int main (int argc, char *argv[]) {
if (argc != 2) {
printf( "Usage:\n feature_vs_label [TRAIN FILE]\n\n");
return 1;
}
//------------------------------------------------------------------
csr *labels = csr_malloc(TRAIN_NROWS, TRAIN_NLABELDATA);
csr *features = csr_malloc(TRAIN_NROWS, TRAIN_NFEATUREDATA);
FILE *train;
train = fopen(argv[1], "r");
read_train(train, labels, features);
fclose(train);
int i, j;
for (i = 0; i < features->nrows; ++i) {
for (j = features->ptr[i]; j < features->ptr[i+1]; ++j) {
printf("%d ", features->idx[j]);
}
printf("\n");
}
csr_free(labels);
csr_free(features);
return 0;
}
int main(void) {
struct train tr = {};
read_train(&tr);
printf("\n===========================================================================\n");
print_train(tr);
printf("\n===========================================================================\n");
printf("Введите название станции, для которой\nнеобходимо найти ближайший поезд: ");
char required_station[20];
char c[300] = "";
gets(c);
strncat(required_station, c, 20);
//scanf("%s", &required_station);
next_station(&tr, required_station);
//Освобождение памяти
free(tr.stations_arr);
return EXIT_SUCCESS;
}
void reverse_step (int start_grid[][24], int stop_grid[][24], int vote_case[], double probability_case[]) {
int i, j, n, idx;
//int count_ambiguity[4] = {0, 0, 0, 0};
FLIP_STACK fs = {.size = 0};
for (i = 2; i < 22; ++i) {
for (j = 2; j < 22; ++j) {
idx = get_pattern_idx(stop_grid, i, j);
start_grid[i][j] = vote_case[idx];
//if ((0.15 < probability_case[idx]) && (probability_case[idx] < 0.85)) ++count_ambiguity[0];
//if ((0.3 < probability_case[idx]) && (probability_case[idx] < 0.7)) ++count_ambiguity[1];
//if ((0.4 < probability_case[idx]) && (probability_case[idx] < 0.6)) ++count_ambiguity[2];
//if ((0.45 < probability_case[idx]) && (probability_case[idx] < 0.55)) ++count_ambiguity[3];
// put all the points with median probability into a stack
if (fabs(0.5-probability_case[idx]) < 0.125) push_flip(&fs, i, j, fabs(0.5-probability_case[idx]));
}
}
//printf("%d,%d,%d,%d,%d,\n", count_1s_grid(stop_grid),
// count_ambiguity[0], count_ambiguity[1], count_ambiguity[2], count_ambiguity[3]);
//printf("%d %d %f\n", imax, jmax, probability_max);
quicksort_flips(fs.items, fs.size); // sort the stack
FLIP_POINT ijp;
double score_start, score_flip;
for (n = fs.size; n > 0; --n) {
score_start = difference_forward(start_grid, stop_grid);
ijp = pop_flip(&fs);
flip_point(ijp.i, ijp.j, start_grid);
score_flip = difference_forward(start_grid, stop_grid);
if (score_start <= score_flip) flip_point(ijp.i, ijp.j, start_grid);
}
}
////////////////////////////////////////////////////////////////////////
int count_case_0[5][2097152], count_case_1[5][2097152]; // 2097152 = pow(2, 21)
int vote_case[5][2097152];
double probability_case[5][2097152];
int main () {
// utility parameters
int n, i;
clean_array((int*)count_case_0, 2097152*5);
clean_array((int*)count_case_1, 2097152*5);
// read the train.csv data
FILE *train;
train = fopen ("train.csv", "r");
while (fgetc(train) != '\n') ; // skip the head line
int id, delta, initial_grid[24][24], start_grid[24][24], stop_grid[24][24];
clean_array((int*)initial_grid, 24*24);
clean_array((int*)start_grid, 24*24);
clean_array((int*)stop_grid, 24*24);
// read all the train set and make statistical table for them
for (n = 0; n < 50000; ++n) {
read_train(train, &id, &delta, (int*)start_grid);
for (i = 0; i < delta; ++i) {
conway_step(start_grid, stop_grid);
vote_step(start_grid, stop_grid, count_case_0[i], count_case_1[i]);
copy_grid(start_grid, stop_grid);
}
}
// vote for statistical table
for (i = 0; i < 5; ++i) {
for (n = 0; n < 2097152; ++n) {
if (count_case_0[i][n] < count_case_1[i][n]) vote_case[i][n] = 1;
else vote_case[i][n] = 0;
if (count_case_0[i][n]+count_case_1[i][n] == 0) probability_case[i][n] = 0;
// for the patterns happen really less frequently, we assume the original center is definitely 0.
