交易的多类别分类

%load_ext autoreload
%autoreload
%pip install openai 'openai[datalib]' 'openai[embeddings]' transformers

import openai
import pandas as pd
import numpy as np
import json
import os

COMPLETIONS_MODEL = "gpt-4"

client = openai.OpenAI(api_key=os.environ.get("OPENAI_API_KEY", "<your OpenAI API key if you didn't set as an env var>"))

def request_completion(prompt):

    completion_response = openai.chat.completions.create(
                            prompt=prompt,
                            temperature=0,
                            max_tokens=5,
                            top_p=1,
                            frequency_penalty=0,
                            presence_penalty=0,
                            model=COMPLETIONS_MODEL)

    return completion_response

def classify_transaction(transaction,prompt):

    prompt = prompt.replace('SUPPLIER_NAME',transaction['Supplier'])
    prompt = prompt.replace('DESCRIPTION_TEXT',transaction['Description'])
    prompt = prompt.replace('TRANSACTION_VALUE',str(transaction['Transaction value (£)']))

    classification = request_completion(prompt).choices[0].message.content.replace('\n','')

    return classification

# This function takes your training and validation outputs from the prepare_data function of the Finetuning API, and
# confirms that each have the same number of classes.
# If they do not have the same number of classes the fine-tune will fail and return an error

def check_finetune_classes(train_file,valid_file):

    train_classes = set()
    valid_classes = set()
    with open(train_file, 'r') as json_file:
        json_list = list(json_file)
        print(len(json_list))

    for json_str in json_list:
        result = json.loads(json_str)
        train_classes.add(result['completion'])
        #print(f"result: {result['completion']}")
        #print(isinstance(result, dict))

    with open(valid_file, 'r') as json_file:
        json_list = list(json_file)
        print(len(json_list))

    for json_str in json_list:
        result = json.loads(json_str)
        valid_classes.add(result['completion'])
        #print(f"result: {result['completion']}")
        #print(isinstance(result, dict))

    if len(train_classes) == len(valid_classes):
        print('All good')

    else:
        print('Classes do not match, please prepare data again')

zero_shot_prompt = '''You are a data expert working for the National Library of Scotland.
You are analysing all transactions over £25,000 in value and classifying them into one of five categories.
The five categories are Building Improvement, Literature & Archive, Utility Bills, Professional Services and Software/IT.
If you can't tell what it is, say Could not classify

Transaction:

Supplier: SUPPLIER_NAME
Description: DESCRIPTION_TEXT
Value: TRANSACTION_VALUE

The classification is:'''

embedding_path = './data/transactions_with_embeddings_100.csv'

from utils.embeddings_utils import get_embedding

df['babbage_similarity'] = df.combined.apply(lambda x: get_embedding(x, model='gpt-4'))
df['babbage_search'] = df.combined.apply(lambda x: get_embedding(x, model='gpt-4'))
df.to_csv(embedding_path)

# This step is to remove any existing files if we've already produced training/validation sets for this classifier
#!rm transactions_grouped*

# We output our shuffled dataframe to a .jsonl file and run the prepare_data function to get us our input files
ft_df_sorted.to_json("transactions_grouped.jsonl", orient='records', lines=True)
!openai tools fine_tunes.prepare_data -f transactions_grouped.jsonl -q

# This step creates your model
!openai api fine_tunes.create -t "transactions_grouped_prepared_train.jsonl" -v "transactions_grouped_prepared_valid.jsonl" --compute_classification_metrics --classification_n_classes 5 -m curie

# You can use following command to get fine tuning job status and model name, replace the job name with your job
#!openai api fine_tunes.get -i ft-YBIc01t4hxYBC7I5qhRF3Qdx

# Congrats, you've got a fine-tuned model!
# Copy/paste the name provided into the variable below and we'll take it for a spin
fine_tuned_model = 'curie:ft-personal-2022-10-20-10-42-56'

test_set['predicted_class'] = test_set.apply(lambda x: openai.chat.completions.create(model=fine_tuned_model, prompt=x['prompt'], max_tokens=1, temperature=0, logprobs=5),axis=1)
test_set['pred'] = test_set.apply(lambda x : x['predicted_class']['choices'][0]['text'],axis=1)

test_set['result'] = test_set.apply(lambda x: str(x['pred']).strip() == str(x['completion']).strip(), axis = 1)

holdout_df['combined'] = "Supplier: " + holdout_df['Supplier'].str.strip() + "; Description: " + holdout_df['Description'].str.strip() + '\n\n###\n\n' # + "; Value: " + str(df['Transaction value (£)']).strip()
holdout_df['prediction_result'] = holdout_df.apply(lambda x: openai.chat.completions.create(model=fine_tuned_model, prompt=x['combined'], max_tokens=1, temperature=0, logprobs=5),axis=1)
holdout_df['pred'] = holdout_df.apply(lambda x : x['prediction_result']['choices'][0]['text'],axis=1)