Training dan test set

Prapemrosesan untuk Machine Learning di Python

James Chapman

Curriculum Manager, DataCamp

Mengapa dibagi?

Mengurangi overfitting
Mengevaluasi kinerja pada holdout set

Membagi dataset Anda

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

   X_train y_train            
0      1.0       n
1      4.0       n
       ...
5      5.0       n
6      6.0       n

   X_test y_test
0     9.0      y
1     1.0      n
2     4.0      n

Pengambilan sampel berstrata

Dataset $100$ sampel: $80$ kelas 1 dan $20$ kelas 2
Training set $75$ sampel: $60$ kelas 1 dan $15$ kelas 2
Test set $25$ sampel: $20$ kelas 1 dan $5$ kelas 2

Pengambilan sampel berstrata

X_train,X_test,y_train,y_test = train_test_split(X, y, stratify=y, random_state=42)

y["labels"].value_counts()

class1    80
class2    20
Name: labels, dtype: int64

Pengambilan sampel berstrata

y_train["labels"].value_counts()

class1    60
class2    15
Name: labels, dtype: int64

y_test["labels"].value_counts()

class1    20
class2    5
Name: labels, dtype: int64

Ayo berlatih!

Prapemrosesan untuk Machine Learning di Python