3
我想將文檔中的文本分類到不同的類別。每個文檔只能進入以下類別之一:PR,AR,KID,SAR。使用scikit-learn來區分類似的類別
我發現使用scikit學習和我能夠使用它的一個例子:
import numpy
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.svm import LinearSVC
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.multiclass import OneVsRestClassifier
from pandas import DataFrame
def build_data_frame(path, classification):
rows = []
index = []
f = open(path, mode = 'r', encoding="utf8")
txt = f.read()
rows.append({'text': txt, 'class': classification})
index.append(path)
data_frame = DataFrame(rows, index=index)
return data_frame
# Categories
PR = 'PR'
AR = 'AR'
KID = 'KID'
SAR = 'SAR'
# Training documents
SOURCES = [
(r'C:/temp_training/PR/PR1.txt', PR),
(r'C:/temp_training/PR/PR2.txt', PR),
(r'C:/temp_training/PR/PR3.txt', PR),
(r'C:/temp_training/PR/PR4.txt', PR),
(r'C:/temp_training/PR/PR5.txt', PR),
(r'C:/temp_training/AR/AR1.txt', AR),
(r'C:/temp_training/AR/AR2.txt', AR),
(r'C:/temp_training/AR/AR3.txt', AR),
(r'C:/temp_training/AR/AR4.txt', AR),
(r'C:/temp_training/AR/AR5.txt', AR),
(r'C:/temp_training/KID/KID1.txt', KID),
(r'C:/temp_training/KID/KID2.txt', KID),
(r'C:/temp_training/KID/KID3.txt', KID),
(r'C:/temp_training/KID/KID4.txt', KID),
(r'C:/temp_training/KID/KID5.txt', KID),
(r'C:/temp_training/SAR/SAR1.txt', SAR),
(r'C:/temp_training/SAR/SAR2.txt', SAR),
(r'C:/temp_training/SAR/SAR3.txt', SAR),
(r'C:/temp_training/SAR/SAR4.txt', SAR),
(r'C:/temp_training/SAR/SAR5.txt', SAR)
]
# Real documents
TESTS = [
(r'C:/temp_testing/PR/PR1.txt'),
(r'C:/temp_testing/PR/PR2.txt'),
(r'C:/temp_testing/PR/PR3.txt'),
(r'C:/temp_testing/PR/PR4.txt'),
(r'C:/temp_testing/PR/PR5.txt'),
(r'C:/temp_testing/AR/AR1.txt'),
(r'C:/temp_testing/AR/AR2.txt'),
(r'C:/temp_testing/AR/AR3.txt'),
(r'C:/temp_testing/AR/AR4.txt'),
(r'C:/temp_testing/AR/AR5.txt'),
(r'C:/temp_testing/KID/KID1.txt'),
(r'C:/temp_testing/KID/KID2.txt'),
(r'C:/temp_testing/KID/KID3.txt'),
(r'C:/temp_testing/KID/KID4.txt'),
(r'C:/temp_testing/KID/KID5.txt'),
(r'C:/temp_testing/SAR/SAR1.txt'),
(r'C:/temp_testing/SAR/SAR2.txt'),
(r'C:/temp_testing/SAR/SAR3.txt'),
(r'C:/temp_testing/SAR/SAR4.txt'),
(r'C:/temp_testing/SAR/SAR5.txt')
]
data_train = DataFrame({'text': [], 'class': []})
for path, classification in SOURCES:
data_train = data_train.append(build_data_frame(path, classification))
data_train = data_train.reindex(numpy.random.permutation(data_train.index))
examples = []
for path in TESTS:
f = open(path, mode = 'r', encoding = 'utf8')
txt = f.read()
examples.append(txt)
target_names = [PR, AR, KID, SAR]
classifier = Pipeline([
('vectorizer', CountVectorizer(ngram_range=(1, 2), analyzer='word', strip_accents='unicode', stop_words='english')),
('tfidf', TfidfTransformer()),
('clf', OneVsRestClassifier(LinearSVC()))])
classifier.fit(data_train['text'], data_train['class'])
predicted = classifier.predict(examples)
print(predicted)
輸出:
['PR' 'PR' 'PR' 'PR' 'PR' 'AR' 'AR' 'AR' 'AR' 'AR' 'KID' 'KID' 'KID' 'KID'
'KID' 'AR' 'AR' 'AR' 'SAR' 'AR']
PR,AR和KID是完全認可。
但是,SAR文件(最後5個)沒有正確分類,除了其中一個。 SAR和AR非常相似,這可以解釋算法爲什麼會混淆。
我試圖玩n-grams值,但1(min)和2(max)似乎給出了最好的結果。
任何想法如何提高區分AR和SAR類別的精度?
有沒有辦法顯示特定文件的識別百分比?即PR(70%),這意味着該算法的預測70%的信心
如果你需要的文件,這裏是集:http://1drv.ms/21dnL6j