From f648bd58bec24d5c199e8c31d1cb73bb9096d0f0 Mon Sep 17 00:00:00 2001
From: tomrink <rink@ssec.wisc.edu>
Date: Wed, 1 May 2024 17:07:28 -0500
Subject: [PATCH] snapshot...
---
modules/machine_learning/classification.py | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/modules/machine_learning/classification.py b/modules/machine_learning/classification.py
index c588ceb2..79813e32 100644
--- a/modules/machine_learning/classification.py
+++ b/modules/machine_learning/classification.py
@@ -67,12 +67,11 @@ def plot_confusion_matrix(cm, classes,
plt.xlabel('Predicted label')
-def get_csv_as_dataframe(csv_file, reduce_frac=None, random_state=42):
+def get_csv_as_dataframe(csv_file, reduce_frac=1.0, random_state=42):
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(axis=0, frac=reduce_frac, random_state=random_state)
+ icing_df = icing_df.sample(axis=0, frac=reduce_frac, random_state=random_state)
# # remove approximately half of rows where column_name equals to column_value
# column_name = 'icing_intensity'
--
GitLab