Diabetes Clustering

import pandas as pd
import seaborn as sns

df = pd.read_csv('./diabetes.csv')

df

x = df.drop('Outcome', axis = 1)

y = df['Outcome']

sns.countplot(x = y)

y.value_counts()

from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler()
x_scaled = scaler.fit_transform(x)

from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(x_scaled,y, random_state = 0, test_size = 0.25)

x.shape

x_train.shape

x_test.shape

from sklearn.neighbors import KNeighborsClassifier
knn =KNeighborsClassifier(n_neighbors=5)
knn.fit(x_train, y_train)

from sklearn.metrics import accuracy_score, ConfusionMatrixDisplay
from sklearn.metrics import classification_report
y_pred = knn.predict(x_test)

ConfusionMatrixDisplay.from_predictions(y_test,y_pred)

print(classification_report(y_test, y_pred))

import matplotlib.pyplot as plt
import numpy as np
error = []
for k in range(1,41):
  knn = KNeighborsClassifier(n_neighbors=k)
  knn.fit(x_train, y_train)
  pred = knn.predict(x_test)
  error.append(np.mean(pred != y_test))
error

plt.figure(figsize = [16,9])
plt.xlabel('Value of K')
plt.ylabel('Error')
plt.grid()
plt.xticks(range(1,41))
plt.plot(range(1,41), error, marker='.')

knn = KNeighborsClassifier(n_neighbors=33)
knn.fit(x_train, y_train)

y_pred = knn.predict(x_test)
print(classification_report(y_test, y_pred))