本文整理汇总了Python中sklearn.pipeline.Pipeline.stats['train_pos']方法的典型用法代码示例。如果您正苦于以下问题：Python Pipeline.stats['train_pos']方法的具体用法？Python Pipeline.stats['train_pos']怎么用？Python Pipeline.stats['train_pos']使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类sklearn.pipeline.Pipeline的用法示例。
在下文中一共展示了Pipeline.stats['train_pos']方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: build_psq_classifier
# 需要导入模块: from sklearn.pipeline import Pipeline [as 别名]
# 或者: from sklearn.pipeline.Pipeline import stats['train_pos'] [as 别名]
def build_psq_classifier(end_date_str=None):
"""Build a predictor of whether or not a question will be closed as
homework / for 'lack of context'. This is accomplished by building a
linear SVC model, trained on old post data.
If end_date_str isn't specified, it is initialized to two weeks prior.
Pickles the classifier, an instance of sklearn.svm.LinearSVC. Also stores
some basic data metrics.
Note that we only use posts written after 2013-06-25, the date on which
the first such closure reason was instituted.
"""
if end_date_str == None:
ts = time() - 60 * 60 * 24 * 14
end_date_str = from_timestamp(ts)
con = connect_db()
cur = con.cursor()
trf = TfidfVectorizer(
ngram_range=(2,6),
stop_words='english',
analyzer='char',
preprocessor=preprocess_post
)
reg = LogisticRegression()
clf = Pipeline([('vectorizer', trf), ('reg', reg)])
X_raw = []
Y_raw = []
# Fetch closed questions from database
query = """SELECT * FROM questions WHERE creation_date < '{}' AND
closed_reason='off-topic' AND (closed_desc LIKE '%context%'
OR closed_desc LIKE '%homework%');""".format(end_date_str)
cur.execute(query)
for q in cur:
X_raw.append(q['body_html'])
Y_raw.append(1)
num_closed = len(X_raw)
# Fetch an equal number of un-closed questions
query = """SELECT * FROM questions WHERE creation_date < %s AND
closed_reason IS NULL ORDER BY creation_date LIMIT %s"""
cur.execute(query, [end_date_str, num_closed])
for q in cur:
X_raw.append(q['body_html'])
Y_raw.append(0)
X_raw = [X_raw[i] for i in shuff]
Y_raw = [Y_raw[i] for i in shuff]
# Hold back 20% of examples as test set
X_train, X_test, Y_train, Y_test = train_test_split(
X_raw, Y_raw, test_size=0.2)
test_size = len(X_test)
train_size = len(X_train)
# Perform grid search to tune parameters for F1-score
params = [
{
'vectorizer__ngram_range': [(2,2), (2,4), (2,6), (2,8)],
'reg__penalty': ['l1', 'l2'],
'reg__C': [.01, .03, .1, .3, 1, 3, 10, 30, 100],
'reg__intercept_scaling': [.1,1,10,100]
}
]
gridsearch = GridSearchCV(clf, params, scoring='f1', n_jobs=4, \
pre_dispatch=8)
gridsearch.fit(X_train, Y_train)
clf = gridsearch.best_estimator_
print("Done training classifier!")
print("Parameters from CV:")
for k,v in gridsearch.best_params_.items():
print("{}: {}".format(k,v))
preds = clf.predict(X_test)
print("Done making predictions for test set.")
print("Results:")
clf.stats = dict()
clf.stats['train_size'] = train_size
clf.stats['train_pos'] = np.sum(Y_train)
clf.stats['train_neg'] = train_size - np.sum(Y_train)
clf.stats['test_size'] = test_size
clf.stats['test_pos'] = np.sum(Y_test)
clf.stats['test_neg'] = test_size - np.sum(Y_test)
#.........这里部分代码省略.........