Neyron tarmog‘i. Eng oddiy neyron tarmoq qurish texnologiyasi Ishdan maqsad

Download 0,53 Mb.
bet	2/3
Sana	19.12.2023
Hajmi	0,53 Mb.
	#123948

1 2 3

Bog'liq
anvar robo5
1-Ma\'ruza, Gum.psix shaxs, 1-a, sonli usular 2chi M,ish, 3-laborotoriya ishi, xozirgi zamon ekalogik muammolari, Qizil QQ 30 aprel 1952 jil N 86, Elmurod . Takrorlash, Fonetika va fonologiya haqida umumiy ma’lumot, Dinshunoslik mustaqil ish, ikkinchi jahon urushi diplomatiyasi., 4-amaliy ish taxtid Diyor, Arduino hamda altera de0 qurulmalarini o’rganish, O’zbekiston respublikasi axborot texnologiyalari va kommunikatsi

2-dastur kodi va natijasi
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import load_iris
from keras.models import Sequential
from keras.layers import Dense

# Ma'lumotlarni yuklash

iris = load_iris()
X = iris.data
y = iris.target

# Qiymatlarni binar kategoriyaga aylantiramiz

y = pd.get_dummies(y).values

# Ma'lumotlarni o'qitish va sinov uchun ajratamiz

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Ma'lumotlarni standartlashtiramiz

scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# Modelni tuzamiz

model = Sequential()
model.add(Dense(4, input_dim=4, activation='relu'))
model.add(Dense(3, activation='softmax'))

# Modelni tuzamiz

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

# Modelni o'qitamiz

model.fit(X_train, y_train, epochs=50, batch_size=8, validation_data=(X_test, y_test))
import matplotlib.pyplot as plt

# Modelning o'qitilishi davriga oid ma'lumotlarni olamiz

history = model.history.history

# O'qitish natijalarni grafikga chizamiz

plt.plot(history['accuracy'], label='Training Accuracy')
plt.plot(history['val_accuracy'], label='Validation Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()
plt.show()
# Test ma'lumotlaridan bashqa ma'lumotlarni standartlashtiramiz
X_new = scaler.transform(X_test)