Scikit-LLM：将大语言模型整合进Sklearn的工作流

news2024/10/6 20:39:25

我们以前介绍过Pandas和ChaGPT整合，这样可以不了解Pandas的情况下对DataFrame进行操作。现在又有人开源了Scikit-LLM，它结合了强大的语言模型，如ChatGPT和scikit-learn。但这个并不是让我们自动化scikit-learn，而是将scikit-learn和语言模型进行整合，scikit-learn也可以处理文本数据了。

安装

 pip install scikit-llm

既然要与Open AI的模型整合，就需要他的Key，从Scikit-LLM库中导入SKLLMConfig模块，并添加openAI密钥:

 # importing SKLLMConfig to configure OpenAI API (key and Name)
 fromskllm.configimportSKLLMConfig
 
 # Set your OpenAI API key
 SKLLMConfig.set_openai_key("<YOUR_KEY>")
 
 # Set your OpenAI organization (optional)
 SKLLMConfig.set_openai_org("<YOUR_ORGANIZATION>")

ZeroShotGPTClassifier

通过整合ChatGPT不需要专门的训练就可以对文本进行分类。ZeroShotGPTClassifier，就像任何其他scikit-learn分类器一样，使用非常简单。

 # importing zeroshotgptclassifier module and classification dataset
 fromskllmimportZeroShotGPTClassifier
 fromskllm.datasetsimportget_classification_dataset
 
 # get classification dataset from sklearn
 X, y=get_classification_dataset()
 
 # defining the model
 clf=ZeroShotGPTClassifier(openai_model="gpt-3.5-turbo")
 
 # fitting the data
 clf.fit(X, y)
 
 # predicting the data
 labels=clf.predict(X)

Scikit-LLM在结果上经过了特殊处理，确保响应只包含一个有效的标签。如果响应缺少标签，它还可以进行填充，根据它在训练数据中出现的频率为你选择一个标签。

对于我们自己的带标签的数据，只需要提供候选标签的列表，代码是这个样子的：

 # importing zeroshotgptclassifier module and classification dataset
 fromskllmimportZeroShotGPTClassifier
 fromskllm.datasetsimportget_classification_dataset
 
 # get classification dataset from sklearn for prediction only
 
 X, _=get_classification_dataset()
 
 # defining the model
 clf=ZeroShotGPTClassifier()
 
 # Since no training so passing the labels only for prediction
 clf.fit(None, ['positive', 'negative', 'neutral'])
 
 # predicting the labels
 labels=clf.predict(X)

MultiLabelZeroShotGPTClassifier

多标签也类似

 # importing Multi-Label zeroshot module and classification dataset
 fromskllmimportMultiLabelZeroShotGPTClassifier
 fromskllm.datasetsimportget_multilabel_classification_dataset
 
 # get classification dataset from sklearn 
 X, y=get_multilabel_classification_dataset()
 
 # defining the model
 clf=MultiLabelZeroShotGPTClassifier(max_labels=3)
 
 # fitting the model
 clf.fit(X, y)
 
 # making predictions
 labels=clf.predict(X)

创建MultiLabelZeroShotGPTClassifier类的实例时，指定要分配给每个样本的最大标签数量（这里:max_labels=3）

数据没有没有标签怎么办？可以通过提供候选标签列表来训练没有标记数据的分类器。y的类型应该是List[List[str]]。下面是一个没有标记数据的训练示例:

 # getting classification dataset for prediction only
 X, _=get_multilabel_classification_dataset()
 
 # Defining all the labels that needs to predicted
 candidate_labels= [
     "Quality",
     "Price",
     "Delivery",
     "Service",
     "Product Variety"
 ]
 
 # creating the model
 clf=MultiLabelZeroShotGPTClassifier(max_labels=3)
 
 # fitting the labels only
 clf.fit(None, [candidate_labels])
 
 # predicting the data
 labels=clf.predict(X)

文本向量化

文本向量化是将文本转换为数字的过程，Scikit-LLM中的GPTVectorizer模块，可以将一段文本(无论文本有多长)转换为固定大小的一组向量。

 # Importing the necessary modules and classes
 fromsklearn.pipelineimportPipeline
 fromsklearn.preprocessingimportLabelEncoder
 fromxgboostimportXGBClassifier
 
 # Creating an instance of LabelEncoder class
 le=LabelEncoder()
 
 # Encoding the training labels 'y_train' using LabelEncoder
 y_train_encoded=le.fit_transform(y_train)
 
 # Encoding the test labels 'y_test' using LabelEncoder
 y_test_encoded=le.transform(y_test)
 
 # Defining the steps of the pipeline as a list of tuples
 steps= [('GPT', GPTVectorizer()), ('Clf', XGBClassifier())]
 
 # Creating a pipeline with the defined steps
 clf=Pipeline(steps)
 
 # Fitting the pipeline on the training data 'X_train' and the encoded training labels 'y_train_encoded'
 clf.fit(X_train, y_train_encoded)
 
 # Predicting the labels for the test data 'X_test' using the trained pipeline
 yh=clf.predict(X_test)

文本摘要

GPT非常擅长总结文本。在Scikit-LLM中有一个叫GPTSummarizer的模块。

 # Importing the GPTSummarizer class from the skllm.preprocessing module
 from skllm.preprocessing import GPTSummarizer
 
 # Importing the get_summarization_dataset function
 from skllm.datasets import get_summarization_dataset
 
 # Calling the get_summarization_dataset function
 X = get_summarization_dataset()
 
 # Creating an instance of the GPTSummarizer
 s = GPTSummarizer(openai_model='gpt-3.5-turbo', max_words=15)
 
 # Applying the fit_transform method of the GPTSummarizer instance to the input data 'X'.
 # It fits the model to the data and generates the summaries, which are assigned to the variable 'summaries'
 summaries = s.fit_transform(X)

需要注意的是，max_words超参数是对生成摘要中单词数量的灵活限制。虽然max_words为摘要长度设置了一个粗略的目标，但摘要器可能偶尔会根据输入文本的上下文和内容生成略长的摘要。