Created
February 9, 2014 08:47
-
-
Save caged/8896322 to your computer and use it in GitHub Desktop.
Convert raw NBA JSON to CSV.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env coffee | |
fs = require 'fs' | |
csv = require 'csv' | |
extend = (object, properties) -> | |
for key, val of properties | |
object[key] = val | |
object | |
data = fs.readFileSync("./data/team-abbreviations.csv", 'utf8') | |
.split("\n") | |
.map((r) -> r.split(',')) | |
data.shift() | |
teamabbrs = data.map((d) -> o = {team_name: d[0], team_abbreviation: d[1] }) | |
teams = {} | |
shared = ['GP', 'W', 'L', 'MIN', 'TEAM_ID', 'TEAM_NAME', 'W_PCT'] | |
ignore = ['CFPARAMS', 'CFID'] | |
files = fs.readdirSync './data/teams' | |
for season in files | |
continue if season == '.gitkeep' | |
statfiles = fs.readdirSync "./data/teams/#{season}" | |
allheaders = [] | |
for mode in statfiles | |
data = JSON.parse fs.readFileSync "data/teams/#{season}/#{mode}", 'utf8' | |
params = data.parameters | |
data = data.resultSets[0] | |
headers = data.headers | |
for row, i in data.rowSet | |
team = {} | |
for value,j in row | |
if headers[j] in ignore | |
hdr = null | |
else if headers[j] in shared | |
hdr = headers[j].toLowerCase() | |
else | |
stattype = params.MeasureType.toLowerCase().replace(' ', '_') | |
hdr = "#{stattype}_#{headers[j].toLowerCase()}" | |
team[hdr] = value if hdr | |
id = "#{team.team_id}:#{season}" | |
teams[id] ?= season: season | |
extend teams[id], team | |
teams[id].abbr = teamabbrs.filter((d) -> d.team_name == team.team_name)[0].team_abbreviation | |
headers = Object.keys(teams[Object.keys(teams)[0]]) | |
out = csv().to.path('out/teams.csv', columns: headers, header: true) | |
for id,team of teams | |
out.write team | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment