Photo by Creative Commons Attribution Share-Alike (CCYYSA)

Loading…

Taking too long?

Reload document

Open in new tab

Exploratory Data Analysis

EDA

In [1]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

In [2]:

df = pd.read_csv('heart_dataset.csv')

In [3]:

df.head()

Out[3]:

	age	sex	cp	trestbps	chol	fbs	restecg	thalachh	exang	oldpeak	slope	thal	target
0	63	1	3	145	233	1	0	150	0	2.3	0	1	1
1	37	1	2	130	250	0	1	187	0	3.5	0	2	1
2	41	0	1	130	204	0	0	172	0	1.4	2	2	1
3	56	1	1	120	236	0	1	178	0	0.8	2	2	1
4	57	0	0	120	354	0	1	163	1	0.6	2	2	1

In [4]:

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1888 entries, 0 to 1887
Data columns (total 14 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   age       1888 non-null   int64  
 1   sex       1888 non-null   int64  
 2   cp        1888 non-null   int64  
 3   trestbps  1888 non-null   int64  
 4   chol      1888 non-null   int64  
 5   fbs       1888 non-null   int64  
 6   restecg   1888 non-null   int64  
 7   thalachh  1888 non-null   int64  
 8   exang     1888 non-null   int64  
 9   oldpeak   1888 non-null   float64
 10  slope     1888 non-null   int64  
 11  ca        1888 non-null   int64  
 12  thal      1888 non-null   int64  
 13  target    1888 non-null   int64  
dtypes: float64(1), int64(13)
memory usage: 206.6 KB

In [5]:

df.describe()

Out[5]:

	age	sex	cp	trestbps	chol	fbs	restecg	thalachh	exang	oldpeak	slope	ca	thal	target
count	1888.000000	1888.000000	1888.000000	1888.000000	1888.000000	1888.000000	1888.000000	1888.000000	1888.000000	1888.000000	1888.000000	1888.000000	1888.000000	1888.000000
mean	54.354343	0.688559	1.279131	131.549258	246.855403	0.148305	0.597458	149.424258	0.331568	1.053761	1.421610	0.731462	2.662606	0.517479
std	9.081505	0.463205	1.280877	17.556985	51.609329	0.355496	0.638820	23.006153	0.470901	1.161344	0.619588	1.015735	1.249924	0.499827
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%	47.750000	0.000000	0.000000	120.000000	211.000000	0.000000	0.000000	133.000000	0.000000	0.000000	1.000000	0.000000	2.000000	0.000000
50%	55.000000	1.000000	1.000000	130.000000	241.000000	0.000000	1.000000	152.000000	0.000000	0.800000	1.000000	0.000000	2.000000	1.000000
75%	61.000000	1.000000	2.000000	140.000000	276.000000	0.000000	1.000000	166.000000	1.000000	1.600000	2.000000	1.000000	3.000000	1.000000
max	77.000000	1.000000	4.000000	200.000000	564.000000	1.000000	2.000000	202.000000	1.000000	6.200000	3.000000	4.000000	7.000000	1.000000

In [6]:

df.describe().T

Out[6]:

	count	mean	std	min	25%	50%	75%	max
age	1888.0	54.354343	9.081505	29.0	47.75	55.0	61.0	77.0
sex	1888.0	0.688559	0.463205	0.0	0.00	1.0	1.0	1.0
cp	1888.0	1.279131	1.280877	0.0	0.00	1.0	2.0	4.0
trestbps	1888.0	131.549258	17.556985	94.0	120.00	130.0	140.0	200.0
chol	1888.0	246.855403	51.609329	126.0	211.00	241.0	276.0	564.0
fbs	1888.0	0.148305	0.355496	0.0	0.00	0.0	0.0	1.0
restecg	1888.0	0.597458	0.638820	0.0	0.00	1.0	1.0	2.0
thalachh	1888.0	149.424258	23.006153	71.0	133.00	152.0	166.0	202.0
exang	1888.0	0.331568	0.470901	0.0	0.00	0.0	1.0	1.0
oldpeak	1888.0	1.053761	1.161344	0.0	0.00	0.8	1.6	6.2
slope	1888.0	1.421610	0.619588	0.0	1.00	1.0	2.0	3.0
ca	1888.0	0.731462	1.015735	0.0	0.00	0.0	1.0	4.0
thal	1888.0	2.662606	1.249924	0.0	2.00	2.0	3.0	7.0
target	1888.0	0.517479	0.499827	0.0	0.00	1.0	1.0	1.0

In [7]:

