void LearnVocabFromTrainFile() {
char word[MAX_STRING];
FILE *fin;
long long a, i;
for (a = 0; a < vocab_hash_size; a++) vocab_hash[a] = -1;
fin = fopen(train_file, "rb");
if (fin == NULL) {
printf("ERROR: training data file not found!\n");
exit(1);
}
vocab_size = 0;
AddWordToVocab((char *)"</s>");
while (1) {
ReadWord(word, fin);
if (feof(fin)) break;
train_words++;
if ((debug_mode > 1) && (train_words % 100000 == 0)) {
fprintf(stderr, "%lldK%c", train_words / 1000, 13);
}
i = SearchVocab(word);
if (i == -1) {
a = AddWordToVocab(word);
vocab[a].cn = 1;
} else vocab[i].cn++;
if (vocab_size > vocab_hash_size * 0.7) ReduceVocab();
}
SortVocab();
if (debug_mode > 0) {
fprintf(stderr, "Vocab size: %lld\n", vocab_size);
fprintf(stderr, "Words in train file: %lld\n", train_words);
}
file_size = ftell(fin);
fclose(fin);
}
void LearnVocabFromTrainFile() {
char word[MAX_STRING], last_word[MAX_STRING], bigram_word[MAX_STRING * 2];
FILE *fin;
long long a, i, start = 1;
for (a = 0; a < vocab_hash_size; a++) vocab_hash[a] = -1;
fin = fopen(train_file, "rb");
if (fin == NULL) {
printf("ERROR: training data file not found!\n");
exit(1);
}
vocab_size = 0;
AddWordToVocab((char *)"</s>");
while (1) {
ReadWord(word, fin);
if (feof(fin)) break;
if (!strcmp(word, "</s>")) {
start = 1;
continue;
} else start = 0;
train_words++;
if ((debug_mode > 1) && (train_words % 100000 == 0)) {
printf("Words processed: %lldK Vocab size: %lldK %c", train_words / 1000, vocab_size / 1000, 13);
fflush(stdout);
}
i = SearchVocab(word);
if (i == -1) {
a = AddWordToVocab(word);
vocab[a].cn = 1;
} else vocab[i].cn++;
if (start) continue;
sprintf(bigram_word, "%s_%s", last_word, word);
bigram_word[MAX_STRING - 1] = 0;
strcpy(last_word, word);
i = SearchVocab(bigram_word);
if (i == -1) {
a = AddWordToVocab(bigram_word);
vocab[a].cn = 1;
} else vocab[i].cn++;
if (vocab_size > vocab_hash_size * 0.7) ReduceVocab();
}
SortVocab();
if (debug_mode > 0) {
printf("\nVocab size (unigrams + bigrams): %lld\n", vocab_size);
printf("Words in train file: %lld\n", train_words);
}
fclose(fin);
}
void LearnVocabFromTrainFile() {
char word[MAX_STRING];
FILE *fin;
long long a, i;
for (a = 0; a < vocab_hash_size; a++) vocab_hash[a] = -1;
fin = fopen(train_file, "rb");
if (fin == NULL) {
printf("ERROR: training data file not found!\n");
exit(1);
}
vocab_size = 0;
AddWordToVocab((char *)"</s>");
while (1) {
ReadWord(word, fin);
if(strlen(word)>1)if(word[0]=='_'&&word[1]=='*')continue;
if (feof(fin)) break;
train_words++;
if ((debug_mode > 1) && (train_words % 100000 == 0)) {
printf("%lldK%c", train_words / 1000, 13);
fflush(stdout);
}
i = SearchVocab(word);
if (i == -1) {
a = AddWordToVocab(word);
vocab[a].cn = 1;
} else vocab[i].cn++;
if (vocab_size > vocab_hash_size * 0.7) ReduceVocab();
}
SortVocab();
if (debug_mode > 0) {
printf("Vocab size: %lld\n", vocab_size);
printf("Words in train file: %lld\n", train_words);
}
long long freq_count=0;
//for(a=0;a<vocab_size;a++){
// if(vocab[a].cn > 50000){freq_count+=vocab[a].cn;printf("%s\n",vocab[a].word);}
//}
//printf("freq_count: %lld\n", freq_count);
file_size = ftell(fin);
fclose(fin);
}
void EnsureVocabSize(struct vocabulary *vocab) {
if (vocab->vocab_size > vocab_hash_size * 0.7) ReduceVocab(vocab);
}