import numpy
import random
import seaborn as sns
import matplotlib.pyplot as plt

# 狀態空間
states = ["A","G","C","T","E"]

# 可能的事件序列
transitionName = [["AA","AG","AC","AT","AE"],
                  ["GA","GG","GC","GT","GE"],
                  ["CA","CG","CC","CT","CE"],
                  ["TA","TG","TC","TT","TE"],]

# 概率矩陣（轉移矩陣）
transitionMatrix = [[0.25,0.20,0.20,0.20,0.15],
                    [0.20,0.25,0.20,0.20,0.15],
                    [0.20,0.20,0.25,0.20,0.15],
                    [0.20,0.20,0.20,0.25,0.15]]

def RandomDNAs(Num):
    max_len = 0
    i = 0
    Seq = [] #創建列表(Seq)用于添加堿基，以組成DNA序列
    Len = [] #創建列表(Len)用于記錄每條生成序列的長度
    while i != Num:
        Base = ["A","G","C","T"]
        START = random.choice(Base) #隨機從堿基中選擇一個作為序列的起始堿基
        Seq.append(START) #將起始堿基添加至Seq中
        while START != "E":
            if START == "A":
                change = numpy.random.choice(transitionName[0],p=transitionMatrix[0])
                #以transitionMatrix矩陣第一行的概率分布隨機抽取transitionName第一行包含的事件
                if change == "AA":
                    START = "A" #如果轉移狀態是AA(即A堿基接下來的堿基是A，則將起始堿基設為A)
                elif change == "AG":
                    START = "G"
                elif change == "AC":
                    START = "C"
                elif change == "AT":
                    START = "T"
                elif change == "AE":
                    START = "E"
            elif START == "G":
                change = numpy.random.choice(transitionName[1],p=transitionMatrix[1])
                if change == "GA":
                    START = "A"
                elif change == "GG":
                    START = "G"
                elif change == "GC":
                    START = "C"
                elif change == "GT":
                    START = "T"
                elif change == "GE":
                    START = "E"
            elif START == "C":
                change = numpy.random.choice(transitionName[2],p=transitionMatrix[2])
                if change == "CA":
                    START = "A"
                elif change == "CG":
                    START = "G"
                elif change == "CC":
                    START = "C"
                elif change == "CT":
                    START = "T"
                elif change == "CE":
                    START = "E"
            elif START == "T":
                change = numpy.random.choice(transitionName[3],p=transitionMatrix[3])
                if change == "TA":
                    START = "A"
                elif change == "TG":
                    START = "G"
                elif change == "TC":
                    START = "C"
                elif change == "TT":
                    START = "T"
                elif change == "TE":
                    START = "E"
            if START != "E":
                Seq.append(START) #如果狀態轉移后不為End(E)，則將轉移后的堿基加到Seq序列中
        i += 1
        Len.append(len(Seq))
        if len(Seq) > max_len:
            max_len = len(Seq)
        #print(''.join(Seq))
        Seq.clear()
    plt.hist(numpy.array(Len), bins=max_len, edgecolor="white")
    # 顯示橫軸標簽
    plt.xlabel("DNA Sequence Length")
    # 顯示縱軸標簽
    plt.ylabel("Frequency")
    # 顯示圖標題
    plt.title("Histogram of frequency distribution of DNA sequence length")
    plt.show()
    print("DNA序列的最大長度為:",max_len)
    print("DNA序列長度的眾數為:",max(Len, key=Len.count))

%matplotlib notebook #若未使用Jupyter Notebook，此句不需要
RandomDNAs(1000) #1000表示隨機生成1000條序列