From 009c06e3627bec37c40e5f82315c3dc3b7e8a07d Mon Sep 17 00:00:00 2001
From: tomrink <rink@ssec.wisc.edu>
Date: Wed, 24 Apr 2024 12:50:45 -0500
Subject: [PATCH] snapshot...

---
 modules/machine_learning/classification.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/modules/machine_learning/classification.py b/modules/machine_learning/classification.py
index 757bafe8..e8358bfc 100644
--- a/modules/machine_learning/classification.py
+++ b/modules/machine_learning/classification.py
@@ -12,8 +12,11 @@ from sklearn.tree import DecisionTreeClassifier
 import sklearn.tree as tree
 
 
-def get_csv_as_dataframe(csv_file):
+def get_csv_as_dataframe(csv_file, reduce_frac=None):
     icing_df = pd.read_csv(csv_file)
+    # Random selection of reduce_frac of the rows
+    if reduce_frac is not None:
+        icing_df = icing_df.sample(frac=reduce_frac)
     print(icing_df.describe())
     print(icing_df.shape)
     return icing_df
-- 
GitLab