apriori VDT 2 - 31 Hoang Tran Nhat Minh

apriori.py

import pprint
import pandas as pd

PATH_TO_CSV = r"C:\Users\nhatm\OneDrive - Hanoi University of Science and Technology\Desktop\groceries.csv"
MIN_SUPPORT = 12


def get_frequent_itemsets(transactions, min_support):
    # Count the occurrence of each item
    item_counts = {}
    for transaction in transactions:
        for item in transaction:
            if item in item_counts:
                item_counts[item] += 1
            else:
                item_counts[item] = 1

    # Discard infrequent items
    frequent_items = {frozenset([item]) for item, count in item_counts.items()
                      if count >= min_support}

    # Generate candidate itemsets
    itemsets = frequent_items.copy()
    k = 2
    while True:
        candidate_itemsets = set([itemset1.union(itemset2)
                                  for itemset1 in itemsets
                                  for itemset2 in itemsets
                                  if len(itemset1.union(itemset2)) == k])
        if not candidate_itemsets:
            break

        # Count the occurrence of each candidate itemset
        itemset_counts = dict.fromkeys(candidate_itemsets, 0)
        for transaction in transactions:
            for itemset in candidate_itemsets:
                if itemset.issubset(transaction):
                    itemset_counts[itemset] += 1

        # Discard infrequent itemsets
        frequent_itemsets = {itemset for itemset, count in itemset_counts.items()
                             if count >= min_support}
        if not frequent_itemsets:
            break

        # Add the frequent itemsets to the output
        frequent_items.update(frequent_itemsets)
        itemsets = frequent_itemsets
        k += 1

    return frequent_items


# Test only
pprint.pprint(
    get_frequent_itemsets(
        [
            {'A', 'B', 'D', 'E'},
            {'B', 'C', 'E'},
            {'A', 'B', 'D', 'E'},
            {'A', 'B', 'C', 'E'},
            {'A', 'B', 'C', 'D', 'E'},
            {'B', 'C', 'D'}
        ],
        3
    )
)
print()


# Main program
df = pd.read_csv(PATH_TO_CSV, header=0, index_col=False)
print(df.head())

# Convert the dataframe to a set of transactions
transactions = []
for i in range(df.shape[0]):
    transactions.append(set(df.iloc[i, 1: df.iloc[i, 0] + 1]))
pprint.pprint(transactions[0:5])
print()

print(f'For min_support={MIN_SUPPORT}:')
pprint.pprint(get_frequent_itemsets(transactions, MIN_SUPPORT))


"""Output:
{frozenset({'A', 'E', 'B'}),
 frozenset({'E', 'B', 'C'}),
 frozenset({'D'}),
 frozenset({'A'}),
 frozenset({'A', 'D'}),
 frozenset({'B'}),
 frozenset({'A', 'B'}),
 frozenset({'B', 'D'}),
 frozenset({'A', 'D', 'B'}),
 frozenset({'E'}),
 frozenset({'E', 'C'}),
 frozenset({'E', 'B'}),
 frozenset({'E', 'D'}),
 frozenset({'E', 'B', 'D'}),
 frozenset({'C'}),
 frozenset({'B', 'C'}),
 frozenset({'E', 'A'}),
 frozenset({'A', 'E', 'D'}),
 frozenset({'A', 'B', 'E', 'D'})}

   Item(s)            Item 1               Item 2          Item 3                    Item 4 Item 5 Item 6 Item 7 Item 8 Item 9  ... Item 23 Item 24 Item 25 Item 26 Item 27 Item 28 Item 29 Item 30 Item 31 Item 32
0        4      citrus fruit  semi-finished bread       margarine               ready soups    NaN    NaN    NaN    NaN    NaN  ...     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN
1        3    tropical fruit               yogurt          coffee                       NaN    NaN    NaN    NaN    NaN    NaN  ...     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN
2        1        whole milk                  NaN             NaN                       NaN    NaN    NaN    NaN    NaN    NaN  ...     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN
3        4         pip fruit               yogurt    cream cheese              meat spreads    NaN    NaN    NaN    NaN    NaN  ...     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN
4        4  other vegetables           whole milk  condensed milk  long life bakery product    NaN    NaN    NaN    NaN    NaN  ...     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN     NaN

[5 rows x 33 columns]
[{'citrus fruit', 'semi-finished bread', 'margarine', 'ready soups'},
 {'tropical fruit', 'yogurt', 'coffee'},
 {'whole milk'},
 {'meat spreads', 'yogurt', 'cream cheese', 'pip fruit'},
 {'condensed milk',
  'long life bakery product',
  'other vegetables',
  'whole milk'}]

For min_support=12:
{frozenset({'rolls/buns', 'whole milk'}),
 frozenset({'citrus fruit'}),
 frozenset({'curd'}),
 frozenset({'shopping bags'}),
 frozenset({'bottled water'}),
 frozenset({'whole milk'}),
 frozenset({'fruit/vegetable juice'}),
 frozenset({'yogurt'}),
 frozenset({'coffee'}),
 frozenset({'frankfurter'}),
 frozenset({'root vegetables'}),
 frozenset({'tropical fruit'}),
 frozenset({'soda'}),
 frozenset({'sugar'}),
 frozenset({'newspapers'}),
 frozenset({'rolls/buns'}),
 frozenset({'pastry'}),
 frozenset({'canned beer'}),
 frozenset({'bottled beer'}),
 frozenset({'sausage'}),
 frozenset({'other vegetables'}),
 frozenset({'whole milk', 'other vegetables'})}
"""