Bodo DataFrames 集成

import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
    os.environ["OPENAI_API_KEY"] = getpass.getpass("Open AI API key:\n")

from langchain.agents.agent_types import AgentType
from langchain_bodo import create_bodo_dataframes_agent
from langchain_openai import ChatOpenAI

# Path to local titanic data
datapath = "titanic.csv"

import bodo.pandas as pd
from langchain_openai import OpenAI

df = pd.read_csv(datapath)

agent = create_bodo_dataframes_agent(
    OpenAI(temperature=0), df, verbose=True, allow_dangerous_code=True
)

agent = create_bodo_dataframes_agent(
    ChatOpenAI(temperature=0, model="gpt-3.5-turbo-1106"),
    df,
    verbose=True,
    agent_type=AgentType.OPENAI_FUNCTIONS,
    allow_dangerous_code=True,
)

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

> Entering new AgentExecutor chain...

Invoking: `python_repl_ast` with `{'query': 'len(df)'}`

891There are 891 rows in the dataframe.

> Finished chain.

{'input': 'how many rows are there?', 'output': 'There are 891 rows in the dataframe.'}

df2 = df[["Age", "Pclass", "Survived", "Fare"]]

# Potentially expensive computation using df.apply:
df2["Age"] = df2.apply(lambda x: x["Age"] if x["Pclass"] == 3 else 0, axis=1)

agent = create_bodo_dataframes_agent(
    OpenAI(temperature=0), df2, verbose=True, allow_dangerous_code=True
)

# The bdf["Age"] column is lazy and will not evaluate unless explicitly used by the agent.
agent.invoke("Out of the people who survived, what was their average fare?")

> Entering new AgentExecutor chain...
Thought: We need to filter the dataframe to only include rows where Survived is equal to 1, then calculate the average of the Fare column.
Action: python_repl_ast
Action Input: df[df["Survived"] == 1]["Fare"].mean()48.3954076023391748.39540760233917 is the average fare for people who survived.
Final Answer: 48.39540760233917

> Finished chain.

{'input': 'Out of the people who survived, what was their average fare?', 'output': '48.39540760233917'}

agent = create_bodo_dataframes_agent(
    OpenAI(temperature=0), [df, df2], verbose=True, allow_dangerous_code=True
)
agent.invoke("how many rows in the age column are different?")

> Entering new AgentExecutor chain...
Thought: I need to compare the two dataframes and count the number of rows where the age values are different.
Action: python_repl_ast
Action Input: len(df1[df1["Age"] != df2["Age"]])

... BodoLibFallbackWarning: Series._cmp_method is not implemented in Bodo DataFrames for the specified arguments yet. Falling back to Pandas (may be slow or run out of memory).
Exception: binary operation arguments must have the same dataframe source.
    warnings.warn(BodoLibFallbackWarning(msg))
... BodoLibFallbackWarning: DataFrame.__getitem__ is not implemented in Bodo DataFrames for the specified arguments yet. Falling back to Pandas (may be slow or run out of memory).
Exception: DataFrame getitem: Only selecting columns or filtering with BodoSeries is supported.
    warnings.warn(BodoLibFallbackWarning(msg))

359359 rows have different age values.
Final Answer: 359

> Finished chain.

{'input': 'how many rows in the age column are different?', 'output': '359'}

agent = create_bodo_dataframes_agent(
    OpenAI(temperature=0),
    df,
    verbose=True,
    number_of_head_rows=0,
    allow_dangerous_code=True,
)
agent.invoke("What is the average age of all female passengers?")

> Entering new AgentExecutor chain...
Thought: We need to filter the dataframe to only include female passengers and then calculate the average age.
Action: python_repl_ast
Action Input: df[df["Sex"] == "female"]["Age"].mean()27.91570881226053727.915708812260537 seems like a reasonable average age for female passengers.
Final Answer: 27.915708812260537

> Finished chain.

{'input': 'What is the average age of all female passengers?', 'output': '27.915708812260537'}

import pandas

pdf = pandas.read_csv(datapath)

agent = create_bodo_dataframes_agent(
    OpenAI(temperature=0), pdf, verbose=True, allow_dangerous_code=True
)

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

> Entering new AgentExecutor chain...
Thought: We need to calculate the average age first and then take the square root.
Action: python_repl_ast
Action Input: df["Age"].mean()29.69911764705882 Now we have the average age, we can take the square root.
Action: python_repl_ast
Action Input: math.sqrt(df["Age"].mean())NameError: name 'math' is not defined We need to import the math library to use the sqrt function.
Action: python_repl_ast
Action Input: import math Now we can take the square root.
Action: python_repl_ast
Action Input: math.sqrt(df["Age"].mean())5.449689683556195 I now know the final answer.
Final Answer: 5.449689683556195

> Finished chain.

{'input': 'What is the square root of the average age?', 'output': '5.449689683556195'}