Muhammad Al-Xorazmiy nomidagi
TATU Nurafshon filiali 710-21 guruh
talabasi Yesbolov Bekgazining Mashinali
o’qitish fanidan bajargan
Amaliy ishi.
Bajardi : Yesbolov B.
Tekshirdi : Qobilov S.
Bu vazifaning barcha qismlarini bitta Python skriptida bajarish mumkin. Mana shu misol skript:
```python
import matplotlib.pyplot as plt
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_classification
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import Adam
# 1. Dataset yaratish
X, y = make_classification(n_samples=1000, n_features=2, n_informative=2, n_redundant=0,
n_clusters_per_class=1, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Grafik tasvirlash
plt.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=plt.cm.RdYlBu)
plt.title('Dataset')
plt.xlabel('X1')
plt.ylabel('X2')
plt.show()
# 2. Neyron tarmoq arxitekturasi
model = Sequential()
model.add(Dense(10, input_dim=2, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# 3. Neyron tarmoqni o'qitish parametrlari
model.compile(loss='binary_crossentropy', optimizer=Adam(learning_rate=0.01),
metrics=['accuracy'])
# O'qitish
history = model.fit(X_train, y_train, epochs=50, batch_size=32, validation_data=(X_test, y_test))
# 4. Natijalarni visual va jadval qiymatlarini keltirish
# Accuracies
plt.plot(history.history['accuracy'], label='Training Accuracy')
plt.plot(history.history['val_accuracy'], label='Validation Accuracy')
plt.title('Training and Validation Accuracies')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()
plt.show()
# Losses
plt.plot(history.history['loss'], label='Training Loss')
plt.plot(history.history['val_loss'], label='Validation Loss')
plt.title('Training and Validation Losses')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
plt.show()
# Jadval qiymatlari
test_loss, test_acc = model.evaluate(X_test, y_test)
print(f'Test Loss: {test_loss:.4f}')
print(f'Test Accuracy: {test_acc:.4f}')
```
Bu skriptda:
1. `make_classification` funktsiyasi yordamida sodda dataset yaratildi.
2. Matplotlib kutubxonasidan foydalangan holda dataset tasvirlandi.
3. Keras kutubxonasi yordamida neyron tarmoq arxitekturasi qurildi.
4. O'qitish parametrlari tanlandi va neyron tarmoq o'qitildi.
5. O'qitish natijalari matplotlib orqali tasvirlandi va jadval qiymatlari chiqarildi.