市场篮子分析:数据编码与Apriori算法应用
1. 事务数据特征与数据编码
1.1 数据处理代码示例
在处理事务数据时,首先需要对数据进行排序和编码。以下是一段Python代码示例,用于对事务数据进行排序和编码:
# 2. sort items in alphabetical order
list_nondup_sort_items = sorted(list(set(list_dup_unsort_items)))
# initialize DataFrame with all elements having False value
# name the columns the elements of list_dup_unsort_items
manual_df = pandas.DataFrame(
False,
index=range(len(ll)),
columns=list_dup_unsort_items
)
# change False to True if element is in individual transaction list
# each row is represents the contains of an individual transaction
# (sublist from the original list of lists)
for i in range(len(ll)):
for j in ll[i]:
manual_df.loc[i, j] = True
# return the True/False
Apriori算法与市场篮子分析
超级会员免费看
订阅专栏 解锁全文
1170

被折叠的 条评论
为什么被折叠?



