> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langchain.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Pandas Dataframe integration

> Integrate with the Pandas Dataframe tool using LangChain Python.

This notebook shows how to use agents to interact with a `Pandas DataFrame`. It is mostly optimized for question answering.

**NOTE: this agent calls the `Python` agent under the hood, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**

**NOTE: Since langchain migrated to v0.3 you should upgrade langchain\_openai and langchain.   This would avoid import errors.**

pip install -U langchain\_openai
pip install -U langchain

<Warning>
  The `langchain-experimental` package is no longer maintained. Examples that import from `langchain_experimental` may be outdated or broken. Use with caution.
</Warning>

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain.agents.agent_types import AgentType
from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
from langchain_openai import ChatOpenAI
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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"
)
```

## Using `ZERO_SHOT_REACT_DESCRIPTION`

This shows how to initialize the agent using the `ZERO_SHOT_REACT_DESCRIPTION` agent type.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
agent = create_pandas_dataframe_agent(OpenAI(temperature=0), df, verbose=True)
```

## Using OpenAI functions

This shows how to initialize the agent using the OPENAI\_FUNCTIONS agent type. Note that this is an alternative to the above.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
agent = create_pandas_dataframe_agent(
    ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613"),
    df,
    verbose=True,
    agent_type=AgentType.OPENAI_FUNCTIONS,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
agent.invoke("how many rows are there?")
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new  chain...

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


891There are 891 rows in the dataframe.

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
'There are 891 rows in the dataframe.'
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
agent.invoke("how many people have more than 3 siblings")
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> 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.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
'30 people have more than 3 siblings.'
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
agent.invoke("what's the square root of the average age?")
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> 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.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
'The square root of the average age is 5.449689683556195.'
```

## Multi DataFrame example

This next part shows how the agent can interact with multiple dataframes passed in as a list.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
df1 = df.copy()
df1["Age"] = df1["Age"].fillna(df1["Age"].mean())
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
agent = create_pandas_dataframe_agent(OpenAI(temperature=0), [df, df1], verbose=True)
agent.invoke("how many rows in the age column are different?")
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> 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.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
'177 rows in the age column are different.'
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
```

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/tools/pandas.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>