1 # -*- coding: utf-8 -*-
2 """
3 Created on Wed Feb 22 10:56:39 2023
4
5 @author: admin
6 """
7
8 #代码8-1
9 import numpy as np
10 import pandas as pd
11
12 inputfile = 'D:/anaconda/data/GoodsOrder.csv'
13 data = pd.read_csv(inputfile,encoding='gbk')
14 data.info()
15
16 data = data['id']
17 description = [data.count(),data.min(),data.max()]
18 description = pd.DataFrame(description,index=['Count','Min','Max']).T
19 print('描述性统计结果：\n',np.round(description))
20
21 #代码8-2
22 import pandas as pd
23 inputfile = 'D:/anaconda/data/GoodsOrder.csv'
24 data = pd.read_csv(inputfile,encoding='gbk')
25 group = data.groupby(['Goods']).count().reset_index()
26 sorted = group.sort_values('id',ascending=False)
27 print('销售排行前10商品的销量：\n',sorted[:10])
28
29 import matplotlib.pyplot as plt
30 x = sorted[:10]['Goods']
31 y = sorted[:10]['id']
32 plt.figure(figsize=(8,4))
33 plt.barh(x,y)
34 plt.rcParams['font.sans-serif'] = 'SimHei'
35 plt.xlabel('销量')
36 plt.ylabel('商品类别')
37 plt.title('商品的销量TOP10学号2020310143040')
38 plt.savefig('D:/anaconda/data/top10.png')
39 plt.show()
40
41 data_nums = data.shape[0]
42 for idnex,row in sorted[:10].iterrows():
43 print(row['Goods'],row['id'],row['id']/data_nums)
44
45
46
47 #代码8-3
48 import pandas as pd
49 inputfile1 = 'D:/anaconda/data/GoodsOrder.csv'
50 inputfile2 = 'D:/anaconda/data/GoodsTypes.csv'
51 data = pd.read_csv(inputfile1,encoding='gbk')
52 types = pd.read_csv(inputfile2,encoding='gbk')
53
54 group = data.groupby(['Goods']).count().reset_index()
55 sort = group.sort_values('id',ascending=False).reset_index()
56 data_nums = data.shape[0]
57 del sort['index']
58
59 sort_links = pd.merge(sort,types)
60
61 sort_link = sort_links.groupby(['Types']).sum().reset_index()
62 sort_link = sort_link.sort_values('id',ascending=False).reset_index()
63 del sort_link['index']
64
65 sort_link['count'] = sort_link.apply(lambda line:line['id']/data_nums,axis=1)
66 sort_link.rename(columns={'count':'percent'},inplace=True)
67 print('各类别商品的销量及其占比学号2020310143040：\n',sort_link)
68 outfile1 = 'D:/anaconda/data/percent.csv'
69 sort_link.to_csv(outfile1,index=False,header=True,encoding='gbk')
70
71 import matplotlib.pyplot as plt
72 data = sort_link['percent']
73 labels = sort_link['Types']
74 plt.figure(figsize=(8,6))
75 plt.pie(data,labels=labels,autopct='%1.2f%%')
76 plt.rcParams['font.sans-serif'] = 'SimHei'
77 plt.title('每类商品销售占比学号2020310143040')
78 plt.savefig('D:/anaconda/data/percent.png')
79 plt.show()
80
81 #代码8-4
82 selected = sort_links.loc[sort_links['Types'] == '非酒精饮料']
83 child_nums = selected['id'].sum()
84 selected['child_percent'] = selected.apply(lambda line:line['id']/child_nums,axis=1)
85 selected.rename(columns={'id':'count'},inplace=True)
86 print('非酒精饮料内部商品的销量及其占比：\n',selected)
87 outfile2 = 'D:/anaconda/data/child_percent.csv'
