《机器学习实战》第二章 练习题

1.使用不同的超参数，如kernel="linear"（具有C超参数的多种 值）或kernel="rbf"（C超参数和gamma超参数的多种值），尝试一个 支持向量机回归器（sklearn.svm.SVR），不用担心现在不知道这些超参数的含义。最好的SVR预测器是如何工作的？

from sklearn.model_selection import GridSearchCV

param_grid = [
        {'kernel': ['linear'], 'C': [10., 30., 100., 300., 1000., 3000., 10000., 30000.0]},
        {'kernel': ['rbf'], 'C': [1.0, 3.0, 10., 30., 100., 300., 1000.0],
         'gamma': [0.01, 0.03, 0.1, 0.3, 1.0, 3.0]},
    ]

svm_reg = SVR()
grid_search = GridSearchCV(svm_reg, param_grid, cv=5, scoring='neg_mean_squared_error', verbose=2)
grid_search.fit(housing_prepared, housing_labels)

 

2.尝试用RandomizedSearchCV替换GridSearchCV。

from sklearn.model_selection import RandomizedSearchCV
from scipy.stats import expon, reciprocal

# see https://docs.scipy.org/doc/scipy/reference/stats.html
# for `expon()` and `reciprocal()` documentation and more probability distribution functions.

# Note: gamma is ignored when kernel is "linear"
param_distribs = {
        'kernel': ['linear', 'rbf'],
        'C': reciprocal(20, 200000),
        'gamma': expon(scale=1.0),
    }

svm_reg = SVR()
rnd_search = RandomizedSearchCV(svm_reg, param_distributions=param_distribs,
                                n_iter=50, cv=5, scoring='neg_mean_squared_error',
                                verbose=2, random_state=42)
rnd_search.fit(housing_prepared, housing_labels)

 

3.尝试在准备流水线中添加一个转换器，从而只选出最重要的属性。

from sklearn.base import BaseEstimator, TransformerMixin

def indices_of_top_k(arr, k):
    return np.sort(np.argpartition(np.array(arr), -k)[-k:])

class TopFeatureSelector(BaseEstimator, TransformerMixin):
    def __init__(self, feature_importances, k):
        self.feature_importances = feature_importances
        self.k = k
    def fit(self, X, y=None):
        self.feature_indices_ = indices_of_top_k(self.feature_importances, self.k)
        return self
    def transform(self, X):
        return X[:, self.feature_indices_]
    
k = 5
top_k_feature_indices = indices_of_top_k(feature_importances, k)
top_k_feature_indices
np.array(attributes)[top_k_feature_indices]
sorted(zip(feature_importances, attributes), reverse=True)[:k]
preparation_and_feature_selection_pipeline = Pipeline([
    ('preparation', full_pipeline),
    ('feature_selection', TopFeatureSelector(feature_importances, k))
])
housing_prepared_top_k_features = preparation_and_feature_selection_pipeline.fit_transform(housing)
housing_prepared_top_k_features[0:3]
housing_prepared[0:3, top_k_feature_indices]

4.尝试创建一个覆盖完整的数据准备和最终预测的流水线。

prepare_select_and_predict_pipeline = Pipeline([
    ('preparation', full_pipeline),
    ('feature_selection', TopFeatureSelector(feature_importances, k)),
    ('svm_reg', SVR(**rnd_search.best_params_))
])

prepare_select_and_predict_pipeline.fit(housing, housing_labels)

some_data = housing.iloc[:4]
some_labels = housing_labels.iloc[:4]

print("Predictions:\t", prepare_select_and_predict_pipeline.predict(some_data))
print("Labels:\t\t", list(some_labels))

 

 

5.使用GridSearchCV自动探索一些准备选项。

param_grid = [{
    'preparation__num__imputer__strategy': ['mean', 'median', 'most_frequent'],
    'feature_selection__k': list(range(1, len(feature_importances) + 1))
}]

grid_search_prep = GridSearchCV(prepare_select_and_predict_pipeline, param_grid, cv=5,
                                scoring='neg_mean_squared_error', verbose=2)
grid_search_prep.fit(housing, housing_labels)

grid_search_prep.best_params_