Name : Snehal Kotkar Div : A Roll No.
: 46
Practical No. : 2 Problem Statement : Build a machine learning model using k-Nearest
Neighbors algorithm to predict whether the patients in the "Pima Indians Diabetes Dataset"
have diabetes or not.
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
plt.style.use('ggplot')
df = pd.read_csv('diabetes.csv')
df.head()
Pregnancies Glucose BloodPressure SkinThickness Insulin
BMI \
0 6 148 72 35 0 33.6
1 1 85 66 29 0 26.6
2 8 183 64 0 0 23.3
3 1 89 66 23 94 28.1
4 0 137 40 35 168 43.1
DiabetesPedigreeFunction Age Outcome
0 0.627 50 1
1 0.351 31 0
2 0.672 32 1
3 0.167 21 0
4 2.288 33 1
df.shape
(768, 9)
df.isnull().sum()
Pregnancies 0
Glucose 0
BloodPressure 0
SkinThickness 0
Insulin 0
BMI 0
DiabetesPedigreeFunction 0
Age 0
Outcome 0
dtype: int64
X = df.drop('Outcome',axis=1).values
y = df['Outcome'].values
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test =
train_test_split(X,y,test_size=0.25,random_state=42, stratify=y)
from sklearn.neighbors import KNeighborsClassifier
neighbors = np.arange(1,15)
train_accuracy =np.empty(len(neighbors))
test_accuracy = np.empty(len(neighbors))
for i,k in enumerate(neighbors):
knn = KNeighborsClassifier(n_neighbors=k)
knn.fit(X_train, y_train)
train_accuracy[i] = knn.score(X_train, y_train)
test_accuracy[i] = knn.score(X_test, y_test)
plt.title('k-NN Varying number of neighbors')
plt.plot(neighbors, test_accuracy, label='Testing Accuracy')
plt.plot(neighbors, train_accuracy, label='Training accuracy')
plt.legend()
plt.xlabel('Number of neighbors')
plt.ylabel('Accuracy')
plt.show()
#Setup a knn classifier with k neighbors
knn = KNeighborsClassifier(n_neighbors=4)
#Fit the model
knn.fit(X_train,y_train)
KNeighborsClassifier(n_neighbors=4)
#Get accuracy. Note: In case of classification algorithms score method
represents accuracy.
knn.score(X_test,y_test)
0.7291666666666666
#let us get the predictions using the classifier we had fit above
y_pred = knn.predict(X_test)
y_pred
array([0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 1, 1, 0, 0, 0, 0,
0,
0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0,
0,
1, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0,
0,
0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0,
0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0,
0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0,
0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1,
0,
1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0,
1,
0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0], dtype=int64)