88 sort_link.to_csv(outfile2,index=False,header=True,encoding='gbk')
89
90 import matplotlib.pyplot as plt
91 data = selected['child_percent']
92 labels = selected['Goods']
93 plt.figure(figsize=(8,6))
94 explode = (0.02,0.03,0.04,0.05,0.06,0.07,0.08,0.08,0.3,0.1,0.3)
95
96 plt.pie(data,explode=explode,labels=labels,autopct='%1.2f%%',pctdistance=1.1,labeldistance=1.2)
97 plt.rcParams['font.sans-serif'] = 'SimHei'
98 plt.title("非酒精饮料内部各商品的销售占比学号2020310143040")
99 plt.axis('equal')
100 plt.savefig('D:/anaconda/data/child_persent.png')
101 plt.show()
102
103
104 import pandas as pd
105 inputfile = 'D:/anaconda/data/GoodsOrder.csv'
106 data = pd.read_csv(inputfile,encoding='gbk')
107
108 data['Goods'] = data['Goods'].apply(lambda x:','+x)
109 data = data.groupby('Goods').sum().reset_index()
110 data
111
112 data['Goods'] = data['Goods'].apply(lambda x:[x[1:]])
113 data_list = list(data['Goods'])
114 data_list[:5]
115
116 data_translation = []
117 for i in data_list:
118 p=i[0].split(',')
119 data_translation.append(p)
120 print('数据转换结果的前5个元素：\n',data_translation[0:5])
121
122 from numpy import *
123
124 def loadDataSet():
125 return [['a', 'c', 'e'], ['b', 'd'], ['b', 'c'], ['a', 'b', 'c', 'd'], ['a', 'b'], ['b', 'c'], ['a', 'b'],
126 ['a', 'b', 'c', 'e'], ['a', 'b', 'c'], ['a', 'c', 'e']]
127
128 def createC1(dataSet):
129 C1 = []
130 for transaction in dataSet:
131 for item in transaction:
132 if not [item] in C1:
133 C1.append([item])
134 C1.sort()
135 # 映射为frozenset唯一性的，可使用其构造字典
136 return list(map(frozenset, C1))
137
138 # 从候选K项集到频繁K项集（支持度计算）
139 def scanD(D, Ck, minSupport):
140 ssCnt = {}
141 for tid in D: # 遍历数据集
142 for can in Ck: # 遍历候选项
143 if can.issubset(tid): # 判断候选项中是否含数据集的各项
144 if not can in ssCnt:
145 ssCnt[can] = 1 # 不含设为1
146 else:
147 ssCnt[can] += 1 # 有则计数加1
148 numItems = float(len(D)) # 数据集大小
149 retList = [] # L1初始化
150 supportData = {} # 记录候选项中各个数据的支持度
151 for key in ssCnt:
152 support = ssCnt[key] / numItems # 计算支持度
153 if support >= minSupport:
154 retList.insert(0, key) # 满足条件加入L1中
155 supportData[key] = support
156 return retList, supportData
157
158 def calSupport(D, Ck, min_support):
159 dict_sup = {}
160 for i in D:
161 for j in Ck:
162 if j.issubset(i):
163 if not j in dict_sup:
164 dict_sup[j] = 1
165 else:
166 dict_sup[j] += 1
167 sumCount = float(len(D))
168 supportData = {}
169 relist = []
170 for i in dict_sup:
171 temp_sup = dict_sup[i] / sumCount
172 if temp_sup >= min_support:
173 relist.append(i)
174 # 此处可设置返回全部的支持度数据（或者频繁项集的支持度数据）
175 supportData[i] = temp_sup
176 return relist, supportData
177
178 # 改进剪枝算法
179 def aprioriGen(Lk, k):
180 retList = []
181 lenLk = len(Lk)
182 for i in range(lenLk):
183 for j in range(i + 1, lenLk): # 两两组合遍历
184 L1 = list(Lk[i])[:k - 2]
185 L2 = list(Lk[j])[:k - 2]
186 L1.sort()
187 L2.sort()
