Apriori算法在购物篮分析中的运用

　　购物篮分析是一个很经典的数据挖掘案例,运用到了Apriori算法。下面从网上下载的一超市某月份的数据库,利用Apriori算法进行管理分析。例子使用Python+MongoDB

　　处理过程1 数据建模(将Excel中的数据写入到MongoDB数据库), 2 从数据库中读取数据进行分析。

　　Excel文件http://download.csdn.net/detail/artscrafts/6805689

　　案例配置文件 setting.py

 data_source = 'supermarket.xls'
 host = 'localhost'
 port = 27017
 db_name = 'shopping_basket'
 items_name = 'goods_items'
 record_name = 'transaction_record'

　　读取Excel数据到MongoDB中 load_basket.py

 from xlrd import open_workbook
 from pymongo import MongoClient
 import setting
 
 wb = open_workbook(setting.data_source, encoding_override='utf-8')
 client = MongoClient(setting.host, setting.port)
 db = client[setting.db_name]
 items = []
 
 #read xls
 def read_one_line(workbook, sheet_index=0, row_index=0, start_col_index=0):
     sheet = workbook.sheets()[0]
     max_row = sheet.nrows
     max_col = sheet.ncols
     start_col_index = (start_col_index if (start_col_index > 0 and start_col_index <= max_col) else max_col)
     if row_index < 0 or row_index >= max_row:
         raise IndexError()
     for col_index in xrange(start_col_index, max_col):
         yield sheet.cell(row_index, col_index).value
 
 #read xls
 def readlines(workbook, sheet_index=0, start_row_index=0, end_row_index=None, start_col_index=0, end_col_index=None):
     sheet = workbook.sheets()[sheet_index]
     max_row = sheet.nrows
     max_col = sheet.ncols
     end_row_index = (end_row_index if end_row_index  else max_row)
     end_col_index = (end_col_index if end_col_index  else max_col)
     for row_index in xrange(start_row_index, end_row_index):
         yield [sheet.cell(row_index, col_index).value for col_index in xrange(start_col_index, end_col_index)]
 
 #from xls to mongodb
 def load_items():
     collection = db[setting.items_name]
     items_line = read_one_line(wb, row_index=1, start_col_index=1)
     id = 1
     tmp = []
     for item in items_line:
         if id % 100 == 0:
             collection.insert(tmp)
             tmp = []
         tmp.append({'id':id, 'name':item})
         items.append(item)
         id += 1
 
 # from xls to mongodb
 def load_record():
     collection = db[setting.record_name]
     lines = readlines(wb,start_row_index=2, start_col_index = 1)
     tmp = []
     id = 1
     for line in lines:
         if id % 100 == 0:
             collection.insert(tmp)
             tmp = []
         tmp.append({'id':id, 'items':[items[i] for i in xrange(len(line)) if line[i] == 'T']})
         id += 1
 
 def main():
     print '........start loading........'
     load_items()
     load_record()
     client.close()
     print '.........end loading.........'
 
 if __name__ == '__main__':
     main()

　　进行数据分析 analysis_basket.py

 #Apriori
 from pymongo import MongoClient
 import setting
 
 client = MongoClient(setting.host, setting.port)
 db = client[setting.db_name]
 data = []
 
 #from mongodb to items
 def filldata():
     collection = db[setting.record_name]
     cur = collection.find()
     for row in cur:
         data.append(row['items'])
 
 def connect(items):
     result = {}
     keys = items.keys()
     length = len(keys)
     for i in range(length):
         prev = keys[i][:len(keys[i]) - 1]
         for j in range(i + 1, length):
             tmp = keys[j][:len(keys[j]) - 1]
             if prev == tmp:
                 key = keys[i] + (keys[j][len(keys[i]) - 1],)
                 result[key] = getsupp(key)
             else:
                 break
     return result
 
 def pruning(items, minsupp):
     result = {}
     for key in items.keys():
         if items[key] >= minsupp:
             result[key] = items[key]
     return result
 
 def contain(par, sub):
     for v in sub:
         if not v in par:
             return False
     return True
 
 def getsupp(item):
     supp = 0
     for row in data:
         if contain(row, item):
             supp+=1
     return supp
 
 def apriori(data, minsupp, k):
     candidate_set = {}
     for row in data:
         for i in row:
             key = (i,)
             candidate_set[key] = candidate_set.get(key, 0) + 1
     frequently_set = pruning(candidate_set, minsupp)
     result = {}
     result['k=1'] = frequently_set
     for n in range(2, k):
         candidate_set = connect(frequently_set)
         frequently_set = pruning(candidate_set, minsupp)
         if len(frequently_set) <= 1:
             return result
         result['K=' + str(n)] = frequently_set
     return result
 
 def main():
     filldata()
     client.close()
     res = apriori(data, 30, 8)
 
 if __name__ == '__main__':
     main()