Yankim

br = webdriver.Firefox() #open firefox
br.get('https://www.allrecipes.com/recipes/'+str(yearurls[i])) 
###ID number for year, example 1997 has ID of 14486

html_list = br.find_element_by_id("grid")
urls = html_list.find_elements(By.CLASS_NAME, "favorite") 
#All top 20 recipes have hearts associated with them. Inside 
#the heart contains the unique ID number for the given recipe

for i, e in enumerate(urls):

Yankim

def scrape_recipe(br, year, idnumber):
	#This is called when user wants to scrape for specific recipe site
	#Try functions were used to prevent any one element from stopping the operation
	
	#recipe title
	try:
		rtitle = br.find_element_by_tag_name('h1').text
	except:
		rtitle = 'NA'

Yankim

import numpy as np
import pymongo
import pandas as pd
# Connection to Mongo DB and import recipe and ingredients collections as Pandas
try:
    conn=pymongo.MongoClient()
    print "Connected successfully!!!"
except pymongo.errors.ConnectionFailure, e:
    print "Could not connect to MongoDB: %s" % e 
conn

Yankim

#Loading packages
library(dplyr); library(ggplot2); library(RColorBrewer); library(rworldmap)

#Loading datasets
indicators = read.csv("subbeddata.csv", header = TRUE, stringsAsFactors = FALSE)
allindicators = read.csv("/Users/YannickMac/Dropbox/Applications/Data science/NYCDSA/Data_visualization_project/world-development-indicators/Indicators.csv")

counts <- indicators %>%
    group_by(IndicatorCode, IndicatorName) %>%
    summarise(NumCountries = n_distinct(CountryName),

Yankim

library(shiny); library(maps); library(mapproj); library(dplyr); library(plotly); library(googleVis); library(car)
data("county.fips")
#Join data by county indentification numbe (fips) to the county data in the maps package
flipjoin = function(x) {
    y = read.csv(x)
    left_join(county.fips, y, by = c("fips" = "FIPS"))
}

#Data wrangling for map plot
health2 = flipjoin("data/health.csv")

Yankim

# server.R
library(shiny); library(maps); library(mapproj); library(shinydashboard); library(plotly); library(DT); source("helpers.R")

shinyServer(
    function(input, output) {
        output$map <- renderPlot({
            args <- switch(input$var,
                           "Percent Adult Obese 2009" = list(health2$PCT_OBESE_ADULTS09, "darkgreen", "% Obese"),
                           "Percent Adult Obese 2010" = list(health2$PCT_OBESE_ADULTS10, "darkgreen", "% Obese"),
                           "Percent Adult Diabetic 2009" = list(health2$PCT_DIABETES_ADULTS09, "darkred", "% Diabetic"),

Yankim

library(shiny); library(shinydashboard); library(plotly); source("helpers.R"); library(DT)

shinyUI(dashboardPage(
    dashboardHeader(title = "Food and health demographics in the USA", titleWidth = 400), 
    dashboardSidebar(
        sidebarUserPanel("Yannick Kimmel", image = "Yannick.jpg"),
        
        sidebarMenu(
            menuItem("Map", tabName = "mappanel", icon = icon("map")),
            menuItem("Trends", tabName = "trends", icon = icon("line-chart")),

Yankim

library(xgboost); library(methods); library(pROC); library(caret); library(xgboost); library(readr); library(plyr); library(dplyr)
library(tidyr); library(dummies); library(doMC); registerDoMC(cores = 4)

#Read in the data
#higgs.___.full is raw data
higgs.train.full = read.csv('./data/training.csv', header=T)
higgs.test.full = read.csv('./data/test.csv', header=T)
higgs.testId = higgs.test.full$EventId

#############################################

Yankim

# Grid for the parameter search
#The guidlines for how to tune parameters are commented below and are taken from
# Owen Zheng http://www.slideshare.net/OwenZhang2/tips-for-data-science-competitions
xgb_grid_1 = expand.grid(
  eta = c(.5, 1, 1.5),                #[2-10]/num trees
  max_depth = c(4, 6, 8),             #Start with 6
  nrounds = 100,                      #Fix at 100
  gamma = 0,                          #Usually ok to leave at 0
  colsample_bytree = c(.3, .5, .7),   #.3 - .5
  min_child_weight = 1                #start with 1/sqrt(eventrate)

Yankim

#Predicting training data
xgmat.train <- xgb.DMatrix(as.matrix(higgs.train.dummy), 
                           label = as.numeric(higgs.labels == "X0"),
                           weight = scaled.weight)
xgboostTrainPred <- predict(bst, newdata = xgmat.train)
labels <- ifelse(as.character(higgs.labels)=="X1", 1, 0)

auc = roc(labels, xgboostTrainPred)
plot(auc, print.thres=TRUE)
######## From the graph, we can tell the best threshold is 0.002