class node:

    def __init__(self):

        self.subtree = []



class decisionTree:

    def __init__(self):

        self.raw_data = []

        self.raw_data_lines = 0

        self.a = []

        self.a_num = 0



    def load_data(self, path):

        fp = open(path, "r")

        lines = 0



        line = fp.readline()

        line = line[0:-1]

        line = line.split(",")

        for i in line[1:-1]:

            self.a.append(i)

        self.a_num = len(self.a)

        while True:

            line = fp.readline()

            if line == "":

                break

            line = line[0:-1]

            line = line.split(",")

            self.raw_data.append(line)

            lines+=1



        self.raw_data_lines = lines



    def get_lines(self):

        return self.raw_data_lines



    def tree_generate(self, D, A, node):

        tc = {}

        for i in D:

            _c = self.raw_data[i][7]

            if not _c in tc:

                tc[_c] = 0

            tc[_c] += 1

        max_i = ""

        for i in tc:

            if max_i == "":

                max_i = i

            if tc[max_i] < tc[i]:

                max_i = i

        _max_c = tc[max_i]



        c = ""

        for i in D:

            if c == "":

                c = self.raw_data[i][7]

            if self.raw_data[i][7] != c:

                c = ""

                break

        if c!= "":

            node["C"] = c

            node["leaf"] = 1

            return



        c = ""

        for j in A:

            c = ""

            for i in D:

                if c == "":

                    c = self.raw_data[i][7]

                if self.raw_data[i][7] != c:

                    c = ""

                    break

            if c == "":

                break



        if c != "" or len(A) == 0:

            node["C"] = _max_c

            node["leaf"] = 1

            return



        

        AV = []

        for i in A:

            AV.append(i)



        a_star = AV.pop()

        ta = []

        for i in D:

            _a = self.raw_data[i][a_star]

            if not _a in ta:

                ta.append(_a)



        for _a_star_v in ta:

            DV = []

            for i in D:

                if self.raw_data[i][a_star] == _a_star_v:

                    DV.append(i)



            new_node = {"D":DV, "A":AV, "AS":_a_star_v, "C": 0, "child":[], "leaf":0}

            node["child"].append(new_node)

            if len(DV) == 0:

                new_node["C"] = _max_c

                new_node["leaf"] = 1

                return

            else:

                self.tree_generate(DV, AV, new_node)



    def show_tree(self, node, tab, col):

        star_leaf = ""

        if node["leaf"] == 1:

            star_leaf = "*"



        if col == 0:

            print(tab, "Class:",node["C"], node["AS"], " ",  star_leaf)

        if col == 1:

            print(tab, "Class:",node["C"], " A[", node["A"], "]", star_leaf)

        if col == 2:

            print(tab, "Class:",node["C"], " D[", node["D"], "]", star_leaf)



        for child in node["child"]:

            self.show_tree(child, tab+"\t", col)



dt = decisionTree()

dt.load_data("../dataset/data3.0.csv")



D = [ i for i in range(dt.raw_data_lines) ]

A = [ i for i in range(1, dt.a_num+1) ]





node = {"D":D, "A":A, "AS":"", "C": 0, "child":[], "leaf":0}

dt.tree_generate(D, A, node)



dt.show_tree(node, "", 0)

dt.show_tree(node, "", 1)

dt.show_tree(node, "", 2)