Question:

Implement Logistic regression using NumPy. You should implement your code in the provided logistic$\_$regression.py file. This python file takes two csv files as inputs, which are training and testing csv files. For example, in the following usage scenario, log$\_$training.csv is the training input csv file and log$\_$testing.csv is the testing input csv file.

$python$3$ logistic$\_$regression.py log$\_$training.csv log$\_$testing.csv

Output the Accuracy score of prediction.

provided logistic$\_$regression.py file is as follow:

import numpy as np

import pandas as pd

import math

import sys

import os

#todo define necessary functions

def logistic$\_$regression$($xtrain$,$ ytrain, xtest, ytest$)$:

$"""$

return: Accuracy value

$"""$

#todo fill code here

return $-1$

# do not modify this function

def load$\_$data$()$:

train$\_$filename $=$ sys$.$argv$[1]$

test$\_$filename $=$ sys$.$argv$[2]$

train$\_$feature$\_$matrix $=$ pd$.$read$\_$csv$($train$\_$filename$)$

test$\_$feature$\_$matrix $=$ pd$.$read$\_$csv$($test$\_$filename$)$

train$\_$feature$\_$matrix $=$ train$\_$feature$\_$matrix.dropna$()$

test$\_$feature$\_$matrix $=$ test$\_$feature$\_$matrix.dropna$()$

X$\_$TRAIN $=$ train$\_$feature$\_$matrix.iloc$[$:$,$ :len$($train$\_$feature$\_$matrix.columns$)-1]$

Y$\_$TRAIN $=$ train$\_$feature$\_$matrix.iloc$[$:$,-1]$

X$\_$TEST $=$ test$\_$feature$\_$matrix.iloc$[$:$,$ :len$($test$\_$feature$\_$matrix.columns$)-1]$

Y$\_$TEST $=$ test$\_$feature$\_$matrix.iloc$[$:$,-1]$

return X$\_$TRAIN, Y$\_$TRAIN, X$\_$TEST, Y$\_$TEST

if $\_\_$name$\_\_=="\_\_$main$\_\_"$:

xtrain, ytrain, xtest, ytest $=$ load$\_$data$()$

ACCURACY$\_$SCORE $=$ logistic$\_$regression$($xtrain$,$ ytrain, xtest, ytest$)$

print$("$ACCURACY score is : $",$ ACCURACY$\_$SCORE$)$

$-$log$\_$testing.csv contains in the following format:

male,age,education,currentSmoker,cigsPerDay,BPMeds,prevalentStroke,prevalentHyp,diabetes,totChol,sysBP$,$diaBP,BMI,heartRate,glucose,TenYearCHD

$(1,54,3\mathrm{.}0,0,0\mathrm{.}0,0\mathrm{.}0,0,1,0,258\mathrm{.}0,146\mathrm{.}0,98\mathrm{.}5,26\mathrm{.}05,60\mathrm{.}0,68\mathrm{.}0,0)$

$(0,61,1\mathrm{.}0,0,0\mathrm{.}0,,0,0,0,218\mathrm{.}0,148\mathrm{.}0,80\mathrm{.}0,37\mathrm{.}04,82\mathrm{.}0,78\mathrm{.}0,0)$

There are $2120$ lines of data structured in this way

$-$log$\_$training.csv contains in the following format:

male,age,education,currentSmoker,cigsPerDay,BPMeds,prevalentStroke,prevalentHyp,diabetes,totChol,sysBP$,$diaBP,BMI,heartRate,glucose,TenYearCHD

$(1,39,4\mathrm{.}0,0,0\mathrm{.}0,0\mathrm{.}0,0,0,0,195\mathrm{.}0,106\mathrm{.}0,70\mathrm{.}0,26\mathrm{.}97,80\mathrm{.}0,77\mathrm{.}0,0)$

$(0,46,2\mathrm{.}0,0,0\mathrm{.}0,0\mathrm{.}0,0,0,0,250\mathrm{.}0,121\mathrm{.}0,81\mathrm{.}0,28\mathrm{.}73,95\mathrm{.}0,76\mathrm{.}0,0)$

There are $2120$ lines of data structured in this way

i have attached the image of log$\_$training.csv file