Python 在新（看不见的）文本上部署文本分类模型

我正在研究一个文本分类问题。我附加了一个我训练过的文本分类模型的简单虚拟片段

如何在新文本上部署模型？当模型用于检查预测时，它会正确地对文本进行分类，但是，当使用新数据时，分类是不正确的

这是因为新的文本需要矢量化吗？我错过了一些基本的东西吗

from collections import Counter
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import accuracy_score
import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score, precision_score, recall_score

df = pd.read_csv("/Users/veg.csv")
print (df)

无论您输入到模型中的是什么（新）文本，都必须经过与训练数据完全相同的预处理步骤-此处是已安装在

X\U训练

中的

计数矢量器

：

new_data_vectorized = cv.transform(new_data) # NOT fit_transform
new_predictions = naive_bayes.predict(new_data_vectorized)

check_predictions = []
for i in range(len(X_test)):   
    if predictions[i] == 0:
        check_predictions.append('vegetable')
    if predictions[i] == 1:
        check_predictions.append('fruit')
    if predictions[i] == 2:
        check_predictions.append('tree')
        
dummy_df = pd.DataFrame({'actual_label': list(y_test), 'prediction': check_predictions, 'Text':list(X_test)})
dummy_df.replace(to_replace=0, value='vegetable', inplace=True)
dummy_df.replace(to_replace=1, value='fruit', inplace=True)
dummy_df.replace(to_replace=2, value='tree', inplace=True)
print("DUMMY DF")
print(dummy_df.head(10))

new_data=['carrot', 'grapes',
          'banana', 'potato',
          'birch','carrot', 'grapes',
          'banana', 'potato', 'birch','carrot','grapes',
          'banana', 'potato',
          'birch','carrot', 'grapes',
          'banana', 'potato', 'birch','grapes',
          'banana', 'potato', 'birch']

new_predictions = []
for i in range(len(new_data)):    
    if predictions[i] == 0:
        new_predictions.append('vegetable')
    if predictions[i] == 1:
        new_predictions.append('fruit')
    if predictions[i] == 2:
        new_predictions.append('tree')
        
new_df = pd.DataFrame({'actual_label': list(y_test), 'prediction': new_predictions, 'Text':list(new_data)})        
new_df.replace(to_replace=0, value='vegetable', inplace=True)
new_df.replace(to_replace=1, value='fruit', inplace=True)
new_df.replace(to_replace=2, value='tree', inplace=True)
print("NEW DF")
print(new_df.head(10))

new_data_vectorized = cv.transform(new_data) # NOT fit_transform
new_predictions = naive_bayes.predict(new_data_vectorized)