188 if L1 == L2: # 前k-1项相等，则可相乘，这样可防止重复项出现
189 # 进行剪枝（a1为k项集中的一个元素，b为它的所有k-1项子集）
190 a = Lk[i] | Lk[j] # a为frozenset()集合
191 a1 = list(a)
192 b = []
193 # 遍历取出每一个元素，转换为set，依次从a1中剔除该元素，并加入到b中
194 for q in range(len(a1)):
195 t = [a1[q]]
196 tt = frozenset(set(a1) - set(t))
197 b.append(tt)
198 t = 0
199 for w in b:
200 # 当b（即所有k-1项子集）都是Lk（频繁的）的子集，则保留，否则删除。
201 if w in Lk:
202 t += 1
203 if t == len(b):
204 retList.append(b[0] | b[1])
205 return retList
206
207 def apriori(dataSet, minSupport=0.2):
208 # 前3条语句是对计算查找单个元素中的频繁项集
209 C1 = createC1(dataSet)
210 D = list(map(set, dataSet)) # 使用list()转换为列表
211 L1, supportData = calSupport(D, C1, minSupport)
212 L = [L1] # 加列表框，使得1项集为一个单独元素
213 k = 2
214 while (len(L[k - 2]) > 0): # 是否还有候选集
215 Ck = aprioriGen(L[k - 2], k)
216 Lk, supK = scanD(D, Ck, minSupport) # scan DB to get Lk
217 supportData.update(supK) # 把supk的键值对添加到supportData里
218 L.append(Lk) # L最后一个值为空集
219 k += 1
220 del L[-1] # 删除最后一个空集
221 return L, supportData # L为频繁项集，为一个列表，1，2，3项集分别为一个元素
222
223 # 生成集合的所有子集
224 def getSubset(fromList, toList):
225 for i in range(len(fromList)):
226 t = [fromList[i]]
227 tt = frozenset(set(fromList) - set(t))
228 if not tt in toList:
229 toList.append(tt)
230 tt = list(tt)
231 if len(tt) > 1:
232 getSubset(tt, toList)
233
234 def calcConf(freqSet, H, supportData, ruleList, minConf=0.7):
235 for conseq in H: #遍历H中的所有项集并计算它们的可信度值
236 conf = supportData[freqSet] / supportData[freqSet - conseq] # 可信度计算，结合支持度数据
237 # 提升度lift计算lift = p(a & b) / p(a)*p(b)
238 lift = supportData[freqSet] / (supportData[conseq] * supportData[freqSet - conseq])
239
240 if conf >= minConf and lift > 1:
241 print(freqSet - conseq, '-->', conseq, '支持度', round(supportData[freqSet], 6), '置信度：', round(conf, 6),
242 'lift值为：', round(lift, 6))
243 ruleList.append((freqSet - conseq, conseq, conf))
244
245 # 生成规则
246 def gen_rule(L, supportData, minConf = 0.7):
247 bigRuleList = []
248 for i in range(1, len(L)): # 从二项集开始计算
249 for freqSet in L[i]: # freqSet为所有的k项集
250 # 求该三项集的所有非空子集，1项集，2项集，直到k-1项集，用H1表示，为list类型,里面为frozenset类型，
251 H1 = list(freqSet)
252 all_subset = []
253 getSubset(H1, all_subset) # 生成所有的子集
254 calcConf(freqSet, all_subset, supportData, bigRuleList, minConf)
255 return bigRuleList
256
257 if __name__ == '__main__':
258 dataSet = data_translation
259 L, supportData = apriori(dataSet, minSupport = 0.02)
260 rule = gen_rule(L, supportData, minConf = 0.35)
261
262 selected = sort_links.loc[sort_links['Types'] == '西点']
263 child_nums = selected['id'].sum()
264 selected['child_percent'] = selected.apply(lambda line:line['id']/child_nums,axis=1)
265 selected.rename(columns={'id':'count'},inplace=True)
266 print('西点类商品的销量及其占比：\n',selected)
267 outfile3 = 'D:/anaconda/data/child_percent.csv'
268 sort_link.to_csv(outfile3,index=False,header=True,encoding='gbk')
