Zindi
CompeteJobsLearnChatLeaderboardFor Organisations
PartnersMeet the teamPressCase studiesAI4EAC
Primary competition visual

INEGI UN-GGIM Human Settlement Detection Challenge by ITU

Helping Mexico
1 000 CHF
Completed (~2 years ago)
Classification
213 joined
84 active
InfoDataChatLeaderboard
Starti
02 Sep 24
Closei
28 Sep 24
Reveali
10 Oct 24
User avatar
nymfree
LB score no better than random guesses ~0.5
Data Ā· 7 Sep 2024, 11:55 Ā· 6

My LB scores seem to be no better than random guesses for NN or GBT models, despite local AUC CV being 0.81 for NN and 0.76 for GBT. Has anyone else experienced this?

Discussion 6 answers
User avatar
not_today
10 Sep 2024, 19:30

Facing same problem. Anyone here who can explain this

Upvotes 0
User avatar
nymfree
10 Sep 2024, 19:50

Figured it out. you have to use the provided id_map file

Upvotes 0
User avatar
not_today
10 Sep 2024, 22:22replied to nymfree

I don't understand what you said. Can you explain

Upvotes 0
User avatar
not_today
12 Sep 2024, 10:58replied to nymfree

Can you share any sample notebook?

Upvotes 0
User avatar
nymfree
12 Sep 2024, 11:19replied to not_today

Basically after making predictions, assuming all your predictions are in a list, do:

df = pd.read_csv('id_map.csv')
my_dict = {}
for i,row in df.iterrows():
    my_dict[row['id']] = row['ID']
    
sub = pd.read_csv('SampleSubmission.csv')
for i in range(len(sub)):
    sub.at[i,'class'] = test_predictions[my_dict[sub.at[i,'id']]]
Upvotes 3
User avatar
not_today
12 Sep 2024, 11:29replied to nymfree

thanks

Upvotes 0

Join the largest network for
data scientists and AI builders

AboutFAQsPrivacy PolicyTerms of UseRules
Status
Ā© Zindi 2026