import pandas as pd
from apriori_new import * #導(dǎo)入自行編寫的apriori函數(shù)
import time #導(dǎo)入時(shí)間庫(kù)用來(lái)計(jì)算用時(shí)
import re
import random
import pandas as pd
# 自定義關(guān)聯(lián)規(guī)則算法
def connect_string(x, ms):
 x = list(map(lambda i: sorted(i.split(ms)), x))
 l = len(x[0])
 r = []
 # 生成二項(xiàng)集
 for i in range(len(x)):
  for j in range(i, len(x)):
#if x[i][l-1] != x[j][l-1]:
if x[i][:l - 1] == x[j][:l - 1] and x[i][l - 1] != x[j][
 l - 1]:  # 判斷數(shù)字和字母異同，初次取字母數(shù)字不全相同（即不同癥狀（字母），或同一證型程度不同（數(shù)字））
 r.append(x[i][:l - 1] + sorted([x[j][l - 1], x[i][l - 1]]))
 return r
# 尋找關(guān)聯(lián)規(guī)則的函數(shù)
def find_rule(d, support, confidence, ms=u'--'):
 result = pd.DataFrame(index=['support', 'confidence'])  # 定義輸出結(jié)果
 support_series = 1.0 * d.sum() / len(d)  # 支持度序列
 column = list(support_series[support_series > support].index)  # 初步根據(jù)支持度篩選,符合條件支持度，共 276個(gè)index證型
 k = 0
 while len(column) > 1:  # 隨著項(xiàng)集元素增多 可計(jì)算的column（滿足條件支持度的index）會(huì)被窮盡，隨著證型增多，之間的關(guān)系會(huì)越來(lái)越不明顯，（同時(shí)發(fā)生可能性是小概率了）
  k = k + 1
  print(u'\n正在進(jìn)行第%s次搜索...' % k)
  column = connect_string(column, ms)
  print(u'數(shù)目：%s...' % len(column))
  sf = lambda i: d[i].prod(axis=1, numeric_only=True)  # 新一批支持度的計(jì)算函數(shù)
  len(d)
  # 創(chuàng)建連接數(shù)據(jù)，這一步耗時(shí)、耗內(nèi)存最嚴(yán)重。當(dāng)數(shù)據(jù)集較大時(shí)，可以考慮并行運(yùn)算優(yōu)化。
  # 依次對(duì)column每個(gè)元素（如[['A1', 'A2'], ['A1', 'A3']]中的['A1', 'A2']）運(yùn)算，計(jì)算data_model_中對(duì)應(yīng)該行的乘積，930個(gè)，若['A1', 'A2']二者同時(shí)發(fā)生為1則此行積為1
  d_2 = pd.DataFrame(list(map(sf, column)),index=[ms.join(i) for i in column]).T  # list(map(sf,column)) 276X930  index 276
  support_series_2 = 1.0 * d_2[[ms.join(i) for i in column]].sum() / len(d)  # 計(jì)算連接后的支持度
  column = list(support_series_2[support_series_2 > support].index)  # 新一輪支持度篩選
  support_series = support_series.append(support_series_2)
  column2 = []
  for i in column:  # 遍歷可能的推理，如{A,B,C}究竟是A+B-->C還是B+C-->A還是C+A-->B？
i = i.split(ms)  # 由'A1--B1' 轉(zhuǎn)化為 ['A1', 'B1']
for j in range(len(i)):  #
 column2.append(i[:j] + i[j + 1:] + i[j:j + 1])
  cofidence_series = pd.Series(index=[ms.join(i) for i in column2])  # 定義置信度序列
  for i in column2:  # 計(jì)算置信度序列  如i為['B1', 'A1']
# i置信度計(jì)算：i的支持度除以第一個(gè)證型的支持度，表示第一個(gè)發(fā)生第二個(gè)發(fā)生的概率
cofidence_series[ms.join(i)] = support_series[ms.join(sorted(i))] / support_series[ms.join(i[:len(i) - 1])]
  for i in cofidence_series[cofidence_series > confidence].index:  # 置信度篩選
result[i] = 0.0  # B1--A1 0.330409  A1--B1 0.470833,絕大部分是要剔除掉的，初次全剔除
result[i]['confidence'] = cofidence_series[i]
result[i]['support'] = support_series[ms.join(sorted(i.split(ms)))]
 result = result.T.sort_values(by=['confidence', 'support'],ascending=False)  # 結(jié)果整理，輸出,先按confidence升序，再在confidence內(nèi)部按support升序，默認(rèn)升序，此處降序
 return result

sku_list = [
 '0000001','0000002','0000003','0000004','0000005',
 '0000006','0000007','0000008','0000009','0000010',
 '0000011','0000012','0000013','0000014','0000015',
 '0000016','0000017','0000018','0000019','0000020',
 'A0000001','A0000002','A0000003','A0000004','A0000005',
 'A0000006','A0000007','A0000008','A0000009','A0000010',
 'A0000011','A0000012','A0000013','A0000014','A0000015',
 'A0000016','A0000017','A0000018','A0000019','A0000020',
]
# 隨機(jī)抽取數(shù)據(jù)生成列表
mat = [ random.sample(sku_list, random.randint(2,5))  for i in range(100)]
data = pd.DataFrame(mat,columns=["A","B","C","D","E"])
data = pd.get_dummies(data) # 轉(zhuǎn)換類別變量矩陣
data = data.fillna(0)

support = 0.01 #最小支持度
confidence = 0.05 #最小置信度
ms = '---' #連接符，默認(rèn)'--'，用來(lái)區(qū)分不同元素，如A--B。需要保證原始表格中不含有該字符
start = time.clock() #計(jì)時(shí)開(kāi)始
print(u'\n開(kāi)始搜索關(guān)聯(lián)規(guī)則...')
print(find_rule(data, support, confidence, ms))
end = time.clock() #計(jì)時(shí)結(jié)束
print(u'\n搜索完成，用時(shí)：%0.2f秒' %(end-start))