Skip to content

etcart / RIVet

Go to a project
Commit 3179d5fd by etcart
Options

added comments and explanations

parent d78631fd
Expand all
Inline Side-by-side
Showing with 483 additions and 426 deletions
RIVLowerMorphic.h.gch
No preview for this file type
RIVcentroids.c
#include <stdio.h>
#include <stdlib.h>
#include <dirent.h>
#include <time.h>
#define RIVSIZE 5
#define CACHESIZE 0
#define THRESHOLD 0.70
#include "RIVtoolsCPUlinux.h"
void getcentroids(sparseRIV* centroids, sparseRIV* vectorSet, int centroidCount, int vectorCount);
void directoryToL2s(char *rootString, sparseRIV** fileRIVs, int *fileCount);
int main(int argc, char *argv[]){
clock_t begintotal = clock();
int fileCount = 0;
RIVInit();
sparseRIV *fileRIVs = (sparseRIV*) malloc(1*sizeof(sparseRIV));
char rootString[2000];
if(argc <2){
printf("give me a directory");
return 1;
}
strcpy(rootString, argv[1]);
strcat(rootString, "/");
directoryToL2s(rootString, &fileRIVs, &fileCount);
printf("fileCount: %d\n", fileCount);
getMagnitudes(fileRIVs, fileCount);
clock_t beginnsquared = clock();
sparseRIV centroids[5];
strcpy(centroids[0].name, "boobs");
strcpy(centroids[1].name, "ass");
strcpy(centroids[2].name, "shit");
strcpy(centroids[3].name, "cocks");
strcpy(centroids[4].name, "fuck");
for(int i=0; i<5; i++){
centroids[i] = wordtoL2(centroids[i].name);
}
getMagnitudes(centroids, 5);
getcentroids(centroids, fileRIVs, 5, fileCount);
clock_t endnsquared = clock();
double time = (double)(endnsquared - beginnsquared) / CLOCKS_PER_SEC;
printf("nsquared time:%lf\n\n", time);
printf("%d <", RIVKey.thing);
clock_t endtotal = clock();
double time_spent = (double)(endtotal - begintotal) / CLOCKS_PER_SEC;
printf("total time:%lf\n\n", time_spent);
free(fileRIVs);
return 0;
}
void directoryToL2s(char *rootString, sparseRIV** fileRIVs, int *fileCount){
char pathString[2000];
DIR *directory;
struct dirent *files = 0;
if(!(directory = opendir(rootString))){
printf("location not found, %s\n", rootString);
return;
}
while((files=readdir(directory))){
if(*(files->d_name) == '.') continue;
if(files->d_type == DT_DIR){
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
strcat(pathString, "/");
directoryToL2s(pathString, fileRIVs, fileCount);
}
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
FILE *input = fopen(pathString, "r");
if(!input){
printf("file %s doesn't seem to exist, breaking out of loop", pathString);
return;
}else{
(*fileRIVs) = (sparseRIV*)realloc((*fileRIVs), ((*fileCount)+1)*sizeof(sparseRIV));
(*fileRIVs)[(*fileCount)] = fileToL2Clean(input);
strcpy((*fileRIVs)[(*fileCount)].name, pathString);
fclose(input);
(*fileCount)++;
}
}
}
void getcentroids(sparseRIV* centroids, sparseRIV* vectorSet, int centroidCount, int vectorCount){
float** cosines = malloc(centroidCount*sizeof(int*));
for(int i=0; i<centroidCount; i++){
cosines[i] = cosineCompare(centroids[i], vectorSet, vectorCount);
}
int* centroidIndexes[centroidCount];
int indexCounts[centroidCount];
int* denses[centroidCount];
*centroidIndexes = calloc(vectorCount*centroidCount, sizeof(int));
*denses = malloc(RIVKey.RIVsize*centroidCount * sizeof(int));
for(int i=1; i<centroidCount; i++){
centroidIndexes[i] = centroidIndexes[0]+i*vectorCount;
