Question

嗨，我是机器学习的新手。

我正在使用textblob库进行简单的情感分析。

我正在尝试使用与https://textblob.readthedocs.io/en/dev/classifiers.html上的条件完全匹配的json文件中的数据

当我运行函数时：

def trainAndClassify(name):

with open(name + '.json', 'r') as fp:
    cl = NaiveBayesClassifier(fp, format="json")
    answer = cl.classify("The beer is good. But the hangover is horrible.")
    print( answer )

我得到以下跟踪：

Traceback (most recent call last):
  File "sentiment.py", line 102, in <module>
    run()
  File "sentiment.py", line 95, in run
    constructor(sys.argv[2])
  File "sentiment.py", line 81, in constructor
    cl = NaiveBayesClassifier(fp, format="json")
  File "/usr/local/lib/python3.4/dist-packages/textblob/classifiers.py", line 185, in __init__
    self.train_features = [(self.extract_features(d), c) for d, c in self.train_set]
  File "/usr/local/lib/python3.4/dist-packages/textblob/classifiers.py", line 185, in <listcomp>
    self.train_features = [(self.extract_features(d), c) for d, c in self.train_set]
ValueError: too many values to unpack (expected 2)

我的JSON文件结构如下：

[{"text": "This is a good sentence", "label": "pos"}]

为了简单起见，我将其与伪造数据减少到一行。

我在做什么错了？

TextBlob NaiveBayesClassifier JSON文件

0 个答案: