Cancer.py

import itertools
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.ticker import NullFormatter
import pandas as pd
import numpy as np
import matplotlib.ticker as ticker
from sklearn import preprocessing

df = pd.read_csv('data.csv')
print("numbers of each class in the data set")
print(df['diagnosis'].value_counts())
print("Features\n")
print(df.columns)

X=df[["radius_mean","texture_mean","perimeter_mean","area_mean","smoothness_mean","compactness_mean","concavity_mean","concave points_mean","symmetry_mean","fractal_dimension_mean"]]
y=df["diagnosis"].values
X = preprocessing.StandardScaler().fit(X).transform(X.astype(float))
print(y[0:5])
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.26, random_state=4)
print ('Train set:', X_train.shape,  y_train.shape)
print ('Test set:', X_test.shape,  y_test.shape)

from sklearn.neighbors import KNeighborsClassifier
from sklearn import metrics

Ks = len(X_train)
mean_acc = np.zeros((Ks-1))
std_acc = np.zeros((Ks-1))
ConfustionMx = [];
for n in range(1,Ks):
    
    #Train Model and Predict  
    neigh = KNeighborsClassifier(n_neighbors = n).fit(X_train,y_train)
    yhat=neigh.predict(X_test)
    mean_acc[n-1] = metrics.accuracy_score(y_test, yhat)
    std_acc[n-1]=np.std(yhat==y_test)/np.sqrt(yhat.shape[0])
#plotting graphs for accuracy
plt.plot(range(1,Ks),mean_acc,'g')
plt.fill_between(range(1,Ks),mean_acc - 1 * std_acc,mean_acc + 1 * std_acc, alpha=0.10)
plt.legend(('Accuracy ', '+/- 3xstd'))
plt.ylabel('Accuracy ')
plt.xlabel('Number of Neibors (K)')
plt.tight_layout()
plt.show()
print( "The best accuracy was with", mean_acc.max(), "with k=", mean_acc.argmax()+1) 
k = mean_acc.argmax()+1
#Train Model and Predict  
neigh = KNeighborsClassifier(n_neighbors = k).fit(X_train,y_train)
neigh
yhat = neigh.predict(X_test)
print(yhat[0:5])