Python3：Reutersを使用したマルチラベルテキスト分類21578データセット

Question

次のコードを使用して、スポーツ、政治、お金の3つのカテゴリに分類します。私はこのコードがPrecision recallとF1を計算することがわかります。しかし私は、このコードを使用して、カスタムドキュメントに対してそのラベルを予測する方法を見つけることができません。

from nltk.corpus import stopwords, reuters 
from nltk import word_tokenize 
from nltk.stem.porter import PorterStemmer 
import re 

from sklearn.feature_extraction.text import TfidfVectorizer 
from sklearn.preprocessing import MultiLabelBinarizer 
from sklearn.svm import LinearSVC 
from sklearn.multiclass import OneVsRestClassifier 
from sklearn.metrics import f1_score, precision_score, recall_score 

cachedStopWords = stopwords.words("english") 
def tokenize(text): 
    min_length = 3 
    words = map(lambda word: word.lower(), word_tokenize(text)) 
    words = [word for word in words if word not in cachedStopWords] 
    tokens = (list(map(lambda token: PorterStemmer().stem(token),words))) 
    p = re.compile('[a-zA-Z]+'); 
    filtered_tokens = list(filter (lambda token: p.match(token) and len(token) >= min_length,tokens)) 
    return filtered_tokens 

def represent(documents, representer): 
    train_docs_id = list(filter(lambda doc: doc.startswith("train"), documents)) 
    test_docs_id = list(filter(lambda doc: doc.startswith("test"), documents)) 

    train_docs = [reuters.raw(doc_id) for doc_id in train_docs_id] 
    test_docs = [reuters.raw(doc_id) for doc_id in test_docs_id] 

    # Learn and transform train documents 
    vectorised_train_documents = representer.fit_transform(train_docs) 
    vectorised_test_documents = representer.transform(test_docs) 

    # Transform multilabel labels 
    mlb = MultiLabelBinarizer() 
    train_labels = mlb.fit_transform([reuters.categories(doc_id) for doc_id in train_docs_id]) 
    test_labels = mlb.transform([reuters.categories(doc_id) for doc_id in test_docs_id]) 

    return (vectorised_train_documents, train_labels, vectorised_test_documents, test_labels) 

def evaluate(test_labels, predictions): 
    precision = precision_score(test_labels, predictions, average='micro') 
    recall = recall_score(test_labels, predictions, average='micro') 
    f1 = f1_score(test_labels, predictions, average='micro') 
    print("Micro-average quality numbers") 
    print("Precision: {:.4f}, Recall: {:.4f}, F1-measure: {:.4f}".format(precision, recall, f1)) 

    precision = precision_score(test_labels, predictions, average='macro') 
    recall = recall_score(test_labels, predictions, average='macro') 
    f1 = f1_score(test_labels, predictions, average='macro') 

    print("Macro-average quality numbers") 
    print("Precision: {:.4f}, Recall: {:.4f}, F1-measure: {:.4f}".format(precision, recall, f1)) 

documents = reuters.fileids() 
candidate = {'representer': TfidfVectorizer(tokenizer=tokenize), 
      'estimator': OneVsRestClassifier(LinearSVC(random_state=42))} 
train_docs, train_labels, test_docs, test_labels = represent(documents, candidate['representer']) 
candidate['estimator'].fit(train_docs, train_labels) 
predictions = candidate['estimator'].predict(test_docs) 
evaluate(test_labels, predictions) 

クレジット： https://github.com/miguelmalvarez/reuters-tc/blob/master/notebook/Classification_Reuters.ipynb

Answer 1

あなたはフォルダ内のテキストファイルとしてカスタムドキュメントを格納することができますが、yourfolderを言うことができます。その後、以下のコードを使用して、ロイターのデータを訓練し、テキスト文書のラベルを予測することができます。 all_labelsには、各文書の予測ラベル（タプルとして）のリストが含まれます

import os 


classifier=OneVsRestClassifier(LinearSVC(random_state=42)) 
vectorizer=TfidfVectorizer(tokenizer=tokenize) 

#LOAD AND TRANSFORM TRAINING DOCS 
documents = reuters.fileids() 
train_docs_id = list(filter(lambda doc: doc.startswith("train"), documents)) 

train_docs = [reuters.raw(doc_id) for doc_id in train_docs_id] 
vectorised_train_documents = vectorizer.fit_transform(train_docs) 
mlb = MultiLabelBinarizer() 
train_labels = mlb.fit_transform([reuters.categories(doc_id) for doc_id in train_docs_id]) 

#LEARN CLASSIFICATION MODEL 
classifier=classifier.fit(vectorised_train_documents, train_labels) 


#LOAD AND TRANSFORM TEST DOCS 
documents_yours=os.listdir('yourfoldername') 
test_docs_yours = [open('yourfoldername/'+doc_id).read() for doc_id in documents_yours] 
vectorised_test_documents_yours = vectorizer.transform(test_docs_yours) 


#MAKEPREIDCTIONS 
predictions_yours=classifier.predict(vectorised_test_documents_yours) 
all_labels = mlb.inverse_transform(predictions_yours) 
all_labels