Challenge

Project 1

VVishal Pandit22 Oct 2022

Project 1

When you working on the health of patients then accuracy is deciding factor, Apply different machine learning algorithms and check the accuracy about predicting whether or not the patient has heart disease.

Apply all five different machine learning models Logistic Regression, K-Nearest Neighbours Classifier, Support Vector machine, Decision Tree Classifier, Random Forest Classifier on the given dataset.

In [1]:

import pandas as pd

import numpy as np

In [2]:

# Load data

data = pd.read_csv('heart.csv')

In [3]:

# before data sorting

data.info()

data.describe()


RangeIndex: 303 entries, 0 to 302
Data columns (total 14 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   age       303 non-null    int64  
 1   sex       303 non-null    int64  
 2   cp        303 non-null    int64  
 3   trtbps    303 non-null    int64  
 4   chol      303 non-null    int64  
 5   fbs       303 non-null    int64  
 6   restecg   303 non-null    int64  
 7   thalachh  303 non-null    int64  
 8   exng      303 non-null    int64  
 9   oldpeak   303 non-null    float64
 10  slp       303 non-null    int64  
 11  caa       303 non-null    int64  
 12  thall     303 non-null    int64  
 13  output    303 non-null    int64  
dtypes: float64(1), int64(13)
memory usage: 33.3 KB

Out[3]:

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall	output
count	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000	303.000000
mean	54.366337	0.683168	0.966997	131.623762	246.264026	0.148515	0.528053	149.646865	0.326733	1.039604	1.399340	0.729373	2.313531	0.544554
std	9.082101	0.466011	1.032052	17.538143	51.830751	0.356198	0.525860	22.905161	0.469794	1.161075	0.616226	1.022606	0.612277	0.498835
min	29.000000	0.000000	0.000000	94.000000	126.000000	0.000000	0.000000	71.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	47.500000	0.000000	0.000000	120.000000	211.000000	0.000000	0.000000	133.500000	0.000000	0.000000	1.000000	0.000000	2.000000	0.000000
50%	55.000000	1.000000	1.000000	130.000000	240.000000	0.000000	1.000000	153.000000	0.000000	0.800000	1.000000	0.000000	2.000000	1.000000
75%	61.000000	1.000000	2.000000	140.000000	274.500000	0.000000	1.000000	166.000000	1.000000	1.600000	2.000000	1.000000	3.000000	1.000000
max	77.000000	1.000000	3.000000	200.000000	564.000000	1.000000	2.000000	202.000000	1.000000	6.200000	2.000000	4.000000	3.000000	1.000000

In [4]:

data.shape

Out[4]:

(303, 14)

In [5]:

data=data.dropna()

In [6]:

data.shape

Out[6]:

(303, 14)

In [7]:

# plot the data into features & target

features = pd.DataFrame(data.iloc[:,:-1])

target = pd.DataFrame(data.iloc[:,-1])

In [8]:

X = features

y = target

In [9]:

Out[9]:

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2
...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2

303 rows × 13 columns

In [10]:

Out[10]:

	output
0	1
1	1
2	1
3	1
4	1
...	...
298	0
299	0
300	0
301	0
302	0

303 rows × 1 columns

In [11]:

# split dataset

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 = 1)

In [12]:

# StandardScaler

from sklearn.preprocessing import StandardScaler

sc = StandardScaler()

X_train = sc.fit_transform(X_train)

X_test = sc.transform(X_test)

1.LogisticRegression

In [13]:

# Import LogisticRegression

from sklearn.linear_model import LogisticRegression

In [14]:

LR = LogisticRegression()

print(LR.fit(X_train, y_train))

LogisticRegression()

C:\Users\HP\anaconda3\lib\site-packages\sklearn\utils\validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

In [15]:

y_pred = LR.predict(X_test)

In [16]:

y_pred

Out[16]:

array([0, 1, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0,
       1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0,
       1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1], dtype=int64)

In [17]:

from sklearn.metrics import confusion_matrix

CM = confusion_matrix(y_test, y_pred)

In [18]:

CM

Out[18]:

array([[20, 10],
       [ 6, 25]], dtype=int64)

True positive is 20. True negative is 27. False positive is 10. False negative is 4.

