本文整理匯總了Python中sklearn.feature_extraction.text.TfidfVectorizer.predict方法的典型用法代碼示例。如果您正苦於以下問題：Python TfidfVectorizer.predict方法的具體用法？Python TfidfVectorizer.predict怎麽用？Python TfidfVectorizer.predict使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類sklearn.feature_extraction.text.TfidfVectorizer的用法示例。
在下文中一共展示了TfidfVectorizer.predict方法的2個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: getHistoricalVolatility
# 需要導入模塊: from sklearn.feature_extraction.text import TfidfVectorizer [as 別名]
# 或者: from sklearn.feature_extraction.text.TfidfVectorizer import predict [as 別名]
sp_df = getHistoricalVolatility()
content_df = getScrapedContent()
X, y = combineHistVolColumn(content_df, sp_df)
# vectorize text
clf = TfidfVectorizer(stop_words='english')
clfv = clf.fit_transform(X)
# cross validation
X_train, X_test, y_train, y_test = train_test_split(clfv, y, test_size=0.2, random_state=42)
# use naive bayes
clf = LinearRegression()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
ipdb.set_trace()
# 1 estimator score method
print "Estimator score method: ", clf.score(X_test, y_test)
# 2 scoring parameter
scores = cross_val_score(clf, X_train, y_train, cv=5, scoring='accuracy')
print "Scoring parameter 'accuracy' from cross val: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() / 2)
# 3 scoring via metric functions
# print average_precision_score(y_test, y_pred)
print confusion_matrix(y_test, y_pred)
示例2: _alpha_grid
# 需要導入模塊: from sklearn.feature_extraction.text import TfidfVectorizer [as 別名]
# 或者: from sklearn.feature_extraction.text.TfidfVectorizer import predict [as 別名]
alphas = _alpha_grid(X, y, n_alphas=20)
for alpha in alphas:
r_time4, r_iter4, r_score4, r_time8, r_iter8, r_score8 = 0, 0, 0, 0, 0, 0
c_time4, c_iter4, c_score4, c_time8, c_iter8, c_score8 = 0, 0, 0, 0, 0, 0
for n_iter in [0, 1, 2]:
X_train, X_test, y_train, y_test= train_test_split(X, y, test_size=0.33, random_state=n_iter)
clf = ElasticNet(max_iter=500000, alpha=alpha, tol=1e-4)
print("......") + str(alpha)
t = time()
clf.fit(X_train, y_train)
c_time4 += time() - t
y_pred = np.sign(clf.predict(X_test))
c_iter4 += clf.n_iter_
c_score4 += accuracy_score(y_test, y_pred)
print c_iter4
print c_time4
print c_score4
clf = ElasticNet(max_iter=500000, alpha=alpha, tol=1e-4, random_state=0, selection='random')
print("......") + str(alpha)
t = time()
clf.fit(X_train, y_train)
r_time4 += time() - t
y_pred = np.sign(clf.predict(X_test))
r_iter4 += clf.n_iter_
r_score4 += accuracy_score(y_test, y_pred)
print r_iter4