问题描述
我提前为发布这么多代码道歉。
我正在尝试将 YouTube 评论分为包含意见的评论（无论是正面还是负面）和不使用 NLTK 的朴素贝叶斯分类器的评论，但无论我在预处理阶段做什么，我都无法真正得到精度在0.75以上。与我见过的其他示例相比，这似乎有点低 - 例如，this 教程最终的准确度约为 0.98。
这是我的完整代码
import nltk,re,json,random
from nltk.stem.wordnet import WordNetLemmatizer
from nltk.corpus import stopwords
from nltk.tag import pos_tag
from nltk.tokenize import TweetTokenizer
from nltk import Freqdist,classify,NaiveBayesClassifier
from contractions import CONTRACTION_MAP
from abbreviations import abbrev_map
from tqdm.notebook import tqdm
def expand_contractions(text,contraction_mapping=CONTRACTION_MAP):
text = re.sub(r"’","'",text)
if text in abbrev_map:
return(abbrev_map[text])
text = re.sub(r"\bluv","lov",text)
contractions_pattern = re.compile('({})'.format('|'.join(contraction_mapping.keys())),flags=re.IGnorECASE|re.DOTALL)
def expand_match(contraction):
match = contraction.group(0)
first_char = match[0]
expanded_contraction = contraction_mapping.get(match)\
if contraction_mapping.get(match)\
else contraction_mapping.get(match.lower())
expanded_contraction = first_char+expanded_contraction[1:]
return expanded_contraction
expanded_text = contractions_pattern.sub(expand_match,text)
return expanded_text
def reduce_lengthening(text):
pattern = re.compile(r"(.)\1{2,}")
return pattern.sub(r"\1\1",text)
def lemmatize_sentence(tokens):
lemmatizer = WordNetLemmatizer()
lemmatized_sentence = []
for word,tag in pos_tag(tokens):
if tag.startswith('NN'):
pos = 'n'
elif tag.startswith('VB'):
pos = 'v'
else:
pos = 'a'
lemmatized_sentence.append(lemmatizer.lemmatize(word,pos))
return lemmatized_sentence
def processor(comments_list):
new_comments_list = []
for com in tqdm(comments_list):
com = com.lower()
#expand out contractions
tok = com.split(" ")
z = []
for w in tok:
ex_w = expand_contractions(w)
z.append(ex_w)
st = " ".join(z)
tokenized = tokenizer.tokenize(st)
reduced = [reduce_lengthening(token) for token in tokenized]
new_comments_list.append(reduced)
lemmatized = [lemmatize_sentence(new_com) for new_com in new_comments_list]
return(lemmatized)
def get_all_words(cleaned_tokens_list):
for tokens in cleaned_tokens_list:
for token in tokens:
yield token
def get_comments_for_model(cleaned_tokens_list):
for comment_tokens in cleaned_tokens_list:
yield dict([token,True] for token in comment_tokens)
if __name__ == "__main__":
#=================================================================================~
tokenizer = TweetTokenizer(strip_handles=True,reduce_len=True)
with open ("english_lang/samples/training_set.json","r",encoding="utf8") as f:
train_data = json.load(f)
pos_processed = processor(train_data['pos'])
neg_processed = processor(train_data['neg'])
neu_processed = processor(train_data['neu'])
emotion = pos_processed + neg_processed
random.shuffle(emotion)
em_tokens_for_model = get_comments_for_model(emotion)
neu_tokens_for_model = get_comments_for_model(neu_processed)
em_dataset = [(comment_dict,"Emotion")
for comment_dict in em_tokens_for_model]
neu_dataset = [(comment_dict,"Neutral")
for comment_dict in neu_tokens_for_model]
dataset = em_dataset + neu_dataset
random.shuffle(dataset)
x = 700
tr_data = dataset[:x]
te_data = dataset[x:]
classifier = NaiveBayesClassifier.train(tr_data)
print(classify.accuracy(classifier,te_data))
如果需要，我可以发布我的训练数据集，但可能值得一提的是，YouTube 评论本身的英语质量非常差且不一致（我认为这是模型准确率低的原因）。无论如何，这会被认为是可接受的准确度吗？ 或者，我很可能将这一切都弄错了，并且有一个更好的模型可供使用，在这种情况下，请随时告诉我我是个白痴！ 提前致谢
解决方法
将您的结果与无关教程的结果进行比较在统计上是无效的。在您恐慌之前，请对可能降低模型准确性的因素进行适当的研究。首先，您的模型的准确度不能高于数据集信息中固有的准确度。例如，无论数据集如何，在预测随机二元事件方面，没有任何模型可以（从长远来看）优于 50%。
我们没有合理的方法来评估理论信息内容。如果您需要检查，请尝试将其他一些模型类型应用于相同的数据，并查看它们产生的准确性。运行这些实验是数据科学的正常组成部分。