KNN_on_Diabetes.ipynb

Kernel: Python 3.8.6 64-bit

Implement K-Nearest Neighbors algorithm on diabetes.csv dataset. Compute confusion matrix, accuracy, error rate, precision and recall on the given dataset

    import numpy as np
    import pandas as pd

data = pd.read_csv('./diabetes.csv')
data.head()

#Check for null or missing values
data.isnull().sum()

Pregnancies      0
Glucose          0
BloodPressure    0
SkinThickness    0
Insulin          0
BMI              0
Pedigree         0
Age              0
Outcome          0
dtype: int64

#Replace zero values with mean values
for column in data.columns[1:-3]:
    data[column].replace(0, np.NaN, inplace = True)
    data[column].fillna(round(data[column].mean(skipna=True)), inplace = True)
data.head(10)

X = data.iloc[:, :8] #Features
Y = data.iloc[:, 8:] #Predictor

#Perform Spliting
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=0)

#KNN
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier()
knn_fit = knn.fit(X_train, Y_train.values.ravel())
knn_pred = knn_fit.predict(X_test)

from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score, accuracy_score
print("Confusion Matrix")
print(confusion_matrix(Y_test, knn_pred))
print("Accuracy Score:", accuracy_score(Y_test, knn_pred))
print("Reacal Score:", recall_score(Y_test, knn_pred))
print("F1 Score:", f1_score(Y_test, knn_pred))
print("Precision Score:",precision_score(Y_test, knn_pred))

Confusion Matrix
[[88 19]
 [19 28]]
Accuracy Score: 0.7532467532467533
Reacal Score: 0.5957446808510638
F1 Score: 0.5957446808510638
Precision Score: 0.5957446808510638