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))