#
#  Classify Template 
#
#  Finish the code for the method, nearestNeighbor
#
#  Code file for the book Programmer's Guide to Data Mining
#  http://guidetodatamining.com
#
#  Ron Zacharski
#



class Classifier:

    def __init__(self, filename):

        self.medianAndDeviation = []
        
        # reading the data in from the file
        f = open(filename)
        lines = f.readlines()
        f.close()
        self.format = lines[0].strip().split('\t')
        self.data = []
        for line in lines[1:]:
            fields = line.strip().split('\t')
            ignore = []
            vector = []
            for i in range(len(fields)):
                if self.format[i] == 'num':
                    vector.append(int(fields[i]))
                elif self.format[i] == 'comment':
                    ignore.append(fields[i])
                elif self.format[i] == 'class':
                    classification = fields[i]
            self.data.append((classification, vector, ignore))
        self.rawData = list(self.data)
        # get length of instance vector
        self.vlen = len(self.data[0][1])
        # now normalize the data
        for i in range(self.vlen):
            self.normalizeColumn(i)
        

        
    
    ##################################################
    ###
    ###  CODE TO COMPUTE THE MODIFIED STANDARD SCORE

    def getMedian(self, alist):
        """return median of alist"""
        if alist == []:
            return []
        blist = sorted(alist)
        length = len(alist)
        if length % 2 == 1:
            # length of list is odd so return middle element
            return blist[int(((length + 1) / 2) -  1)]
        else:
            # length of list is even so compute midpoint
            v1 = blist[int(length / 2)]
            v2 =blist[(int(length / 2) - 1)]
            return (v1 + v2) / 2.0
        

    def getAbsoluteStandardDeviation(self, alist, median):
        """given alist and median return absolute standard deviation"""
        sum = 0
        for item in alist:
            sum += abs(item - median)
        return sum / len(alist)


    def normalizeColumn(self, columnNumber):
       """given a column number, normalize that column in self.data"""
       # first extract values to list
       col = [v[1][columnNumber] for v in self.data]
       median = self.getMedian(col)
       asd = self.getAbsoluteStandardDeviation(col, median)
       #print("Median: %f   ASD = %f" % (median, asd))
       self.medianAndDeviation.append((median, asd))
       for v in self.data:
           v[1][columnNumber] = (v[1][columnNumber] - median) / asd


    def normalizeVector(self, v):
        """We have stored the median and asd for each column.
        We now use them to normalize vector v"""
        vector = list(v)
        for i in range(len(vector)):
            (median, asd) = self.medianAndDeviation[i]
            vector[i] = (vector[i] - median) / asd
        return vector

    
    ###
    ### END NORMALIZATION
    ##################################################



    def manhattan(self, vector1, vector2):
        """Computes the Manhattan distance."""
        return sum(map(lambda v1, v2: abs(v1 - v2), vector1, vector2))


    def nearestNeighbor(self, itemVector):
        """return nearest neighbor to itemVector"""
        
        return ((0, ("REPLACE THIS LINE WITH CORRECT RETURN", [0], [])))
    
    def classify(self, itemVector):
        """Return class we think item Vector is in"""
        return(self.nearestNeighbor(self.normalizeVector(itemVector))[1][0])
 

def unitTest():
    classifier = Classifier('athletesTrainingSet.txt')
    br = ('Basketball', [72, 162], ['Brittainey Raven'])
    nl = ('Gymnastics', [61, 76], ['Viktoria Komova'])
    cl = ("Basketball", [74, 190], ['Crystal Langhorne'])
    # first check normalize function
    brNorm = classifier.normalizeVector(br[1])
    nlNorm = classifier.normalizeVector(nl[1])
    clNorm = classifier.normalizeVector(cl[1])
    assert(brNorm == classifier.data[1][1])
    assert(nlNorm == classifier.data[-1][1])
    print('normalizeVector fn OK')
    # check distance
    assert (round(classifier.manhattan(clNorm, classifier.data[1][1]), 5) == 1.16823)
    assert(classifier.manhattan(brNorm, classifier.data[1][1]) == 0)
    assert(classifier.manhattan(nlNorm, classifier.data[-1][1]) == 0)
    print('Manhattan distance fn OK')
    # Brittainey Raven's nearest neighbor should be herself
    result = classifier.nearestNeighbor(brNorm)
    assert(result[1][2]== br[2])
    # Nastia Liukin's nearest neighbor should be herself
    result = classifier.nearestNeighbor(nlNorm)
    assert(result[1][2]== nl[2])
    # Crystal Langhorne's nearest neighbor is Jennifer Lacy"
    assert(classifier.nearestNeighbor(clNorm)[1][2][0] == "Jennifer Lacy")
    print("Nearest Neighbor fn OK")
    # Check if classify correctly identifies sports
    assert(classifier.classify(br[1]) == 'Basketball')
    assert(classifier.classify(cl[1]) == 'Basketball')
    assert(classifier.classify(nl[1]) == 'Gymnastics')
    print('Classify fn OK')



unitTest()