//assign variable to link
mig_url = 'https://gist.githubusercontent.com/cesandoval/b834ac93c07e03ec5205843b97f68017/raw/6dff0d45ed26352a7a3c7afb4ace0bad1ce8ba20/MIG_18022019163824069.csv'
//load to csv array via d3
mig = d3.csv(mig_url)
//import first 5 rows
z.head(200,mig)
//get length of csv
mig.length
//check shape
({rows: mig.length, columns:Object.keys(mig[0]).length})
//check column names
migrationColumns = Object.keys(mig[0])
z.unique(z.getCol('CO2', mig))
migByVariable = z.groupBy(x=>x.Variable, mig)
//sum by inflows by country
inflow_df = z.gbSum("Value", z.groupBy(a => a['CO2'], migByVariable['Inflows of foreign population by nationality']))
outflow_df = z.gbSum("Value", z.groupBy(a => a['CO2'], migByVariable['Outflows of foreign population by nationality']))
z.head(5,inflow_df)
z.head(5,outflow_df)
//sum stock by country
stock_df = z.gbSum("Value", z.groupBy(a => a['CO2'], migByVariable['Stock of foreign-born population by country of birth']))
//get unique countries in dataset
uniqueCountry = z.unique(z.getCol('CO2', mig))
/*{
let outflow_df_format = []
let uniqueCountryOutflow = z.unique(z.getCol('group', outflow_df))
//loop through all 35 values of inflow array; if it's also in the 27 of outflow array, ignore
//if not in the 27, add a row and make sum of that row 0
for(let j=0; j<inflow_df.length; j++){
console.log("evaluating country: "+inflow_df[j].group);
if(uniqueCountryOutflow.indexOf(inflow_df[j].group)<0){
console.log(inflow_df[j].group+ " is not yet in Outflow array")
outflow_df_format.push({['group']:inflow_df[j].group,['sum']:0})
} else {
outflow_df_format.push(inflow_df[j])
}
}
return outflow_df_format
}*/
//everything added
new_df = {
let sum_df = []
//add to the main df
for(var i = 0; i<inflow_df.length; i++){
sum_df.push({['CO2']: inflow_df[i].group, Inflow: inflow_df[i].sum, Outflow: outflow_df[i].sum, Stock: stock_df[i].sum})
}
return sum_df
}
z.head(5,new_df)
//load the data
join_url = 'https://gist.githubusercontent.com/cesandoval/b834ac93c07e03ec5205843b97f68017/raw/0c14fa1b1f65a610491417b2894fceecde5f4260/country-and-continent-codes-list-csv_csv.csv'
df = d3.csv(join_url)
//view the df
z.head(5,new_df)
//pick out two columns from the df
two_df = z.pickCols(['Three_Letter_Country_Code','Continent_Name'],df)
//merge the df and the created columns df
merged_df = z.merge(new_df,two_df,'CO2','Three_Letter_Country_Code',"_df1","_df2")
z.head(10,merged_df)
//count inflows, outflows, and stock by continent
//merged_df_grouped = z.groupBy(a=>a['Continent_Name'],merged_df)
ct_inflow = z.gbSum("Inflow", z.groupBy(a => a['Continent_Name'], merged_df))
ct_outflow = z.gbSum("Outflow", z.groupBy(a => a['Continent_Name'], merged_df))
ct_stock = z.gbSum("Stock", z.groupBy(a => a['Continent_Name'], merged_df))
ct_df = {
let temp = []
//add to the main df
for(var i = 0; i<7; i++){
temp.push({['Continent']: ct_inflow[i].group, Inflow: ct_inflow[i].sum, Outflow: ct_outflow[i].sum, Stock: ct_stock[i].sum})
}
return temp
}
//Create single Zebras table
variablegroup = z.groupBy(a => a.Variable, mig)
filterByYear = z.filter(r=> r["Year"]==2016 && r["Variable"]=='Stock of foreign-born population by country of birth',mig)
//sum and group the 2016 stock by country
stock_2016 = z.gbSum("Value",z.groupBy(r => r['Country of birth/nationality'],filterByYear))
z.head(5,stock_2016)
low_mig = z.filter(r=> r['sum']<=50000,stock_2016)
med_mig = z.filter(r=> r['sum']>50000 && r['sum']<100000,stock_2016)
high_mig = z.filter(r=> r['sum']>=100000,stock_2016)
//make new array using deriveCol
difference = z.deriveCol(r => r.Inflow - r.Outflow,new_df)
inflowOutflow = z.addCol("inflow-outflow",difference,new_df)
z.head(5,inflowOutflow)
// Your code here
Purpose-built for displays of data
Observable is your go-to platform for exploring data and creating expressive data visualizations. Use reactive JavaScript notebooks for prototyping and a collaborative canvas for visual data exploration and dashboard creation.
