step1 complete step2 started

src/step2.py

@@ -0,0 +1,29 @@
+import pandas as pd
+from Levenshtein import distance
+
+
+def print_status(new, sys, bool_class):
+    print(f"\nEinträge in Import Liste: {len(new)}")
+    print(f"Einträge in System Liste: {len(sys)}")
+
+    if bool_class:
+        merged_df = pd.merge(new, sys, on=['name', 'vorname'], how='outer', indicator=True)
+        matches = pd.merge(new, sys, on=['name', 'vorname'])
+        matches = matches[['name', 'vorname', 'klasse']]
+    else:
+        merged_df = pd.merge(new, sys, on=['name', 'vorname'], how='outer', indicator=True)
+        matches = pd.merge(new, sys, on=['name', 'vorname'])
+        matches = matches[['name', 'vorname']]
+
+    # Subsets für Zeilen erstellen, die nur in einem der DataFrames vorhanden sind
+    only_new = merged_df[merged_df['_merge'] == 'left_only'].drop(columns=['_merge'])
+    only_sys = merged_df[merged_df['_merge'] == 'right_only'].drop(columns=['_merge'])
+
+    print("\nAnzahl Übereinstimmungen:", len(matches))
+    print("Anzahl neuer Nutzer:", len(only_new))
+    print("Anzahl veralteter Nutzer:", len(only_sys))
+    print(matches)
+
+
+def search_typos(new, sys):
+    matches = pd.merge(new, sys, on=['name', 'vorname'])