Iris Species Web App

Sara Rafi

Introduction

  • Iris a flowering plant with 260-300 species

  • Different species have different characteristics

  • These characteristics include:

    Length

    Width

    Length

    Width

  • Based on these characteristics the app identifies if an iris plant is :

    setosa

    virginica

    versicolor

Building the Model

  • Dataset:

    The model is bulit on the The model is built using the the iris data set collected by Ronald Fisher in 1936

    This data set consists of 50 samples from each of three iris species

  • Model

    The final model is a random walk model

The Prediction Model

m

## Random Forest 
## 
## 150 samples
##   4 predictor
##   3 classes: 'setosa', 'versicolor', 'virginica' 
## 
## No pre-processing
## Resampling: Bootstrapped (25 reps) 
## Summary of sample sizes: 150, 150, 150, 150, 150, 150, ... 
## Resampling results across tuning parameters:
## 
##   mtry  Accuracy   Kappa      Accuracy SD  Kappa SD  
##   2     0.9445418  0.9161825  0.02357213   0.03560454
##   3     0.9438562  0.9151566  0.02391551   0.03616346
##   4     0.9431387  0.9140672  0.02334345   0.03528496
## 
## Accuracy was used to select the optimal model using  the largest value.
## The final value used for the model was mtry = 2.

How the App Works

width