diff --git a/src/preprocessing.py b/src/preprocessing.py
new file mode 100644
index 0000000..e1dc958
--- /dev/null
+++ b/src/preprocessing.py
@@ -0,0 +1,24 @@
+from sys import argv
+from pandas import read_table
+
+
+def read_header(filename):
+    with open(filename, "r") as f:
+        header = f.readline().split()
+    return header[0], header[1]
+
+
+def parse_file(filename):
+    n, m = read_header(filename)
+    df = read_table(
+        filename, names=["source", "destination", "distance"], sep=" ", skiprows=[0]
+    )
+    return n, m, df
+
+
+def main():
+    parse_file(argv[1])
+
+
+if __name__ == "__main__":
+    main()