|
-misol: vektor mashinasini qo‘llab-quvvatlash (SVM) yordamida tasniflash
| | bet | 29/182 | | Sana | 19.05.2024 | | Hajmi | 5,69 Mb. | | #244351 |
Bog'liq Python sun\'iy intellekt texnologiyasi Dasrlik 20241-misol: vektor mashinasini qo‘llab-quvvatlash (SVM) yordamida tasniflash
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score
# Ma’lumotlarni yuklash (masalan, Iris dataset)
iris = datasets.load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=42)
# SVM modelini yaratish va o‘qitish
svm_model = SVC(kernel='linear')
svm_model.fit(X_train, y_train)
# Sinov ma’lumotlarini bashorat qilish
y_pred = svm_model.predict(X_test)
# Modelning aniqligini baholash
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy}')
2-misol: Chiziqli regressiya yordamida regressiya
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
# Ma’lumotlarni yuklash (masalan, diabetes dataset)
diabetes = datasets.load_diabetes()
X_train, X_test, y_train, y_test = train_test_split(diabetes.data, diabetes.target, test_size=0.2, random_state=42)
# Chiziqli regressiya modelini yaratish va o‘qitish
linear_reg_model = LinearRegression()
linear_reg_model.fit(X_train, y_train)
# Sinov ma’lumotlarini bashorat qilish
y_pred = linear_reg_model.predict(X_test)
# Modelning standart xatosini baholash
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error: {mse}')
Bu oddiy misollar va scikit-learn kutubxonasi turli xil mashinalarni o‘rganish vazifalari uchun juda ko‘p funktsionallik va imkoniyatlarni taqdim etadi. Scikit-learn hujjatlarida siz turli xil usullar va ularning parametrlari haqida juda ko‘p ma’lumotlarni topishingiz mumkin.
Python-da scikit-learn kabi asosiy mashinalarni o‘rganish kutubxonalaridan foydalanish misollari keltirilgan:
|
| |
