Python程序设计~数据处理学习

1.read file

infile = open(fileName,'r')#for line in infile:#遍历文件listVar = [line.rstrip() for line in infile]将每一行生成列表strVar =  infile.read()#读取文件全部内容置于一个字符串strVar = infile.readline()#读取当前指针指向的那一行，刚开始是置于文件第一行，执行语句后，将置于末尾。准备读取下一行infile.close()#close file

Test.txt文件中内容如下GoogleBaiduYahoo其实是以下的方式Google\nBaidu\nYahoo\n

2.create file

outfile = open(fileName,'w')outfile.write(strVar)outfile.writelines(strVar)#file.write(str)的参数是一个字符串，就是你要写入文件的内容.#file.writelines(sequence)的参数是序列，比如列表，它会迭代帮你写入文件.outfile.close()

3.opened for append

outfile = open(fileName,'a')#打开文件在文件末尾添加outfile.write(strVar)outfile.writelines(strVar)outfile.close()

4.set
list列表是元素的顺序存储容器，而且允许元素重复
set集合是元素的无序存储容器，不允许元素重复

{"spam","ni"},{3,4,7},{True,7,"eleven"},{'a','b',(3,4)}#以上都是set#集合操作word = {"spam","ni"}set.add()#word.add("eggs")#words = {"spam","ni","eggs"}set.discard()#discard丢弃，抛弃; 解雇; 出牌;word.discard("ni")words = {"spam"}set.clear()#words.clear() words = {}set#set([3,7,3])#{3,7}set#set((3,7,3))#{7,3}

{x*x for x in range(-3,3)}#{0,1,4,9}set1.union(set2)#set1∪set2set1.intersection(set2)#set1∩set2set1.difference(set2)#set1-set2

File1.txtAlphaBravoCharlieFile2.txtBravoDeltadef main():    infile = open("File1.txt",'r')    firstSet = {line.rstrip() for line in infile}    infile.close()    infile = open("File2.txt",'r')    firstSet = {line.rstrip() for line in infile}    infile.close()    outfile = open("Union.txt",'w')    outfile.writelines(set1.union(set2))    outfile.close()    outfile = open("Intersection.txt",'w')    outfile.writelines(set1.intersection(set2))    outfile.close()    outfile = open("Difference.txt",'w')    outfile.writelines(set1.difference(set2))    outfile.close()main()Union.txt#Alpha,Bravo,Charlie,DeltaIntersection.txt#BravoDifference.txt#Alpha,Charlie

5.csv文件
将数据以逗号分隔（当然也可以不是逗号）
譬如csvDemo.csv
name,passwd,age,address
zhangsan,123456,15,sichuang
lisi，45612,15，jiangshu
可以在excel中打开

UN.txtCanada,North America,34.8,385500France,Europe,66.3,211209New Zealand,Austrlia/Oceania,4.4,103738Nigeria,Africa,177.2,356669Pakistan,Asia,196.2,310403Peru,South America,30.1,496226#-----------------def main():continent = input("Enter the name of a continent:")continent = continent.title()#Allow for all lowercase lettersif continent != 'Antarctica':    infile = open("UN.txt",'r')    for line in infile:        data = line.split(',')        if data[1] == continent:            print(data[0])else:    print("There are no counteries in Antarctica")#-------Enter the name of a continent:North AmericaCanada

6.dict字典

bob = {"firstName":"Robert","lastName":"Smith","age":19}print(bob["firstName"],bob["lastName"],"is",bob["age"],"years old.")[RUN]Robert Smith is 19 years old.

dict操作

len(d)#字典中元素(键值对)的个数x in d#如果x是字典的一个键，返回Truex:y in d#如果x:y是字典中的元素，返回True#not ind[key1] = value1#返回key1对应的值，否者抛出异常d.get(key1,default)#如果存在key1则返回value1，否者返回defaultlist(d.keys())#返回字典键组成的listlist(d.values())#返回字典值组成的listlist(d.items())#返回(key,value)形成的二元组组成的列表，其中d[key]=valuelist(d)#set(d)#tuple(d)#返回字典的键组成的列表，集合，元组c = {}#创建一个字典c = dict(d)#创建字典d的一个拷贝d.update(c)#将字典c所有的元素合并入字典d。如果两个元素拥有相同的键，则使用c中的值替换d中的值

实例

eg 1:def translate(color):#英语翻译成意大利语    if color == "red":        return "rojo"    elif color == "blue":        return "aloz"    elif color == "green":        return "verdi"    elif color == "white":        return "blanco"#-----translate = {"red":"rojo","blue":"aloz","green":"verdi","white":"blanco"}eg 2:list1 = [["one",1],["two",2],["three",3]]或list1 = [("one",1),("two",2),("three",3)]dict(list1){"one":1,"two":2,"three":3}eg 3:Textese.txtanyone,neiare,rate,8band,b&be,b#-----def main():    texteseDict = createDictionary("Textese.txt")    print("Enter a simple sentence in lowercase letters without")    sentence = input("any punctuation: ")    print()    translate(sentence,texteseDict)def createDictionary(fileName):    infile = open(fileName,'r')    textList = [line.rstrip() for line in infile]    infile.close()    return dict([var.split(',') for var in textList])def translate(sentence,texteseDict):    words = sentence.split()    for word in words:        print(texteseDict.get(word,word)+" ",end = " ")main()

---

耗时2h写好