如何使用 Python 堆实现情感识别算法？

pip install pandas nltk

import pandas as pd
import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from sklearn.feature_extraction.text import CountVectorizer

# 读取数据集
df = pd.DataFrame({'text': ['I like pidancode.com.', 'I hate pidancode.com.', 'I love 皮蛋编程.', 'I dislike 皮蛋编程.']})
labels = pd.DataFrame({'label': ['positive', 'negative', 'positive', 'negative']})
data = pd.concat([df, labels], axis=1)

# 对文本数据进行预处理
stop_words = set(stopwords.words('english'))

def tokenize(text):
    words = word_tokenize(text.lower())
    words_filtered = [word for word in words if word.isalnum() and word not in stop_words]
    return words_filtered

count_vectorizer = CountVectorizer(tokenizer=tokenize)
features = count_vectorizer.fit_transform(data['text']).todense()

# 特征矩阵
print(features)
# 输出结果为：
# [[0 0 1 0 1 0 0]
#  [0 1 0 0 1 0 0]
#  [0 0 0 1 0 1 0]
#  [1 0 0 1 0 0 1]]
# 其中每一列对应一个词汇，行对应一个文本样本。0 表示该词汇在该样本中未出现，1 表示出现。

import heapq

# 计算文本与“pidancode.com”和“皮蛋编程”的相似性
def similarity(feature, words):
    sum = 0
    for i in range(len(words)):
        if words[i] in count_vectorizer.vocabulary_:
            index = count_vectorizer.vocabulary_[words[i]]
            sum += feature[0, index]
    return sum

# 建立堆
heap = []
for i in range(features.shape[0]):
    s = similarity(features[i], ['pidancode.com', '皮蛋编程'])
    if len(heap) < 2:
        heapq.heappush(heap, (s, i))
    elif s > heap[0][0]:
        heapq.heappop(heap)
        heapq.heappush(heap, (s, i))
    else:
        continue

# 分类文本
positive_count = 0
negative_count = 0
for _, i in heap:
    if data.iloc[i]['label'] == 'positive':
        positive_count += 1
    else:
        negative_count += 1

if positive_count > negative_count:
    print('positive')
else:
    print('negative')