269
270 import matplotlib.pyplot as plt
271 data = selected['child_percent']
272 labels = selected['Goods']
273 plt.figure(figsize=(8,6))
274 explode = (0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03)
275
276 plt.pie(data,explode=explode,labels=labels,autopct='%1.2f%%',pctdistance=1.1,labeldistance=1.2)
277 plt.rcParams['font.sans-serif'] = 'SimHei'
278 plt.title("西点类各商品的销售占比学号2020310143040")
279 plt.axis('equal')
280 plt.savefig('D:/anaconda/data/child_persent_西点.png')
281 plt.show()
# -*- coding: utf-8 -*-"""Created on Wed Feb 22 10:56:39 2023
@author: admin"""
#代码8-1import numpy as npimport pandas as pd
inputfile = 'D:/anaconda/data/GoodsOrder.csv'data = pd.read_csv(inputfile,encoding='gbk')data.info()
data = data['id']description = [data.count(),data.min(),data.max()]description = pd.DataFrame(description,index=['Count','Min','Max']).Tprint('描述性统计结果：\n',np.round(description))
#代码8-2import pandas as pdinputfile = 'D:/anaconda/data/GoodsOrder.csv'data = pd.read_csv(inputfile,encoding='gbk')group = data.groupby(['Goods']).count().reset_index()sorted = group.sort_values('id',ascending=False)print('销售排行前10商品的销量：\n',sorted[:10])
import matplotlib.pyplot as pltx = sorted[:10]['Goods']y = sorted[:10]['id']plt.figure(figsize=(8,4))plt.barh(x,y)plt.rcParams['font.sans-serif'] = 'SimHei'plt.xlabel('销量')plt.ylabel('商品类别')plt.title('商品的销量TOP10学号2020310143040')plt.savefig('D:/anaconda/data/top10.png')plt.show()
data_nums = data.shape[0]for idnex,row in sorted[:10].iterrows(): print(row['Goods'],row['id'],row['id']/data_nums)
#代码8-3import pandas as pdinputfile1 = 'D:/anaconda/data/GoodsOrder.csv'inputfile2 = 'D:/anaconda/data/GoodsTypes.csv'data = pd.read_csv(inputfile1,encoding='gbk')types = pd.read_csv(inputfile2,encoding='gbk')
group = data.groupby(['Goods']).count().reset_index()sort = group.sort_values('id',ascending=False).reset_index()data_nums = data.shape[0]del sort['index']
sort_links = pd.merge(sort,types)
sort_link = sort_links.groupby(['Types']).sum().reset_index()sort_link = sort_link.sort_values('id',ascending=False).reset_index()del sort_link['index']
sort_link['count'] = sort_link.apply(lambda line:line['id']/data_nums,axis=1)sort_link.rename(columns={'count':'percent'},inplace=True)print('各类别商品的销量及其占比学号2020310143040：\n',sort_link)outfile1 = 'D:/anaconda/data/percent.csv'sort_link.to_csv(outfile1,index=False,header=True,encoding='gbk')
import matplotlib.pyplot as pltdata = sort_link['percent']labels = sort_link['Types']plt.figure(figsize=(8,6))plt.pie(data,labels=labels,autopct='%1.2f%%')plt.rcParams['font.sans-serif'] = 'SimHei'plt.title('每类商品销售占比学号2020310143040')plt.savefig('D:/anaconda/data/percent.png')plt.show()