else probability_case[i][n] = (double)count_case_1[i][n] / (double)(count_case_0[i][n]+count_case_1[i][n]);
}
}
//------------------------------------------------------------------
// check prediction accuracy
///*
train = fopen ("train.csv", "r");
while (fgetc(train) != '\n') ; // skip the head line
FILE *pred;
pred = fopen ("pred.csv", "w");
fprintf(pred, "id,");
for (n = 1; n < 401; ++n) fprintf(pred, "start.%d,", n);
for (n = 1; n < 400; ++n) fprintf(pred, "diff.%d,", n);
fprintf(pred, "diff.400\n");
double difference_all = 0;
for (n = 0; n < 50000; ++n) {
read_train (train, &id, &delta, (int*)initial_grid);
copy_grid(start_grid, initial_grid);
for (i = 0; i < delta; ++i) {
//for (i = 0; i < 1; ++i) {
conway_step(start_grid, stop_grid);
copy_grid(start_grid, stop_grid);
}
for (i = delta-1; i >= 0; --i) {
//for (i = 0; i >= 0; --i) {
reverse_step (start_grid, stop_grid, vote_case[i], probability_case[i]);
copy_grid(stop_grid, start_grid);
}
write_pred(pred, id, initial_grid, start_grid);
difference_all += difference_grids(initial_grid, start_grid);
}
printf("training set score: %f\n", difference_all/50000);
fclose(pred);
//*/
fclose(train);
//------------------------------------------------------------------
// make submission file
/*
FILE *test;
test = fopen ("test.csv", "r");
while (fgetc(train) != '\n') ; // skip the head line
FILE *submission;
submission = fopen ("submission.csv", "w");
fprintf(submission, "id,");
for (n = 1; n < 400; ++n) fprintf(submission, "start.%d,", n);
fprintf(submission, "start.400\n");
for (n = 0; n < 50000; ++n) {
read_test(test, &id, &delta, stop_grid);
for (i = delta-1; i >= 0; --i) {
reverse_step (start_grid, stop_grid, vote_case[i], probability_case[i]);
copy_grid(stop_grid, start_grid);
}
write_submission(submission, id, start_grid);
}
fclose(test);
fclose(submission);
*/
return 0;
// goes the reverse check (see everything after vote_case in reverse_step).
// however, the imporvement seems really tiny.
// for the cutoff of points which need to be checked reversely,
// I use all the predicted data (50000+50000) and got the following table.
// threshold | score
// 0 | 0.128226
// 0.05 | 0.127253
// 0.1 | 0.126986
// 0.12 | 0.126851
// 0.125 | 0.126803 <--
// 0.127 | 0.126826
// 0.13 | 0.126824
// 0.135 | 0.126889
// 0.14 | 0.126914
// 0.15 | 0.127000
// so I use 0.127 (should use 0.125) to predict the test set.
// predicted set score: 0.12957 (-0.0003)
// the improvement is even smaller than I thought, I think it should be around 0.0014.
// :-(
// probably the imporvement of the training set, is because we use the training set
// itself to calculate the scores, which gives bias.
//---------------------
// then use 0.125, and set the probably to be 0.5 if the pattern never appear.
// predicted set score: 0.13034 (+0.0004) -- even go worse~~
//---------------------
// if ruling out the unfrequent patterns, it doesn't seem help.
// 0.125 | 0.127049 (rule out < 2)
// 0.125 | 0.127095 (rule out < 4)
}
int main(int argc, char **argv[])
{
string name;
vector<Mat>Images(100), TestImages(50);
vector<Mat> Descriptor(100), TestDescriptor(50), TestPcafeature(50);
vector<vector<KeyPoint>>Keypoints(100), TestKeypoint(50);
Mat histogram = Mat::zeros(100, Cluster, CV_32F);
Mat Testhistogram = Mat::zeros(50, Cluster, CV_32F);
Mat Keyword = Mat::zeros(Cluster, 20, CV_32F);
Mat full_Descriptor, Pcafeature, Pcaduplicate, clusteridx, trainlabels(100, 1, CV_32F);
vector<vector<DMatch>> matches(50);
Mat predicted(Testhistogram.rows, 1, CV_32F);
// Read Training Images.
read_train(Images, name);
//Calculate SIFT features for the Training Images.
calculate_SIFT(Images,Keypoints,Descriptor);
merge_descriptor(full_Descriptor,Descriptor);
//Compute PCA for all the features across all Images.
