Discussion

Home     Discussion Board      KDD CUP of Fresh Air      Data get and result submit tutorial

Patrick Gao

KDD18 Organizer

KDD18 Organizer

Data get and result submit tutorial

posted in   KDD CUP of Fresh Air

March 2, 2018, 7:56 a.m.

23  comments

Ren

March 31, 2018, 7:40 p.m.

Reply

0
<p>Any chance we can get air quality data from 2018-01-31 to 2018-03-31? </p> <p>The data section proviced the history air quality data from 2017-01-01-14:00 to 2018-01-31-15:00. But using the api the air quality data starts from 2018-03-31-07:00. There is 2 month worth history data missing in between.</p>
  • Ren reply Ren

    March 31, 2018, 7:40 p.m.

    Reply

    0
    <p>My above statement is on Beijing’s air quality data. For London, I see the csv file contain history from 2017-01-01:0:00 to 2018-03-09:9:00. The api for london also return data earlist from 2018-03-31-07:00. So there are 22 days of data missing.</p>

Ren

March 31, 2018, 10:34 p.m.

Reply

1
<p>One more thing I noticed is that, London air quality has no value for O3 for both historical from csv and new data via api.</p>

望着蓝天的海

April 1, 2018, 2:18 a.m.

Reply

1
<p>I am also confused about this,the London_historical_aqi_forecast_stations_20180331.csv only have the PM2.5 PM10,NO2</p>
  • 望着蓝天的海 reply Ren

    March 31, 2018, 10:34 p.m.

    Reply

    3
    <p>You need to predict the concentration of PM2.5/PM10/O3 for 35 stations in Beijing and PM2.5/PM10 for13 stations in London.</p>
  • Ren reply Ren

    March 31, 2018, 10:34 p.m.

    Reply

    0
    <p>Thanks for pointing it out. </p>

G13

April 1, 2018, 3:07 a.m.

Reply

3
<p>Test submission by API was error as below.<br>Is the server running now?</p> <p>“<h1>Server Error (500)</h1>“</p>
  • Biendata Staff

    Xinyu reply Ren

    March 31, 2018, 7:40 p.m.

    Reply

    8
    <p>Thank you very much for this request.</p> <p>We will upload the dataset today or tomorrow.</p> <p>Xinyu from Biendata</p>
  • Biendata Staff

    Xinyu reply G13

    April 1, 2018, 3:07 a.m.

    Reply

    0
    <p>Please use filename instead of display_name.</p> <p>We have updated the post.</p>
  • Ren reply Ren

    March 31, 2018, 7:40 p.m.

    Reply

    0
    <p>Great, thank you!</p>

Yasin Seven

April 2, 2018, 7:11 a.m.

Reply

0
<p>I have a question about Meteorology Data,<br>Is there any way to have access for Meteorology Data Forecast for next 48 hours? In the relevant API, entries exist until 6 hours ago.</p>
  • Ren reply Ren

    March 31, 2018, 7:40 p.m.

    Reply

    2
    <p>Hi Xinyu,</p> <p>zhiwuyuan_aq from beijing has no data from either the posted csv file for Feb to March 2018, and the API. Is there anything wrong with data retrieval with this station?</p>
  • fersebas reply Ren

    March 31, 2018, 7:40 p.m.

    Reply

    1
    <p>And the observed meteo data? ty</p>

Ren

April 2, 2018, 8:07 p.m.

Reply

1
<p>Howdy, organizer!</p> <p>So I was finally able to submit my test submissions using the API after some debugging. I found that the API seems only accepting integer values in submissions, which is bothering. Can you make changes to accept float prediction values?</p>
  • Biendata Staff

    Xinyu reply Ren

    April 2, 2018, 8:07 p.m.

    Reply

    1
    <p>That seems, at least from our side, is not true.</p> <p>We can submit files with decimals. Please send your token, submission file and error message, to <a href="mailto:supprot@biendata.com">supprot@biendata.com</a></p>

PlrS

April 3, 2018, 10:56 a.m.

Reply

2
<p>Both Air quality and Meteorology APIs are many hours behind.<br>Is this a technical issue?</p>
  • KDD18 Organizer

    KDD18 Organizer

    Patrick Gao reply PlrS

    April 3, 2018, 10:56 a.m.

    Reply

    0
    <p>It ‘ s UTC time</p>
  • fersebas reply PlrS

    April 3, 2018, 10:56 a.m.

    Reply

    0
    <p>I see</p> <p>2945491,TD5,2018-04-03 11&#58;00&#58;00,6.8,,,,,</p> <p>last record now…</p>
  • Ren reply Ren

    April 2, 2018, 8:07 p.m.

    Reply

    0
    <p>My email got rejected … Can you take a look at the following error message? </p> <p>Error Icon<br>Message not delivered<br>Your message couldn’t be delivered to <a href="mailto:supprot@biendata.com">supprot@biendata.com</a> because the remote server is misconfigured. See technical details below for more information.<br>The response from the remote server was:<br>550 5.4.1 [<a href="mailto:supprot@biendata.com">supprot@biendata.com</a>]: Recipient address rejected: Access denied [BL2NAM02FT064.eop-nam02.prod.protection.outlook.com]</p> <p>Thank you!</p>
  • Ren reply Ren

    April 2, 2018, 8:07 p.m.

    Reply

    0
    <p>Ah i see, you mis-spelled support… My mail got through now.</p>

MO

April 6, 2018, 12:12 a.m.

Reply

0
<p>Hi. Does Data API provide only data between 2018/4/01 00 - 2018/4/30 23 ? Or, can we also download data between 2018/5/1 - 2018/5/31 ?</p>
  • KDD18 Organizer

    KDD18 Organizer

    Patrick Gao reply MO

    April 6, 2018, 12:12 a.m.

