1+ {
2+ "nbformat" : 4 ,
3+ "nbformat_minor" : 0 ,
4+ "metadata" : {
5+ "colab" : {
6+ "name" : " eclat.ipynb"
7+ "provenance" : [],
8+ "collapsed_sections" : [],
9+ "toc_visible" : true
10+ },
11+ "kernelspec" : {
12+ "name" : " python3"
13+ "display_name" : " Python 3"
14+ }
15+ },
16+ "cells" : [
17+ {
18+ "cell_type" : " markdown"
19+ "metadata" : {
20+ "id" : " 1fziHl7Ar94J"
21+ },
22+ "source" : [
23+ " # Eclat"
24+ ]
25+ },
26+ {
27+ "cell_type" : " markdown"
28+ "metadata" : {
29+ "id" : " eiNwni1xsEgT"
30+ },
31+ "source" : [
32+ " ## Importing the libraries"
33+ ]
34+ },
35+ {
36+ "cell_type" : " code"
37+ "metadata" : {
38+ "id" : " DUF77Qr1vqyM"
39+ "outputId" : " 34b8aa55-2acb-4995-fd1a-681a5f38fbc4"
40+ "colab" : {
41+ "base_uri" : " https://localhost:8080/"
42+ "height" : 188
43+ }
44+ },
45+ "source" : [
46+ " !pip install apyori"
47+ ],
48+ "execution_count" : 1 ,
49+ "outputs" : [
50+ {
51+ "output_type" : " stream"
52+ "text" : [
53+ " Collecting apyori\n "
54+ " Downloading https://files.pythonhosted.org/packages/5e/62/5ffde5c473ea4b033490617ec5caa80d59804875ad3c3c57c0976533a21a/apyori-1.1.2.tar.gz\n "
55+ " Building wheels for collected packages: apyori\n "
56+ " Building wheel for apyori (setup.py) ... \u001b [?25l\u001b [?25hdone\n "
57+ " Created wheel for apyori: filename=apyori-1.1.2-cp36-none-any.whl size=5975 sha256=8f53091a20bda1c225ea3b1f2e0b370cda3bbd00dbc94685b752fa3c2f044d26\n "
58+ " Stored in directory: /root/.cache/pip/wheels/5d/92/bb/474bbadbc8c0062b9eb168f69982a0443263f8ab1711a8cad0\n "
59+ " Successfully built apyori\n "
60+ " Installing collected packages: apyori\n "
61+ " Successfully installed apyori-1.1.2\n "
62+ ],
63+ "name" : " stdout"
64+ }
65+ ]
66+ },
67+ {
68+ "cell_type" : " code"
69+ "metadata" : {
70+ "id" : " UJfitBClsJlT"
71+ },
72+ "source" : [
73+ " import numpy as np\n "
74+ " import matplotlib.pyplot as plt\n "
75+ " import pandas as pd"
76+ ],
77+ "execution_count" : 2 ,
78+ "outputs" : []
79+ },
80+ {
81+ "cell_type" : " markdown"
82+ "metadata" : {
83+ "id" : " vLt-7XUKsXBd"
84+ },
85+ "source" : [
86+ " ## Data Preprocessing"
87+ ]
88+ },
89+ {
90+ "cell_type" : " code"
91+ "metadata" : {
92+ "id" : " J_A-UFOAsaDf"
93+ },
94+ "source" : [
95+ " dataset = pd.read_csv('Market_Basket_Optimisation.csv', header = None)\n "
96+ " transactions = []\n "
97+ " for i in range(0, 7501):\n "
98+ " transactions.append([str(dataset.values[i,j]) for j in range(0, 20)])"
99+ ],
100+ "execution_count" : 4 ,
101+ "outputs" : []
102+ },
103+ {
104+ "cell_type" : " markdown"
105+ "metadata" : {
106+ "id" : " 1wYZdBd5sea_"
107+ },
108+ "source" : [
109+ " ## Training the Eclat model on the dataset"
110+ ]
111+ },
112+ {
113+ "cell_type" : " code"
114+ "metadata" : {
115+ "id" : " YzIk4vXZsj5i"
116+ },
117+ "source" : [
118+ " from apyori import apriori\n "
119+ " rules = apriori(transactions = transactions, min_support = 0.003, min_confidence = 0.2, min_lift = 3, min_length = 2, max_length = 2)"
120+ ],
121+ "execution_count" : 5 ,
122+ "outputs" : []
123+ },
124+ {
125+ "cell_type" : " markdown"
126+ "metadata" : {
127+ "id" : " b176YNwWspiO"
128+ },
129+ "source" : [
130+ " ## Visualising the results"
131+ ]
132+ },
133+ {
134+ "cell_type" : " markdown"
135+ "metadata" : {
136+ "id" : " iO6bF_dImT-E"
137+ },
138+ "source" : [
139+ " ### Displaying the first results coming directly from the output of the apriori function"
140+ ]
141+ },
142+ {
143+ "cell_type" : " code"
144+ "metadata" : {
145+ "id" : " kvF-sLc6ifhd"
146+ },
147+ "source" : [