denses[i] = denses[0] +i*RIVKey.RIVsize;
}
float token = 2.0;
int counter = 0;
for(int i=0; i<vectorCount; i++){
token = 2.0;
printf("\nfor vector %d:\n", i);
for(int j = 0; j<centroidCount; j++){
printf("centroid %d: %f", j, cosines[j][i]);
if(fabsf(cosines[j][i])< token){
token = fabsf(cosines[j][i]);
counter = j;
}
}
centroidIndexes[counter][indexCounts[counter]] = i;
indexCounts[counter] += 1;
}
for(int i=0; i<centroidCount; i++){
memset(denses[i], 0, RIVKey.RIVsize);
printf("\n\nnumber %d\n", i);
for(int j=0; j<indexCounts[i]; i++){
addS2D(denses[i], vectorSet[j]);
for(int k=0; k<RIVKey.RIVsize; k++){
printf("%d, ", denses[i][k]);
}
}
}
}
#include <stdio.h>
#include <stdlib.h>
#include <dirent.h>
#include <time.h>
#define RIVSIZE 5
#define CACHESIZE 0
#define THRESHOLD 0.70
#include "RIVtoolsCPUlinux.h"
void getcentroids(sparseRIV* centroids, sparseRIV* vectorSet, int centroidCount, int vectorCount);
void directoryToL2s(char *rootString, sparseRIV** fileRIVs, int *fileCount);
int main(int argc, char *argv[]){
clock_t begintotal = clock();
int fileCount = 0;
RIVInit();
sparseRIV *fileRIVs = (sparseRIV*) malloc(1*sizeof(sparseRIV));
char rootString[2000];
if(argc <2){
printf("give me a directory");
return 1;
}
strcpy(rootString, argv[1]);
strcat(rootString, "/");
directoryToL2s(rootString, &fileRIVs, &fileCount);
printf("fileCount: %d\n", fileCount);
getMagnitudes(fileRIVs, fileCount);
clock_t beginnsquared = clock();
sparseRIV centroids[5];
strcpy(centroids[0].name, "boobs");
strcpy(centroids[1].name, "ass");
strcpy(centroids[2].name, "shit");
strcpy(centroids[3].name, "cocks");
strcpy(centroids[4].name, "fuck");
for(int i=0; i<5; i++){
centroids[i] = wordtoL2(centroids[i].name);
}
getMagnitudes(centroids, 5);
getcentroids(centroids, fileRIVs, 5, fileCount);
clock_t endnsquared = clock();
double time = (double)(endnsquared - beginnsquared) / CLOCKS_PER_SEC;
printf("nsquared time:%lf\n\n", time);
printf("%d <", RIVKey.thing);
clock_t endtotal = clock();
double time_spent = (double)(endtotal - begintotal) / CLOCKS_PER_SEC;
printf("total time:%lf\n\n", time_spent);
free(fileRIVs);
return 0;
}
void directoryToL2s(char *rootString, sparseRIV** fileRIVs, int *fileCount){
char pathString[2000];
DIR *directory;
struct dirent *files = 0;
if(!(directory = opendir(rootString))){
printf("location not found, %s\n", rootString);
return;
}
while((files=readdir(directory))){
if(*(files->d_name) == '.') continue;
if(files->d_type == DT_DIR){
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
strcat(pathString, "/");
directoryToL2s(pathString, fileRIVs, fileCount);
}
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
FILE *input = fopen(pathString, "r");
if(!input){
printf("file %s doesn't seem to exist, breaking out of loop", pathString);
return;
}else{
(*fileRIVs) = (sparseRIV*)realloc((*fileRIVs), ((*fileCount)+1)*sizeof(sparseRIV));
(*fileRIVs)[(*fileCount)] = fileToL2Clean(input);
strcpy((*fileRIVs)[(*fileCount)].name, pathString);
fclose(input);
(*fileCount)++;
}
}
}
void getcentroids(sparseRIV* centroids, sparseRIV* vectorSet, int centroidCount, int vectorCount){
float** cosines = malloc(centroidCount*sizeof(int*));
for(int i=0; i<centroidCount; i++){
