Code: Select all
from sklearn.model_selection import train_test_split
from sklearn import model_selection
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import roc_auc_score
# implementing train-test-split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.34, random_state=66)
# random forest model creation
rfc = RandomForestClassifier(n_estimators=200, random_state=39, max_depth=4)
rfc.fit(X_train,y_train)
# predictions
rfc_predict = rfc.predict(X_test)
print("=== Confusion Matrix ===")
print(confusion_matrix(y_test, rfc_predict))
print('\n')
print("=== Classification Report ===")
print(classification_report(y_test, rfc_predict))
< /code>
out [1]: < /p>
=== Confusion Matrix ===
[[16243 1011]
[ 827 16457]]
=== Classification Report ===
precision recall f1-score support
0 0.95 0.94 0.95 17254
1 0.94 0.95 0.95 17284
accuracy 0.95 34538
macro avg 0.95 0.95 0.95 34538
weighted avg 0.95 0.95 0.95 34538
# from sklearn import cross_validation
from sklearn.model_selection import cross_validate
kfold = KFold(n_splits=10)
conf_matrix_list_of_arrays = []
kf = cross_validate(rfc, X, y, cv=kfold)
print(kf)
for train_index, test_index in kf:
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
rfc.fit(X_train, y_train)
conf_matrix = confusion_matrix(y_test, rfc.predict(X_test))
conf_matrix_list_of_arrays.append(conf_matrix)
< /code>
Datensatz besteht aus diesem Datenrahmen: < /p>
Temperaturreihe Parallel Shading Anzahl der Zellenspannung (V) Strom (i) I /V Prozentsatz von Solar Panel Cell Shade ISShade
30 10 1 2 10 1.11 2,19 1,97 1985 1 20.0 1
27 5 2 10 10 2.33 4,16 1,79 1517 3 100.0 1
30 5 2 7 10 2,01 4,34 2,16 3532 1 70,0 1
40 2 4 3 8 1.13 -20.87 -18.47 6180 1 37,5 1
45 5 2 4 10 1.13 6.52 5.77 8812 3 40.0 1
< /pre>