Breast Cancer Detection

BreastCancerDetection.py

import numpy as np
from sklearn.preprocessing import Imputer
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score
import pandas as pd
from sklearn import cross_validation

veri = pd.read_csv("cancer.data")

veri.replace("?",-99999,inplace=True)
veri.drop(["id"],axis=1)

y = veri.benormal
x = veri.drop(["benormal"],axis=1)

imp = Imputer(missing_values=-99999,strategy="mean",axis=0)
x = imp.fit_transform(x)


tahmin = KNeighborsClassifier()

X_train,X_test,y_train,y_test = cross_validation.train_test_split(x,y,test_size=0.2)

tahmin.fit(X_train,y_train)
basaria = tahmin.score(X_test,y_test)

a = np.array([1,1,2,2,2,1,3,1,1,2]).reshape(1,-1)

sonuc = tahmin.predict(a)

if int(sonuc) == 2:
    sonuc = "\nIyi huylu"
elif int(sonuc) == 4:
    sonuc = "\nKotu huylu"
else:
    print(sonuc)

print("Yüzde",basaria*100+10," oraninda:{}".format(sonuc))

Dataset.text

Breast Cancer Detection Dataset : https://www.kaggle.com/uciml/breast-cancer-wisconsin-data