cosines[i] = cosineCompare(centroids[i], vectorSet, vectorCount);
}
int* centroidIndexes[centroidCount];
int indexCounts[centroidCount];
int* denses[centroidCount];
*centroidIndexes = calloc(vectorCount*centroidCount, sizeof(int));
*denses = malloc(RIVKey.RIVsize*centroidCount * sizeof(int));
for(int i=1; i<centroidCount; i++){
centroidIndexes[i] = centroidIndexes[0]+i*vectorCount;
denses[i] = denses[0] +i*RIVKey.RIVsize;
}
float token = 2.0;
int counter = 0;
for(int i=0; i<vectorCount; i++){
token = 2.0;
printf("\nfor vector %d:\n", i);
for(int j = 0; j<centroidCount; j++){
printf("centroid %d: %f", j, cosines[j][i]);
if(fabsf(cosines[j][i])< token){
token = fabsf(cosines[j][i]);
counter = j;
}
}
centroidIndexes[counter][indexCounts[counter]] = i;
indexCounts[counter] += 1;
}
for(int i=0; i<centroidCount; i++){
memset(denses[i], 0, RIVKey.RIVsize);
printf("\n\nnumber %d\n", i);
for(int j=0; j<indexCounts[i]; i++){
addS2D(denses[i], vectorSet[j]);
for(int k=0; k<RIVKey.RIVsize; k++){
printf("%d, ", denses[i][k]);
}
}
}
}
RIVcull
No preview for this file type
RIVcullCPUlinux.c
#include <stdio.h>
#include <stdlib.h>
#include <dirent.h>
#include <time.h>
#define RIVSIZE 5000
#define CACHESIZE 0
#define NONZEROS 2
#define THRESHOLD 0.7
#define COSINEACTION do {\
if(cosine > THRESHOLD){ \
printf("%s\t%s\n%f\n", baseRIV.name, (*multipliers).name, cosine);\
(*multipliers).boolean = 0; \
RIVKey.thing++; \
}\
}while(0)
#include "RIVtoolsMorphic.h"
void directoryToL2s(char *rootString, sparseRIV** fileRIVs, int *fileCount);
int main(int argc, char *argv[]){
clock_t begintotal = clock();
int fileCount = 0;
RIVInit();
sparseRIV *fileRIVs = (sparseRIV*) malloc(1*sizeof(sparseRIV));
char rootString[2000];
if(argc <2){
printf("give me a directory");
return 1;
}
strcpy(rootString, argv[1]);
strcat(rootString, "/");
directoryToL2s(rootString, &fileRIVs, &fileCount);
printf("fileCount: %d\n", fileCount);
sparseRIV* fileRIVs_slider = fileRIVs;
sparseRIV* fileRIVs_stop = fileRIVs+fileCount;
while(fileRIVs_slider <fileRIVs_stop){
(*fileRIVs_slider).magnitude = getMagnitudeSparse(*fileRIVs_slider);
fileRIVs_slider++;
}
clock_t beginnsquared = clock();
float cosine;
float minmag;
float maxmag;
denseRIV baseDense;
baseDense.values = malloc(RIVSIZE*sizeof(int));
fileRIVs_slider = fileRIVs;
sparseRIV* comparators_slider;
while(fileRIVs_slider<fileRIVs_stop){
comparators_slider = fileRIVs;
memset(baseDense.values, 0, RIVSIZE*sizeof(int));
baseDense.values = addS2D(baseDense.values, *fileRIVs_slider);
baseDense.magnitude = (*fileRIVs_slider).magnitude;
minmag = baseDense.magnitude*.85;
maxmag = baseDense.magnitude*1.15;
while(comparators_slider < fileRIVs_slider){
if((*comparators_slider).magnitude < maxmag && (*comparators_slider).magnitude > minmag && (*comparators_slider).boolean){
cosine = cosCompare(baseDense, *comparators_slider);
if(cosine>THRESHOLD){
printf("%s\t%s\n%f\n", (*fileRIVs_slider).name , (*comparators_slider).name, cosine);
(*comparators_slider).boolean = 0;
RIVKey.thing++;
}
}
comparators_slider++;
//cosineCompare(fileRIVs[i], fileRIVs, i);
}
fileRIVs_slider++;
}
clock_t endnsquared = clock();
double time = (double)(endnsquared - beginnsquared) / CLOCKS_PER_SEC;