148+ " results = list(rules)"
149+ ],
150+ "execution_count" : 6 ,
151+ "outputs" : []
152+ },
153+ {
154+ "cell_type" : " code"
155+ "metadata" : {
156+ "id" : " eAD8Co4_l9IE"
157+ "outputId" : " 2f6d5b69-9be2-454b-ac7e-728a15dab23e"
158+ "colab" : {
159+ "base_uri" : " https://localhost:8080/"
160+ "height" : 188
161+ }
162+ },
163+ "source" : [
164+ " results"
165+ ],
166+ "execution_count" : 7 ,
167+ "outputs" : [
168+ {
169+ "output_type" : " execute_result"
170+ "data" : {
171+ "text/plain" : [
172+ " [RelationRecord(items=frozenset({'light cream', 'chicken'}), support=0.004532728969470737, ordered_statistics=[OrderedStatistic(items_base=frozenset({'light cream'}), items_add=frozenset({'chicken'}), confidence=0.29059829059829057, lift=4.84395061728395)]),\n "
173+ " RelationRecord(items=frozenset({'mushroom cream sauce', 'escalope'}), support=0.005732568990801226, ordered_statistics=[OrderedStatistic(items_base=frozenset({'mushroom cream sauce'}), items_add=frozenset({'escalope'}), confidence=0.3006993006993007, lift=3.790832696715049)]),\n "
174+ " RelationRecord(items=frozenset({'escalope', 'pasta'}), support=0.005865884548726837, ordered_statistics=[OrderedStatistic(items_base=frozenset({'pasta'}), items_add=frozenset({'escalope'}), confidence=0.3728813559322034, lift=4.700811850163794)]),\n "
175+ " RelationRecord(items=frozenset({'fromage blanc', 'honey'}), support=0.003332888948140248, ordered_statistics=[OrderedStatistic(items_base=frozenset({'fromage blanc'}), items_add=frozenset({'honey'}), confidence=0.2450980392156863, lift=5.164270764485569)]),\n "
176+ " RelationRecord(items=frozenset({'herb & pepper', 'ground beef'}), support=0.015997866951073192, ordered_statistics=[OrderedStatistic(items_base=frozenset({'herb & pepper'}), items_add=frozenset({'ground beef'}), confidence=0.3234501347708895, lift=3.2919938411349285)]),\n "
177+ " RelationRecord(items=frozenset({'ground beef', 'tomato sauce'}), support=0.005332622317024397, ordered_statistics=[OrderedStatistic(items_base=frozenset({'tomato sauce'}), items_add=frozenset({'ground beef'}), confidence=0.3773584905660377, lift=3.840659481324083)]),\n "
178+ " RelationRecord(items=frozenset({'olive oil', 'light cream'}), support=0.003199573390214638, ordered_statistics=[OrderedStatistic(items_base=frozenset({'light cream'}), items_add=frozenset({'olive oil'}), confidence=0.20512820512820515, lift=3.1147098515519573)]),\n "
179+ " RelationRecord(items=frozenset({'olive oil', 'whole wheat pasta'}), support=0.007998933475536596, ordered_statistics=[OrderedStatistic(items_base=frozenset({'whole wheat pasta'}), items_add=frozenset({'olive oil'}), confidence=0.2714932126696833, lift=4.122410097642296)]),\n "
180+ " RelationRecord(items=frozenset({'shrimp', 'pasta'}), support=0.005065991201173177, ordered_statistics=[OrderedStatistic(items_base=frozenset({'pasta'}), items_add=frozenset({'shrimp'}), confidence=0.3220338983050847, lift=4.506672147735896)])]"
181+ ]
182+ },
183+ "metadata" : {
184+ "tags" : []
185+ },
186+ "execution_count" : 7
187+ }
188+ ]
189+ },
190+ {
191+ "cell_type" : " markdown"
192+ "metadata" : {
193+ "id" : " MFkQP-fcjDBC"
194+ },
195+ "source" : [
196+ " ### Putting the results well organised into a Pandas DataFrame"
197+ ]
198+ },
199+ {
200+ "cell_type" : " code"
201+ "metadata" : {
202+ "id" : " gyq7Poi0mMUe"
203+ },
204+ "source" : [
205+ " def inspect(results):\n "
206+ " lhs = [tuple(result[2][0][0])[0] for result in results]\n "
207+ " rhs = [tuple(result[2][0][1])[0] for result in results]\n "
