Het aantal variabelen bepalen

Introductie tot Predictive Analytics in Python

Nele Verbiest, Ph.D

Data Scientist @PythonPredictions

De AUC evalueren

auc_values = []
variables_evaluate = []

for v in variables_forward:
    variables_evaluate.append(v)
    auc_value = auc(variables_evaluate, ["target"], basetable)
    auc_values.append(auc_value)
Introductie tot Predictive Analytics in Python

De AUC evalueren

Introductie tot Predictive Analytics in Python

Overfitting

Introductie tot Predictive Analytics in Python

Overfitting opsporen

Introductie tot Predictive Analytics in Python

Opsplitsen

from sklearn.model_selection import train_test_split

X = basetable.drop("target", 1)
y = basetable["target"]

X_train, X_test, y_train, y_test = 
    train_test_split(X, y, test_size=0.4, stratify = Y)

train = pd.concat([X_train, y_train], axis=1)
test = pd.concat([X_test, y_test], axis=1)
Introductie tot Predictive Analytics in Python

De cut-off bepalen

  • Hoge test-AUC
  • Weinig variabelen
Introductie tot Predictive Analytics in Python

De cut-off bepalen

Introductie tot Predictive Analytics in Python

Laten we oefenen!

Introductie tot Predictive Analytics in Python

Preparing Video For Download...