From 72709651fa51c79e801451471fa9e1815af6f05e Mon Sep 17 00:00:00 2001
From: Laborratte5 <laborratte5@gmail.com>
Date: Sun, 22 Jun 2025 18:00:20 +0200
Subject: [PATCH] Parse cli arguments using argparse

---
 src/cluster_test/cluster.py | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/src/cluster_test/cluster.py b/src/cluster_test/cluster.py
index 1973f47..f431ccf 100644
--- a/src/cluster_test/cluster.py
+++ b/src/cluster_test/cluster.py
@@ -1,3 +1,4 @@
+import argparse
 import numpy as np
 import pandas
 from sklearn.impute import SimpleImputer
@@ -32,8 +33,18 @@ def classify(X, data_frame):
     return data_frame[y_pred < 0]
 
 if __name__ == '__main__':
-    data_frame = read_excel("tests/Beispiel Auswertung2.xlsx")
-    X = pandas.get_dummies(data_frame) # OneHotEncode categorical values
+    parser = argparse.ArgumentParser()
+    parser.add_argument("file")
+    parser.add_argument(
+        "--data-column",
+        default="Messpunkt",
+        help="Used to identify the columns containing measurements. The heading of each column containing data should contain the specified value."
+    )
+    args = parser.parse_args()
+
+    data_frame = read_excel(args.file)
+    X = data_frame.filter(like=args.data_column, axis='columns')
+    X = pandas.get_dummies(X) # OneHotEncode categorical values
     pipe = make_pipeline(SimpleImputer(add_indicator=True))
     X = pipe.fit_transform(X)
     outlier = classify(X, data_frame)