#代码8-4selected = sort_links.loc[sort_links['Types'] == '非酒精饮料']child_nums = selected['id'].sum()selected['child_percent'] = selected.apply(lambda line:line['id']/child_nums,axis=1)selected.rename(columns={'id':'count'},inplace=True)print('非酒精饮料内部商品的销量及其占比：\n',selected)outfile2 = 'D:/anaconda/data/child_percent.csv'sort_link.to_csv(outfile2,index=False,header=True,encoding='gbk')
import matplotlib.pyplot as pltdata = selected['child_percent']labels = selected['Goods']plt.figure(figsize=(8,6))explode = (0.02,0.03,0.04,0.05,0.06,0.07,0.08,0.08,0.3,0.1,0.3)
plt.pie(data,explode=explode,labels=labels,autopct='%1.2f%%',pctdistance=1.1,labeldistance=1.2)plt.rcParams['font.sans-serif'] = 'SimHei'plt.title("非酒精饮料内部各商品的销售占比学号2020310143040")plt.axis('equal')plt.savefig('D:/anaconda/data/child_persent.png')plt.show()
import pandas as pdinputfile = 'D:/anaconda/data/GoodsOrder.csv'data = pd.read_csv(inputfile,encoding='gbk')
data['Goods'] = data['Goods'].apply(lambda x:','+x)data = data.groupby('Goods').sum().reset_index()data
data['Goods'] = data['Goods'].apply(lambda x:[x[1:]])data_list = list(data['Goods'])data_list[:5]
data_translation = []for i in data_list: p=i[0].split(',') data_translation.append(p)print('数据转换结果的前5个元素：\n',data_translation[0:5])
from numpy import * def loadDataSet(): return [['a', 'c', 'e'], ['b', 'd'], ['b', 'c'], ['a', 'b', 'c', 'd'], ['a', 'b'], ['b', 'c'], ['a', 'b'], ['a', 'b', 'c', 'e'], ['a', 'b', 'c'], ['a', 'c', 'e']] def createC1(dataSet): C1 = [] for transaction in dataSet: for item in transaction: if not [item] in C1: C1.append([item]) C1.sort() # 映射为frozenset唯一性的，可使用其构造字典 return list(map(frozenset, C1))
# 从候选K项集到频繁K项集（支持度计算）def scanD(D, Ck, minSupport): ssCnt = {} for tid in D: # 遍历数据集 for can in Ck: # 遍历候选项 if can.issubset(tid): # 判断候选项中是否含数据集的各项 if not can in ssCnt: ssCnt[can] = 1 # 不含设为1 else: ssCnt[can] += 1 # 有则计数加1 numItems = float(len(D)) # 数据集大小 retList = [] # L1初始化 supportData = {} # 记录候选项中各个数据的支持度 for key in ssCnt: support = ssCnt[key] / numItems # 计算支持度 if support >= minSupport: retList.insert(0, key) # 满足条件加入L1中 supportData[key] = support return retList, supportData
def calSupport(D, Ck, min_support): dict_sup = {} for i in D: for j in Ck: if j.issubset(i): if not j in dict_sup: dict_sup[j] = 1 else: dict_sup[j] += 1 sumCount = float(len(D)) supportData = {} relist = [] for i in dict_sup: temp_sup = dict_sup[i] / sumCount if temp_sup >= min_support: relist.append(i) # 此处可设置返回全部的支持度数据（或者频繁项集的支持度数据） supportData[i] = temp_sup return relist, supportData
