-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path05-association-rule-learning.Rmd
179 lines (127 loc) · 3.92 KB
/
05-association-rule-learning.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
# Association Rule Learning
## Apriori
### Importing the libraries
**Python**
```{python}
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
```
### Data Preprocessing
**Python**
```{python}
dataset = pd.read_csv('Market_Basket_Optimisation.csv', header = None)
transactions = []
for i in range(0, 7501):
transactions.append([str(dataset.values[i,j]) for j in range(0, 20)])
```
**R**
```{r}
# install.packages('arules')
library(arules)
dataset = read.csv('Market_Basket_Optimisation.csv', header = FALSE)
dataset = read.transactions('Market_Basket_Optimisation.csv', sep = ',', rm.duplicates = TRUE)
summary(dataset)
itemFrequencyPlot(dataset, topN = 10)
```
### Training the Apriori model on the dataset
**Python**
Run the following command in the terminal to install the apyori package: pip install apyori
```{python}
from apyori import apriori
rules = apriori(transactions = transactions, min_support = 0.003, min_confidence = 0.2, min_lift = 3, min_length = 2, max_length = 2)
```
**R**
```{r}
rules = apriori(data = dataset, parameter = list(support = 0.004, confidence = 0.2))
```
### Visualising the results
**Python**
Displaying the first results coming directly from the output of the apriori function:
```{python}
results = list(rules)
results
```
Putting the results well organised into a Pandas DataFrame:
```{python}
def inspect(results):
lhs = [tuple(result[2][0][0])[0] for result in results]
rhs = [tuple(result[2][0][1])[0] for result in results]
supports = [result[1] for result in results]
confidences = [result[2][0][2] for result in results]
lifts = [result[2][0][3] for result in results]
return list(zip(lhs, rhs, supports, confidences, lifts))
resultsinDataFrame = pd.DataFrame(inspect(results), columns = ['Left Hand Side', 'Right Hand Side', 'Support', 'Confidence', 'Lift'])
```
Displaying the results non sorted:
```{python}
resultsinDataFrame
```
Displaying the results sorted by descending lifts:
```{python}
resultsinDataFrame.nlargest(n = 10, columns = 'Lift')
```
**R**
```{r}
inspect(sort(rules, by = 'lift')[1:10])
```
## Eclat
Run the following command in the terminal to install the apyori package: pip install apyori
### Importing the libraries
**Python**
```{python}
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
```
### Data Preprocessing
**Python**
```{python}
dataset = pd.read_csv('Market_Basket_Optimisation.csv', header = None)
transactions = []
for i in range(0, 7501):
transactions.append([str(dataset.values[i,j]) for j in range(0, 20)])
```
**R**
```{r}
# install.packages('arules')
library(arules)
dataset = read.csv('Market_Basket_Optimisation.csv')
dataset = read.transactions('Market_Basket_Optimisation.csv', sep = ',', rm.duplicates = TRUE)
summary(dataset)
itemFrequencyPlot(dataset, topN = 10)
```
### Training the Eclat model on the dataset
**Python**
```{python}
from apyori import apriori
rules = apriori(transactions = transactions, min_support = 0.003, min_confidence = 0.2, min_lift = 3, min_length = 2, max_length = 2)
```
**R**
```{r}
rules = eclat(data = dataset, parameter = list(support = 0.003, minlen = 2))
```
### Visualising the results
**Python**
Displaying the first results coming directly from the output of the apriori function:
```{python}
results = list(rules)
results
```
Putting the results well organised into a Pandas DataFrame:
```{python}
def inspect(results):
lhs = [tuple(result[2][0][0])[0] for result in results]
rhs = [tuple(result[2][0][1])[0] for result in results]
supports = [result[1] for result in results]
return list(zip(lhs, rhs, supports))
resultsinDataFrame = pd.DataFrame(inspect(results), columns = ['Product 1', 'Product 2', 'Support'])
```
Displaying the results sorted by descending supports:
```{python}
resultsinDataFrame.nlargest(n = 10, columns = 'Support')
```
**R**
```{r}
inspect(sort(rules, by = 'support')[1:10])
```