printf("nsquared time:%lf\n\n", time);
printf("%d <", RIVKey.thing);
clock_t endtotal = clock();
double time_spent = (double)(endtotal - begintotal) / CLOCKS_PER_SEC;
printf("total time:%lf\n\n", time_spent);
free(fileRIVs);
return 0;
}
void directoryToL2s(char *rootString, sparseRIV** fileRIVs, int *fileCount){
char pathString[2000];
DIR *directory;
struct dirent *files = 0;
if(!(directory = opendir(rootString))){
printf("location not found, %s\n", rootString);
return;
}
while((files=readdir(directory))){
if(*(files->d_name) == '.') continue;
if(files->d_type == DT_DIR){
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
strcat(pathString, "/");
directoryToL2s(pathString, fileRIVs, fileCount);
}
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
FILE *input = fopen(pathString, "r");
if(!input){
printf("file %s doesn't seem to exist, breaking out of loop", pathString);
return;
}else{
(*fileRIVs) = (sparseRIV*)realloc((*fileRIVs), ((*fileCount)+1)*sizeof(sparseRIV));
(*fileRIVs)[(*fileCount)] = fileToL2(input);
strcpy((*fileRIVs)[(*fileCount)].name, pathString);
fclose(input);
(*fileCount)++;
}
}
}
#include <stdio.h>
#include <stdlib.h>
#include <dirent.h>
#include <time.h>
#define RIVSIZE 5000
#define CACHESIZE 0
#define NONZEROS 2
#define THRESHOLD 0.7
#define COSINEACTION do {\
if(cosine > THRESHOLD){ \
printf("%s\t%s\n%f\n", baseRIV.name, (*multipliers).name, cosine);\
(*multipliers).boolean = 0; \
RIVKey.thing++; \
}\
}while(0)
#include "RIVtoolsMorphic.h"
void directoryToL2s(char *rootString, sparseRIV** fileRIVs, int *fileCount);
int main(int argc, char *argv[]){
clock_t begintotal = clock();
int fileCount = 0;
RIVInit();
sparseRIV *fileRIVs = (sparseRIV*) malloc(1*sizeof(sparseRIV));
char rootString[2000];
if(argc <2){
printf("give me a directory");
return 1;
}
strcpy(rootString, argv[1]);
strcat(rootString, "/");
directoryToL2s(rootString, &fileRIVs, &fileCount);
printf("fileCount: %d\n", fileCount);
sparseRIV* fileRIVs_slider = fileRIVs;
sparseRIV* fileRIVs_stop = fileRIVs+fileCount;
while(fileRIVs_slider <fileRIVs_stop){
(*fileRIVs_slider).magnitude = getMagnitudeSparse(*fileRIVs_slider);
fileRIVs_slider++;
}
clock_t beginnsquared = clock();
float cosine;
float minmag;
float maxmag;
denseRIV baseDense;
baseDense.values = malloc(RIVSIZE*sizeof(int));
fileRIVs_slider = fileRIVs;
sparseRIV* comparators_slider;
while(fileRIVs_slider<fileRIVs_stop){
comparators_slider = fileRIVs;
memset(baseDense.values, 0, RIVSIZE*sizeof(int));
baseDense.values = addS2D(baseDense.values, *fileRIVs_slider);
baseDense.magnitude = (*fileRIVs_slider).magnitude;
minmag = baseDense.magnitude*.85;
maxmag = baseDense.magnitude*1.15;
while(comparators_slider < fileRIVs_slider){
if((*comparators_slider).magnitude < maxmag && (*comparators_slider).magnitude > minmag && (*comparators_slider).boolean){
cosine = cosCompare(baseDense, *comparators_slider);
if(cosine>THRESHOLD){
printf("%s\t%s\n%f\n", (*fileRIVs_slider).name , (*comparators_slider).name, cosine);
(*comparators_slider).boolean = 0;
RIVKey.thing++;
}
}
comparators_slider++;
//cosineCompare(fileRIVs[i], fileRIVs, i);
}
fileRIVs_slider++;
}
clock_t endnsquared = clock();
