Project 1

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score,confusion_matrix
crash_data = pd.read_csv('heart.csv')

print(np.unique(crash_data['sex'],return_counts=True))

crash_data_columns_list = list(crash_data.columns)

print(crash_data_columns_list)

features = list(set(crash_data_columns_list)- set(['sex']))
print(features)

target = list(['sex'])
y= crash_data[target].values

y= crash_data['sex'].values
print(y)

x = crash_data[features].values

train_x, test_x, train_y, test_y = train_test_split(x, y, test_size=0.3,random_state=0)

scaler= StandardScaler()

scaler.fit(train_x)

train_x = scaler.transform(train_x)

test_x = scaler.transform(test_x)

logistic = LogisticRegression()

logistic.fit(train_x,train_y)

prediction= logistic.predict(test_x)

confusion_matrix = confusion_matrix(prediction,test_y)
print(confusion_matrix)

accuracy_score= accuracy_score(prediction,test_y)
print(accuracy_score)

print('Misclassified samples: %d' % (test_y != prediction).sum())

Output is

(array([0, 1], dtype=int64), array([ 96, 207], dtype=int64))
['age', 'sex', 'cp', 'trtbps', 'chol', 'fbs', 'restecg', 'thalachh', 'exng', 'oldpeak', 'slp', 'caa', 'thall', 'output']
['thalachh', 'exng', 'output', 'caa', 'cp', 'trtbps', 'chol', 'oldpeak', 'slp', 'age', 'fbs', 'restecg', 'thall']
[1 1 0 1 0 1 0 1 1 1 1 0 1 1 0 0 0 0 1 0 1 1 1 1 1 0 1 1 0 1 0 1 1 1 1 0 0
 1 0 0 0 1 1 0 1 1 1 1 0 0 0 1 1 0 0 1 1 1 1 0 0 1 1 1 1 0 1 0 1 0 1 1 1 1
 0 0 1 1 1 1 1 1 0 1 0 0 1 1 0 0 1 1 1 0 0 1 0 1 1 1 1 1 0 1 1 0 1 0 0 0 0
 1 0 1 1 0 1 1 0 0 0 1 0 0 0 0 1 0 0 0 0 0 1 1 0 0 0 1 1 1 0 1 0 0 0 1 0 0
 1 1 1 0 1 0 0 0 1 1 1 1 1 0 1 1 1 1 1 0 1 1 1 1 1 1 1 1 1 1 1 1 1 0 0 1 1
 1 1 1 1 1 0 1 1 1 1 1 1 1 1 1 1 1 1 1 0 1 1 0 1 1 1 1 1 0 1 0 0 1 1 1 0 1
 1 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 1 1 1 1 0 1 1 1 1 1 0 1 1 1 1 1 0
 1 0 1 1 0 1 1 0 1 1 1 1 1 1 1 1 1 1 1 0 1 1 1 1 1 1 1 1 1 1 0 1 1 0 1 1 1
 0 1 0 1 1 1 0]
[[ 7 12]
 [14 58]]
0.7142857142857143
Misclassified samples: 26