PCA pca;
perform_PCA(full_Descriptor, Pcafeature, pca);
//Perform K-Means on all the PCA reduced features.
Pcafeature.convertTo(Pcaduplicate, CV_32F);
calculate_Kmeans(Pcaduplicate, clusteridx);
//Calculate the Keywords in the Feature Space.
make_dictionary(clusteridx, Pcaduplicate, Keyword);
//Get the Histogram for each Training Image.
hist(Descriptor, clusteridx, histogram);
//Read Test Image
read_test(TestImages, name);
//Calculate the SIFT feature for all the test Images.
calculate_SIFT(TestImages, TestKeypoint, TestDescriptor);
//Project the SIFT feature of each feature on the lower dimensional PCA plane calculated above.
pca_testProject(TestDescriptor, TestPcafeature, pca);
//Find the Label by searching for keywords closest to current feature.
get_matches(TestPcafeature,Keyword,matches);
//Calculate Histogram for each test Image.
hist_test(TestDescriptor, matches, Testhistogram);
//Perform classification through Knn Classifier.
train_labels(trainlabels);
KNearest knn;
train_classifier(histogram, trainlabels, knn);
test_classify(Testhistogram,predicted,knn);
//Calculate Accuracy for each class.
calculate_accuracy(predicted);
getchar();
return 0;
}
void reverse_step (int start_grid[][24], int stop_grid[][24], int vote_case[]) {
int i, j, n, idx;
FLIP_STACK fs = {.size = 0};
for (i = 2; i < 22; ++i) {
for (j = 2; j < 22; ++j) {
idx = get_pattern_idx(stop_grid, i, j);
start_grid[i][j] = vote_case[idx]%2;
if (vote_case[idx] >= 2) push_flip(&fs, i, j);
}
}
FLIP_POINT ijp;
double score_start, score_flip;
for (n = fs.size; n > 0; --n) {
score_start = difference_forward(start_grid, stop_grid);
ijp = pop_flip(&fs);
flip_point(ijp.i, ijp.j, start_grid);
score_flip = difference_forward(start_grid, stop_grid);
if (score_start <= score_flip) flip_point(ijp.i, ijp.j, start_grid);
}
}
////////////////////////////////////////////////////////////////////////
unsigned int count_case_0[5][2097152], count_case_1[5][2097152]; // 2097152 = pow(2, 21)
int vote_case[5][2097152];
//double probability_case[5][2097152];
int main () {
// utility parameters
int n, i;
clean_array((int*)count_case_0, 2097152*5);
clean_array((int*)count_case_1, 2097152*5);
// read the train.csv data
FILE *train;
train = fopen ("train.csv", "r");
while (fgetc(train) != '\n') ; // skip the head line
int id, delta, initial_grid[24][24], start_grid[24][24], stop_grid[24][24];
clean_array((int*)initial_grid, 24*24);
clean_array((int*)start_grid, 24*24);
clean_array((int*)stop_grid, 24*24);
// read all the train set and make statistical table for them
for (n = 0; n < 50000; ++n) {
read_train(train, &id, &delta, (int*)start_grid);
for (i = 0; i < delta; ++i) {
conway_step(start_grid, stop_grid);
vote_step(start_grid, stop_grid, count_case_0[i], count_case_1[i]);
copy_grid(start_grid, stop_grid);
}
}
// vote for statistical table
for (i = 0; i < 5; ++i) {
for (n = 0; n < 2097152; ++n) {
vote_case[i][n] = vote_pattern(n, count_case_0[i][n], count_case_1[i][n], i);
//if (count_case_0[i][n]+count_case_1[i][n] == 0) probability_case[i][n] = 0;
//else probability_case[i][n] = (double)count_case_1[i][n] / (double)(count_case_0[i][n]+count_case_1[i][n]);
}
}
//------------------------------------------------------------------
// check prediction accuracy
/*
train = fopen ("train.csv", "r");
while (fgetc(train) != '\n') ; // skip the head line
FILE *pred;
pred = fopen ("pred.csv", "w");
fprintf(pred, "id,");
for (n = 1; n < 401; ++n) fprintf(pred, "start.%d,", n);
for (n = 1; n < 400; ++n) fprintf(pred, "diff.%d,", n);
fprintf(pred, "diff.400\n");
double difference_all = 0;
for (n = 0; n < 50000; ++n) {
read_train (train, &id, &delta, (int*)initial_grid);
copy_grid(start_grid, initial_grid);
for (i = 0; i < delta; ++i) {
conway_step(start_grid, stop_grid);
copy_grid(start_grid, stop_grid);
}
for (i = delta-1; i >= 0; --i) {
reverse_step (start_grid, stop_grid, vote_case[i]);
copy_grid(stop_grid, start_grid);
}
write_pred(pred, id, initial_grid, start_grid);
difference_all += difference_grids(initial_grid, start_grid);
}
printf("training set score: %f\n", difference_all/50000);
fclose(pred);
*/
fclose(train);
//------------------------------------------------------------------
// make submission file
///*
FILE *test;
test = fopen ("test.csv", "r");
while (fgetc(train) != '\n') ; // skip the head line
FILE *submission;
submission = fopen ("submission.csv", "w");
fprintf(submission, "id,");
for (n = 1; n < 400; ++n) fprintf(submission, "start.%d,", n);
fprintf(submission, "start.400\n");
for (n = 0; n < 50000; ++n) {
read_test(test, &id, &delta, stop_grid);
for (i = delta-1; i >= 0; --i) {
reverse_step (start_grid, stop_grid, vote_case[i]);
copy_grid(stop_grid, start_grid);
}
write_submission(submission, id, start_grid);
}
fclose(test);
fclose(submission);
//*/
return 0;
// training set score: 0.124948 (-0.00054)
// real score: 0.12685 (-0.00002)
// actual improvement is really tiny compare to the training set one.
