跳到主要内容
本笔记本展示了如何使用代理与 Pandas DataFrame 交互。它主要针对问答进行了优化。 注意：此代理在底层调用 Python 代理，该代理执行 LLM 生成的 Python 代码 - 如果 LLM 生成的 Python 代码有害，这可能会很糟糕。请谨慎使用。 注意：由于 langchain 已迁移到 v0.3，您应该升级 langchain_openai 和 langchain。这将避免导入错误。 pip install -U langchain_openai pip install -U langchain
from langchain.agents.agent_types import AgentType
from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
from langchain_openai import 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"
)

​
使用 ZERO_SHOT_REACT_DESCRIPTION

这展示了如何使用 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.'

​
多数据框示例

下一部分展示了代理如何与作为列表传入的多个数据框进行交互。 
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.'
在 GitHub 上编辑此页面源文件。
以编程方式连接这些文档到 Claude、VSCode 等，通过 MCP 获取实时答案。
© . This site is unofficial and not affiliated with LangChain, Inc.