Upload notebook.ipynb

notebook.ipynb

@@ -0,0 +1,159 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5ROgtvTfTdy9"
+      },
+      "source": [
+        "## FlexTab Examples\n",
+        "Model page: https://huggingface.co/SAP/FlexTab"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "N-54dB6iTdy_"
+      },
+      "source": [
+        "The model you are trying to use is gated. Please make sure you have access to it by visiting the model page.To run inference, either set HF_TOKEN in your environment variables/ Secrets or run the following cell to login. 🤗"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "o7iIwHVHTdzA"
+      },
+      "outputs": [],
+      "source": [
+        "from huggingface_hub import login\n",
+        "login(new_session=False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Uninstall conflicting packages from the default Colab environment\n",
+        "!pip uninstall torch torchvision torchaudio -y`"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6GqTz9gYTdzB"
+      },
+      "outputs": [],
+      "source": [
+        "# Install FlexTab core code\n",
+        "!pip install git+https://github.com/SAP-samples/flextab"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "jzA1dexsTdzB"
+      },
+      "outputs": [],
+      "source": [
+        "from sklearn.datasets import load_breast_cancer\n",
+        "from sklearn.metrics import accuracy_score\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "\n",
+        "from flextab import FlexTabClassifier\n",
+        "\n",
+        "# Load sample data\n",
+        "X, y = load_breast_cancer(return_X_y=True)\n",
+        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=42)\n",
+        "\n",
+        "# Initialize a classifier, 8k context and 8-fold bagging gives best performance, reduce if running out of memory\n",
+        "clf = FlexTabClassifier(max_context_size=8192, bagging=8)\n",
+        "\n",
+        "clf.fit(X_train, y_train)\n",
+        "\n",
+        "# Predict probabilities\n",
+        "prediction_probabilities = clf.predict_proba(X_test)\n",
+        "# Predict labels\n",
+        "predictions = clf.predict(X_test)\n",
+        "print(\"Accuracy\", accuracy_score(y_test, predictions))"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZlG2jXfWTdzC"
+      },
+      "outputs": [],
+      "source": [
+        "from sklearn.datasets import fetch_openml\n",
+        "from sklearn.metrics import r2_score\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "\n",
+        "from flextab import FlexTabRegressor\n",
+        "\n",
+        "# Load sample data\n",
+        "df = fetch_openml(data_id=531, as_frame=True)\n",
+        "X = df.data\n",
+        "y = df.target.astype(float)\n",
+        "\n",
+        "# Train-test split\n",
+        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, random_state=42)\n",
+        "\n",
+        "# Initialize the regressor, 8k context and 8-fold bagging gives best performance, reduce if running out of memory\n",
+        "regressor = FlexTabRegressor(max_context_size=8192, bagging=8)\n",
+        "\n",
+        "regressor.fit(X_train, y_train)\n",
+        "\n",
+        "# Predict on the test set\n",
+        "predictions = regressor.predict(X_test)\n",
+        "\n",
+        "r2 = r2_score(y_test, predictions)\n",
+        "print(\"R² Score:\", r2)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from sklearn.metrics import accuracy_score, roc_auc_score\n",
+        "\n",
+        "from flextab import FlexTabMatcher\n",
+        "from flextab.utils.test_utils import load_febrl4\n",
+        "\n",
+        "left_train, left_test, right_train, right_test, y_train, y_test = load_febrl4()\n",
+        "\n",
+        "matcher = FlexTabMatcher(max_context_size=8192, bagging=1)\n",
+        "matcher.fit(left_train, right_train, y_train)\n",
+        "predictions = matcher.predict(left_test, right_test)\n",
+        "print(f'Accuracy {accuracy_score(y_test, predictions):.2%}')\n",
+        "# Probabilities (e.g. for thresholding or AUROC):\n",
+        "# probas = matcher.predict_proba_matching(left_test, right_test)\n",
+        "# print(f'AUROC {roc_auc_score(y_test, probas[:, 1]):.2%}')"
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "gpuType": "T4",
+      "machine_shape": "hm",
+      "provenance": []
+    },
+    "kaggle": {
+      "accelerator": "gpu"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}