}
int main () {
// utility parameters
int n, i;
clean_array((int*)count_case_0, 2097152*5);
clean_array((int*)count_case_1, 2097152*5);
// read the train.csv data
FILE *train;
train = fopen ("train.csv", "r");
while (fgetc(train) != '\n') ; // skip the head line
int id, delta, initial_grid[24][24], start_grid[24][24], stop_grid[24][24];
clean_array((int*)initial_grid, 24*24);
clean_array((int*)start_grid, 24*24);
clean_array((int*)stop_grid, 24*24);
// read all the train set and make statistical table for them
for (n = 0; n < 50000; ++n) {
read_train(train, &id, &delta, (int*)start_grid);
for (i = 0; i < delta; ++i) {
conway_step(start_grid, stop_grid);
vote_step(start_grid, stop_grid, count_case_0[i], count_case_1[i]);
copy_grid(start_grid, stop_grid);
}
}
// vote for statistical table
for (i = 0; i < 5; ++i) {
for (n = 0; n < 2097152; ++n)
vote_case[i][n] = vote_pattern(n, count_case_0[i][n], count_case_1[i][n], i);
}
//------------------------------------------------------------------
// check prediction accuracy
///*
train = fopen ("train.csv", "r");
while (fgetc(train) != '\n') ; // skip the head line
FILE *pred;
pred = fopen ("pred.csv", "w");
fprintf(pred, "id,");
for (n = 1; n < 401; ++n) fprintf(pred, "start.%d,", n);
for (n = 1; n < 400; ++n) fprintf(pred, "diff.%d,", n);
fprintf(pred, "diff.400\n");
double difference_all = 0;
for (n = 0; n < 50000; ++n) {
read_train (train, &id, &delta, (int*)initial_grid);
copy_grid(start_grid, initial_grid);
for (i = 0; i < delta; ++i) {
conway_step(start_grid, stop_grid);
copy_grid(start_grid, stop_grid);
}
for (i = delta-1; i >= 0; --i) {
reverse_step (start_grid, stop_grid, vote_case[i]);
copy_grid(stop_grid, start_grid);
}
write_pred(pred, id, initial_grid, start_grid);
difference_all += difference_grid(initial_grid, start_grid);
}
printf("training set score: %f\n", difference_all/50000);
fclose(pred);
//*/
fclose(train);
//------------------------------------------------------------------
// make submission file
///*
FILE *test;
test = fopen ("test.csv", "r");
while (fgetc(train) != '\n') ; // skip the head line
FILE *submission;
submission = fopen ("submission.csv", "w");
fprintf(submission, "id,");
for (n = 1; n < 400; ++n) fprintf(submission, "start.%d,", n);
fprintf(submission, "start.400\n");
for (n = 0; n < 50000; ++n) {
read_test(test, &id, &delta, stop_grid);
for (i = delta-1; i >= 0; --i) {
reverse_step (start_grid, stop_grid, vote_case[i]);
copy_grid(stop_grid, start_grid);
}
write_submission(submission, id, start_grid);
}
fclose(test);
fclose(submission);
//*/
return 0;
// training set score: 0.12549
// real score: 0.12687
// I also tried set up vote_case table cutoff based on different delta number.
// it may helps (the entire table parameter need a long time to be fixed),
// but a naive setup of the final step (5->6) to 0.5 makes everything goes worse.
}