机器学习与R之KNN

k近邻法与kd树(与本文基本无关)
为了提高k近邻搜索的效率，可以考虑使用特殊的结构存储训练数据，以减少计算距离的次数。具体方法有很多，这里介绍kd树方法
参考 http://blog.csdn.net/qll125596718/article/details/8426458

R语言KNN实现

library(class)  

knn(train,test ,laber,k)
wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k = 21) 

K常用方法 K=训练数据数量的平方根

字符变量利用哑变量编码，eg：0/1

Python版实现
http://blog.csdn.net/q383700092/article/details/51757762
R语言版调用函数
http://blog.csdn.net/q383700092/article/details/51759313
MapReduce简化实现版
http://blog.csdn.net/q383700092/article/details/51780865
spark版
后续添加

rm(list=ls())
# import the CSV file
wbcd <- read.csv("wisc_bc_data.csv", stringsAsFactors = FALSE)

# examine the structure of the wbcd data frame
str(wbcd)

# drop the id feature
wbcd <- wbcd[-1]

# table of diagnosis
table(wbcd$diagnosis)

# recode diagnosis as a factor
wbcd$diagnosis <- factor(wbcd$diagnosis, levels = c("B", "M"),
                         labels = c("Benign", "Malignant"))

# table or proportions with more informative labels
round(prop.table(table(wbcd$diagnosis)) * 100, digits = 1)

# summarize three numeric features
summary(wbcd[c("radius_mean", "area_mean", "smoothness_mean")])

# create normalization function最大最小归一化
normalize <- function(x) {
  return ((x - min(x)) / (max(x) - min(x)))
}

# test normalization function - result should be identical
normalize(c(1, 2, 3, 4, 5))
normalize(c(10, 20, 30, 40, 50))

# normalize the wbcd data |lapply把函数应用到列表的每一个元素
wbcd_n <- as.data.frame(lapply(wbcd[2:31], normalize))

# confirm that normalization worked
summary(wbcd_n$area_mean)

# create training and test data
wbcd_train <- wbcd_n[1:469, ]
wbcd_test <- wbcd_n[470:569, ]

# create labels for training and test data

wbcd_train_labels <- wbcd[1:469, 1]
wbcd_test_labels <- wbcd[470:569, 1]

## Step 3: Training a model on the data ----

# load the "class" library
library(class)

wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test,
                      cl = wbcd_train_labels, k = 21)

## Step 4: Evaluating model performance ----评估性能

# load the "gmodels" library
library(gmodels)

# Create the cross tabulation of predicted vs. actual
CrossTable(x = wbcd_test_labels, y = wbcd_test_pred,
           prop.chisq = FALSE)

## Step 5: Improving model performance ----提高模型性能

# use the scale() function to z-score standardize a data frame  scale()z分数归一化
wbcd_z <- as.data.frame(scale(wbcd[-1]))

# confirm that the transformation was applied correctly
summary(wbcd_z$area_mean)

# create training and test datasets
wbcd_train <- wbcd_z[1:469, ]
wbcd_test <- wbcd_z[470:569, ]

# re-classify test cases
wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test,
                      cl = wbcd_train_labels, k = 21)

# Create the cross tabulation of predicted vs. actual
CrossTable(x = wbcd_test_labels, y = wbcd_test_pred,
           prop.chisq = FALSE)

# try several different values of k
wbcd_train <- wbcd_n[1:469, ]
wbcd_test <- wbcd_n[470:569, ]

wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=1)
CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)

wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=5)
CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)

wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=11)
CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)

wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=15)
CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)

wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=21)
CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)

wbcd_test_pred <- knn(train = wbcd_train, test = wbcd_test, cl = wbcd_train_labels, k=27)
CrossTable(x = wbcd_test_labels, y = wbcd_test_pred, prop.chisq=FALSE)