# List of numeric variables
numeric_vars = ['age', 'trestbps', 'chol', 'thalachh', 'oldpeak']

# Create distplots for each numeric variable
for var in numeric_vars:
    plt.figure(figsize=(10, 6))
    sns.histplot(df[var], kde=True, bins=30)
    plt.title(f'Distribution of {var}')
    plt.xlabel(var)
    plt.ylabel('Density')
    plt.show()

No description has been provided for this image

In [8]:

categorical_vars = ['sex', 'cp', 'fbs', 'restecg', 'exang', 'slope', 'ca', 'thal', 'target']

for var in categorical_vars:
    plt.figure(figsize=(8, 6))
    df[var].value_counts().plot.pie(autopct='%1.1f%%', startangle=90, cmap='Pastel1')
    plt.title(f'Distribution of {var}')
    plt.ylabel('')
    plt.show()

In [9]:

from sklearn.preprocessing import StandardScaler

# Initialize the scaler
scaler = StandardScaler()

# Fit and transform the numeric variables
df[numeric_vars] = scaler.fit_transform(df[numeric_vars])

# Display the first few rows of the scaled dataframe
df.head()

Out[9]:

	age	sex	cp	trestbps	chol	fbs	restecg	thalachh	exang	oldpeak	slope	thal	target
0	0.952259	1	3	0.766322	-0.268538	1	0	0.025032	0	1.073386	0	1	1
1	-1.911461	1	2	-0.088265	0.060947	0	1	1.633724	0	2.106945	0	2	1
2	-1.470888	0	1	-0.088265	-0.830601	0	0	0.981551	0	0.298216	2	2	1
3	0.181258	1	1	-0.657990	-0.210394	0	1	1.242420	0	-0.218564	2	2	1
4	0.291401	0	0	-0.657990	2.076620	0	1	0.590248	1	-0.390824	2	2	1

In [10]:

# Calculate the correlation matrix
corr_matrix = df.corr()

# Create a heatmap
plt.figure(figsize=(12, 8))
sns.heatmap(corr_matrix, annot=True, fmt='.2f', cmap='coolwarm', linewidths=0.5)
plt.title('Correlation Heatmap')
plt.show()

In [ ]:

Logistic Regression

LogisticReg

In [1]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

In [2]:

df = pd.read_csv('C:\\Users\\Dell\\Desktop\\Python Notebooks\\AI 201\\HEART ATTACK\\heart_dataset.csv')

In [3]:

X = df.iloc[:, :-1].values
y = df.iloc[:, -1].values

In [4]:

# One Hot Encoding columns Sex, CP, FBS, RestECG, Exang, Slope, CA, and Thal
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [1, 2, 5, 6, 8, 10, 11, 12])], remainder='passthrough')
X = np.array(ct.fit_transform(X))

In [5]:

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X[:, [0, 3, 4, 7, 9]] = sc.fit_transform(X[:, [0, 3, 4, 7, 9]])

In [6]:

# Splitting the dataset into the Training set and Test set
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 [7]:

# Training the Logistic Regression model on the Training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(C=0.1, max_iter=300, penalty='l2', solver='lbfgs', random_state = 0)
classifier.fit(X_train, y_train)

c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(

Out[7]:

LogisticRegression(C=0.1, max_iter=300, random_state=0)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

In [8]:

# Predicting the Test set results
y_pred = classifier.predict(X_test)

In [9]:

# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score
cm = confusion_matrix(y_test, y_pred)
print(cm)
print(accuracy_score(y_test, y_pred))

[[139  31]
 [ 36 172]]
0.8227513227513228

In [10]:

from sklearn.model_selection import cross_val_score
scores = cross_val_score(classifier, X_test, y_test, cv = 10)
print("Cross-Validation Accuracy Scores", scores.mean())

c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(

Cross-Validation Accuracy Scores 0.8043385490753913

c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
c:\Users\Dell\anaconda3\Lib\site-packages\sklearn\linear_model\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(

In [11]:

accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred, average='weighted')
recall = recall_score(y_test, y_pred, average='weighted')
f1 = f1_score(y_test, y_pred, average='weighted')

print("Accuracy Score:", accuracy)
print("Precision Score:", precision)
print("Recall Score:", recall)
print("F1 Score:", f1)

Accuracy Score: 0.8227513227513228
Precision Score: 0.8234524461125446
Recall Score: 0.8227513227513228
F1 Score: 0.8229575784849243

In [12]:

#plot_roc_curve(classifier, X_test, y_test, name = "Logistic Regression")
#plt.title("Logistic Regression Roc Curve And AUC")
#plt.plot([0, 1], [0, 1], "r--")
#plt.show()
from sklearn.metrics import RocCurveDisplay
RocCurveDisplay.from_estimator(estimator=classifier, X=X_test, y=y_test, name = "Logistic Regression")
plt.title("Logistic Regression Roc Curve And AUC")
plt.plot([0, 1], [0, 1], "r--")
plt.show()

In [13]:

# Define the parameter grid
# param_grid = {
#     'penalty': ['l1', 'l2', 'elasticnet', 'none'],
#     'C': [0.01, 0.1, 1, 10, 100],
#     'solver': ['newton-cg', 'lbfgs', 'liblinear', 'sag', 'saga'],
#     'max_iter': [100, 200, 300]
# }

# # Initialize the GridSearchCV object
# grid_search = GridSearchCV(estimator=classifier, param_grid=param_grid, cv=10, n_jobs=-1, scoring='accuracy')

# # Fit the grid search to the data
# grid_search.fit(X_train, y_train)

# # Print the best parameters and best score
# print("Best Parameters:", grid_search.best_params_)
# print("Best Score:", grid_search.best_score_)

Naive Bayes

NaiveBayes

In [1]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import GridSearchCV

In [2]:

df = pd.read_csv('C:\\Users\\Dell\\Desktop\\Python Notebooks\\AI 201\\HEART ATTACK\\heart_dataset.csv')

In [3]:

X = df.iloc[:, :-1].values
y = df.iloc[:, -1].values

In [4]:

# One Hot Encoding columns Sex, CP, FBS, RestECG, Exang, Slope, CA, and Thal
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [1, 2, 5, 6, 8, 10, 11, 12])], remainder='passthrough')
X = np.array(ct.fit_transform(X))

In [5]:

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X[:, [0, 3, 4, 7, 9]] = sc.fit_transform(X[:, [0, 3, 4, 7, 9]])

In [6]:

# Splitting the dataset into the Training set and Test set
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 [7]:

# Training the Naive Bayes model on the Training set
from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
classifier.fit(X_train, y_train)

Out[7]:

GaussianNB()

In [8]:

# Predicting the Test set results
y_pred = classifier.predict(X_test)

In [9]:

# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score
cm = confusion_matrix(y_test, y_pred)
print(cm)
print(accuracy_score(y_test, y_pred))

[[134  36]
 [ 39 169]]
0.8015873015873016

In [10]:

from sklearn.model_selection import cross_val_score
scores = cross_val_score(classifier, X_test, y_test, cv = 10)
print("Cross-Validation Accuracy Scores", scores.mean())

Cross-Validation Accuracy Scores 0.7331436699857752

In [11]:

from sklearn.metrics import RocCurveDisplay
RocCurveDisplay.from_estimator(estimator=classifier, X=X_test, y=y_test, name = "Naive Bayes")
plt.title("Naive Bayes Roc Curve And AUC")
plt.plot([0, 1], [0, 1], "r--")
plt.show()

In [12]:

# Hyperparameter optimization using GridSearchCV
param_grid = {
    'var_smoothing': np.logspace(0, -9, num=100)
}
grid_search = GridSearchCV(estimator=GaussianNB(), param_grid=param_grid, cv=10, n_jobs=-1, scoring='accuracy')
grid_search.fit(X_train, y_train)
print("Best parameters found: ", grid_search.best_params_)
print("Best cross-validation accuracy: ", grid_search.best_score_)

Best parameters found:  {'var_smoothing': 3.511191734215127e-05}
Best cross-validation accuracy:  0.7867549668874172

In [13]:

# Evaluating the model with the best found parameters on the test set
best_classifier = grid_search.best_estimator_
y_pred_best = best_classifier.predict(X_test)

cm_best = confusion_matrix(y_test, y_pred_best)
print("Confusion Matrix with best parameters:\n", cm_best)
print("Accuracy Score with best parameters:", accuracy_score(y_test, y_pred_best))

accuracy = accuracy_score(y_test, y_pred_best)
precision = precision_score(y_test, y_pred_best, average='weighted')
recall = recall_score(y_test, y_pred_best, average='weighted')
f1 = f1_score(y_test, y_pred_best, average='weighted')

print("Accuracy Score:", accuracy)
print("Precision Score:", precision)
print("Recall Score:", recall)
print("F1 Score:", f1)

Confusion Matrix with best parameters:
 [[135  35]
 [ 44 164]]
Accuracy Score with best parameters: 0.791005291005291
Accuracy Score: 0.791005291005291
Precision Score: 0.7926703066929338
Recall Score: 0.791005291005291
F1 Score: 0.7913893128792842

