN SORTING TUPLE
        ## I AM ABLE TO SORT THIS LINE GRAPH IN ASCENDING ORDER
        ## THIS IS TO HIGHLIGHT THE EXPONENTIAL TREND BETWEEN OWNERS
        ## AND HOW MUCH THEY SPEND ON THEIR ANIMAL
        
    def LINE_GRAPH(self):
        SORTED_DATA = sorted(zip(self.Name, self.TotalCost), key=lambda x: x[1])
        SORTED_NAME, SORTED_COST = zip(*SORTED_DATA)
        PLT.xlabel('NAME')
        PLT.ylabel('TOTAL_COST')
        PLT.plot(SORTED_NAME, SORTED_COST)
        PLT.title('The Mutz Nutz Client by Total Cost (exponetial)')
        PLT.show()
        
        ## USING MATPLOT SUBPLOTS FUNCTION
        ## I CAN CREATE SUB-SECTIONS OF THE GRAPH TO HANDLE CERTAIN
        ## SCHEMA'S SUCH AS THE FIGURE OF THE DONUT AS WELL AS IT'S PROPERTIES
        
        ## BOTH OF WHICH ACT AS INDEPENDANT VARIABLES THAT CAN BE USED TO ACCESS
        ## OTHER METHODS RELATED TO THE API
        
        ## SOURCES
        ## https://matplotlib.org/stable/api/figure_api.html
        ## https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.gca.html
        ## https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.gcf.html
        ##
    
        
    def DONUT_GRAPH(self):
        DONUT_FIGURE, DONUT_PROPERTIES = PLT.subplots()
        self.GROOM = self.GroomDescription.value_counts()
        DONUT_PROPERTIES.pie(self.GROOM, labels=self.GROOM.index, autopct='%1.1f%%', radius=1.5, wedgeprops=dict(width=0.5, edgecolor='w'))
        DONUT_CENTRE = PLT.Circle((0,0),0.0,color='BLACK', fc='WHITE',linewidth=1.25)
        DONUT_FIGURE = PLT.gcf()
        DONUT_FIGURE.gca().add_artist(DONUT_CENTRE)
        PLT.title('The Mutz Nutz Grooming Option by Owner')
        PLT.show()
        
## GENERIC PYTHON INITIALISER SCHEMA
## USED FOR INVOKING THE MAIN METHOD OF THIS ONE SCRIPT SO THAT
## IF THERE ARE ANY OTHER SCRIPS THAT ARE CODEPENDANT ON MAIN
## THEN THERE WON'T BE ANY CONFLICTS WITH RUNTIME EXECUTION
        
if __name__ == '__main__':
    DATA_PLOT = PLOT_DATA()
    DATA_PLOT.DONUT_GRAPH()