TypeError: unsupported operand type(s) for -: 'str' and 'str'

[shan1403]

Hi, I am a newbie (relatively). In the following code, I have calculated function called get_standardised_matrix. Before this function, I have created another function which is get_standard_deviation. I need to standardise a matrix by using get_standard_deviation. This all should be done without using numpy.

Now I am getting the following error, I am stuck in this code from many hours now and quite frustrated at the moment . THerefore, any URGENT help will be highly appreciated please?

get_k_nearest_labels('Data.csv','Learning_Data.csv','Learning_Data_Labels.csv',1)
[21:51, 12/24/2018] Nida: Traceback (most recent call last):
File "C:/Users/Nida/Desktop/Nida-CSEE/Python/python-assignment.py", line 87, in <module>
get_k_nearest_labels('Data.csv','Learning_Data.csv','Learning_Data_Labels.csv',1)
File "C:/Users/Nida/Desktop/Nida-CSEE/Python/python-assignment.py", line 84, in get_k_nearest_labels
distance=get_distance(file_open[0],fopen[i])
File "C:/Users/Nida/Desktop/Nida-CSEE/Python/python-assignment.py", line 23, in get_distance
euclidean += pow((test2[i][k]-test1[j][k]),2)
TypeError: unsupported operand type(s) for -: 'str' and 'str'
>>>

Following is my script.

import csv

def load_from_csv(filename):
    
    with open(filename,'r') as csvfile:
        readCSV=list(csv.reader(csvfile,delimiter=','))
        for row in readCSV:           
         return readCSV

print('Data from "Data.csv" file :',load_from_csv('Data.csv'))           


import math
def get_distance(test1,test2):
    euclidean = 0

    euclidean_list_complete = []

    for i in range(len(test2)):
        euclidean_list = []
        for j in range(len(test1)):
            for k in range(len(test1[0])):
                euclidean += pow((test2[i][k]-test1[j][k]),2)      
            euclidean_list.append(math.sqrt(euclidean))
            euclidean = 0
            euclidean_list.sort(reverse=True)
        euclidean_list_complete.append(euclidean_list)
        del euclidean_list

    print ('Euclidean Distance between two matrix :\n',euclidean_list_complete)
get_distance([[2,3,5],[12,3,5],[2,3,6]],[[1,2,3],[3,4,6],[4,5,8]])


import statistics

def get_standard_deviation(matrix, col):
    
    #list1=matrix
    #print(list1)
    #print(matrix.columns.values)
    i=col-1
    new_list=[item[i] for item in matrix]
    result= statistics.stdev(new_list)
    return result
print('The Standard Deviation of the elements in the column number passed as a parameter :',get_standard_deviation([[2,5,8],[4,8,2]],1))



def ave(matrix):
    average=sum(matrix)/len(matrix)
    print('Average of a matrix :',average)
    #print(ave[2,3,4])
    


def get_standardised_matrix(matrix):
    
    col = 0
    i = 0
    getdeviation=get_standard_deviation(matrix, col)
    mycolunmlist = []
    while i < len(matrix):
        mycolunmlist.append(matrix[i][col])
        i += 1
    print('My colunm List :',mycolunmlist)
    for i in range(len(mycolunmlist)):
        #print(matrix[i][col])
        standard =(matrix[i][col]-ave(mycolunmlist))/get_standard_deviation(matrix, col)
        matrix.insert(matrix[i][col],standard)
        
    print('standardised matrix is :',matrix)
    #not working
#print('The standardised matrix',get_standardised_matrix([[2,5,8],[4,8,2]]))



def get_k_nearest_labels(rowmatrix, matrix, new_matrix, k):
    file_open=load_from_csv(rowmatrix)
    print(file_open[0])
    fopen=load_from_csv(matrix)
    newfile=load_from_csv(new_matrix)
    rowmatrix[0]
    for i in range(len(fopen)):
        print(fopen[i])
        distance=get_distance(file_open[0],fopen[i])
        print(distance)