Week_4_Heart_Disease_Prediction.py

import os
print(os.getcwd())

os.chdir('F:\\Locker\\Sai\\SaiHCourseNait\\DecBtch\\R_Datasets\\')

print(os.getcwd())

import pandas as pd

# import warnings filter
from warnings import simplefilter
# ignore all future warnings
simplefilter(action='ignore', category = FutureWarning)
# import warnings filter
from warnings import simplefilter
# ignore all future warnings
simplefilter(action='ignore', category = FutureWarning)


df = pd.read_csv('cleveland_heart_disease.csv', header = None)
df.head()

df.columns = ['age', 'sex', 'cp', 'trestbps', 'chol',
              'fbs', 'restecg', 'thalach', 'exang', 
              'oldpeak', 'slope', 'ca', 'thal', 'target']

df.head()

### 1 = male, 0 = female
df.isnull().sum()

df['target'].unique()

df['target'] = df.target.map({0: 0, 1: 1, 2: 1, 3: 1, 4: 1})

df['target'].unique()

df['sex'].unique()

df['sex'] = df.sex.map({0: 'female', 1: 'male'})

df['sex'].unique()

df['thal'].isnull().sum()

df['thal'] = df.thal.fillna(df.thal.mean())
df['thal'].isnull().sum()


df['ca'].isnull().sum()

df['ca'] = df.ca.fillna(df.ca.mean())
df['ca'].isnull().sum()


import matplotlib.pyplot as plt
import seaborn as sns

# distribution of target vs age 
sns.set_context("paper", font_scale = 2, rc = {"font.size": 20,"axes.titlesize": 25,"axes.labelsize": 20}) 
sns.catplot(kind = 'count', data = df, x = 'age', hue = 'target', order = df['age'].sort_values().unique())
plt.title('Variation of Age for each target class')
plt.show()

 
# barplot of age vs sex with hue = target
sns.catplot(kind = 'bar', data = df, y = 'age', x = 'sex', hue = 'target')
plt.title('Distribution of age vs sex with the target class')
plt.show()

df['sex'] = df.sex.map({'female': 0, 'male': 1})
df['sex'].unique() 


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

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)

X_train

from sklearn.preprocessing import StandardScaler as ss
sc = ss()
X_train = sc.fit_transform(X_train)
X_train

X_test = sc.transform(X_test)

#########################################   Logistic Regression  #############################################################
'''
X = df.iloc[:, :-1].values
y = df.iloc[:, -1].values

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)
'''

from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression()
classifier.fit(X_train, y_train)

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

from sklearn.metrics import confusion_matrix
cm_test = confusion_matrix(y_pred, y_test)
cm_test

y_pred_train = classifier.predict(X_train)
cm_train = confusion_matrix(y_pred_train, y_train)

print()
print('Accuracy for training set for Logistic Regression = {}'.format((cm_train[0][0] + cm_train[1][1])/len(y_train)))
print('Accuracy for test set for Logistic Regression = {}'.format((cm_test[0][0] + cm_test[1][1])/len(y_test)))