Concrete-ML provides partial support for Pandas, with most available models (linear and tree-based models) usable on Pandas dataframes just as they would be used with NumPy arrays.

The table below summarizes current compatibility:


The following example considers a LogisticRegression model on a simple classification problem. A more advanced example can be found in the Titanic use case notebook, which considers a XGBClassifier.

import numpy as np
import pandas as pd
from import LogisticRegression
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split

# Create the data set as a Pandas dataframe
X, y = make_classification(
X, y = pd.DataFrame(X), pd.DataFrame(y)

# Retrieve train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=42)

# Instantiate the model
model = LogisticRegression(n_bits=8)

# Fit the model, y_train)

# Evaluate the model on the test set in clear
y_pred_clear = model.predict(X_test)

# Compile the model

# Perform the inference in FHE
y_pred_fhe = model.predict(X_test, execute_in_fhe=True)

# Assert that FHE predictions are the same as the clear predictions
    f"{(y_pred_fhe == y_pred_clear).sum()} "
    f"examples over {len(y_pred_fhe)} have a FHE inference equal to the clear inference."

# Output:
    # 100 examples over 100 have a FHE inference equal to the clear inference.

Last updated