import giskard

# Replace this with your own data & model creation.
df = giskard.demo.titanic_df()
demo_data_processing_function, demo_sklearn_model = giskard.demo.titanic_pipeline()

# Wrap your Pandas DataFrame with Giskard.Dataset (test set, a golden dataset, etc.).
giskard_dataset = giskard.Dataset(
    df=df,  # A pandas.DataFrame that contains the raw data (before all the pre-processing steps) and the actual ground truth variable (target).
    target="Survived",  # Ground truth variable
    name="Titanic dataset", # Optional
    cat_columns=['Pclass', 'Sex', "SibSp", "Parch", "Embarked"]  # List of categorical columns. Optional, but is a MUST if available. Inferred automatically if not.
)

# Wrap your model with Giskard.Model. Check the dedicated doc page: https://docs.giskard.ai/en/latest/guides/wrap_model/index.html
# you can use any tabular, text or LLM models (PyTorch, HuggingFace, LangChain, etc.),
# for classification, regression & text generation.
def prediction_function(df):
    # The pre-processor can be a pipeline of one-hot encoding, imputer, scaler, etc.
    preprocessed_df = demo_data_processing_function(df)
    return demo_sklearn_model.predict_proba(preprocessed_df)

giskard_model = giskard.Model(
    model=prediction_function,  # A prediction function that encapsulates all the data pre-processing steps and that could be executed with the dataset used by the scan.
    model_type="classification",  # Either regression, classification or text_generation.
    name="Titanic model",  # Optional
    classification_labels=demo_sklearn_model.classes_,  # Their order MUST be identical to the prediction_function's output order
    feature_names=['PassengerId', 'Pclass', 'Name', 'Sex', 'Age', 'SibSp', 'Parch', 'Fare', 'Embarked'],  # Default: all columns of your dataset
)

scan_results = giskard.scan(giskard_model, giskard_dataset)

display(scan_results)

from deepeval import evaluate
from deepeval.metrics import HallucinationMetric
from deepeval.test_case import LLMTestCase

input = "What if these shoes don't fit?"
context = ["All customers are eligible for a 30 day full refund at no extra costs."]
# Replace this with the actual output from your LLM application
actual_output = "We offer a 30-day full refund at no extra costs."

hallucination_metric = HallucinationMetric(threshold=0.7)
test_case = LLMTestCase(
    input=input,
    actual_output=actual_output,
    context=context
)
evaluate([test_case], [hallucination_metric])

import promptfoo from 'promptfoo';

const results = await promptfoo.evaluate({
  prompts: ['Rephrase this in French: {{body}}', 'Rephrase this like a pirate: {{body}}'],
  providers: ['openai:gpt-3.5-turbo'],
  tests: [
    {
      vars: {
        body: 'Hello world',
      },
    },
    {
      vars: {
        body: "I'm hungry",
      },
    },
  ],
});

from deepchecks.tabular.suites import model_evaluation

suite = model_evaluation()

suite_result = suite.run(train_dataset=train_dataset, test_dataset=test_dataset, model=model)

suite_result.save_as_html() # replace this with suite_result.show() or suite_result.show_in_window() to see results inline or in window

# or suite_result.results[0].value with the relevant check index to process the check result's values in python

# It is recommended to deploy within a virtual environment

import great_expectations as gx

context = gx.get_context()