Notes

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sn
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
from sklearn import neighbors, datasets, preprocessing

a=pd.read_csv('C:\Users\kuru\Desktop\car_data.csv')



print(a)#Excell tablosu ekrana yazıldı.


a.head(30)

a.shape

xpoint=np.array(a[['Age','AnnualSalary']])
ypoint=np.array(a[['Purchased','User ID']])

plt.scatter(xpoint,ypoint, color='yellow')

a.value_counts('Gender')

a.value_counts("Age")

a.info

x= a.iloc[:, [2,3]].values
print(x)

y=a.iloc[:,4].values
print(y)

d={'Male':1,'Female':2}
a['Gender']=a['Gender'].map(d)

train,test = train_test_split(a, test_size=0.25, random_state=1)
x_train = train[['Age','AnnualSalary']]
y_train = train['Purchased']
x_test = test[['Age','AnnualSalary']]
y_test = test['Purchased']

scaler = preprocessing.StandardScaler().fit(x_train)
x_train = scaler.transform(x_train)
x_test = scaler.transform(x_test)

knn = neighbors.KNeighborsClassifier(n_neighbors=3)
knn.fit(x_train, y_train)
y_pred = knn.predict(x_test)

print(accuracy_score(y_test, y_pred))
#print(classification_report(y_test, y_pred))
#print(confusion_matrix(y_test, y_pred))

siniflandirma_model =KNeighborsClassifier(n_neighbors=5, metric='minkowski', p=2 )
siniflandirma_model.fit(x_train,y_train)

siniflandirma= KNeighborsClassifier(n_neighbors=5, metric='minkowski', p=2 )
siniflandirma.fit(x_train, y_train)

print(siniflandirma.predict([[30,10000]]))

train,test = train_test_split(a, test_size=0.25, random_state=1)
x_train = train[['Age','Gender']]
y_train = train['Purchased']
x_test = test[['Age','Gender']]
y_test = test['Purchased']

siniflandirma= KNeighborsClassifier(n_neighbors=5, metric='minkowski', p=2 )
siniflandirma.fit(x_train, y_train)

siniflandirma_accuracy = accuracy_score(y_test, tree_model.predict(x_test), normalize=True, sample_weight=None)
cm = confusion_matrix(Y_test,siniflandirma_model.predict(X_test))
siniflandirma_accuracy

print(siniflandirma.predict([[30,1]]))

sn.scatterplot(data=a, x="Age", y="AnnualSalary", hue="Purchased") #yaş ve yıllık maaşa göre alım çizelgesi

from sklearn.neighbors import NearestNeighbors

deneme = NearestNeighbors(n_neighbors=1,radius=1,algorithm='auto', leaf_size=30, metric='minkowski', p=2, metric_params=None, n_jobs=None)

dizi=np.array(a[['Age','AnnualSalary','Purchased']])

deneme.fit(dizi)

plt.scatter(dizi["Age"],dizi["AnnualSalary"],c="blue")
plt.show()

print(dizi)

print(deneme.kneighbors([[10., 40000., 0.]],return_distance=False))

print(deneme.kneighbors([[10., 40000., 0.]],return_distance=True))

t=deneme.kneighbors_graph([[10., 40000., 0.]])#csr formatında dizi olusturuluyor.
t.toarray()

print(t)