独家 | Scikit-LLM：Sklearn邂逅大语言模型

pip install scikit-llm

# importing SKLLMConfig to configure OpenAI API (key and Name)
from skllm.config import SKLLMConfig

# Set your OpenAI API key
SKLLMConfig.set_openai_key("<YOUR_KEY>")

# Set your OpenAI organization (optional)
SKLLMConfig.set_openai_org("<YOUR_ORGANIZATION>")

# importing zeroshotgptclassifier module and classification dataset
from skllm import ZeroShotGPTClassifier
from skllm.datasets import get_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)

# importing zeroshotgptclassifier module and classification dataset
from skllm import ZeroShotGPTClassifier
from skllm.datasets import get_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)

# importing Multi-Label zeroshot module and classification dataset
from skllm import MultiLabelZeroShotGPTClassifier
from skllm.datasets import get_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)

# 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)

# Importing the GPTVectorizer class from the skllm.preprocessing module
from skllm.preprocessing import GPTVectorizer

# Creating an instance of the GPTVectorizer class and assigning it to the variable 'model'
model = GPTVectorizer()  

# transorming the
vectors = model.fit_transform(X)

# Importing the necessary modules and classes
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import LabelEncoder
from xgboost import XGBClassifier

# 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)

# 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)