PandasDataFrame

这个笔记本展示了如何使用代理与Pandas DataFrame进行交互。它主要优化用于问题回答。

NOTE: 此代理会在后台调用 Python 代理，该代理执行由LLM生成的Python代码 - 如果LLM生成的Python代码有害，则可能会造成不良后果。请谨慎使用。

注意：自从 LangChain 迁移至 0.3 版本后，你应该升级 langchain_openai 和 LangChain。这可以避免导入错误。

pip install --upgrade langchain_openai pip install --upgrade langchain

from langchain.agents.agent_types import AgentType
from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
from langchain_openai import ChatOpenAI

API 参考:代理类型 |create_pandas_dataframe_agent |ChatOpenAI

import pandas as pd
from langchain_openai import OpenAI

df = pd.read_csv(
    "https://raw.githubusercontent.com/pandas-dev/pandas/main/doc/data/titanic.csv"
)

API 参考:OpenAI

使用 ZERO_SHOT_REACT_DESCRIPTION

这显示了如何使用ZERO_SHOT_REACT_DESCRIPTION代理类型初始化代理。

agent = create_pandas_dataframe_agent(OpenAI(temperature=0), df, verbose=True)

使用OpenAI函数

这展示了如何使用OPENAI_FUNCTIONS代理类型初始化代理。请注意，这是上述方法的替代方案。

agent = create_pandas_dataframe_agent(
    ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613"),
    df,
    verbose=True,
    agent_type=AgentType.OPENAI_FUNCTIONS,
)

agent.invoke("how many rows are there?")

> Entering new  chain...

Invoking: `python_repl_ast` with `df.shape[0]`


891There are 891 rows in the dataframe.

> Finished chain.

'There are 891 rows in the dataframe.'

agent.invoke("how many people have more than 3 siblings")

> Entering new AgentExecutor chain...
Thought: I need to count the number of people with more than 3 siblings
Action: python_repl_ast
Action Input: df[df['SibSp'] > 3].shape[0]
Observation: 30
Thought: I now know the final answer
Final Answer: 30 people have more than 3 siblings.

> Finished chain.

'30 people have more than 3 siblings.'

agent.invoke("whats the square root of the average age?")

> Entering new AgentExecutor chain...
Thought: I need to calculate the average age first
Action: python_repl_ast
Action Input: df['Age'].mean()
Observation: 29.69911764705882
Thought: I now need to calculate the square root of the average age
Action: python_repl_ast
Action Input: math.sqrt(df['Age'].mean())
Observation: NameError("name 'math' is not defined")
Thought: I need to import the math library
Action: python_repl_ast
Action Input: import math
Observation: 
Thought: I now need to calculate the square root of the average age
Action: python_repl_ast
Action Input: math.sqrt(df['Age'].mean())
Observation: 5.449689683556195
Thought: I now know the final answer
Final Answer: The square root of the average age is 5.449689683556195.

> Finished chain.

'The square root of the average age is 5.449689683556195.'

Multi DataFrame 示例

这接下来的部分展示了代理如何与作为列表传入的多个数据框架进行交互。

df1 = df.copy()
df1["Age"] = df1["Age"].fillna(df1["Age"].mean())

agent = create_pandas_dataframe_agent(OpenAI(temperature=0), [df, df1], verbose=True)
agent.invoke("how many rows in the age column are different?")

> Entering new AgentExecutor chain...
Thought: I need to compare the age columns in both dataframes
Action: python_repl_ast
Action Input: len(df1[df1['Age'] != df2['Age']])
Observation: 177
Thought: I now know the final answer
Final Answer: 177 rows in the age column are different.

> Finished chain.

'177 rows in the age column are different.'

相关

• 工具概念指南 概念引导
• Tool 如何使用指南