Learning Best Practices for Model Evaluation and Hyperparameter Tuning

1.  Streamlining workflows with pipelines

 1.1 Loading the Breast Cancer Wisconsin dataset

from distutils.version import LooseVersion as Version
from sklearn import __version__ as sklearn_version
import numpy as np
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split

df = pd.read_csv('./datasets/wdbc/wdbc.data', header=None) # https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data X = df.loc[:, 2:].values
y = df.loc[:, 1].values
le = LabelEncoder()
y = le.fit_transform(y)
y_enc = le.transform(['M', 'B'])
X_train, X_test, y_train, y_test = \
train_test_split(X, y, test_size=0.20, random_state=1)

1.2 Combining transformers and estimators in a pipeline

from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
pipe_lr = Pipeline([('scl', StandardScaler()),
('pca', PCA(n_components=2)),
('clf', LogisticRegression(random_state=1))])

pipe_lr.fit(X_train, y_train)
print('Test Accuracy: %.3f' % pipe_lr.score(X_test, y_test))

2 Using k-fold cross-validation to assess model performance

2.1 K-fold cross-validation

from sklearn.model_selection import StratifiedKFold
kfold = StratifiedKFold(n_splits=10, random_state=1).split(X_train, y_train)
scores = []
for k, (train, test) in enumerate(kfold):
pipe_lr.fit(X_train[train], y_train[train])
score = pipe_lr.score(X_train[test], y_train[test])
scores.append(score)
print('Fold: %s, Class dist.: %s, Acc: %.3f' % (k + 1,
np.bincount(y_train[train]), score))

2.2 scikit-learn also implements a k-fold cross-validation scorer, which allows us to evaluate our model using stratifed k-fold cross-validation more effciently

from sklearn.model_selection import cross_val_score

scores = cross_val_score(estimator=pipe_lr, X=X_train, y=y_train, cv=10, n_jobs=1)print('CV accuracy scores: %s' % scores)print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))

3. Debugging algorithms with learning and validation curves

3.1 Diagnosing bias and variance problems with learning curves 

import matplotlib.pyplot as plt
from sklearn.model_selection import learning_curve
pipe_lr = Pipeline([('scl', StandardScaler()),
('clf', LogisticRegression(penalty='l2', random_state=0))])

train_sizes, train_scores, test_scores =\
learning_curve(estimator=pipe_lr,
X=X_train,
y=y_train,
train_sizes=np.linspace(0.1, 1.0, 10),
cv=10,
n_jobs=1)

train_mean = np.mean(train_scores, axis=1)
train_std = np.std(train_scores, axis=1)
test_mean = np.mean(test_scores, axis=1)
test_std = np.std(test_scores, axis=1)

plt.plot(train_sizes, train_mean,
color='blue', marker='o',
markersize=5, label='training accuracy')

plt.fill_between(train_sizes,
train_mean + train_std,
train_mean - train_std,
alpha=0.15, color='blue')

plt.plot(train_sizes, test_mean,
color='green', linestyle='--',
marker='s', markersize=5,
label='validation accuracy')

plt.fill_between(train_sizes,
test_mean + test_std,
test_mean - test_std,
alpha=0.15, color='green')

plt.grid()
plt.xlabel('Number of training samples')
plt.ylabel('Accuracy')
plt.legend(loc='lower right')
plt.ylim([0.8, 1.0])
plt.show()

3.2 Addressing overftting and underftting with validation curves

param_range = [0.001, 0.01, 0.1, 1.0, 10.0, 100.0]
train_scores, test_scores = validation_curve(
estimator=pipe_lr,
X=X_train,
y=y_train,
param_name='clf__C',
param_range=param_range,
cv=10)

train_mean = np.mean(train_scores, axis=1)
train_std = np.std(train_scores, axis=1)
test_mean = np.mean(test_scores, axis=1)
test_std = np.std(test_scores, axis=1)

plt.plot(param_range, train_mean,
color='blue', marker='o',
markersize=5, label='training accuracy')

plt.fill_between(param_range, train_mean + train_std,
train_mean - train_std, alpha=0.15,
color='blue')

plt.plot(param_range, test_mean,
color='green', linestyle='--',
marker='s', markersize=5,
label='validation accuracy')

plt.fill_between(param_range,
test_mean + test_std,
test_mean - test_std,
alpha=0.15, color='green')

plt.grid()
plt.xscale('log')
plt.legend(loc='lower right')
plt.xlabel('Parameter C')
plt.ylabel('Accuracy')
plt.ylim([0.8, 1.0])
plt.show()

4 Fine-tuning machine learning models via grid search

4.1 Tuning hyperparameters via grid search

from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
pipe_svc = Pipeline([('scl', StandardScaler()),
('clf', SVC(random_state=1))])

param_range = [0.0001, 0.001, 0.01, 0.1, 1.0, 10.0, 100.0, 1000.0]

param_grid = [{'clf__C': param_range,
'clf__kernel': ['linear']},
{'clf__C': param_range,
'clf__gamma': param_range,
'clf__kernel': ['rbf']}]

gs = GridSearchCV(estimator=pipe_svc,
param_grid=param_grid,
scoring='accuracy',
cv=10,
n_jobs=-1)
gs = gs.fit(X_train, y_train)
print('Validation accuracy', gs.best_score_)
print('Best parameters', gs.best_params_)

clf = gs.best_estimator_
clf.fit(X_train, y_train)
print('Test accuracy: %.3f' % clf.score(X_test, y_test))

4.2 Algorithm selection with nested cross-validation

from sklearn.tree import DecisionTreeClassifier
gs = GridSearchCV(estimator=pipe_svc,
param_grid=param_grid,
scoring='accuracy',
cv=2)

# Note: Optionally, you could use cv=2
# in the GridSearchCV above to produce
# the 5 x 2 nested CV that is shown in the figure.

scores = cross_val_score(gs, X_train, y_train, scoring='accuracy', cv=5)
print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))

gs = Gri
af51
dSearchCV(estimator=DecisionTreeClassifier(random_state=0),
param_grid=[{'max_depth': [1, 2, 3, 4, 5, 6, 7, None]}],
scoring='accuracy',
cv=2)
scores = cross_val_score(gs, X_train, y_train, scoring='accuracy', cv=5)
print('CV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))

Reference：《Python Machine Learning》