使用GridSearchCV进行网格搜索微调模型

import numpy as np
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model.logistic import LogisticRegression
from sklearn.model_selection import train_test_split, cross_val_score, GridSearchCV
from sklearn.metrics import roc_curve, auc
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.pipeline import Pipeline
from sklearn.metrics import precision_score, recall_score, accuracy_score

pipeline = Pipeline([
    ('vect', TfidfVectorizer(stop_words='english')),
    ('clf', LogisticRegression())
])
parameters = {
    'vect__max_df': (0.25, 0.5, 0.75),
    'vect__stop_words': ('english', None),
    'vect__max_features': (2500, 5000, None),
    'vect__ngram_range': ((1, 1), (1, 2)),
    'vect__use_idf': (True, False),
    'clf__penalty': ('l1', 'l2'),
    'clf__C': (0.01, 0.1, 1, 10),
}


df = pd.read_csv('./sms.csv')
X = df['message']
y = df['label']
label_encoder = LabelEncoder()
y = label_encoder.fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y)

grid_search = GridSearchCV(pipeline, parameters, n_jobs=-1, verbose=1, scoring='accuracy', cv=3)
grid_search.fit(X_train, y_train)

print('Best score: %0.3f' % grid_search.best_score_)
print('Best parameters set:')
best_parameters = grid_search.best_estimator_.get_params()
for param_name in sorted(parameters.keys()):
    print('\t%s: %r' % (param_name, best_parameters[param_name]))

predictions = grid_search.predict(X_test)
print('Accuracy: %s' % accuracy_score(y_test, predictions))
print('Precision: %s' % precision_score(y_test, predictions))
print('Recall: %s' % recall_score(y_test, predictions))

df = pd.read_csv('./sms.csv')
X_train_raw, X_test_raw, y_train, y_test = train_test_split(df['message'], df['label'], random_state=11)
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(X_train_raw)
X_test = vectorizer.transform(X_test_raw)
classifier = LogisticRegression()
classifier.fit(X_train, y_train)
scores = cross_val_score(classifier, X_train, y_train, cv=5)
print('Accuracies: %s' % scores)
print('Mean accuracy: %s' % np.mean(scores))
precisions = cross_val_score(classifier, X_train, y_train, cv=5, scoring='precision')
print('Precision: %s' % np.mean(precisions))
recalls = cross_val_score(classifier, X_train, y_train, cv=5, scoring='recall')
print('Recall: %s' % np.mean(recalls))
f1s = cross_val_score(classifier, X_train, y_train, cv=5, scoring='f1')
print('F1 score: %s' % np.mean(f1s))

微调后：

Best score: 0.983
Best parameters set:
clf__C: 10
clf__penalty: 'l2'
vect__max_df: 0.5
vect__max_features: None
vect__ngram_range: (1, 2)
vect__stop_words: None
vect__use_idf: True
Accuracy: 0.9863701578192252
Precision: 0.994535519125683
Recall: 0.91

微调前：

Accuracies: [0.95221027 0.95454545 0.96172249 0.96052632 0.95209581]
Mean accuracy: 0.9562200683094717
Precision: 0.992542742398164
Recall: 0.6836050302748021
F1 score: 0.8090678466269784

我们可以看到极大的改善了Recall，极大的优化了模型，GridSearchCV其实就是暴力搜索。该方法在小数据集上很有用，数据集大了就不太适用。

在大数据集的情况下，容易造成内存溢出，试试下面的GridSearchCV + SVM的代码，看看是不是溢出了。

import matplotlib.pyplot as plt
from sklearn.datasets import fetch_mldata, fetch_openml
import matplotlib.cm as cm
from sklearn.metrics import classification_report
from sklearn.model_selection import GridSearchCV, train_test_split
from sklearn.pipeline import Pipeline
from sklearn.svm import SVC

mnist = fetch_openml('mnist_784')
# print(mnist.shape)
counter = 1
for i in range(1, 4):
    for j in range(1, 6):
        plt.subplot(3, 5, counter)
        plt.imshow(mnist.data[(i - 1) * 8000 + j*200].reshape((28, 28)), cmap=cm.Greys_r)
        plt.axis('off')
        counter += 1
plt.show()
if __name__ == '__main__':
    X, y = mnist.data, mnist.target
    X = X/255.0*2 - 1
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=11)

    pipeline = Pipeline([
        ('clf', SVC(kernel='rbf', gamma=0.01, C=100))
    ])

    parameters = {
        'clf__gamma': (0.01, 0.03),
        'clf__C': (0.1, 0.3),
    }

    grid_search = GridSearchCV(pipeline, parameters, n_jobs=2, verbose=1, scoring='accuracy')
    grid_search.fit(X_train[:10000], y_train[:10000])
    print('Best score: %0.3f' % grid_search.best_score_)
    print('Best parameters set:')
    best_parameters = grid_search.best_estimator_.get_params()
    for param_name in sorted(parameters.keys()):
        print('\t%s: %r' % (param_name, best_parameters[param_name]))

    predictions = grid_search.predict(X_test)
    print(classification_report(y_test, predictions))