double time = (double)(endnsquared - beginnsquared) / CLOCKS_PER_SEC;
printf("nsquared time:%lf\n\n", time);
printf("%d <", RIVKey.thing);
clock_t endtotal = clock();
double time_spent = (double)(endtotal - begintotal) / CLOCKS_PER_SEC;
printf("total time:%lf\n\n", time_spent);
free(fileRIVs);
return 0;
}
void directoryToL2s(char *rootString, sparseRIV** fileRIVs, int *fileCount){
char pathString[2000];
DIR *directory;
struct dirent *files = 0;
if(!(directory = opendir(rootString))){
printf("location not found, %s\n", rootString);
return;
}
while((files=readdir(directory))){
if(*(files->d_name) == '.') continue;
if(files->d_type == DT_DIR){
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
strcat(pathString, "/");
directoryToL2s(pathString, fileRIVs, fileCount);
}
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
FILE *input = fopen(pathString, "r");
if(!input){
printf("file %s doesn't seem to exist, breaking out of loop", pathString);
return;
}else{
(*fileRIVs) = (sparseRIV*)realloc((*fileRIVs), ((*fileCount)+1)*sizeof(sparseRIV));
(*fileRIVs)[(*fileCount)] = fileToL2(input);
strcpy((*fileRIVs)[(*fileCount)].name, pathString);
fclose(input);
(*fileCount)++;
}
}
}
RIVread
No preview for this file type
RIVread.c
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#define CACHESIZE 100000
#include "RIVtoolsCPUlinux.h"
#include <sys/stat.h>
#include <sys/types.h>
#include <unistd.h>
#include <dirent.h>
#include <error.h>
void fileGrind(FILE* textFile);
void addS2Ds(denseRIV *denseSet, sparseRIV additive, int RIVCount);
int checkDupe(denseRIV* RIVSet, char* word, int wordCount);
void directoryGrind(char *rootString);
int main(int argc, char *argv[]){
clock_t begintotal = clock();
RIVInit();
char pathString[1000];
strcpy(pathString, argv[1]);
strcat(pathString, "/");
directoryGrind(pathString);
clock_t endtotal = clock();
double time_spent = (double)(endtotal - begintotal) / CLOCKS_PER_SEC;
printf("total time:%lf\n\n", time_spent);
RIVCleanup();
return 0;
}
void addS2Ds(denseRIV *denseSet, sparseRIV additive, int RIVCount){
denseRIV *denseSet_slider;
denseRIV *dense_stop = denseSet+RIVCount;
int *locations = additive.locations;
int *locations_stop = locations+additive.count;
int *values = additive.values;
//int *target;
while(locations<locations_stop){
denseSet_slider = denseSet;
while(denseSet_slider<dense_stop){
(*denseSet_slider).values[*locations]+= *values;
//*target+=*values;
denseSet_slider++;
}
locations++;
values++;
}
}
int checkDupe(denseRIV* RIVSet, char* word, int wordCount){
denseRIV* RIVStop = RIVSet+wordCount;
while(RIVSet<RIVStop){
if(!strcmp(word, RIVSet->name)){
return 1;
}
RIVSet++;
}
return 0;
}
void directoryGrind(char *rootString){
char pathString[2000];
DIR *directory;
struct dirent *files = 0;
if(!(directory = opendir(rootString))){
printf("location not found, %s\n", rootString);
return;
}
while((files=readdir(directory))){
while(!strcmp(files->d_name, ".") || !strcmp(files->d_name, "..")){
files = readdir(directory);
}
if(files->d_type == DT_DIR){
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
strcat(pathString, "/");
directoryGrind(pathString);
}
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
printf("%s\n", pathString);
