가장 간단한 지표
Python으로 배우는 Market Basket Analysis
Isaiah Hull
Visiting Associate Professor of Finance, BI Norwegian Business School
지표와 가지치기
- 지표(metric)는 규칙의 성능을 측정합니다.
- {humor} $\rightarrow$ {poetry}
- 0.81
- {fiction} $\rightarrow$ {travel}
- 0.23
- {humor} $\rightarrow$ {poetry}
- 가지치기(pruning)는 지표로 규칙을 걸러냅니다.
- 유지: {humor} $\rightarrow$ {poetry}
- 제거: {fiction} $\rightarrow$ {travel}
가장 간단한 지표
- 지지도(support)는 아이템셋이 포함된 거래의 비율입니다.
$$\frac{\text{items 포함 거래 수}}{\text{전체 거래 수}}$$
$$\frac{\text{milk 포함 거래 수}}{\text{전체 거래 수}}$$
language의 지지도
| TID | Transaction |
|---|---|
| 0 | travel, humor, fiction |
| 1 | humor, language |
| 2 | humor, biography, cooking |
| 3 | cooking, language |
| 4 | travel |
{language}의 지지도 = 2 / 10 = 0.2
| TID | Transaction |
|---|---|
| 5 | poetry, health, travel, history |
| 6 | humor |
| 7 | travel |
| 8 | poetry, fiction, humor |
| 9 | fiction, biography |
{Humor} $\rightarrow$ {Language}의 지지도
| TID | Transaction |
|---|---|
| 0 | travel,humor,fiction |
| 1 | humor,language |
| 2 | humor,biography,cooking |
| 3 | cooking,language |
| 4 | travel |
{language} $\rightarrow$ {humor}의 지지도 = 0.1
| TID | Transaction |
|---|---|
| 5 | poetry,health,travel,history |
| 6 | humor |
| 7 | travel |
| 8 | poetry,fiction,humor |
| 9 | fiction,biography |
데이터 준비
print(transactions)
[['travel', 'humor', 'fiction'],
...
['fiction', 'biography']]
from mlxtend.preprocessing import TransactionEncoder
# Instantiate transaction encoder
encoder = TransactionEncoder().fit(transactions)
데이터 준비
# One-hot encode itemsets by applying fit and transform
onehot = encoder.transform(transactions)
# Convert one-hot encoded data to DataFrame
onehot = pd.DataFrame(onehot, columns = encoder.columns_)
print(onehot)
biography cooking ... poetry travel
0 False False ... False True
...
9 True False ... False False
단일 아이템의 지지도 계산
print(onehot.mean())
biography 0.2
cooking 0.2
fiction 0.3
health 0.1
history 0.1
humor 0.5
language 0.2
poetry 0.2
travel 0.4
dtype: float64
복수 아이템의 지지도 계산
import numpy as np
# Define itemset that contains fiction and poetry
onehot['fiction+poetry'] = np.logical_and(onehot['fiction'],onehot['poetry'])
print(onehot.mean())
biography 0.2
cooking 0.2
... ...
travel 0.4
fiction+poetry 0.1
dtype: float64
Lass uns üben!
Python으로 배우는 Market Basket Analysis