    Reply

    0
    <p>Of course yes</p>

Michael Gong

April 7, 2018, 8:03 a.m.

Reply

5
<p>Could we have the grid weather data of 2018-03-27 05&#58;00&#58;00 ~ 2018-03-31 07&#58;00&#58;00 ?</p>
  • MO reply MO

    April 6, 2018, 12:12 a.m.

    Reply

    0
    <p>Thank you!</p>

HALLEY

April 9, 2018, 2:04 p.m.

Reply

0
<p>I got a 500 error with this code:</p> <p>files={‘file’: open(‘C:\KDD\sample_submission_0408.csv’,’rb’)}</p> <p>data = {<br> “user_id”: “HALLEY233”,<br> “team_token”: “xxxxx”,<br> “description”: “Naive model”,<br> “filename”: “sample_submission_0408”,<br>}</p> <p>url = ‘<a href="https://biendata.com/competition/kdd_2018_submit/">https://biendata.com/competition/kdd_2018_submit/</a>‘<br>response = requests.post(url, files=files, data=data, verify=False)</p> <p>Is it some server issue? Thanks!</p>
  • HALLEY reply G13

    April 1, 2018, 3:07 a.m.

    Reply

    0
    <p>Hello, i got the same error saying Server Error. I am curious how did you solve that problem? I am using filename instead of Display name but it does not help. Thank you in advance!</p>

jz455

April 10, 2018, 3:59 a.m.

Reply

0
<p>Is it possible to get the AQ or MEO data before 2017-01-01?</p>

WanQuan

April 13, 2018, 6:32 a.m.

Reply

0
<p>Hi,<br>It seems like I can only get data from time in 01:00 to 23:00 by example code.</p> <p>import requests<br>url = ‘<a href="https://biendata.com/competition/meteorology/bj/2018-04-01-0/2018-04-01-23/2k0d1d8">https://biendata.com/competition/meteorology/bj/2018-04-01-0/2018-04-01-23/2k0d1d8</a>‘<br>respones= requests.get(url)<br>with open (“bj_meteorology_2018-04-01-0-2018-04-01-23.csv”,’w’) as f:<br> f.write(respones.text)</p> <p>How can I get data at 00:00(24:00)?</p>
  • WanQuan reply WanQuan

    April 13, 2018, 6:32 a.m.

    Reply

    0
    <p>OK, I know how it works, ignore me.</p>

WanQuan

April 13, 2018, 7:54 a.m.

Reply

0
<p>Hi,<br>Regards meteorology grid data, I dont know the detail location of each gird point.<br>Can we get the grid map, or Could you please give more futher explaination for gird point?</p>

hzhwcmhf

April 13, 2018, 9:13 a.m.

Reply

3
<blockquote> <p>After April 30th, no new external data can be used.<br>Does it mean I can’t use an old public API to obtain new data after April?<br>Or I just post the API in forum before May, and use it to obtain real-time data such as weather forecasting or AQI prediction.</p> </blockquote>

crux

April 14, 2018, 10:37 p.m.

Reply

3
<p>Hi,<br>Is there any chance we can get this missing dataset:</p> <ul> <li>Beijing’s Meteorological station data<br>2018-01-31 16:00 ~ 2018-03-31 06:00</li></ul>

makingmoney

April 15, 2018, 12:45 p.m.

Reply

0
<p>Could host tell us what precise started time of is so that we can use all the data available? It looks like we only have data started from 2018-03-31 to now. Right?</p>

GYJ

April 18, 2018, 3:30 a.m.

Reply

0
<p>How can i know my team token?</p>
  • GYJ reply GYJ

    April 18, 2018, 3:30 a.m.

    Reply

    0
    <p>Cause I can’t find it in the website <a href="https://biendata.com/competition/kdd_2018/team/my_team/">https://biendata.com/competition/kdd_2018/team/my_team/</a></p>

rapirent

April 20, 2018, 7:30 p.m.

Reply

0
<p>I got a 500 error code with the sample code, is the server closed in the night?</p>

why94nb

April 23, 2018, 3:56 a.m.

Reply

0
<p>So I have seen several posts about this 500 server error, but no reply from the organizer. I am wondering how did you fix the problem? Thanks.</p>
  • joy reply Ren

    March 31, 2018, 7:40 p.m.

    Reply

    0
    <p>can we get the meo data from 2017-01-01 to 2018-03 now?</p>
  • rapirent reply rapirent

    April 20, 2018, 7:30 p.m.

    Reply

    0
    <p>solved, the first row should have no space, meaning <code>test_id, PM2.5, PM10, O3</code> will not be accepted</p>
  • koji reply WanQuan

    April 13, 2018, 6:32 a.m.

    Reply

    0
    <p>I have a same issue.<br>How do you get data at 0:00 (24:00)?</p>

Vikas Maurya

May 1, 2018, 5:02 a.m.

Reply

0
<p>Please clearify it….<br>suppose we are predicting at time ‘t’, so shoud we predict for…<br>t+24 hr and t+48 hr or,<br>t+i hr where i ∈ {1, 2, …. , 48}</p>

thaihq

May 1, 2018, 7:51 a.m.

Reply

0
<p>Today I submit and receive below message<br>{“success”: false, “msg”: “Exceeds limit”}<br>How can I solve it?</p>
  • lbdhr reply thaihq

    May 1, 2018, 7:51 a.m.

    Reply

    0
    <p>me, too. But I only submitted twice today. Do you solve this problem?</p>
  • BigPlato reply Ren

    March 31, 2018, 7:40 p.m.

    Reply

    0
    <p>Sorry to trouble you, do you know how to solve the problem of missing data of zhiwuyuan in Beijing?</p>