[RFC] Add a Galaxy tool for TabPFN package (by Prof. Hutter's group)

tools/tabpfn/.shed.yml

@@ -0,0 +1,13 @@
+name: tabpfn
+owner: bgruening
+description: Tabular data prediction using TabPFN using Pytorch.
+long_description: |
+  The TabPFN is a neural network that learned to do tabular data prediction.
+  This is the original CUDA-supporting pytorch impelementation.
+remote_repository_url: https://github.com/bgruening/galaxytools/tree/master/tools/tabpfn
+homepage_url: https://github.com/bgruening/galaxytools/tree/master/tools/tabpfn
+type:
+categories:
+  - Machine Learning
+maintainers:
+  anuprulez

tools/tabpfn/main.py

@@ -0,0 +1,54 @@
+"""
+Tabular data prediction using TabPFN
+"""
+import argparse
+import time
+
+import matplotlib.pyplot as plt
+import pandas as pd
+from sklearn.metrics import accuracy_score, average_precision_score, precision_recall_curve
+from tabpfn import TabPFNClassifier
+
+
+def separate_features_labels(data):
+    df = pd.read_csv(data, sep=",")
+    labels = df.iloc[:, -1]
+    features = df.iloc[:, :-1]
+    return features, labels
+
+
+def train_evaluate(args):
+    """
+    Train TabPFN
+    """
+    tr_features, tr_labels = separate_features_labels(args["train_data"])
+    te_features, te_labels = separate_features_labels(args["test_data"])
+    classifier = TabPFNClassifier(device='cpu', N_ensemble_configurations=32)
+    s_time = time.time()
+    classifier.fit(tr_features, tr_labels)
+    e_time = time.time()
+    print("Time taken by TabPFN for training: {} seconds".format(e_time - s_time))
+    y_eval, p_eval = classifier.predict(te_features, return_winning_probability=True)
+    print('Accuracy', accuracy_score(te_labels, y_eval))
+    pred_probas_test = classifier.predict_proba(te_features)
+    te_features["predicted_labels"] = y_eval
+    te_features.to_csv("output_predicted_data", sep="\t", index=None)
+    precision, recall, thresholds = precision_recall_curve(te_labels, pred_probas_test[:, 1])
+    average_precision = average_precision_score(te_labels, pred_probas_test[:, 1])
+    plt.figure(figsize=(8, 6))
+    plt.plot(recall, precision, label=f'Precision-Recall Curve (AP={average_precision:.2f})')
+    plt.xlabel('Recall')
+    plt.ylabel('Precision')
+    plt.title('Precision-Recall Curve')
+    plt.legend(loc='lower left')
+    plt.grid(True)
+    plt.savefig("output_prec_recall_curve.png")
+
+
+if __name__ == "__main__":
+    arg_parser = argparse.ArgumentParser()
+    arg_parser.add_argument("-trdata", "--train_data", required=True, help="Train data")
+    arg_parser.add_argument("-tedata", "--test_data", required=True, help="Test data")
+    # get argument values
+    args = vars(arg_parser.parse_args())
+    train_evaluate(args)

tools/tabpfn/tabpfn.xml

@@ -0,0 +1,62 @@
+<tool id="tabpfn" name="Tabular data prediction using TabPFN" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0">
+    <description>with PyTorch</description>
+    <macros>
+        <token name="@TOOL_VERSION@">0.1</token>
+        <token name="@VERSION_SUFFIX@">0</token>
+    </macros>
+    <creator>
+        <organization name="European Galaxy Team" url="https://galaxyproject.org/eu/" />
+        <person givenName="Anup" familyName="Kumar" email="[email protected]" />
+        <person givenName="Frank" familyName="Hutter" email="[email protected]" />
+    </creator>
+    <requirements>
+	<requirement type="package" version="0.1.10">tabpfn</requirement>
+	<requirement type="package" version="2.2.2">pandas</requirement>
+	<requirement type="package" version="3.9.2">matplotlib</requirement>
+    </requirements>
+    <version_command>echo "@VERSION@"</version_command>
+    <command detect_errors="aggressive">
+    <![CDATA[
+        python '$__tool_directory__/main.py'
+            --train_data '$train_data'
+            --test_data '$test_data'
+    ]]>
+    </command>
+    <inputs>
+	<param name="train_data" type="data" format="csv" label="Train data" help="Please provide training data for training model."/>
+        <param name="test_data" type="data" format="csv" label="Test data" help="Please provide test data for evaluating model."/>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="output_predicted_data" from_work_dir="output_predicted_data" label="Predicted data"></data>
+        <data format="png" name="output_prec_recall_curve" from_work_dir="output_prec_recall_curve.png" label="Precision-recall curve"></data>
+    </outputs>
+    <tests>
+        <test>
+	    <param name="train_data" value="local_train_rows" ftype="csv" />
+	    <param name="test_data" value="local_test_rows" ftype="csv" />
+            <output name="output_predicted_data" file="output_predicted_data" ftype="tabular">
+	        <assert_contents>
+		    <has_n_columns n="42" />
+     	            <has_n_lines n="838" />
+	        </assert_contents>
+	    </output>
+        </test>
+    </tests>
+    <help>
+        <![CDATA[
+            **What it does**
+
+            Prediction on tabular data by TabPFN
+
+            **Input files**
+            - Training data
+            - Test data
+
+            **Output files**
+            - Predicted data along with predicted labels
+        ]]>
+    </help>
+    <citations>
+        <citation type="doi">10.48550/arXiv.2207.01848</citation>
+    </citations>
+</tool>