在先前构建的模型上使用predict_proba时发生TypeError

Question

我训练并保存了以下模型

filename = 'finalized_model.sav'
pickle.dump(rf, open(filename, 'wb'))

现在我正在编写一个获取测试数据集的Web服务，因此我加载了模型并预测了概率

def getCuisine():
    content=jsonify(request.json)
    test = pd.io.json.json_normalize(request.json)
    tfidf_vect = pickle.load(open("vectorizer.pickle", "rb"))
    test['ingredients'] = [str(map(makeString, x)) for x in test['ingredients']]
    test_transform = tfidf_vect.transform(test['ingredients'].values)
    le = preprocessing.LabelEncoder()
    X_test = test_transform
    y_test = le.fit_transform(test['cuisine'].values)

    # load the model
    filename = 'finalized_model.sav'
    loaded_model = pickle.load(open(filename, 'rb'))
    #predict
    predicted_labels = loaded_model.predict_proba(X_test)

但是我遇到了错误

TypeError: '<' not supported between instances of 'NoneType' and 'int' 

第predicted_labels = loaded_model.predict_proba(X_test)行

我想念什么？

编辑：

根据评论，我在下面尝试了

content=request.json()
test = pd.io.json.json_normalize(content)

但是随后出现错误TypeError: 'list' object is not callable。请参阅下面的示例输入。

不过，不要以为阅读请求是问题所在。我尝试使用以下本地文件读取panda，但仍收到原始错误TypeError: '<' not supported between instances of 'NoneType' and 'int'

test = pd.read_json('./test.json')

样本输入

[
  {
    "id": 25693,
    "cuisine": "southern_us",
    "ingredients": [
      "plain flour",
      "ground pepper",
      "salt",
      "tomatoes",
      "ground black pepper",
      "thyme",
      "eggs",
      "green tomatoes",
      "yellow corn meal",
      "milk",
      "vegetable oil"
    ]
  }
  ]