FILE *input = fopen(pathString, "r+");
if(input){
fileGrind(input);
fclose(input);
}
}
}
void fileGrind(FILE* textFile){
sparseRIV aggregateRIV = fileToL2Clean(textFile);
fseek(textFile, 0, SEEK_SET);
int wordCount = 0;
denseRIV *RIVArray = (denseRIV*)malloc(aggregateRIV.frequency*sizeof(denseRIV));
char word[200];
while(fscanf(textFile, "%99s", word)){
if(feof(textFile)) break;
if(!(*word))continue;
if(!isWordClean((char*)word)){
continue;
}
if(checkDupe(RIVArray, word, wordCount)){
continue;
}
RIVArray[wordCount] = lexPull(word);
if(!*((RIVArray[wordCount].name))) break;
int* thing = RIVArray[wordCount].frequency;
*thing = *thing + 1;
//printf("%s, %d, %d\n", RIVArray[wordCount].name, *(RIVArray[wordCount].frequency), *thing);
wordCount++;
}
//printf("%d\n", wordCount);
addS2Ds(RIVArray, aggregateRIV, wordCount);
denseRIV* RIVArray_slider = RIVArray;
denseRIV* RIVArray_stop = RIVArray+wordCount;
while(RIVArray_slider<RIVArray_stop){
lexPush(*RIVArray_slider);
RIVArray_slider++;
}
free(RIVArray);
free(aggregateRIV.locations);
//free(aggregateRIV.values);
}
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#define CACHESIZE 100000
#include "RIVtoolsCPUlinux.h"
#include <sys/stat.h>
#include <sys/types.h>
#include <unistd.h>
#include <dirent.h>
#include <error.h>
void fileGrind(FILE* textFile);
void addS2Ds(denseRIV *denseSet, sparseRIV additive, int RIVCount);
int checkDupe(denseRIV* RIVSet, char* word, int wordCount);
void directoryGrind(char *rootString);
int main(int argc, char *argv[]){
clock_t begintotal = clock();
RIVInit();
char pathString[1000];
strcpy(pathString, argv[1]);
strcat(pathString, "/");
directoryGrind(pathString);
clock_t endtotal = clock();
double time_spent = (double)(endtotal - begintotal) / CLOCKS_PER_SEC;
printf("total time:%lf\n\n", time_spent);
RIVCleanup();
return 0;
}
void addS2Ds(denseRIV *denseSet, sparseRIV additive, int RIVCount){
denseRIV *denseSet_slider;
denseRIV *dense_stop = denseSet+RIVCount;
int *locations = additive.locations;
int *locations_stop = locations+additive.count;
int *values = additive.values;
//int *target;
while(locations<locations_stop){
denseSet_slider = denseSet;
while(denseSet_slider<dense_stop){
(*denseSet_slider).values[*locations]+= *values;
//*target+=*values;
denseSet_slider++;
}
locations++;
values++;
}
}
int checkDupe(denseRIV* RIVSet, char* word, int wordCount){
denseRIV* RIVStop = RIVSet+wordCount;
while(RIVSet<RIVStop){
if(!strcmp(word, RIVSet->name)){
return 1;
}
RIVSet++;
}
return 0;
}
void directoryGrind(char *rootString){
char pathString[2000];
DIR *directory;
struct dirent *files = 0;
if(!(directory = opendir(rootString))){
printf("location not found, %s\n", rootString);
return;
}
while((files=readdir(directory))){
while(!strcmp(files->d_name, ".") || !strcmp(files->d_name, "..")){
files = readdir(directory);
}
if(files->d_type == DT_DIR){
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
strcat(pathString, "/");
directoryGrind(pathString);
}
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
printf("%s\n", pathString);
FILE *input = fopen(pathString, "r+");
if(input){
fileGrind(input);
fclose(input);
}
}
}
void fileGrind(FILE* textFile){
sparseRIV aggregateRIV = fileToL2Clean(textFile);
