Attribute Error: how to resolve it?

Hi
I want to run code in python for prediction of urban expansion but I am getting the following error:
Traceback (most recent call last):
File “”, line 1, in
File “”, line 5, in init
AttributeError: ‘landcover’ object has no attribute ‘performChecks’
code is as follows:
#Defining class to read land cover file of two time periods
class landcover():
def init(self, file1, file2):
self.ds_lc1, self.arr_lc1 = readraster(file1)
self.ds_lc2, self.arr_lc2 = readraster(file2)
self.performChecks()
def performChecks(self):
#check the rows and columns of input land cover datasets
print(“Checking the size of input rasters…”)
if (self.ds_lc1.RasterXSize == self.ds_lc2.RasterXSize) and (self.ds_lc1.RasterYSize == self.ds_lc2.RasterYSize):
print(“Land cover data size matched.”)
self.row, self.col = (self.ds_lc1.RasterYSize, self.ds_lc1.RasterXSize)
else:
print(“Input land cover files have different height and width.”)
#Check the number of classes in input land cover images
print("\nChecking feature classes in land cover data…")
if (self.arr_lc1.max() == self.arr_lc2.max()) and (self.arr_lc1.min() == self.arr_lc2.min()):
print(“The classes in input land cover files are matched.”)
self.nFeature = (self.arr_lc1.max() - self.arr_lc1.min())
else:
print(“Input land cover data have different class values/ size.”)

def transitionMatrix(self):
    self.tMatrix = np.random.randint(1, size=(self.nFeature, self.nFeature))
    for x in range(0,self.row):
        for y in range(0,self.col):
            t1_pixel = self.arr_lc1[x,y]
            t2_pixel = self.arr_lc2[x,y]
            self.tMatrix[t1_pixel-1, t2_pixel-1] += 1
    self.tMatrixNorm = np.random.randint(1, size=(4,5)).astype(float)
    print("\nTransition Matrix computed, normalisation in progress..")
    #Creating normalised transition matrix
    for x in range(0, self.tMatrix.shape[0]):
        for y in range(0, self.tMatrix.shape[1]):
            self.tMatrixNorm[x,y] = self.tMatrix[x,y]/(self.tMatrix[x,:]).sum()

Any help would be highly appreciated