Accuracy only 50% plz help

anandprakash1091971 · June 21, 2020, 4:57pm

CodingJoshi/MachineLearningCodingBlocks/blob/master/🏆Diabetes Detection Challenge.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",

This file has been truncated. show original

where is my error

CrazyRabbit · June 21, 2020, 5:10pm

Hey @anandprakash1091971

There is no error. Rather, you have to increase accuracy through Hyper-parameter Tuning. In KNN, only parameter we have is K. So, try different values of k (e.g Odd numbers in a range like 10-25).
Also, scale the data. Scaling is of utmost importance in KNN.

Hope this helps!

anandprakash1091971 · June 21, 2020, 5:53pm

without scalling accuracy is 50 after scalling 76%
after increasing value of k to 25 accuracy reach 79%

how to increase it further ??

thanks

CrazyRabbit · June 21, 2020, 5:59pm

Hey @anandprakash1091971
79% is the maximum accuracy you can achieve with KNN. To increase it further, you need more complex algorithms like Neural Networks, Ensemble Methods etc. You can safely move on to the further contents of the course.

CrazyRabbit · June 26, 2020, 9:48am

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.