fseek(textFile, 0, SEEK_SET);
int wordCount = 0;
denseRIV *RIVArray = (denseRIV*)malloc(aggregateRIV.frequency*sizeof(denseRIV));
char word[200];
while(fscanf(textFile, "%99s", word)){
if(feof(textFile)) break;
if(!(*word))continue;
if(!isWordClean((char*)word)){
continue;
}
if(checkDupe(RIVArray, word, wordCount)){
continue;
}
RIVArray[wordCount] = lexPull(word);
if(!*((RIVArray[wordCount].name))) break;
int* thing = RIVArray[wordCount].frequency;
*thing = *thing + 1;
//printf("%s, %d, %d\n", RIVArray[wordCount].name, *(RIVArray[wordCount].frequency), *thing);
wordCount++;
}
//printf("%d\n", wordCount);
addS2Ds(RIVArray, aggregateRIV, wordCount);
denseRIV* RIVArray_slider = RIVArray;
denseRIV* RIVArray_stop = RIVArray+wordCount;
while(RIVArray_slider<RIVArray_stop){
lexPush(*RIVArray_slider);
RIVArray_slider++;
}
free(RIVArray);
free(aggregateRIV.locations);
//free(aggregateRIV.values);
}
saturation 0 → 100644
File added
saturation.c 0 → 100644
#include <stdio.h>
#include <stdlib.h>
#include <dirent.h>
#include <time.h>
#include "RIVtoolsCPUlinux.h"
void directoryToL2s(char *rootString);
int main(){
RIVInit();
char rootString[] = "lexicon/";
directoryToL2s(rootString);
}
void directoryToL2s(char *rootString){
sparseRIV fileRIV;
char pathString[2000];
DIR *directory;
struct dirent *files = 0;
if(!(directory = opendir(rootString))){
printf("location not found, %s\n", rootString);
return;
}
while((files=readdir(directory))){
if(*(files->d_name) == '.') continue;
if(files->d_type == DT_DIR){
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
strcat(pathString, "/");
directoryToL2s(pathString);
}
strcpy(pathString, rootString);
strcat(pathString, files->d_name);
FILE *input = fopen(pathString, "r");
if(!input){
printf("file %s doesn't seem to exist, breaking out of loop", pathString);
return;
}else{
denseRIV temp = lexPull(pathString);
fileRIV = consolidateD2S(temp.values);
strcpy(fileRIV.name, pathString);
float count = fileRIV.count;
printf("%s, saturation: %f\n", fileRIV.name, count);
fclose(input);
free(temp.values);
//free(fileRIV.locations);
}
}
}
saturation.o 0 → 100644
File added
testfolder/numba2.txt
meet_verb discuss_verb non-grid_adjective am_noun process_verb attendee_noun julia_noun lynn_noun steve_noun sheila_noun
calendar_noun entry_noun appointment_noun
description_noun meet_verb discuss_verb non-grid_adjective am_noun process_verb attendee_noun julia_noun lynn_noun steve_noun sheila_noun jerry_noun conference_noun room_noun
date_noun time_noun pm_noun pm_noun central_noun standard_noun time_noun
detailed_adjective description_noun united_noun states_noun license_noun
meet_verb discuss_verb non-grid_adjective am_noun process_verb attendee_noun julia_noun lynn_noun steve_noun sheila_noun
calendar_noun entry_noun appointment_noun
description_noun meet_verb discuss_verb non-grid_adjective am_noun process_verb attendee_noun julia_noun lynn_noun steve_noun sheila_noun jerry_noun conference_noun room_noun
date_noun time_noun pm_noun pm_noun central_noun standard_noun time_noun
detailed_adjective description_noun united_noun states_noun license_noun
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or sign in to comment