如何向矢量化数据集添加特征?

Question

我想写一个朴素基础文本分类器。 因为sklearn不接受"文本形式"功能，所以我正在使用TfidfVectorizer转换它们。

我成功地仅使用转换后的数据作为特征来创建这样的分类。代码如下所示：

### text vectorization--go from strings to lists of numbers
vectorizer = TfidfVectorizer(sublinear_tf=True, max_df=0.5,
stop_words='english')
X_train_transformed = vectorizer.fit_transform(X_train_raw['url'])
X_test_transformed  = vectorizer.transform(X_test_raw['url'])
### feature selection, because text is super high dimensional and 
### can be really computationally chewy as a result
selector = SelectPercentile(f_classif, percentile=1)
selector.fit(X_train_transformed, y_train_raw)
X_train = selector.transform(X_train_transformed).toarray()
X_test  = selector.transform(X_test_transformed).toarray()
clf = GaussianNB()
clf.fit(X_train, y_train_raw)
.....

一切都按预期工作，但是当我想添加另一个功能时，我遇到了问题，例如。 指示天气的标志 给定的文本包含某个关键字。 我尝试了多种方法来正确转换"url"功能，然后将转换后的功能与另一个布尔功能相结合，但没有成功。 假设我有一个包含两个功能的熊猫框架："url"(我要转换)和"contains_keyword"标志，任何提示应该如何完成？

失败的解决方案如下所示：

vectorizer = CountVectorizer(min_df=1)
X_train_transformed = vectorizer.fit_transform(X_train_raw['url'])
X_test_transformed  = vectorizer.transform(X_test_raw['url'])
selector = SelectPercentile(f_classif, percentile=1)
selector.fit(X_train_transformed, y_train_raw)
X_train_selected = selector.transform(X_train_transformed)
X_test_selected  = selector.transform(X_test_transformed)
X_train_raw['transformed_url'] = X_train_selected.toarray().tolist()
X_train_without = X_train_raw.drop(['url'], axis=1)
X_train = X_train_without.values

这将生成包含布尔标志和列表的行，该列表是 sklearn 模型的错误输入。我不知道我应该如何正确转换它。感谢任何帮助。

以下是测试数据：

url,target,ads_keyword
googleadapis l google com,1,True
googleadapis l google com,1,True
clients1 google com,1,False
c go-mpulse net,1,False
translate google pl,1,False

URL - 从 DNS 查询中获取的拆分域

目标 - 用于分类的目标类

ads_keyword - 表示天气的标志 "URL"包含"广告"字样。

我想使用 TfidfVectorizer 转换"url"，并将转换后的数据与"ads_keyword"(将来可能还会有更多功能)一起使用作为用于训练朴素贝叶斯模型的特征。

Answer 1

这是一个演示，展示了如何使用GridSearchCV联合功能以及如何调整超参数。

不幸的是，您的样本数据集太小，无法训练真实模型......

try:
from pathlib import Path
except ImportError:             # Python 2
from pathlib2 import Path
import os
import re
from pprint import pprint
import pandas as pd
import numpy as np
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.preprocessing import FunctionTransformer, LabelEncoder, LabelBinarizer, StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.feature_selection import SelectPercentile
from sklearn.feature_extraction import DictVectorizer
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.model_selection import GridSearchCV
from sklearn.linear_model import SGDClassifier
from sklearn.naive_bayes import MultinomialNB, GaussianNB
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.externals import joblib
from scipy.sparse import csr_matrix, hstack

class ColumnSelector(BaseEstimator, TransformerMixin):
def __init__(self, name=None, position=None,
as_cat_codes=False, sparse=False):
self.name = name
self.position = position
self.as_cat_codes = as_cat_codes
self.sparse = sparse
def fit(self, X, y=None):
return self
def transform(self, X, **kwargs):
if self.name is not None:
col_pos = X.columns.get_loc(self.name)
elif self.position is not None:
col_pos = self.position
else:
raise Exception('either [name] or [position] parameter must be not-None')
if self.as_cat_codes and X.dtypes.iloc[col_pos] == 'category':
ret = X.iloc[:, col_pos].cat.codes
else:
ret = X.iloc[:, col_pos]
if self.sparse:
ret = csr_matrix(ret.values.reshape(-1,1))
return ret
union = FeatureUnion([
('text', 
Pipeline([
('select', ColumnSelector('url')),
#('pct', SelectPercentile(percentile=1)),
('vect', TfidfVectorizer(sublinear_tf=True, max_df=0.5,
stop_words='english')),
]) ),
('ads',
Pipeline([
('select', ColumnSelector('ads_keyword', sparse=True,
as_cat_codes=True)),
#('scale', StandardScaler(with_mean=False)),
]) )
])
pipe = Pipeline([
('union', union),
('clf', MultinomialNB())
])
param_grid = [
{
'union__text__vect': [TfidfVectorizer(sublinear_tf=True,
max_df=0.5,
stop_words='english')],
'clf': [SGDClassifier(max_iter=500)],
'union__text__vect__ngram_range': [(1,1), (2,5)],
'union__text__vect__analyzer': ['word','char_wb'],
'clf__alpha': np.logspace(-5, 0, 6),
#'clf__max_iter': [500],
},
{
'union__text__vect': [TfidfVectorizer(sublinear_tf=True,
max_df=0.5,
stop_words='english')],
'clf': [MultinomialNB()],
'union__text__vect__ngram_range': [(1,1), (2,5)],
'union__text__vect__analyzer': ['word','char_wb'],
'clf__alpha': np.logspace(-4, 2, 7),
},
#{        # NOTE: does NOT support sparse matrices!
#    'union__text__vect': [TfidfVectorizer(sublinear_tf=True,
#                                          max_df=0.5,
#                                          stop_words='english')],
#    'clf': [GaussianNB()],
#    'union__text__vect__ngram_range': [(1,1), (2,5)],
#    'union__text__vect__analyzer': ['word','char_wb'],
#},
]
gs_kwargs = dict(scoring='roc_auc', cv=3, n_jobs=1, verbose=2)
X_train, X_test, y_train, y_test = 
train_test_split(df[['url','ads_keyword']], df['target'], test_size=0.33)
grid = GridSearchCV(pipe, param_grid=param_grid, **gs_kwargs)
grid.fit(X_train, y_train)
# prediction
predicted = grid.predict(X_test)