In [14]:

RocCurveDisplay.from_estimator(estimator=best_classifier, X=X_test, y=y_test, name="Naive Bayes (Best Params)")
plt.title("Naive Bayes Roc Curve And AUC (Best Params)")
plt.plot([0, 1], [0, 1], "r--")
plt.show()

In [ ]:

Artificial Neural Network

ANN

In [1]:

from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive

In [2]:

import numpy as np
import pandas as pd
import tensorflow as tf
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score, KFold
from sklearn.metrics import RocCurveDisplay

In [3]:

tf.__version__

Out[3]:

'2.17.1'

In [4]:

df = pd.read_csv('/content/drive/MyDrive/ARTIFICIAL INTELLIGENCE/AI 201/FOR IN PERSON PRESENTATION/heart_dataset.csv')

X = df.iloc[:, :-1].values
y = df.iloc[:, -1].values

In [5]:

# One Hot Encoding columns Sex, CP, FBS, RestECG, Exang, Slope, CA, and Thal
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [1, 2, 5, 6, 8, 10, 11, 12])], remainder='passthrough')
X = np.array(ct.fit_transform(X))

# Feature Scaling
sc = StandardScaler()
X[:, [0, 3, 4, 7, 9]] = sc.fit_transform(X[:, [0, 3, 4, 7, 9]])

In [6]:

# Splitting the dataset into the Training set and Test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 1)

In [7]:

ann = tf.keras.models.Sequential()

In [8]:

ann.add(tf.keras.layers.Dense(units=6, activation='relu'))

In [9]:

ann.add(tf.keras.layers.Dense(units=6, activation='relu'))

In [10]:

ann.add(tf.keras.layers.Dense(units=1, activation='sigmoid'))

In [11]:

ann.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])

In [12]:

ann.fit(X_train, y_train, batch_size = 32, epochs = 100)

