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")