Batch Evaluations

import pandas as pd

from phoenix.evals import evaluate_dataframe
from phoenix.evals.metrics import PrecisionRecallFScore

precision_recall_fscore = PrecisionRecallFScore(positive_label="Yes")

df = pd.DataFrame(
    {
        "output": [["Yes", "Yes", "No"], ["Yes", "No", "No"]],
        "expected": [["Yes", "No", "No"], ["Yes", "No", "No"]],
    }
)

result = evaluate_dataframe(dataframe=df, evaluators=[precision_recall_fscore])
result.head()

from phoenix.evals import bind_evaluator, evaluate_dataframe
from phoenix.evals.llm import LLM
from phoenix.evals.metrics import FaithfulnessEvaluator, exact_match

df = pd.DataFrame(
    {
        # exact_match columns
        "output": ["Yes", "Yes", "No"],
        "expected": ["Yes", "No", "No"],
        # faithfulness columns (need mapping)
        "context": ["This is a test", "This is another test", "This is a third test"],
        "query": [
            "What is the name of this test?",
            "What is the name of this test?",
            "What is the name of this test?",
        ],
        "response": ["First test", "Another test", "Third test"],
    }
)

llm = LLM(provider="openai", model="gpt-4o")
faithfulness_evaluator = bind_evaluator(
    FaithfulnessEvaluator(llm=llm), {"input": "query", "output": "response"}
)

result = evaluate_dataframe(dataframe=df, evaluators=[exact_match, faithfulness_evaluator])
result.head()

from phoenix.evals.llm import LLM
from phoenix.evals.metrics import FaithfulnessEvaluator
from phoenix.evals import async_evaluate_dataframe

df = pd.DataFrame(
    {
        "context": ["This is a test", "This is another test", "This is a third test"],
        "input": [
            "What is the name of this test?",
            "What is the name of this test?",
            "What is the name of this test?",
        ],
        "output": ["First test", "Another test", "Third test"],
    }
)

llm = LLM(provider="openai", model="gpt-4o")
faithfulness_evaluator = FaithfulnessEvaluator(llm=llm)

result = await async_evaluate_dataframe(dataframe=df, evaluators=[faithfulness_evaluator], concurrency=5)
result.head()