La metrica più semplice
Analisi del carrello in Python
Isaiah Hull
Visiting Associate Professor of Finance, BI Norwegian Business School
Metriche e pruning
- Una metrica misura le prestazioni delle regole.
- {humor} $\rightarrow$ {poetry}
- 0.81
- {fiction} $\rightarrow$ {travel}
- 0.23
- {humor} $\rightarrow$ {poetry}
- Il pruning usa le metriche per scartare regole.
- Tieni: {humor} $\rightarrow$ {poetry}
- Scarta: {fiction} $\rightarrow$ {travel}
La metrica più semplice
- La metrica supporto misura la quota di transazioni che contengono un itemset.
$$\frac{\text{numero di transazioni con item}}{\text{numero di transazioni}}$$
$$\frac{\text{numero di transazioni con milk}}{\text{transazioni totali}}$$
Supporto per language
| TID | Transazione |
|---|---|
| 0 | travel, humor, fiction |
| 1 | humor, language |
| 2 | humor, biography, cooking |
| 3 | cooking, language |
| 4 | travel |
Supporto per {language} = 2 / 10 = 0.2
| TID | Transazione |
|---|---|
| 5 | poetry, health, travel, history |
| 6 | humor |
| 7 | travel |
| 8 | poetry, fiction, humor |
| 9 | fiction, biography |
Supporto per {Humor} $\rightarrow$ {Language}
| TID | Transazione |
|---|---|
| 0 | travel,humor,fiction |
| 1 | humor,language |
| 2 | humor,biography,cooking |
| 3 | cooking,language |
| 4 | travel |
SUPPORTO per {language} $\rightarrow$ {humor} = 0.1
| TID | Transazione |
|---|---|
| 5 | poetry,health,travel,history |
| 6 | humor |
| 7 | travel |
| 8 | poetry,fiction,humor |
| 9 | fiction,biography |
Preparare i dati
print(transactions)
[['travel', 'humor', 'fiction'],
...
['fiction', 'biography']]
from mlxtend.preprocessing import TransactionEncoder
# Instantiate transaction encoder
encoder = TransactionEncoder().fit(transactions)
Preparare i dati
# 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
Calcolare il supporto per singoli item
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
Calcolare il supporto per più item
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
¡Vamos a practicar!
Analisi del carrello in Python
