From 2e6f06eb1d0e8e113a14ae6fa247213a5373f706 Mon Sep 17 00:00:00 2001
From: Tristan Smith <tristan.smith@gmail.com>
Date: Sun, 26 May 2024 23:51:32 -0400
Subject: [PATCH] Added a pandas script for cleaning up csv.
---
organize_csv.py | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
create mode 100644 organize_csv.py
diff --git a/organize_csv.py b/organize_csv.py
new file mode 100644
index 0000000..33e5f84
--- /dev/null
+++ b/organize_csv.py
@@ -0,0 +1,20 @@
+# Not sure how this will act on a number of machines.
+
+import pandas as pd
+
+df = pd.read_csv('results.csv')
+
+df = df.drop_duplicates()
+
+df = df.sort_values(by=['Worker ID', 'IP Address'])
+
+# Group by Worker ID, IP Address, Log File, and Error Type
+df['Error Count'] = 1
+df_grouped = df.groupby(['Worker ID', 'IP Address', 'Log File', 'Error Type'], as_index=False).agg({
+ 'Error Message': 'first',
+ 'Error Count': 'sum'
+})
+
+df_grouped.to_csv('cleaned_results_grouped.csv', index=False)
+
+print(df_grouped)