stormxuwz

# gist only to keep record from https://www.jiqizhixin.com/articles/bb59b879-e030-400d-abbc-d9c0708266ff

# Random Forest Algorithm on Sonar Dataset
from random import seed
from random import randrange
from csv import reader
from math import sqrt

# Load a CSV file
def load_csv(filename):

stormxuwz

# list_forecasts = [[1,3],[2,5]]

## cover(1pm, 7pm, [[1,3], [5,7]])
## return [[3,5]]

def cover(startTime, endTime, list_forecasts):
    n = len(list_forecasts)
    

stormxuwz

plot_gly_on_map <- function(newDF, global = FALSE, trend = FALSE, outputFile = "test.png"){
	# newDF$value <- newDF$summerSum_UHY - newDF$springSum_UHY
	longRange <- range(newDF$Long)
	latRange <- range(newDF$Lat)
	bbox <- make_bbox(longRange,latRange,f = 0.3)
	# myMap <- get_map(location=bbox, source="stamn",crop=TRUE,color="bw",maptype="terrain")
	myMap <- get_map(location = bbox, maptype="toner-lite", source="stamen",zoom=7,color = "bw",crop=TRUE)
	# ggmap(myMap)
	SU_locations <- unique(newDF[,c("Station","Lat","Long")])

stormxuwz

-- LaunchBar Action Script
-- apple script to append launchbar input to the last line of omnioutliner

on handle_string(_string)
	
	tell application "OmniOutliner 4.6.1"
		set theDocument to the front document
		set newRow to make new row at last row of front document
		set topic of newRow to _string
		outdent newRow

stormxuwz

# This is a pure python K-means implementation
import numpy as np

def calDistance(x,y):
	# return the distance of x and y
	return np.sum((x-y)**2)


def assignClusters(centers,data):
	distance = np.zeros((len(data),len(centers)))

stormxuwz

## Classification starts now
library(MASS)
library(e1071)
library(rda)
####################################
 qda.model=function(traindata){
 	qda.result=qda(Y~.,data=traindata)
 	return(qda.result)
 }

stormxuwz

randomForest_clf <- function(matTrain,trainLabel,matTest,...){
	library(randomForest)
	rf_model<-randomForest(matTrain,trainLabel,ntree=500)
	rf_predict<-predict(rf_model,matTest)
	return(rf_predict)
}


xgboost_clf_1000 <- function(matTrain,trainLabel,matTest,...){
	library(xgboost)

stormxuwz

from __future__ import division
import numpy as np
import chainer  # only for import the data at this script


def softmax(z):
	# z is a vector
    return np.exp(z) / np.sum(np.exp(z))

def sigmoid(x):

stormxuwz

import numpy as np

def slidingWindow(x,max_error):
	n=len(x)
	leftNode=0
	segmentList=[]
	print n
	
	while leftNode<n-1:
		print leftNode

stormxuwz

from __future__ import division
import numpy as np


class OnlineClf(object):
	
	def __init__(self,iterNum,R):
		self.w=None
		self.iterNum=iterNum
		self.misNum=[[0,0]]