import pandas as pd
import numpy as np
from matplotlib.pyplot import subplots

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import PolynomialFeatures
from sklearn.metrics import r2_score, mean_squared_error
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression

ckd = pd.read_csv('ckd.csv')
ckd = ckd[['Age', 'Blood Pressure', 'Blood Glucose Random', 'White Blood Cell Count', 'Red Blood Cell Count', 'Class']]
ckd

# Logistic Regression

X = ckd[['Age', 'Blood Pressure', 'Blood Glucose Random', 'White Blood Cell Count', 'Red Blood Cell Count']]
y = ckd['Class']

# Create a train:test split of the data 
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.30, random_state=42, stratify=y
)

# We shall use the StandardScaler to scale the training dataset
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
# The transform method is then used to scale the test data using parameters
# obtained from the training data.
X_test_scaled = scaler.transform(X_test)

from sklearn.linear_model import LogisticRegression
logreg = LogisticRegression(max_iter=1000)

logreg.fit(X_train, y_train)
y_pred = logreg.predict(X_test)

from sklearn.metrics import accuracy_score, confusion_matrix, classification_report
# Evaluate
print('Evaluation of Logistic Regression classification')
print("Accuracy:", accuracy_score(y_test, y_pred))
print("\nConfusion Matrix:")
print(confusion_matrix(y_test, y_pred))
print("\nClassification Report:")
print(classification_report(y_test, y_pred))

Evaluation of Logistic Regression classification
Accuracy: 0.9583333333333334

Confusion Matrix:
[[34  1]
 [ 1 12]]

Classification Report:
              precision    recall  f1-score   support

           0       0.97      0.97      0.97        35
           1       0.92      0.92      0.92        13

    accuracy                           0.96        48
   macro avg       0.95      0.95      0.95        48
weighted avg       0.96      0.96      0.96        48

from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(n_neighbors=9)
knn.fit(X_train, y_train)
y_pred = knn.predict(X_test)

# Evaluate
print('Evaluation of KNN classification')
print("Accuracy:", accuracy_score(y_test, y_pred))
print("\nConfusion Matrix:")
print(confusion_matrix(y_test, y_pred))
print("\nClassification Report:")
print(classification_report(y_test, y_pred))

Evaluation of KNN classification
Accuracy: 0.8541666666666666

Confusion Matrix:
[[35  0]
 [ 7  6]]

Classification Report:
              precision    recall  f1-score   support

           0       0.83      1.00      0.91        35
           1       1.00      0.46      0.63        13

    accuracy                           0.85        48
   macro avg       0.92      0.73      0.77        48
weighted avg       0.88      0.85      0.83        48

X = ckd[['Age', 'Blood Pressure', 'Blood Glucose Random', 'White Blood Cell Count', 'Red Blood Cell Count']]
y = ckd['Class']

# Create a train:test split of the data 
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.30, random_state=42, stratify=y
)

from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

# Create and train the classifier
gnb_model = GaussianNB()
gnb_model.fit(X_train, y_train)

# Make predictions
y_pred = gnb_model.predict(X_test)

# Evaluate
print("Accuracy:", accuracy_score(y_test, y_pred))
print("\nConfusion Matrix:")
print(confusion_matrix(y_test, y_pred))
print("\nClassification Report:")
print(classification_report(y_test, y_pred))

Accuracy: 0.9791666666666666

Confusion Matrix:
[[35  0]
 [ 1 12]]

Classification Report:
              precision    recall  f1-score   support

           0       0.97      1.00      0.99        35
           1       1.00      0.92      0.96        13

    accuracy                           0.98        48
   macro avg       0.99      0.96      0.97        48
weighted avg       0.98      0.98      0.98        48

	Age	Blood Pressure	Blood Glucose Random	White Blood Cell Count	Red Blood Cell Count	Class
0	48	70	117	6700	3.9	1
1	53	90	70	12100	3.7	1
2	63	70	380	4500	3.8	1
3	68	80	157	11000	2.6	1
4	61	80	173	9200	3.2	1
...	...	...	...	...	...	...
153	55	80	140	6700	4.9	0
154	42	70	75	7800	6.2	0
155	12	80	100	6600	5.4	0
156	17	60	114	7200	5.9	0
157	58	80	131	6800	6.1	0