-
Notifications
You must be signed in to change notification settings - Fork 42
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
0 parents
commit 271ed13
Showing
5 changed files
with
119 additions
and
0 deletions.
There are no files selected for viewing
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,2 @@ | ||
*.csv | ||
*.m~ |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,10 @@ | ||
Winning Code for the EMC Data Science Global Hackathon (Air Quality Prediciton) | ||
------------------------------------------------------------------------------- | ||
|
||
https://www.kaggle.com/c/dsg-hackathon | ||
|
||
To execute this code, | ||
|
||
1. Download TrainingData.csv from https://www.kaggle.com/c/dsg-hackathon/data and put it in this folder | ||
2. Run make_predictions.m from the Matlab command prompt | ||
3. Copy the resulting predictions from |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,45 @@ | ||
function [fea_train, train_targets, fea_test, test_chunk_id] = features(data, prediction_offset) | ||
|
||
time_back = 8; | ||
|
||
fea_train = zeros(40000, 3 + 89*time_back); | ||
fea_test = zeros(500, 3 + 89*time_back); | ||
|
||
train_targets = zeros(40000, 39); | ||
|
||
test_chunk_id = []; | ||
|
||
fea_cnt = 0; | ||
test_cnt = 0; | ||
for i=1:size(data,1)-time_back-prediction_offset+1 | ||
if data(i,2)==data(i+time_back+prediction_offset-1,2) | ||
fea_cnt = fea_cnt + 1; | ||
fea_train(fea_cnt,1:3) = data(i, 4:6); | ||
this_fea = data(i:i+time_back-1,7:95); | ||
fea_train(fea_cnt,4:end) = this_fea(:)'; | ||
|
||
train_targets(fea_cnt, :) = data(i+time_back+prediction_offset-1, 95-39+1:95); | ||
end | ||
|
||
if data(i,2) ~= data(i+1,2) | ||
test_cnt = test_cnt + 1; | ||
i_back = i - time_back + 1; | ||
fea_test(test_cnt,1:3) = data(i_back, 4:6); | ||
|
||
this_fea = data(i_back:i_back+time_back-1,7:95); | ||
fea_test(test_cnt,4:end) = this_fea(:)'; | ||
test_chunk_id(end+1) = data(i_back,2); | ||
end | ||
end | ||
|
||
test_cnt = test_cnt + 1; | ||
i_back = size(data,1) - time_back + 1; | ||
fea_test(test_cnt,1:3) = data(i_back, 4:6); | ||
|
||
this_fea = data(i_back:i_back+time_back-1,7:95); | ||
fea_test(test_cnt,4:end) = this_fea(:)'; | ||
test_chunk_id(end+1) = data(i_back,2); | ||
|
||
train_targets = train_targets(1:fea_cnt,:); | ||
fea_train = fea_train(1:fea_cnt,:); | ||
fea_test = fea_test(1:test_cnt, :); |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,36 @@ | ||
function make_predictions() | ||
|
||
prediction_offsets = [1 2 3 4 5 10 17 24 48 72]; | ||
|
||
data = read_data(); | ||
|
||
test_predictions = zeros(2100,39); | ||
|
||
matlabpool open 4 | ||
options = statset('UseParallel','always'); | ||
|
||
for p=1:10 | ||
prediction_offset = prediction_offsets(p); | ||
[fea_train, train_targets, fea_test, test_chunk_id] = features(data, prediction_offset); | ||
tic | ||
for i=1:size(train_targets,2) | ||
[p,i] | ||
locs = find(train_targets(:,i)>=0); | ||
tm = TreeBagger(12,fea_train(locs,:),train_targets(locs,i),'method','regression','minleaf',200,'options',options); | ||
pred = predict(tm,fea_test); | ||
for j=1:length(test_chunk_id) | ||
test_predictions(test_chunk_id(j)*10-10+p,i) = pred(j); | ||
end | ||
end | ||
toc | ||
end | ||
|
||
for i=1:210 | ||
if isempty(find(i==test_chunk_id)) | ||
for j=1:39 | ||
test_predictions( (i-1)*10+1:i*10,j) = median(test_predictions(:,j)); | ||
end | ||
end | ||
end | ||
|
||
dlmwrite('predictions.csv',test_predictions); |
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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,26 @@ | ||
function data = read_data() | ||
|
||
fid = fopen('TrainingData.csv'); | ||
fgetl(fid); | ||
|
||
data = zeros(37821,95); | ||
days = {'"Saturday"','"Sunday"','"Monday"','"Tuesday"','"Wednesday"','"Thursday"','"Friday"'}; | ||
row_cnt = 0; | ||
|
||
while ~feof(fid) | ||
row_cnt = row_cnt + 1 | ||
line = fgetl(fid); | ||
C = strread(line,'%s','delimiter',','); | ||
for i=1:95 | ||
if i==5 | ||
data(row_cnt,5) = find(strcmp(days,C{5})); | ||
else | ||
if strcmp(C{i},'NA') | ||
data(row_cnt,i) = -1000000; | ||
else | ||
data(row_cnt,i) = str2num(C{i}); | ||
end | ||
end | ||
end | ||
end | ||
|