From 99573c5494efcd10b07ab2a6b0e90b40623cecbd Mon Sep 17 00:00:00 2001
From: tomrink <rink@ssec.wisc.edu>
Date: Thu, 16 May 2024 09:48:56 -0500
Subject: [PATCH] snapshot...
---
modules/machine_learning/classification.py | 27 ++++++++++++++--------
1 file changed, 17 insertions(+), 10 deletions(-)
diff --git a/modules/machine_learning/classification.py b/modules/machine_learning/classification.py
index 8b8cfcc6..18040b7a 100644
--- a/modules/machine_learning/classification.py
+++ b/modules/machine_learning/classification.py
@@ -15,8 +15,14 @@ import sklearn.tree as tree
from sklearn.tree import export_graphviz
# The independent variables (features) we want to use:
-# params = ['cld_temp_acha', 'supercooled_cloud_fraction', 'cld_reff_dcomp', 'cld_opd_dcomp', 'cld_cwp_dcomp']
-params = ['cld_temp_acha', 'supercooled_cloud_fraction', 'cld_reff_dcomp', 'cld_opd_dcomp']
+# feature_params = ['cld_temp_acha', 'supercooled_cloud_fraction', 'cld_reff_dcomp', 'cld_opd_dcomp', 'cld_cwp_dcomp']
+# feature_params = ['cld_temp_acha', 'supercooled_cloud_fraction', 'cld_reff_dcomp', 'cld_opd_dcomp']
+feature_params = ['cld_temp_acha', 'supercooled_cloud_fraction', 'cld_reff_acha', 'cld_opd_acha']
+
+# The dependent variable (target)
+target_param = 'icing_intensity'
+
+params = feature_params + [target_param]
def metrics(y_true, y_pred, y_pred_prob=None):
@@ -74,15 +80,16 @@ def plot_confusion_matrix(cm, classes,
def get_feature_target_data(csv_file, reduce_frac=1.0, random_state=42, standardize=True, remove_nan=False):
icing_df = pd.read_csv(csv_file)
+ icing_df = icing_df[params]
+
# Random selection of reduce_frac of the rows
icing_df = icing_df.sample(axis=0, frac=reduce_frac, random_state=random_state)
- # Remove these, more than half seem to be NaN
- icing_df = icing_df.drop('lwc_dcomp', axis=1)
- icing_df = icing_df.drop('iwc_dcomp', axis=1)
-
- # Remove this column for now.
- icing_df = icing_df.drop('cld_geo_thick', axis=1)
+ # # Remove these, more than half seem to be NaN
+ # icing_df = icing_df.drop('lwc_dcomp', axis=1)
+ # icing_df = icing_df.drop('iwc_dcomp', axis=1)
+ # # Remove this column for now.
+ # icing_df = icing_df.drop('cld_geo_thick', axis=1)
print('num obs, features: ', icing_df.shape)
if remove_nan:
@@ -91,7 +98,7 @@ def get_feature_target_data(csv_file, reduce_frac=1.0, random_state=42, standard
# icing_df = icing_df[icing_df.cld_temp_acha < 273.10]
- x = np.asarray(icing_df[params])
+ x = np.asarray(icing_df[feature_params])
if standardize:
stdSclr = preprocessing.StandardScaler()
stdSclr.fit(x)
@@ -100,7 +107,7 @@ def get_feature_target_data(csv_file, reduce_frac=1.0, random_state=42, standard
joblib.dump(stdSclr, '/Users/tomrink/stdSclr_4.pkl')
# The dependent variable (target) --------------------------------------------
- y = np.asarray(icing_df['icing_intensity'])
+ y = np.asarray(icing_df[target_param])
y = np.where(y == -1, 0, y)
y = np.where(y >= 1, 1, y)
--
GitLab