2/18/25, 10:33 PM Untitled
Name: Sahil Govind chaudhari
Rol no: TI2134
In [37]: import pandas as pd
In [38]: from mlxtend.frequent_patterns import apriori,association_rules
Q1.
In [6]: dataset=[['Bread','Milk'],['Bread','Diaper','Beer','Eggs'],['Milk','Diaper','Bee
['Bread','Milk','Diaper','Beer'],['Bread','Milk','Diaper','Coke']]
In [7]: dataset
Out[7]: [['Bread', 'Milk'],
['Bread', 'Diaper', 'Beer', 'Eggs'],
['Milk', 'Diaper', 'Beer', 'Coke'],
['Bread', 'Milk', 'Diaper', 'Beer'],
['Bread', 'Milk', 'Diaper', 'Coke']]
In [14]: from mlxtend.preprocessing import TransactionEncoder
te=TransactionEncoder()
te_array=te.fit(dataset).transform(dataset)
df=pd.DataFrame(te_array,columns=te.columns_)
df
Out[14]: Beer Bread Coke Diaper Eggs Milk
0 False True False False False True
1 True True False True True False
2 True False True True False True
3 True True False True False True
4 False True True True False True
In [15]: freq_items=apriori(df,min_support=0.5,use_colnames=True)
print(freq_items)
support itemsets
0 0.6 (Beer)
1 0.8 (Bread)
2 0.8 (Diaper)
3 0.8 (Milk)
4 0.6 (Diaper, Beer)
5 0.6 (Bread, Diaper)
6 0.6 (Bread, Milk)
7 0.6 (Diaper, Milk)
In [18]: rule=association_rules(freq_items,metric='confidence',min_threshold=0.5)
print(rule)
file:///C:/Users/91982/Downloads/Untitled (1).html 1/4
2/18/25, 10:33 PM Untitled
antecedents consequents antecedent support consequent support support \
0 (Diaper) (Beer) 0.8 0.6 0.6
1 (Beer) (Diaper) 0.6 0.8 0.6
2 (Bread) (Diaper) 0.8 0.8 0.6
3 (Diaper) (Bread) 0.8 0.8 0.6
4 (Bread) (Milk) 0.8 0.8 0.6
5 (Milk) (Bread) 0.8 0.8 0.6
6 (Diaper) (Milk) 0.8 0.8 0.6
7 (Milk) (Diaper) 0.8 0.8 0.6
confidence lift representativity leverage conviction zhangs_metric \
0 0.75 1.2500 1.0 0.12 1.6 1.00
1 1.00 1.2500 1.0 0.12 inf 0.50
2 0.75 0.9375 1.0 -0.04 0.8 -0.25
3 0.75 0.9375 1.0 -0.04 0.8 -0.25
4 0.75 0.9375 1.0 -0.04 0.8 -0.25
5 0.75 0.9375 1.0 -0.04 0.8 -0.25
6 0.75 0.9375 1.0 -0.04 0.8 -0.25
7 0.75 0.9375 1.0 -0.04 0.8 -0.25
jaccard certainty kulczynski
0 0.75 0.375 0.875
1 0.75 1.000 0.875
2 0.60 -0.250 0.750
3 0.60 -0.250 0.750
4 0.60 -0.250 0.750
5 0.60 -0.250 0.750
6 0.60 -0.250 0.750
7 0.60 -0.250 0.750
Q2.
In [21]: dataset=[['User1','KGF','Salaar','Pushpa'],['User2','Toxic','Salaar','Bahubali']
['User4','KGF','Salaar','Bahubali','Pushpa'],['User5','Salaar','Bahubal
dataset
Out[21]: [['User1', 'KGF', 'Salaar', 'Pushpa'],
['User2', 'Toxic', 'Salaar', 'Bahubali'],
['User3', 'KGF', 'Toxic', 'Salaar'],
['User4', 'KGF', 'Salaar', 'Bahubali', 'Pushpa'],
['User5', 'Salaar', 'Bahubali', 'Pushpa']]
In [22]: te=TransactionEncoder()
te_array=te.fit(dataset).transform(dataset)
df=pd.DataFrame(te_array,columns=te.columns_)
df
Out[22]: Bahubali KGF Pushpa Salaar Toxic User1 User2 User3 User4 User5
0 False True True True False True False False False False
1 True False False True True False True False False False
2 False True False True True False False True False False
3 True True True True False False False False True False
4 True False True True False False False False False True
file:///C:/Users/91982/Downloads/Untitled (1).html 2/4
2/18/25, 10:33 PM Untitled
In [35]: freq_items=apriori(df,min_support=0.5,use_colnames=True)
print(freq_items)
support itemsets
0 0.6 (Bahubali)
1 0.6 (KGF)
2 0.6 (Pushpa)
3 1.0 (Salaar)
4 0.6 (Salaar, Bahubali)
5 0.6 (Salaar, KGF)
6 0.6 (Salaar, Pushpa)
In [36]: rules=association_rules(freq_items,metric='confidence',min_threshold=0.5)
print(rule)
antecedents consequents antecedent support consequent support \
4 (Toxic) (Bahubali) 0.4 0.6
12 (Toxic) (KGF) 0.4 0.6
27 (Toxic) (User2) 0.4 0.2
30 (Toxic) (User3) 0.4 0.2
32 (Bahubali, Pushpa) (KGF) 0.4 0.6
.. ... ... ... ...
10 (Salaar) (KGF) 1.0 0.6
16 (Salaar) (Pushpa) 1.0 0.6
3 (Bahubali) (Salaar) 0.6 1.0
11 (KGF) (Salaar) 0.6 1.0
17 (Pushpa) (Salaar) 0.6 1.0
support confidence lift representativity leverage conviction \
4 0.2 0.5 0.833333 1.0 -0.04 0.8
12 0.2 0.5 0.833333 1.0 -0.04 0.8
27 0.2 0.5 2.500000 1.0 0.12 1.6
30 0.2 0.5 2.500000 1.0 0.12 1.6
32 0.2 0.5 0.833333 1.0 -0.04 0.8
.. ... ... ... ... ... ...
10 0.6 0.6 1.000000 1.0 0.00 1.0
16 0.6 0.6 1.000000 1.0 0.00 1.0
3 0.6 1.0 1.000000 1.0 0.00 inf
11 0.6 1.0 1.000000 1.0 0.00 inf
17 0.6 1.0 1.000000 1.0 0.00 inf
zhangs_metric jaccard certainty kulczynski
4 -0.25 0.25 -0.250 0.416667
12 -0.25 0.25 -0.250 0.416667
27 1.00 0.50 0.375 0.750000
30 1.00 0.50 0.375 0.750000
32 -0.25 0.25 -0.250 0.416667
.. ... ... ... ...
10 0.00 0.60 0.000 0.800000
16 0.00 0.60 0.000 0.800000
3 0.00 0.60 0.000 0.800000
11 0.00 0.60 0.000 0.800000
17 0.00 0.60 0.000 0.800000
[226 rows x 14 columns]
C:\Users\91982\anaconda3\Lib\site-packages\mlxtend\frequent_patterns\association_
rules.py:186: RuntimeWarning: invalid value encountered in divide
cert_metric = np.where(certainty_denom == 0, 0, certainty_num / certainty_deno
m)
file:///C:/Users/91982/Downloads/Untitled (1).html 3/4
2/18/25, 10:33 PM Untitled
In [ ]:
file:///C:/Users/91982/Downloads/Untitled (1).html 4/4