In [19]:

score = LR.score(X_test, y_test)

print(score)

# 0.7377049180327869

# 0.7704918032786885

0.7377049180327869

In [20]:

import matplotlib.pyplot as plt

import seaborn as sns

from sklearn import metrics

In [21]:

plt.figure(figsize=(9,9))

sns.heatmap(CM, annot=True, fmt=".3f", linewidths=.5, square = True, cmap = 'Blues_r');

plt.ylabel('Actual label');

plt.xlabel('Predicted label');

all_sample_title = 'Accuracy Score: {0}'.format(score)

plt.title(all_sample_title, size = 15);

In [22]:

from sklearn import metrics

LR_Accuracy = metrics.accuracy_score(y_test, y_pred)

print('LogisticRegression Accuracy: ', LR_Accuracy)

LogisticRegression Accuracy:  0.7377049180327869

2.K-Nearest Neighbours Classifier

In [23]:

from sklearn.neighbors import KNeighborsClassifier

In [24]:

KNN = KNeighborsClassifier()

KNN.fit(X, y)

y_pred = KNN.predict(X)

C:\Users\HP\anaconda3\lib\site-packages\sklearn\neighbors\_classification.py:198: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().
  return self._fit(X, y)

In [25]:

KNN_Accuracy = metrics.accuracy_score(y, y_pred)

print('KNN_Accuracy: ', KNN_Accuracy)

KNN_Accuracy:  0.7656765676567657

3.Support Vector machine

In [26]:

# Importing libraries

from sklearn.svm import SVC

from sklearn.metrics import accuracy_score

In [27]:

clf = SVC(kernel= 'linear')

clf.fit(X_train, y_train)

C:\Users\HP\anaconda3\lib\site-packages\sklearn\utils\validation.py:993: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

Out[27]:

SVC(kernel='linear')

In [28]:

# performing predictions on the test dataset

y_pred = clf.predict(X_test)

print('SVM_Accuracy: ',accuracy_score(y_test, y_pred))

SVM_Accuracy:  0.7213114754098361

4.Decision Tree Classifier

In [29]:

# Load libraries

from sklearn.tree import DecisionTreeClassifier

In [30]:

# classifer object

clf = DecisionTreeClassifier()

# Train Decision Tree Classifer

clf = clf.fit(X_train,y_train)

In [31]:

# performing predictions on the test dataset

y_pred = clf.predict(X_test)

In [32]:

# Model Accuracy, how often is the classifier correct?

DTC_Accuracy = metrics.accuracy_score(y_test, y_pred)

print("Accuracy:", DTC_Accuracy)

Accuracy: 0.7377049180327869

5.Random Forest Classifier

In [33]:

from sklearn.ensemble import RandomForestClassifier

In [34]:

# classifer object

clf = RandomForestClassifier()

clf.fit(X_train, y_train)

# performing predictions on the test dataset

y_pred = clf.predict(X_test)

# accuracy calculation

RFC_Accuracy = metrics.accuracy_score(y_test, y_pred)

print("ACCURACY Random Forest Classifier: ", RFC_Accuracy)

C:\Users\HP\AppData\Local\Temp\ipykernel_7612\2306489415.py:4: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().
  clf.fit(X_train, y_train)

ACCURACY Random Forest Classifier:  0.7704918032786885

Project 1

Project 1

1.LogisticRegression

2.K-Nearest Neighbours Classifier

3.Support Vector machine

4.Decision Tree Classifier

5.Random Forest Classifier

Ship work like this
in your own course.

Talk to a career counsellor

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2
...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2
...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2

Project 1

1.LogisticRegression

2.K-Nearest Neighbours Classifier

3.Support Vector machine

4.Decision Tree Classifier

5.Random Forest Classifier

Ship work like thisin your own course.

Talk to a career counsellor

Ship work like this
in your own course.

	age	sex	cp	trtbps	chol	fbs	restecg	thalachh	exng	oldpeak	slp	caa	thall
0	63	1	3	145	233	1	0	150	0	2.3	0	0	1
1	37	1	2	130	250	0	1	187	0	3.5	0	0	2
2	41	0	1	130	204	0	0	172	0	1.4	2	0	2
3	56	1	1	120	236	0	1	178	0	0.8	2	0	2
4	57	0	0	120	354	0	1	163	1	0.6	2	0	2
...	...	...	...	...	...	...	...	...	...	...	...	...	...
298	57	0	0	140	241	0	1	123	1	0.2	1	0	3
299	45	1	3	110	264	0	1	132	0	1.2	1	0	3
300	68	1	0	144	193	1	1	141	0	3.4	1	2	3
301	57	1	0	130	131	0	1	115	1	1.2	1	1	3
302	57	0	1	130	236	0	0	174	0	0.0	1	1	2