Python的pandas库实战进行一个数据处理的工作

下面进行一个目标处理的步骤：将对应满足要求的数据找出来进行处理。

在Excel中完全可以进行但是为了熟悉下pandas中数据框的用法，这里就花点时间试验下；
图片的格式在下方：

主函数：

main.py

import setDF2
import re
import numpy as np
import pandas as pd 
#在data1中找出我们需要的词并输出它们的参数；准备到下次分析

def fuzzyfinder(user_input, collection):
        suggestions = []
        pattern = '.*?'.join(user_input)    # Converts 'djm' to 'd.*?j.*?m'
        regex = re.compile(pattern)         # Compiles a regex.
        for item in collection:
            match = regex.search(item)      # Checks if the current item matches the regex.
            if match:
                suggestions.append((len(match.group()), match.start(), item))
        return [x for _, _, x in sorted(suggestions)]

#去掉 “/n”
def remove_n(l):
    for i in range(len(l)):
        l[i] = l[i].split('
')[0]
    return l

#往一个集合里面添加一个列表里面的all元素(element)
def add_all(c,s):
    for e in c:
        s.add(e)
    return s

#传递进来一个词表，返回匹配的字符串表
def returnAllword(als):
    set_kw = remove_n(open('C:\Users\Administrator\Desktop\word.txt','r+').readlines())
    s = set()   
    for string in set_kw:
        collection = fuzzyfinder(string,als)
        s = add_all(collection,s)
    al = list(s)
    return al

#对字符串进行二次处理，里面的字符串元素必须都是来自我们要求的字符
def exchange2(l):
    set_kw = remove_n(open('C:\Users\Administrator\Desktop\word.txt','r+').readlines())
    aal = []    
    s_e = set(' ')    
    for st in set_kw:
        s_e = add_all(list(st),s_e)
    for e in l:
        if(set(e) & s_e == set(e)):
            aal.append(e)
    return aal

#已知搜索词，提取数据框中的对应数据
def returnListIndex(bl):
    list_all = data1.搜索词
    list_index = []    
    for i in range(len(data1)):
        if(list_all[i] in bl):
            list_index.append(str(i))
    return list_index

'''step1: 500关键词中寻找搜索词对应的搜索词和我们对应的词条有关的词'''
file = 'F:\By\August\160816\热搜探究\0816_ws1.csv'
data1 = setDF2.setDF2(file)

bl = exchange2(returnAllword(data1.搜索词))
list_index = returnListIndex(bl)
da = np.array(bl)
da.shape = len(da),1
df = pd.DataFrame(da,index = da,columns = ['条件词'])

data2 = pd.DataFrame(data1,index = list_index)

''' step2:选取商城点击率较高 且 搜索人气>200的椅子//点击率'''
re_index = []
for i in np.arange(1,len(data2)):
    swap = pd.DataFrame(data1,index = [data1.index[i]])
    if((float(swap.搜索人气)> 200) & (float(swap.商城点击占比) > 0.40) & (float(swap.直通车参考价) < 2.57)):
        re_index.append(str(i))
    else:
        pass
ddv = pd.DataFrame(data1,index = re_index)
print (ddv)               #print()满足条件的所有df中的关键词

'''step3:将目标写出到本地'''
ddv.to_csv('C:\Users\Administrator\Desktop\result_word.csv')

辅助函数setDF2.py

#等同于pandas.read_csv
import pandas as pd  
import numpy as np  
  
def strToD(x):  
    str1 = x.split('
')[0]  
    return str1  
   
def setDF2(file):     
    strings = open(file,'r+').readlines()  
    open(file,'r+').close()  
    names = [];  
    data = []  
    columes = [];  
    for string1 in strings[1:len(strings)]:  
        hang = string1.split(',')  
        for element in np.arange(0,len(hang)):  
            hang[element] = strToD(hang[element])  
        if(string1 == strings[1]):  
            columes = string1.split(',')[1:len(string1)]
            columes[len(columes) - 1] =  strToD(columes[len(columes) - 1])
        else:  
            data.extend(hang[1:len(hang)])  
            names.append(hang[0])
    dd = np.array(data)  
    dd.shape = len(names),len(columes)  
    df = pd.DataFrame(dd,names,columes)  
    
    return df  

ps:那个桌面文档的TXT就是根据特征选的关键字了；；