SKLearn Naive Bayes：在 tfidf 矢量化后添加特征

因此，我的任务是训练一个电话记录模型。以下代码执行此操作。一些背景信息： - x 是一个字符串列表，每个第 i 个元素是一个完整的转录本 - y 是布尔值列表，表示调用的结果是正还是负。

以下代码有效，但这是我的问题。我想将通话时长作为一项训练功能。我假设在 TFIDF 转换器对转录本进行矢量化之后，我只需将通话持续时间功能连接到 TFIDF 输出，对吗？也许这比我想象的要容易，但是我在代码开头看到的 pandas 数据框中都有文字记录和持续时间。因此，如果我有持续时间的数据框列（numpy 数组），我需要做什么才能将该功能添加到我的模型中？

附加问题：

• 我是否缺少关于朴素贝叶斯模型的基本假设，该假设将我限制在矢量化字符串上？
• 我应该在管道的哪一步添加新功能？
• 这甚至可以在管道中完成吗？还是我必须将其分开才能做这样的事情？

Code:

import numpy as np
import pandas as pd
import random
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.pipeline import Pipeline
from sklearn.linear_model import SGDClassifier
from sklearn.grid_search import GridSearchCV
from sklearn.cross_validation import cross_val_score
from sklearn.feature_selection import SelectPercentile
from sklearn.metrics import roc_auc_score
from sklearn.feature_selection import chi2


def main():
filename = 'QA_training.pkl'
splitRatio = 0.67
dataframe = loadData(filename)
x, y = getTrainingData(dataframe)
print len(x), len(y)

x_train, x_test = splitDataset(x, splitRatio)
y_train, y_test = splitDataset(y, splitRatio)

#x_train = np.asarray(x_train)

percentiles = [10, 15, 20, 25, 30, 35, 40, 45, 50]

MNNB_pipe = Pipeline([('vec', CountVectorizer()),('tfidf', TfidfTransformer()),('select', SelectPercentile(score_func=chi2)),('clf', MultinomialNB())])
MNNB_param_grid = {
#'vec__max_features': (10, 25, 50, 100, 250, 500, 1000, 2500, 5000, 10000),
'tfidf__use_idf': (True, False),
'tfidf__sublinear_tf': (True, False),
'vec__binary': (True, False),
'tfidf__norm': ('l1', 'l2'),
'clf__alpha': (1, 0.1, 0.01, 0.001, 0.0001, 0.00001),
'select__percentile': percentiles
}
MNNB_search = GridSearchCV(MNNB_pipe, param_grid=MNNB_param_grid, cv=10, scoring='roc_auc', n_jobs=-1, verbose=1)
MNNB_search = MNNB_search.fit(x_train, y_train)
MNNB_search_best_cv = cross_val_score(MNNB_search.best_estimator_, x_train, y_train, cv=10, scoring='roc_auc', n_jobs=-1, verbose=10)

SGDC_pipe = Pipeline([('vec', CountVectorizer()),('tfidf', TfidfTransformer()),('select', SelectPercentile(score_func=chi2)),('clf', SGDClassifier())])
SGDC_param_grid = {
#'vec__max_features': [10, 25, 50, 100, 250, 500, 1000, 2500, 5000, 10000],
'tfidf__use_idf': [True, False],
'tfidf__sublinear_tf': [True, False],
'vec__binary': [True, False],
'tfidf__norm': ['l1', 'l2'],
'clf__loss': ['modified_huber','log'],
'clf__penalty': ['l1','l2'],
'clf__alpha': [1e-3],
'clf__n_iter': [5,10],
'clf__random_state': [42],
'select__percentile': percentiles
}
SGDC_search = GridSearchCV(SGDC_pipe, param_grid=SGDC_param_grid, cv=10, scoring='roc_auc', n_jobs=-1, verbose=1)
SGDC_search = SGDC_search.fit(x_train, y_train)
SGDC_search_best_cv = cross_val_score(SGDC_search.best_estimator_, x_train, y_train, cv=10, scoring='roc_auc', n_jobs=-1, verbose=10)

# pre_SGDC = SGDC_clf.predict(x_test)
# print (np.mean(pre_SGDC == y_test))

mydata = [{'model': MNNB_search.best_estimator_.named_steps['clf'],'features': MNNB_search.best_estimator_.named_steps['select'], 'mean_cv_scores': MNNB_search_best_cv.mean()},
          #{'model': GNB_search.best_estimator_.named_steps['classifier'],'features': GNB_search.best_estimator_.named_steps['select'], 'mean_cv_scores': GNB_search_best_cv.mean()},
          {'model': SGDC_search.best_estimator_.named_steps['clf'],'features': SGDC_search.best_estimator_.named_steps['select'], 'mean_cv_scores': SGDC_search_best_cv.mean()}]
model_results_df = pd.DataFrame(mydata)
model_results_df.to_csv("best_model_results.csv")

据我所知，sklearn 管道是 API 驱动的——管道本身并没有发生真正的魔法。因此，从这个角度来看，您应该能够创建自己的包装器TfidfVectorizer这就是你想要它做的事。例如，假设您有一个如下所示的 DataFrame：

df = pd.DataFrame({'text': ['foo text', 'bar text'], 'duration': [1, 2]})

您可能可以按如下方式实现转换：

class MyVectorizer(object):
    def __init__(self, tfidf_kwargs=None):
        self._tfidf = TfidfVectorizer(**(tfidf_kwargs or None))

    def fit(self, X, y=None):
        self._tfidf.fit(X['text'], y)
        return self

    def fit_transform(self, X, y=None):
        self.fit(X)
        return self.transform(X, copy=False)

    def transform(self, X, copy=True):
        result = self._tfidf.transform(X['text'], copy=copy)
        # result is a sparse matrix.  I'm not sure of a clean way
        # to add a column to a sparse matrix.  If you have the
        # memory, you can use a dense matrix instead...
        return np.column_stack((result, X['duration']))

然后我认为您应该准备好使用它而不是原始的 tfidf 矢量化器。