如何对CSV文件进行问答

%pip install -qU langchain langchain-openai langchain-community langchain-experimental pandas

# Using LangSmith is recommended but not required. Uncomment below lines to use.
# import os
# os.environ["LANGCHAIN_TRACING_V2"] = "true"
# os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()

!wget https://web.stanford.edu/class/archive/cs/cs109/cs109.1166/stuff/titanic.csv -O titanic.csv

import pandas as pd

df = pd.read_csv("titanic.csv")
print(df.shape)
print(df.columns.tolist())

from langchain_community.utilities import SQLDatabase
from sqlalchemy import create_engine

engine = create_engine("sqlite:///titanic.db")
df.to_sql("titanic", engine, index=False)

db = SQLDatabase(engine=engine)
print(db.dialect)
print(db.get_usable_table_names())
print(db.run("SELECT * FROM titanic WHERE Age < 2;"))

from langchain_community.agent_toolkits import create_sql_agent

agent_executor = create_sql_agent(llm, db=db, agent_type="openai-tools", verbose=True)

agent_executor.invoke({"input": "what's the average age of survivors"})

ai_msg = llm.invoke(
    "I have a pandas DataFrame 'df' with columns 'Age' and 'Fare'. Write code to compute the correlation between the two columns. Return Markdown for a Python code snippet and nothing else."
)
print(ai_msg.content)

import pandas as pd
from langchain_core.prompts import ChatPromptTemplate
from langchain_experimental.tools import PythonAstREPLTool

df = pd.read_csv("titanic.csv")
tool = PythonAstREPLTool(locals={"df": df})
tool.invoke("df['Fare'].mean()")

llm_with_tools = llm.bind_tools([tool], tool_choice=tool.name)
response = llm_with_tools.invoke(
    "I have a dataframe 'df' and want to know the correlation between the 'Age' and 'Fare' columns"
)
response

response.tool_calls

from langchain_core.output_parsers.openai_tools import JsonOutputKeyToolsParser

parser = JsonOutputKeyToolsParser(key_name=tool.name, first_tool_only=True)
(llm_with_tools | parser).invoke(
    "I have a dataframe 'df' and want to know the correlation between the 'Age' and 'Fare' columns"
)

system = f"""You have access to a pandas dataframe `df`. \
Here is the output of `df.head().to_markdown()`:

\`\`\`
{df.head().to_markdown()}
\`\`\`

Given a user question, write the Python code to answer it. \
Return ONLY the valid Python code and nothing else. \
Don't assume you have access to any libraries other than built-in Python ones and pandas."""
prompt = ChatPromptTemplate.from_messages([("system", system), ("human", "{question}")])
code_chain = prompt | llm_with_tools | parser
code_chain.invoke({"question": "What's the correlation between age and fare"})

chain = prompt | llm_with_tools | parser | tool
chain.invoke({"question": "What's the correlation between age and fare"})

from operator import itemgetter

from langchain_core.messages import ToolMessage
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import MessagesPlaceholder
from langchain_core.runnables import RunnablePassthrough

system = f"""You have access to a pandas dataframe `df`. \
Here is the output of `df.head().to_markdown()`:

\`\`\`
{df.head().to_markdown()}
\`\`\`

Given a user question, write the Python code to answer it. \
Don't assume you have access to any libraries other than built-in Python ones and pandas.
Respond directly to the question once you have enough information to answer it."""
prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            system,
        ),
        ("human", "{question}"),
        # This MessagesPlaceholder allows us to optionally append an arbitrary number of messages
        # at the end of the prompt using the 'chat_history' arg.
        MessagesPlaceholder("chat_history", optional=True),
    ]
)


def _get_chat_history(x: dict) -> list:
    """Parse the chain output up to this point into a list of chat history messages to insert in the prompt."""
    ai_msg = x["ai_msg"]
    tool_call_id = x["ai_msg"].additional_kwargs["tool_calls"][0]["id"]
    tool_msg = ToolMessage(tool_call_id=tool_call_id, content=str(x["tool_output"]))
    return [ai_msg, tool_msg]


chain = (
    RunnablePassthrough.assign(ai_msg=prompt | llm_with_tools)
    .assign(tool_output=itemgetter("ai_msg") | parser | tool)
    .assign(chat_history=_get_chat_history)
    .assign(response=prompt | llm | StrOutputParser())
    .pick(["tool_output", "response"])
)

chain.invoke({"question": "What's the correlation between age and fare"})

from langchain_experimental.agents import create_pandas_dataframe_agent

agent = create_pandas_dataframe_agent(
    llm, df, agent_type="openai-tools", verbose=True, allow_dangerous_code=True
)
agent.invoke(
    {
        "input": "What's the correlation between age and fare? is that greater than the correlation between fare and survival?"
    }
)

df_1 = df[["Age", "Fare"]]
df_2 = df[["Fare", "Survived"]]

tool = PythonAstREPLTool(locals={"df_1": df_1, "df_2": df_2})
llm_with_tool = llm.bind_tools(tools=[tool], tool_choice=tool.name)
df_template = """\`\`\`python
{df_name}.head().to_markdown()
>>> {df_head}
\`\`\`"""
df_context = "\n\n".join(
    df_template.format(df_head=_df.head().to_markdown(), df_name=df_name)
    for _df, df_name in [(df_1, "df_1"), (df_2, "df_2")]
)

system = f"""You have access to a number of pandas dataframes. \
Here is a sample of rows from each dataframe and the python code that was used to generate the sample:

{df_context}

Given a user question about the dataframes, write the Python code to answer it. \
Don't assume you have access to any libraries other than built-in Python ones and pandas. \
Make sure to refer only to the variables mentioned above."""
prompt = ChatPromptTemplate.from_messages([("system", system), ("human", "{question}")])

chain = prompt | llm_with_tool | parser | tool
chain.invoke(
    {
        "question": "return the difference in the correlation between age and fare and the correlation between fare and survival"
    }
)