208+ " supports = [result[1] for result in results]\n "
209+ " return list(zip(lhs, rhs, supports))\n "
210+ " resultsinDataFrame = pd.DataFrame(inspect(results), columns = ['Product 1', 'Product 2', 'Support'])"
211+ ],
212+ "execution_count" : 8 ,
213+ "outputs" : []
214+ },
215+ {
216+ "cell_type" : " markdown"
217+ "metadata" : {
218+ "id" : " IjrrlYW4jpTR"
219+ },
220+ "source" : [
221+ " ### Displaying the results sorted by descending supports"
222+ ]
223+ },
224+ {
225+ "cell_type" : " code"
226+ "metadata" : {
227+ "id" : " nI7DJXng-nxQ"
228+ "outputId" : " bbbe4321-f112-4e81-ad32-7c7197d96891"
229+ "colab" : {
230+ "base_uri" : " https://localhost:8080/"
231+ "height" : 314
232+ }
233+ },
234+ "source" : [
235+ " resultsinDataFrame.nlargest(n = 10, columns = 'Support')"
236+ ],
237+ "execution_count" : 9 ,
238+ "outputs" : [
239+ {
240+ "output_type" : " execute_result"
241+ "data" : {
242+ "text/html" : [
243+ " <div>\n "
244+ " <style scoped>\n "
245+ " .dataframe tbody tr th:only-of-type {\n "
246+ " vertical-align: middle;\n "
247+ " }\n "
248+ " \n "
249+ " .dataframe tbody tr th {\n "
250+ " vertical-align: top;\n "
251+ " }\n "
252+ " \n "
253+ " .dataframe thead th {\n "
254+ " text-align: right;\n "
255+ " }\n "
256+ " </style>\n "
257+ " <table border=\" 1\" class=\" dataframe\" >\n "
258+ " <thead>\n "
259+ " <tr style=\" text-align: right;\" >\n "
260+ " <th></th>\n "
261+ " <th>Product 1</th>\n "
262+ " <th>Product 2</th>\n "
263+ " <th>Support</th>\n "
264+ " </tr>\n "
265+ " </thead>\n "
266+ " <tbody>\n "
267+ " <tr>\n "
268+ " <th>4</th>\n "
269+ " <td>herb & pepper</td>\n "
270+ " <td>ground beef</td>\n "
271+ " <td>0.015998</td>\n "
272+ " </tr>\n "
273+ " <tr>\n "
274+ " <th>7</th>\n "
275+ " <td>whole wheat pasta</td>\n "
276+ " <td>olive oil</td>\n "
277+ " <td>0.007999</td>\n "
278+ " </tr>\n "
279+ " <tr>\n "
280+ " <th>2</th>\n "
281+ " <td>pasta</td>\n "
282+ " <td>escalope</td>\n "
283+ " <td>0.005866</td>\n "
284+ " </tr>\n "
285+ " <tr>\n "
286+ " <th>1</th>\n "
287+ " <td>mushroom cream sauce</td>\n "
288+ " <td>escalope</td>\n "
289+ " <td>0.005733</td>\n "
290+ " </tr>\n "
291+ " <tr>\n "
292+ " <th>5</th>\n "
293+ " <td>tomato sauce</td>\n "
294+ " <td>ground beef</td>\n "
295+ " <td>0.005333</td>\n "
296+ " </tr>\n "
297+ " <tr>\n "
298+ " <th>8</th>\n "
299+ " <td>pasta</td>\n "
300+ " <td>shrimp</td>\n "
301+ " <td>0.005066</td>\n "
302+ " </tr>\n "
303+ " <tr>\n "
304+ " <th>0</th>\n "
305+ " <td>light cream</td>\n "
306+ " <td>chicken</td>\n "
307+ " <td>0.004533</td>\n "
308+ " </tr>\n "
309+ " <tr>\n "
310+ " <th>3</th>\n "
311+ " <td>fromage blanc</td>\n "
312+ " <td>honey</td>\n "
313+ " <td>0.003333</td>\n "
314+ " </tr>\n "
315+ " <tr>\n "
316+ " <th>6</th>\n "
317+ " <td>light cream</td>\n "
318+ " <td>olive oil</td>\n "
319+ " <td>0.003200</td>\n "
320+ " </tr>\n "
321+ " </tbody>\n "
322+ " </table>\n "
323+ " </div>"
324+ ],
325+ "text/plain" : [
326+ " Product 1 Product 2 Support\n "
327+ " 4 herb & pepper ground beef 0.015998\n "
328+ " 7 whole wheat pasta olive oil 0.007999\n "
329+ " 2 pasta escalope 0.005866\n "
330+ " 1 mushroom cream sauce escalope 0.005733\n "
331+ " 5 tomato sauce ground beef 0.005333\n "
332+ " 8 pasta shrimp 0.005066\n "
333+ " 0 light cream chicken 0.004533\n "
334+ " 3 fromage blanc honey 0.003333\n "
335+ " 6 light cream olive oil 0.003200"
336+ ]
337+ },
338+ "metadata" : {
339+ "tags" : []
340+ },
341+ "execution_count" : 9
342+ }
343+ ]
344+ }
345+ ]
346+ }
0 commit comments