Dari workflow ke pipeline

Merancang Alur Kerja Machine Learning di Python

Dr. Chris Anagnostopoulos

Honorary Associate Professor

Meninjau kembali workflow kita

from sklearn.ensemble import RandomForestClassifier as rf
X_train, X_test, y_train, y_test = train_test_split(X, y)

grid_search = GridSearchCV(rf(), param_grid={'max_depth': [2, 5, 10]})
grid_search.fit(X_train, y_train)
depth = grid_search.best_params_['max_depth']

vt = SelectKBest(f_classif, k=3).fit(X_train, y_train)
clf = rf(max_depth=best_value).fit(vt.transform(X_train), y_train)
accuracy_score(clf.predict(vt.transform(X_test), y_test))

Kekuatan grid search

Optimalkan max_depth:

pg = {'max_depth': [2,5,10]}
gs = GridSearchCV(rf(),  
   param_grid=pg)
gs.fit(X_train, y_train)
depth = gs.best_params_['max_depth']

Tabel semua kombinasi nilai depth dan jumlah estimator, menunjukkan tiga nilai dieksplorasi dan satu terbaik.

Kekuatan grid search

Lalu optimalkan n_estimators:

pg = {'n_estimators': [10,20,30]}
gs = GridSearchCV(
   rf(max_depth=depth),  
   param_grid=pg)
gs.fit(X_train, y_train)
n_est = gs.best_params_[
    'n_estimators']

Tabel semua kombinasi nilai depth dan jumlah estimator, menunjukkan lima nilai dieksplorasi dan lainnya jadi terbaik.

Kekuatan grid search

Gabungkan max_depth dan n_estimators:

pg = {
   'max_depth': [2,5,10],
   'n_estimators': [10,20,30]
}
gs = GridSearchCV(rf(),  
   param_grid=pg)
gs.fit(X_train, y_train)
print(gs.best_params_) 

{'max_depth': 10, 'n_estimators': 20}

Tabel semua kombinasi nilai depth dan jumlah estimator, menunjukkan semua nilai dieksplorasi dan hasil terbaik sama.

Pipeline

Pada diagram ini, random forest dengan dua hiperparameter terhubung ke pemilih fitur dengan satu hiperparameter melalui sebuah panah.

Pipeline

Kedua objek dibungkus dalam satu kotak.

Pipeline

from sklearn.pipeline import Pipeline
pipe = Pipeline([
    ('feature_selection', SelectKBest(f_classif)), 
    ('classifier', RandomForestClassifier())
])

params = dict(
    feature_selection__k=[2, 3, 4],
    classifier__max_depth=[5, 10, 20]
)

grid_search = GridSearchCV(pipe, param_grid=params)
gs = grid_search.fit(X_train, y_train).best_params_

{'classifier__max_depth': 20, 'feature_selection__k': 4}

Kustomisasi pipeline Anda

from sklearn.metrics import roc_auc_score, make_scorer
auc_scorer = make_scorer(roc_auc_score)

grid_search = GridSearchCV(pipe, param_grid=params, scoring=auc_scorer)

Jangan berlebihan

params = dict(
    feature_selection__k=[2, 3, 4], 
    clf__max_depth=[5, 10, 20], 
    clf__n_estimators=[10, 20, 30] 
)
grid_search = GridSearchCV(pipe, params, cv=10)

3 x 3 x 3 x 10 = 270 pelatihan classifier!

Workflow supercharged

Merancang Alur Kerja Machine Learning di Python