M uhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti

M
uhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti


Mashinali o'qitishga kirish fanidan
Amaliy ishi 2

Guruh : 713-21

Topshirdi: Xushvaqtov Shamsiddin Tekshirdi:  Ochilov Mannon Musinovich

17 .Davlatlarni sinflashtirish O’zgatuvchi tanlamadagi misollar soni 40 Sinflar soni 3 Xususiyatlari soni 4

import numpy as np
dataset=np.array([
[4,5,1,2,0], #iqtisodiy_progressiy,inflatsiya_darajasi,demografik_usishi,it_progressiy,Class
[4,6,5,2,0],
[6,8,3,0,1],
[14,5,1,2,0],
[4,6,5,2,0],
[24,5,1,2,0],
[4,6,5,2,1],
[6,8,3,0,1],
[6,8,3,0,1],
[5.6,2.1,2.0,1,2],
[4,6,5,2,0],
[6,8,3,0,1],
[14,5,1,2,2],
[4,6,5,2,0],
[24,5,1,2,2],
[4,6,5,2,1],
[6,8,3,0,2],
[6,8,3,0,1],
[5.6,2.1,2.0,1,1],
[4,6,5,2,0],
[6,8,3,0,1],
[14,5,1,2,0],
[4,6,5,2,0],
[24,5,1,2,0],
[4,6,5,2,2],
[6,8,3,0,1],
[6,8,3,0,1],
[5.6,2.1,2.0,1,2],
[4,6,5,2,0],
[6,8,3,0,1],
[14,5,1,2,0],
[4,6,5,2,2],
[24,5,1,2,0],
[4,6,5,2,1],
[6,8,3,0,1],
[6,8,3,0,2]
])
x=dataset[:,0] #iqtisodiy_progressiy
y=dataset[:,2] #inflatsiya_darajasi
c=dataset[:,-1] #sinf
from matplotlib import pyplot as plt
plt.figure(figsize=(8,6))

plt.scatter(x[c==0],y[c==0],s=40, alpha=1,label='1-sinf',color='g',marker='s')
plt.scatter(x[c==1],y[c==1], s=40, alpha=0.7,label='2-sinf',color='b',marker='^')

# plt.scatter(x[c==2],y[c==2], s=40, alpha=0.8,label='3-sinf')

plt.xlabel('xususiyat-1')
plt.ylabel('xususiyat-2')
plt.legend()
plt.grid()
plt.show()

# Modelni qurish uchun datasetni train va test qismlarga ajratish
X_train= dataset[:,:-1] #barcha xususiyatlar
Y_train=dataset[:,-1] #sinf
array([[ 4. , 5. , 1. , 2. ],
[ 4. , 6. , 5. , 2. ],
[ 6. , 8. , 3. , 0. ],
[14. , 5. , 1. , 2. ],
[ 4. , 6. , 5. , 2. ],
[24. , 5. , 1. , 2. ],
[ 4. , 6. , 5. , 2. ],
[ 6. , 8. , 3. , 0. ],
[ 6. , 8. , 3. , 0. ],
[ 5.6, 2.1, 2. , 1. ]])
[ ]
Y_train
account_circle
array([0., 0., 1., 0., 0., 0., 1., 1., 1., 1.])
from sklearn.model_selection import train_test_split
from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(X_train, Y_train, test_size=0.15, random_state=42)

x_train.shape

x_test.shape

from sklearn.linear_model import LogisticRegression

logisticRegr = LogisticRegression()

logisticRegr.fit(x_train, y_train)

train_pred = logisticRegr.predict(x_train)

#train to'plam uchun
score = logisticRegr.score(x_train, y_train)
print(score)
test_pred = logisticRegr.predict(x_test)
#test to'plam uchun
score = logisticRegr.score(x_test, y_test)
print(score)
from sklearn.metrics import confusion_matrix
#train to'plam uchun
cm = confusion_matrix(y_train, train_pred)
print(cm)
#test to'plam uchun
cm = confusion_matrix(y_test, test_pred)
print(cm)
#datasetda yo'q misol bilan testlash
logisticRegr.predict([[4.7,6,3,0]])[0]
Xulosa
Logistik regressiya bu o'zgaruvchilardan o'zaro bog'liqlikni aniqlash usulidir, ulardan biri qat'iyan bog'liq, boshqalari esa mustaqil. Buning uchun logistik funksiyada) foydalaniladi. Logistik regressiyaning amaliy qiymati shundaki, u bir yoki bir nechta mustaqil o'zgaruvchini o'z ichiga olgan voqealarni bashorat qilishning kuchli statistik usuli hisoblanadi.