通过元提示增强您的提示

import pandas as pd
import openai 
from concurrent.futures import ThreadPoolExecutor, as_completed
from tqdm import tqdm
from pydantic import BaseModel
from datasets import load_dataset

client = openai.Client()

ds = load_dataset("RealTimeData/bbc_news_alltime", "2024-08")
df = pd.DataFrame(ds['train']).sample(n=100, random_state=1)
df.head()

def get_model_response(messages, model="o1-preview"):
    response = client.chat.completions.create(
        messages=messages,
        model=model,
    )
    return response.choices[0].message.content


complex_prompt = get_model_response([{"role": "user", "content": meta_prompt.format(simple_prompt=simple_prompt)}])
complex_prompt

generate_summaries(df.iloc[0])

# Add new columns to the dataframe for storing itineraries
df['simple_summary'] = None
df['complex_summary'] = None

# Use ThreadPoolExecutor to generate itineraries concurrently
with ThreadPoolExecutor() as executor:
    futures = {executor.submit(generate_summaries, row): index for index, row in df.iterrows()}
    for future in tqdm(as_completed(futures), total=len(futures), desc="Generating Itineraries"):
        index = futures[future]
        simple_itinerary, complex_itinerary = future.result()
        df.at[index, 'simple_summary'] = simple_itinerary
        df.at[index, 'complex_summary'] = complex_itinerary

df.head()

def evaluate_summaries(row):
    simple_messages = [{"role": "user", "content": evaluation_prompt.format(original_article=row["content"], summary=row['simple_summary'])}]
    complex_messages = [{"role": "user", "content": evaluation_prompt.format(original_article=row["content"], summary=row['complex_summary'])}]
    
    simple_summary = client.beta.chat.completions.parse(
        model="gpt-4o",
        messages=simple_messages,
        response_format=ScoreCard)
    simple_summary = simple_summary.choices[0].message.parsed
    
    complex_summary = client.beta.chat.completions.parse(
        model="gpt-4o",
        messages=complex_messages,
        response_format=ScoreCard)
    complex_summary = complex_summary.choices[0].message.parsed
    
    return simple_summary, complex_summary

# Add new columns to the dataframe for storing evaluations
df['simple_evaluation'] = None
df['complex_evaluation'] = None

# Use ThreadPoolExecutor to evaluate itineraries concurrently
with ThreadPoolExecutor() as executor:
    futures = {executor.submit(evaluate_summaries, row): index for index, row in df.iterrows()}
    for future in tqdm(as_completed(futures), total=len(futures), desc="Evaluating Summaries"):
        index = futures[future]
        simple_evaluation, complex_evaluation = future.result()
        df.at[index, 'simple_evaluation'] = simple_evaluation
        df.at[index, 'complex_evaluation'] = complex_evaluation

df.head()

import matplotlib.pyplot as plt

df["simple_scores"] = df["simple_evaluation"].apply(lambda x: [score for key, score in x.model_dump().items() if key != 'justification'])
df["complex_scores"] = df["complex_evaluation"].apply(lambda x: [score for key, score in x.model_dump().items() if key != 'justification'])


# Calculate average scores for each criterion
criteria = [
    'Categorisation',
    'Keywords and Tags',
    'Sentiment Analysis',
    'Clarity and Structure',
    'Detail and Completeness'
]

# Calculate average scores for each criterion by model
simple_avg_scores = df['simple_scores'].apply(pd.Series).mean()
complex_avg_scores = df['complex_scores'].apply(pd.Series).mean()


# Prepare data for plotting
avg_scores_df = pd.DataFrame({
    'Criteria': criteria,
    'Original Prompt': simple_avg_scores,
    'Improved Prompt': complex_avg_scores
})

# Plotting
ax = avg_scores_df.plot(x='Criteria', kind='bar', figsize=(6, 4))
plt.ylabel('Average Score')
plt.title('Comparison of Simple vs Complex Prompt Performance by Model')
plt.xticks(rotation=45, ha='right')
plt.tight_layout()
plt.legend(loc='upper left', bbox_to_anchor=(1, 1))
plt.show()