From 2c47ece998e3c2522deb409f51c45cf00c17e309 Mon Sep 17 00:00:00 2001
From: tomrink <rink@ssec.wisc.edu>
Date: Fri, 26 Apr 2024 10:54:10 -0500
Subject: [PATCH] snapshot...
---
modules/machine_learning/classification.py | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/modules/machine_learning/classification.py b/modules/machine_learning/classification.py
index 3e30531f..0d4c3993 100644
--- a/modules/machine_learning/classification.py
+++ b/modules/machine_learning/classification.py
@@ -57,6 +57,18 @@ def get_csv_as_dataframe(csv_file, reduce_frac=None, random_state=42):
if reduce_frac is not None:
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'
+ # column_value = -1
+ # if column_name in icing_df.columns:
+ # df_to_reduce = icing_df[icing_df[column_name] == column_value]
+ # icing_df = icing_df[icing_df[column_name] != column_value]
+ #
+ # if reduce_frac is not None:
+ # df_to_reduce = df_to_reduce.sample(axis=0, frac=0.5, random_state=random_state)
+ #
+ # icing_df = pd.concat([icing_df, df_to_reduce])
+
return icing_df
--
GitLab