# 改进剪枝算法def aprioriGen(Lk, k): retList = [] lenLk = len(Lk) for i in range(lenLk): for j in range(i + 1, lenLk): # 两两组合遍历 L1 = list(Lk[i])[:k - 2] L2 = list(Lk[j])[:k - 2] L1.sort() L2.sort() if L1 == L2: # 前k-1项相等，则可相乘，这样可防止重复项出现 # 进行剪枝（a1为k项集中的一个元素，b为它的所有k-1项子集） a = Lk[i] | Lk[j] # a为frozenset()集合 a1 = list(a) b = [] # 遍历取出每一个元素，转换为set，依次从a1中剔除该元素，并加入到b中 for q in range(len(a1)): t = [a1[q]] tt = frozenset(set(a1) - set(t)) b.append(tt) t = 0 for w in b: # 当b（即所有k-1项子集）都是Lk（频繁的）的子集，则保留，否则删除。 if w in Lk: t += 1 if t == len(b): retList.append(b[0] | b[1]) return retList
def apriori(dataSet, minSupport=0.2):# 前3条语句是对计算查找单个元素中的频繁项集 C1 = createC1(dataSet) D = list(map(set, dataSet)) # 使用list()转换为列表 L1, supportData = calSupport(D, C1, minSupport) L = [L1] # 加列表框，使得1项集为一个单独元素 k = 2 while (len(L[k - 2]) > 0): # 是否还有候选集 Ck = aprioriGen(L[k - 2], k) Lk, supK = scanD(D, Ck, minSupport) # scan DB to get Lk supportData.update(supK) # 把supk的键值对添加到supportData里 L.append(Lk) # L最后一个值为空集 k += 1 del L[-1] # 删除最后一个空集 return L, supportData # L为频繁项集，为一个列表，1，2，3项集分别为一个元素
# 生成集合的所有子集def getSubset(fromList, toList): for i in range(len(fromList)): t = [fromList[i]] tt = frozenset(set(fromList) - set(t)) if not tt in toList: toList.append(tt) tt = list(tt) if len(tt) > 1: getSubset(tt, toList)
def calcConf(freqSet, H, supportData, ruleList, minConf=0.7): for conseq in H: #遍历H中的所有项集并计算它们的可信度值 conf = supportData[freqSet] / supportData[freqSet - conseq] # 可信度计算，结合支持度数据 # 提升度lift计算lift = p(a & b) / p(a)*p(b) lift = supportData[freqSet] / (supportData[conseq] * supportData[freqSet - conseq]) if conf >= minConf and lift > 1: print(freqSet - conseq, '-->', conseq, '支持度', round(supportData[freqSet], 6), '置信度：', round(conf, 6), 'lift值为：', round(lift, 6)) ruleList.append((freqSet - conseq, conseq, conf)) # 生成规则def gen_rule(L, supportData, minConf = 0.7): bigRuleList = [] for i in range(1, len(L)): # 从二项集开始计算 for freqSet in L[i]: # freqSet为所有的k项集 # 求该三项集的所有非空子集，1项集，2项集，直到k-1项集，用H1表示，为list类型,里面为frozenset类型， H1 = list(freqSet) all_subset = [] getSubset(H1, all_subset) # 生成所有的子集 calcConf(freqSet, all_subset, supportData, bigRuleList, minConf) return bigRuleList if __name__ == '__main__': dataSet = data_translation L, supportData = apriori(dataSet, minSupport = 0.02) rule = gen_rule(L, supportData, minConf = 0.35) selected = sort_links.loc[sort_links['Types'] == '西点']child_nums = selected['id'].sum()selected['child_percent'] = selected.apply(lambda line:line['id']/child_nums,axis=1)selected.rename(columns={'id':'count'},inplace=True)print('西点类商品的销量及其占比：\n',selected)outfile3 = 'D:/anaconda/data/child_percent.csv'sort_link.to_csv(outfile3,index=False,header=True,encoding='gbk')
import matplotlib.pyplot as pltdata = selected['child_percent']labels = selected['Goods']plt.figure(figsize=(8,6))explode = (0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03,0.03)
plt.pie(data,explode=explode,labels=labels,autopct='%1.2f%%',pctdistance=1.1,labeldistance=1.2)plt.rcParams['font.sans-serif'] = 'SimHei'plt.title("西点类各商品的销售占比学号2020310143040")plt.axis('equal')plt.savefig('D:/anaconda/data/child_persent_西点.png')plt.show() 标签：sort,plt,0.03,supportData,关联,商品,规则,csv,data From： https://www.cnblogs.com/i3wood/p/17234039.html