Epoch 1/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 2s 2ms/step - accuracy: 0.6209 - loss: 1.2411
Epoch 2/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6153 - loss: 0.8739
Epoch 3/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 7ms/step - accuracy: 0.6113 - loss: 0.8462
Epoch 4/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6216 - loss: 0.7336
Epoch 5/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6504 - loss: 0.6834
Epoch 6/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6337 - loss: 0.6596
Epoch 7/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6748 - loss: 0.6172
Epoch 8/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6750 - loss: 0.6145
Epoch 9/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6832 - loss: 0.5821
Epoch 10/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6947 - loss: 0.5568
Epoch 11/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.6924 - loss: 0.5701
Epoch 12/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7099 - loss: 0.5461
Epoch 13/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6984 - loss: 0.5537
Epoch 14/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7303 - loss: 0.5270
Epoch 15/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7132 - loss: 0.5483
Epoch 16/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7294 - loss: 0.5084
Epoch 17/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7217 - loss: 0.5254
Epoch 18/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7294 - loss: 0.5156
Epoch 19/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7338 - loss: 0.5015
Epoch 20/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7471 - loss: 0.4994
Epoch 21/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7517 - loss: 0.4830
Epoch 22/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7636 - loss: 0.4783
Epoch 23/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7525 - loss: 0.4786
Epoch 24/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7669 - loss: 0.4657
Epoch 25/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7541 - loss: 0.4791
Epoch 26/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7527 - loss: 0.4696
Epoch 27/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7595 - loss: 0.4655
Epoch 28/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7657 - loss: 0.4502
Epoch 29/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7706 - loss: 0.4515
Epoch 30/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7798 - loss: 0.4472
Epoch 31/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7692 - loss: 0.4395
Epoch 32/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7809 - loss: 0.4392
Epoch 33/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7947 - loss: 0.4170
Epoch 34/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7656 - loss: 0.4564
Epoch 35/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - accuracy: 0.7669 - loss: 0.4506
Epoch 36/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7785 - loss: 0.4283
Epoch 37/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7858 - loss: 0.4273
Epoch 38/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8189 - loss: 0.3949
Epoch 39/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - accuracy: 0.8016 - loss: 0.4074
Epoch 40/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7897 - loss: 0.4219
Epoch 41/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - accuracy: 0.7937 - loss: 0.4241
Epoch 42/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8030 - loss: 0.4093
Epoch 43/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7840 - loss: 0.4192
Epoch 44/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7985 - loss: 0.4379
Epoch 45/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7960 - loss: 0.4128
Epoch 46/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - accuracy: 0.8079 - loss: 0.4224
Epoch 47/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - accuracy: 0.8155 - loss: 0.4016
Epoch 48/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7996 - loss: 0.4060
Epoch 49/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7848 - loss: 0.4591
Epoch 50/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8106 - loss: 0.3994
Epoch 51/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8253 - loss: 0.3829
Epoch 52/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7994 - loss: 0.3947
Epoch 53/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8317 - loss: 0.3736
Epoch 54/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8131 - loss: 0.3968
Epoch 55/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7945 - loss: 0.4178
Epoch 56/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8035 - loss: 0.4187
Epoch 57/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7862 - loss: 0.4444
Epoch 58/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8030 - loss: 0.4062
Epoch 59/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8093 - loss: 0.4157
Epoch 60/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8162 - loss: 0.3970
Epoch 61/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8081 - loss: 0.4241
Epoch 62/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8085 - loss: 0.4160
Epoch 63/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.7977 - loss: 0.4202
Epoch 64/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8094 - loss: 0.4067
Epoch 65/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8167 - loss: 0.3961
Epoch 66/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8282 - loss: 0.3934
Epoch 67/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8156 - loss: 0.4060
Epoch 68/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8182 - loss: 0.3985
Epoch 69/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8113 - loss: 0.4008
Epoch 70/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8002 - loss: 0.4059
Epoch 71/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8270 - loss: 0.3929
Epoch 72/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8152 - loss: 0.4018
Epoch 73/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8224 - loss: 0.3971
Epoch 74/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8252 - loss: 0.3878
Epoch 75/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8368 - loss: 0.3825
Epoch 76/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8306 - loss: 0.3762
Epoch 77/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8183 - loss: 0.4025
Epoch 78/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8129 - loss: 0.3980
Epoch 79/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7880 - loss: 0.4325
Epoch 80/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8309 - loss: 0.3850
Epoch 81/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8052 - loss: 0.4209
Epoch 82/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8391 - loss: 0.3665
Epoch 83/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8116 - loss: 0.4003
Epoch 84/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8177 - loss: 0.3865
Epoch 85/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8108 - loss: 0.4145
Epoch 86/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8285 - loss: 0.3924
Epoch 87/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8349 - loss: 0.3936
Epoch 88/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8101 - loss: 0.4180
Epoch 89/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8158 - loss: 0.4174
Epoch 90/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8245 - loss: 0.3724
Epoch 91/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8407 - loss: 0.3704
Epoch 92/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8245 - loss: 0.3955
Epoch 93/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8138 - loss: 0.4078
Epoch 94/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8299 - loss: 0.3807
Epoch 95/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8018 - loss: 0.4280
Epoch 96/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8166 - loss: 0.4264
Epoch 97/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8173 - loss: 0.3928
Epoch 98/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8227 - loss: 0.4052
Epoch 99/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8489 - loss: 0.3765
Epoch 100/100
48/48 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8214 - loss: 0.3850

Out[12]:

<keras.src.callbacks.history.History at 0x7d9eafaa9780>

In [13]:

y_pred = ann.predict(X_test)
y_pred = (y_pred > 0.5)

12/12 ━━━━━━━━━━━━━━━━━━━━ 0s 5ms/step

In [14]:

from sklearn.metrics import confusion_matrix, accuracy_score
cm = confusion_matrix(y_test, y_pred)
print(cm)
print("Accuracy Score", accuracy_score(y_test, y_pred))

[[132  38]
 [ 27 181]]
Accuracy Score 0.828042328042328

In [15]:

accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred, average='weighted')
recall = recall_score(y_test, y_pred, average='weighted')
f1 = f1_score(y_test, y_pred, average='weighted')

print("Accuracy Score:", accuracy)
print("Precision Score:", precision)
print("Recall Score:", recall)
print("F1 Score:", f1)

Accuracy Score: 0.828042328042328
Precision Score: 0.828150135636997
Recall Score: 0.828042328042328
F1 Score: 0.8273825671802651

In [16]:

from sklearn.metrics import roc_curve, auc

In [17]:

# Plotting the ROC Curve

# Compute predicted probabilities
y_pred_prob = ann.predict(X_test).ravel()

# Compute ROC curve and ROC area
fpr, tpr, thresholds = roc_curve(y_test, y_pred_prob)
roc_auc = auc(fpr, tpr)

# Plot ROC curve
plt.figure()
plt.plot(fpr, tpr, color='darkorange', lw=2, label='ROC curve (area = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ANN ROC Curve and AUC')
plt.legend(loc="lower right")
plt.show()

12/12 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step

Predicting Heart Attack Risk

More posts

A Shared Passion

God is My Refuge and My Fortress

My Silent Grind

God’s Blessings