如何使用 Tf-idf 特征来训练你的模型？

Question

from sklearn.feature_extraction.text import TfidfVectorizer
tfidf = TfidfVectorizer(sublinear_tf= True, 
                       min_df = 5, 
                       norm= 'l2', 
                       ngram_range= (1,2), 
                       stop_words ='english')

feature1 = tfidf.fit_transform(df.Rejoined_Stem)
array_of_feature = feature1.toarray()

我使用上面的代码来获取我的文本文档的功能。

from sklearn.naive_bayes import MultinomialNB # Multinomial Naive Bayes on Lemmatized Text
X_train, X_test, y_train, y_test = train_test_split(df['Rejoined_Lemmatize'], df['Product'], random_state = 0)
X_train_counts = tfidf.fit_transform(X_train)
clf = MultinomialNB().fit(X_train_counts, y_train)
y_pred = clf.predict(tfidf.transform(X_test))

然后我使用这段代码来训练我的模型。 有人可以解释一下在训练模型时究竟是如何使用上述特征的，因为在训练时没有在任何地方使用该 feature1 变量吗？？

Answer 1

不，您没有使用feature1，因为您执行了另一个转换X_train_count。

让我们按逻辑流程浏览您的代码，并仅使用在特征提取和模型训练中使用的变量。

# imports used
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB

# split data random state 0 and test_size 0.25 default as you did not give the test_size

X_train, X_test, y_train, y_test = train_test_split(df[['Rejoined_Lemmatize']], df['Product'], random_state = 0)

# you initiated your transformer to `fit_transform` X_train, and `transform` X_test

tfidf = TfidfVectorizer(sublinear_tf= True, 
                       min_df = 5, 
                       norm= 'l2', 
                       ngram_range= (1,2), 
                       stop_words ='english')


X_train_counts = tfidf.fit_transform(X_train)
X_test_counts = tfidf.transform(X_test)

# you initiated your model and fit X_train_counts and y_train
clf = MultinomialNB()
cls.fit(X_train_counts, y_train)

# you predicted from your transformed features
y_pred = clf.predict(X_test_counts)

有一种更好的方式来使用 Scikit-learn API，它可以消除混淆并帮助您避免混淆。这种方式使用Pipelines

# imports used: see Pipeline
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB

# split data random state 0 and test_size 0.25 default as you did not give the test_size

X_train, X_test, y_train, y_test = train_test_split(df[['Rejoined_Lemmatize']], df['Product'], random_state = 0)

# get the params
tfidf_params = dict(sublinear_tf= True, 
                       min_df = 5, 
                       norm= 'l2', 
                       ngram_range= (1,2), 
                       stop_words ='english')

# create a Pipeline that will do features transformation then pass to the model

clf = Pipeline(steps=[
('features', TfidfVectorizer(**tfidf_params)),
('model', MultinomialNB())
])

# Use clf as a model, fit X_train and y_train
cls.fit(X_train, y_train)

# predicted 
y_pred = clf.predict(X_test)

管道的作用，.fit 是对数据进行 fit_transform，然后将其传递给模型。在.predict 中，它将在传递给模型之前进行转换。

这种方法的最大优点是您可以轻松地轻松切换模型或变压器。以下是模型基线比较的示例：

# collection to store results 
from collections import defaultdict
import pandas as pd

from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer

# models to test
from sklearn.linear_model import PassiveAggressiveClassifier 
from sklearn.linear_model import RidgeClassifierCV
from sklearn.linear_model import SGDClassifier
from sklearn.linear_model import LogisticRegressionCV     


# insistent our storage 
bench_mark = defaultdict(list)

# split data random state 0 and test_size 0.25 default as you did not give the test_size

X_train, X_test, y_train, y_test = train_test_split(df[['Rejoined_Lemmatize']], df['Product'], random_state = 0)

# get the transformer params
tfidf_params = dict(sublinear_tf= True, 
                       min_df = 5, 
                       norm= 'l2', 
                       ngram_range= (1,2), 
                       stop_words ='english')

# list of models we would like to complete 
models = [
PassiveAggressiveClassifier(C=1e-1,max_iter=1e3,  tol=1e3), 
RidgeClassifierCV(scoring='roc_auc', cv=10),
LogisticRegressionCV(cv=5,solver='saga',scoring='accuracy', random_state=1, n_jobs=-1),
SGDClassifier(loss='log', random_state=1, max_iter=101),
 ]

# train, test and store each model 
for model in models:

    # our pipeline is changed to accept model
    clf = Pipeline(steps=[
        ('features', TfidfVectorizer(**tfidf_params)),
        ('model', model) #just model not model() as we have done that in models list
    ])

    clf.fit(X_train,y_train)
     score = clf.score(X_test,y_test)

    model_name = clf.named_steps['model'].__class__.__name__ # hack to get name

    model_params = clf.named_steps['model']. get_params()


    print(f'{model_name} Scored: {score:.3f}\n')

    bench_mark['model_name'].append(model_name)
    bench_mark['score'].append(score)
    bench_mark['model'].append(clf)
    bench_mark['used_params'].append(model_params)

# in the end, place the bench_mark to DataFrame
models_df = pd.DataFrame(bench_mark)

# now you have the trained modes in DataFrame, their scores and parameters. 
#You can access and use any model.

logistic_reg = models_df[models_df['model_name']=='LogisticRegressionCV']['model'].iloc[0]

y_preds = logistic_reg.predict(X_test)

希望对你有帮助