Upload New File

8ca11bfe · Sanghoon · 137277c4 · 8ca11bfe
Commit 8ca11bfe authored May 04, 2022 by Sanghoon
Hide whitespace changes
Inline Side-by-side

Showing with 215 additions and 0 deletions

Pima_R_code_notebook.ipynb ...lassification/Diabetes Example/Pima_R_code_notebook.ipynb +215 -0

No files found.
--- a/Crash Course on Naive Bayes Classification/Diabetes Example/Pima_R_code_notebook.ipynb
+++ b/Crash Course on Naive Bayes Classification/Diabetes Example/Pima_R_code_notebook.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Develop algorithm to predict whether a person has diabetes given health factors\n",
+    "\n",
+    "#Prepare a clean R environment in work space.\n",
+    "rm(list=ls()) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Use setwd() to navigate the data directory and specify desired folder. Here we are using Rstudio Editor directory.\n",
+    "setwd(dirname(rstudioapi::getSourceEditorContext()$path))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Import our csv file data\n",
+    "data=read.csv(\"pima.csv\",header=TRUE) "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Construct a training data set\n",
+    "TrainingPct=0.8 #Percent of data to train model on\n",
+    "TrainingSample=floor(TrainingPct*dim(data)[1])  #Number of observations to train the model on , #dim()[n] = Retrieve or set the n dimension of an object\n",
+    "TestSample=dim(data)[1]-TrainingSample #Number of observations to test the model on"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "TrainingData=data[1:TrainingSample,]  #Get the training data\n",
+    "Diabetes_categ=unique(TrainingData$diabetes) #Categorize diabetes by taking unique elements of the column diabetes(which is 0 and 1 in this case)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "MeanMat=matrix(0,length(Diabetes_categ),dim(TrainingData)[2]-1)  #Initialize matrix for mean values in training sample\n",
+    "SDMat=matrix(0,length(Diabetes_categ),dim(TrainingData)[2]-1)  #Initialize matrix for standard deviations(st dev) in training sample\n",
+    "MargProb=rep(0,length(Diabetes_categ)) #Initialize vector for marginal probabilities\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for (i in 1:length(Diabetes_categ)){  #Using for loop, loop through whether or not the person has diabetes\n",
+    "Data_categ=subset(TrainingData,TrainingData$diabetes==Diabetes_categ[i]) #Subset training sample based on whether or not the person has diabetes\n",
+    "    for (j in 1:(dim(Data_categ)[2]-1)){ #Using for loop, loop through obtain mean, st dev, and marginal probability\n",
+    "  mean_val=mean(Data_categ[,j]) #Calculates mean\n",
+    "  sd_val=sd(Data_categ[,j]) #Calculates st dev\n",
+    "  MeanMat[i,j]=mean_val\n",
+    "  SDMat[i,j]=sd_val\n",
+    "  MargProb[i]=dim(Data_categ)[1]/dim(TrainingData)[1]  #Calculates marginal probability\n",
+    "}\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ProbList=list(MeanMat=MeanMat,SDMat=SDMat,MargProb=MargProb)  #Stores the training data (mean, sd, marg prob in a list)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Construct a test sample\n",
+    "TestData=data[(TrainingSample+1):dim(data)[1],] #Select all except the training sample from the data\n",
+    "TestVec=TestData[1,]\n",
+    "AssignedMat=matrix(0,dim(TestData)[1],3)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Construct a function NB classifier\n",
+    "pima_fn<-function(TestVec,ProbList){\n",
+    "  \n",
+    "  #Bring in training data as separate matrices and vectors - mean, st dev, and marg prob\n",
+    "  MeanMat=ProbList$MeanMat\n",
+    "  SDMat=ProbList$SDMat\n",
+    "  MargProb=ProbList$MargProb\n",
+    "  ProbTestMat=matrix(0,length(MargProb),length(TestVec))\n",
+    "  \n",
+    "  for (j in 1:length(TestVec)){  #Loop through the different elements of the patient (various variables)\n",
+    "    \n",
+    "    for (k in 1:length(ProbList$MargProb)){ #Loop through the options as to whether or not the patient has diabetes\n",
+    "      \n",
+    "      if (j<length(TestVec))\n",
+    "      {ProbTestMat[k,j]=dnorm(as.numeric(TestVec[j]),MeanMat[k,j],SDMat[k,j])}  #Calculate the normal density value\n",
+    "      else\n",
+    "      {ProbTestMat[k,j]=MargProb[k]}  #Calculate marg prob\n",
+    "    }\n",
+    "    Probs=apply(ProbTestMat,1,prod)  #Calculate the product across probabilities\n",
+    "    ind=which.max(Probs)  #Find which probability is higher\n",
+    "    AssignedVec=c(Probs,Diabetes_categ[ind])  \n",
+    "  }\n",
+    "  return(list(AssignedVec=AssignedVec[1:2],AssignedCondition=AssignedVec[3]))  #Elements returned as a list.\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Load NB classifier\n",
+    "\n",
+    "for (i in 1:dim(TestData)[1]){\n",
+    "    \n",
+    "    TestVec=TestData[i,1:(dim(TestData)[2]-1)]\n",
+    "    result<-pima_fn(TestVec,ProbList)\n",
+    "    AssignedMat[i,]=c(as.numeric(result$AssignedVec),result$AssignedCondition)\n",
+    "}\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "CheckMat=data.frame(cbind(TestData$diabetes,AssignedMat[,3]))\n",
+    "colnames(CheckMat)=c(\"Actual\",\"Assigned\")\n",
+    "Pct_Accuracy=sum(CheckMat$Actual==CheckMat$Assigned)/dim(TestData)[1]  #Computes the percent accuracy\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[1] \"Classifier Percent Accuracy\"\n",
+      "[1] 0.721519\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"Classifier Percent Accuracy\") #Print our accuracy as percent value.\n",
+    "print(Pct_Accuracy)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Executing function in a sample data set to predict likelihood of diabetes\n",
+    "Example=read.csv(file=\"Example_Diabetes.csv\",header=TRUE)\n",
+    "Ex1<-pima_fn(Example[1,],ProbList)\n",
+    "Ex2<-pima_fn(Example[2,],ProbList)\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "R",
+   "language": "R",
+   "name": "ir"
+  },
+  "language_info": {
+   "codemirror_mode": "r",
+   "file_extension": ".r",
+   "mimetype": "text/x-r-source",
+   "name": "R",
+   "pygments_lexer": "r",
+   "version": "3.4.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}