From keras. Models import sequential.
From keras. Layers import dense.
İmport numpy as np.
From sklearn. Model_selection import train_test_split.
İmport matplotlib. Pyplot as plt.
From sklearn import metrics.
Dataset = np. Genfromtxt('emission_dataset. Csv', delimiter=',')
Giris = dataset[1:, 0:8]
Cikis = dataset[1:, 8]
# Çıktı değişkeni CO2 emisyonları olarak değiştirilir.
Cikis = cikis[:, 0]
Giris_train, giris_test, cikis_train, cikis_test = train_test_split(giris, cikis, test_size=0.2, random_state = 0)
Model = Sequential()
Model. Add(dense(6, input_dim = 8, activation='relu'))
Model. Add(dense(6, activation='relu'))
Model. Add(dense(6, activation='relu'))
Model. Add(dense(6, activation='relu'))
Model. Add(dense(1, activation='sigmoid'))
Model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
Model. Fit(giris_train, cikis_train, epochs = 30, batch_size = 5)
Cikis_pred = model. Predict(giris_test)
Cikis_pred = (cikis_pred > 0.5).flatten()
Print("doğruluk:", metrics. Accuracy_score(cikis_test, cikis_pred))
CM = confusion_matrix(cikis_test, cikis_pred)
İndex = ['Düşük', 'Yüksek']
Columns = ['Düşük', 'Yüksek']
Cm_df = pd. Dataframe(CM, columns, index)
Plt. Figure(figsize=(10, 6))
Sns. Heatmap(cm_df, annot = true, fmt="D")