Factual presented in explanation is different from original factual

[fabiensatalia]

When generating counterfactual explanations then looking at the factual in the explanation structure returned, I observe small differences. Namely, the value in column "BP" changes a bit. MWE follows:

import os
import random
from urllib.request import urlretrieve

import dice_ml
from lightgbm import LGBMRegressor
import numpy as np
import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler


def diabetes_df():
    url = "https://www4.stat.ncsu.edu/~boos/var.select/diabetes.tab.txt"
    # safety measure for MacOS, see
    # https://docs.python.org/3/library/urllib.request.html#module-urllib.request
    os.environ["no_proxy"] = "*"
    file_name, _ = urlretrieve(url)
    df = pd.read_csv(file_name, sep="\t").astype({"SEX": str}).astype({"SEX": "category"})
    return df.sample(200, random_state=1)


def data_and_model(df, numerical, categorical, target_column):
    np.random.seed(1)
    numeric_transformer = Pipeline(steps=[("scaler", StandardScaler())])
    categorical_transformer = Pipeline(steps=[("onehot", OneHotEncoder(handle_unknown="ignore"))])
    transformations = ColumnTransformer(
        transformers=[
            ("num", numeric_transformer, numerical),
            ("cat", categorical_transformer, categorical),
        ]
    )
    #
    X = df.drop(target_column, axis=1)
    y = df[target_column]
    clf = Pipeline(steps=[("preprocessor", transformations), ("regressor", LGBMRegressor())])
    model = clf.fit(X, y)
    return X, y, model


# Data set
df = diabetes_df()
numerical = ["AGE", "BMI", "BP", "S1", "S2", "S3", "S4", "S5", "S6"]
categorical = ["SEX"]
x_train, y_train, model = data_and_model(df, numerical, categorical, "Y")
factuals = x_train[0:1]

seed = 5
random.seed(seed)
np.random.seed(seed)

# Ask for counterfactual explanations
df_for_dice = pd.concat([x_train, y_train], axis=1)
dice_data = dice_ml.Data(dataframe=df_for_dice, continuous_features=numerical, outcome_name="Y")
dice_model = dice_ml.Model(model=model, backend="sklearn", model_type="regressor")
dice_explainer = dice_ml.Dice(dice_data, dice_model, method="genetic")
features_to_vary = ["BMI", "BP", "S1", "S2", "S3", "S4", "S5", "S6"]
explanations = dice_explainer.generate_counterfactuals(
    factuals,
    total_CFs=5,
    desired_range=[60, 90],
    features_to_vary=features_to_vary,
    posthoc_sparsity_algorithm="binary",
)
print(explanations.cf_examples_list[0].test_instance_df)
print(factuals)

And here is the output:

   AGE SEX   BMI         BP   S1     S2    S3   S4      S5  S6          Y
0   60   1  23.4  76.669998  247  148.0  65.0  3.8  5.1358  77  93.585579
     AGE SEX   BMI     BP   S1     S2    S3   S4      S5  S6
246   60   1  23.4  76.67  247  148.0  65.0  3.8  5.1358  77

[simon19891101]

Yours look like a precision issue. Mine looks even worse: the categorical feature totally flipped! See the original factual (blue "V0") and the factual in the prediction (red "V0"). Hope @amit-sharma can throw some light upon. Many thanks.