machine_learning_rf_pipeline.py

from sklearn import datasets
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix

cancer = datasets.load_breast_cancer()
x = cancer.data
y = cancer.target

print(x.shape)
## (569, 30)

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.2)

# create a pipeline to process data
ppln = Pipeline([
           ('scale', StandardScaler()),
           ('pca', PCA(0.80)),
           ('clf', RandomForestClassifier(max_depth=3))
       ])
ppln.fit(x_train, y_train)

# prediction
y_pred = ppln.predict(x_test)

confusion_matrix(y_test, y_pred)
## array([[40,  0],
##        [ 5, 69]])