Python: pandas + gpt3.5 用一句话让 LLM 分析数据

介绍

pandas-ai 是一个开源套件，能够让使用者用 Prompt 的方式请 LLM 帮忙分析 DataFrame (等价于excel) 里面的数据。

使用方式

以下直接照搬专案说明文件内容:

要求 PandasAI 查找 DataFrame 中某列值大于 5 的所有行

import pandas as pdfrom pandasai import SmartDataframe# Sample DataFramedf = pd.DataFrame({    "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"],    "gdp": [19294482071552, 2891615567872, 2411255037952, 3435817336832, 1745433788416, 1181205135360, 1607402389504, 1490967855104, 4380756541440, 14631844184064],    "happiness_index": [6.94, 7.16, 6.66, 7.07, 6.38, 6.4, 7.23, 7.22, 5.87, 5.12]})# Instantiate a LLMfrom pandasai.llm import OpenAIllm = OpenAI(api_token="YOUR_API_TOKEN")df = SmartDataframe(df, config={"llm": llm})df.chat('Which are the 5 happiest countries?')

输出:

6            Canada7         Australia1    United Kingdom3           Germany0     United StatesName: country, dtype: object

要求 PandasAI 执行更複杂的查询。例如，您可以要求 PandasAI 计算 2 个最不幸福国家的 GDP 总和：

df.chat('What is the sum of the GDPs of the 2 unhappiest countries?')

输出:

19012600725504

请 PandasAI 绘製图表：

df.chat(    "Plot the histogram of countries showing for each the gdp, using different colors for each bar",)

输出:

重头戏: 如何免费使用?

以 OpenAI LLM 模型作为核心，我们需要有 OpenAI API Key，那不就是要付费了吗? (っ °Д °;)っ

但是!!! 我不想付费怎么办? 我就是客家阿（；´д｀）ゞ

大家可以参考我前几两篇的文章:

在前两篇文章中，我们知道 gpt4free 透过逆向工程方式，让我们可以免费、无限次数的使用 OpenAI 的 gpt3.5 模型。

那么老套路重现，我们只要把 gpt4free 作为 LLM 模型核心，这样就可以在不需要付费的情况下使用 pandas-ai 了! >_<

透过继承方式实现，如下:

import g4fimport pandas as pdfrom pandasai import SmartDataframe, PandasAIfrom pandasai.llm import LLMfrom pandasai.prompts.base import AbstractPromptclass Gpt4free(LLM):    """    Class to wrap gpt4free LLMs and make PandasAI interoperable    with gpt4free.    """    def __init__(        self,        model: str = "gpt-3.5-turbo",        provider: g4f.Provider = None,        stream: bool = False,    ):        """        __init__ method of Gpt4free Class        Args:            model (str): Model of OpenAI API.            provider (g4f.Provider): The Provider of OpenAI API.            stream (bool): Completion with streaming.        """        self.model = model        self.provider = provider        self.stream = stream    def call(self, instruction: AbstractPrompt, suffix: str = "") -> str:        prompt = instruction.to_string() + suffix        try:            response = g4f.ChatCompletion.create(                model=self.model,                provider=self.provider,                messages=[{"role": "user", "content": prompt}],            )        except Exception as e:            raise RuntimeError(f"Failed to create chat completion with Gpt4free: {str(e)}") from e        return response    @property    def type(self) -> str:        return "gpt4free"# Sample DataFramedf = pd.DataFrame({    "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"],    "gdp": [19294482071552, 2891615567872, 2411255037952, 3435817336832, 1745433788416, 1181205135360, 1607402389504, 1490967855104, 4380756541440, 14631844184064],    "happiness_index": [6.94, 7.16, 6.66, 7.07, 6.38, 6.4, 7.23, 7.22, 5.87, 5.12]})# Instance a LLMllm = Gpt4free()df = SmartDataframe(df, config={"llm": llm})print(df.chat('Which are the 5 happiest countries?'))print(df.chat('What is the sum of the GDPs of the 2 unhappiest countries?'))# Plotpandas_ai = PandasAI(llm, verbose=True, save_charts=True)df.chat(    "Plot the histogram of countries showing for each the gdp, using different colors for each bar",)

输出结果将与说明文件一致ಥ_ಥ

补充: 原本小弟发了一个 PR#613，想让用户可以直接轻鬆实现，省去自行宣告Gpt4free继承的程式，但是gpt4free 毕竟是种逆向工程，对于商业需求开发也不好，想想还是关了。当然，各位也可以参考这个 PR 直接改写本地原生套件，但切记不要用去商业开发...