From fb5dfb20f553b617075da6e7499e351668802cd7 Mon Sep 17 00:00:00 2001
From: tomrink <rink@ssec.wisc.edu>
Date: Wed, 24 Apr 2024 15:35:31 -0500
Subject: [PATCH] snapshot...
---
modules/machine_learning/classification.py | 50 ++++++++++++++++++++--
1 file changed, 46 insertions(+), 4 deletions(-)
diff --git a/modules/machine_learning/classification.py b/modules/machine_learning/classification.py
index e29641b4..dcbfa2de 100644
--- a/modules/machine_learning/classification.py
+++ b/modules/machine_learning/classification.py
@@ -2,13 +2,14 @@ import pandas as pd
import pylab as pl
import numpy as np
import scipy.optimize as opt
-from sklearn import preprocessing
+from sklearn import preprocessing, svm
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix, accuracy_score, jaccard_score, f1_score, precision_score, recall_score, roc_auc_score
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier
import sklearn.tree as tree
from sklearn.tree import export_graphviz
@@ -136,7 +137,7 @@ def k_nearest_neighbors_all(x, y, k_s=10):
plt.show()
-def decision_tree(x, y, max_depth=4):
+def decision_tree(x, y, criterion='entropy', max_depth=4):
x_train, x_test, y_train, y_test = train_test_split( x, y, test_size=0.2, random_state=4)
print('Train set:', x_train.shape, y_train.shape)
print('Test set:', x_test.shape, y_test.shape)
@@ -146,7 +147,7 @@ def decision_tree(x, y, max_depth=4):
print('num no icing test: ', np.sum(y_test == 0))
print('num icing test: ', np.sum(y_test == 1))
- DT = DecisionTreeClassifier(criterion="entropy", max_depth=max_depth).fit(x_train, y_train)
+ DT = DecisionTreeClassifier(criterion=criterion, max_depth=max_depth).fit(x_train, y_train)
yhat = DT.predict(x_test)
yhat_prob = DT.predict_proba(x_test)
@@ -158,7 +159,48 @@ def decision_tree(x, y, max_depth=4):
print('AUC: ', "{:.4f}".format(roc_auc_score(y_test, yhat_prob[:, 1])))
return DT
-
# export_graphviz(DT, out_file='tree.dot', filled=True, feature_names=['cld_geo_thick', 'cld_temp_acha', 'conv_cloud_fraction', 'supercooled_cloud_fraction', 'cld_reff_dcomp', 'cld_opd_dcomp', 'iwc_dcomp'])
# !dot -Tpng tree.dot -o tree.png
+
+def SVM(x, y, kernel='rbf'):
+ x_train, x_test, y_train, y_test = train_test_split( x, y, test_size=0.2, random_state=4)
+ print('Train set:', x_train.shape, y_train.shape)
+ print('Test set:', x_test.shape, y_test.shape)
+
+ x_train = np.where(np.isnan(x_train), 0, x_train)
+ x_test = np.where(np.isnan(x_test), 0, x_test)
+ print('num no icing test: ', np.sum(y_test == 0))
+ print('num icing test: ', np.sum(y_test == 1))
+
+ clf = svm.SVC(kernel=kernel)
+ clf = clf.fit(x_train, y_train)
+ yhat = clf.predict(x_test)
+
+ print('Accuracy: ', "{:.4f}".format(accuracy_score(y_test, yhat)))
+ print('Jaccard Idx: ', "{:.4f}".format(jaccard_score(y_test, yhat)))
+ print('Precision: ', "{:.4f}".format(precision_score(y_test, yhat)))
+ print('Recall: ', "{:.4f}".format(recall_score(y_test, yhat)))
+ print('F1: ', "{:.4f}".format(f1_score(y_test, yhat)))
+
+
+def random_forest(x, y, criterion='entropy', max_depth=4):
+ x_train, x_test, y_train, y_test = train_test_split( x, y, test_size=0.2, random_state=4)
+ print('Train set:', x_train.shape, y_train.shape)
+ print('Test set:', x_test.shape, y_test.shape)
+
+ x_train = np.where(np.isnan(x_train), 0, x_train)
+ x_test = np.where(np.isnan(x_test), 0, x_test)
+ print('num no icing test: ', np.sum(y_test == 0))
+ print('num icing test: ', np.sum(y_test == 1))
+
+ rnd_clf = RandomForestClassifier(criterion=criterion, max_depth=max_depth).fit(x_train, y_train)
+ yhat = rnd_clf.predict(x_test)
+ yhat_prob = rnd_clf.predict_proba(x_test)
+
+ print('Accuracy: ', "{:.4f}".format(accuracy_score(y_test, yhat)))
+ print('Jaccard Idx: ', "{:.4f}".format(jaccard_score(y_test, yhat)))
+ print('Precision: ', "{:.4f}".format(precision_score(y_test, yhat)))
+ print('Recall: ', "{:.4f}".format(recall_score(y_test, yhat)))
+ print('F1: ', "{:.4f}".format(f1_score(y_test, yhat)))
+ print('AUC: ', "{:.4f}".format(roc_auc_score(y_test, yhat_prob[:, 1])))
--
GitLab