fann_train_data.c

python 神经网络 数据挖掘 python实现的神经网络算法

	factor = new_span / old_span;

	for(dat = 0; dat < num_data; dat++)
	{
		for(elem = 0; elem < num_elem; elem++)
		{
			temp = (data[dat][elem] - old_min) * factor + new_min;
			if(temp < new_min)
			{
				data[dat][elem] = new_min;
				/*
				 * printf("error %f < %f\n", temp, new_min); 
				 */
			}
			else if(temp > new_max)
			{
				data[dat][elem] = new_max;
				/*
				 * printf("error %f > %f\n", temp, new_max); 
				 */
			}
			else
			{
				data[dat][elem] = temp;
			}
		}
	}
}

/*
 * Scales the inputs in the training data to the specified range 
 */
FANN_EXTERNAL void FANN_API fann_scale_input_train_data(struct fann_train_data *train_data,
														fann_type new_min, fann_type new_max)
{
	fann_scale_data(train_data->input, train_data->num_data, train_data->num_input, new_min,
					new_max);
}

/*
 * Scales the inputs in the training data to the specified range 
 */
FANN_EXTERNAL void FANN_API fann_scale_output_train_data(struct fann_train_data *train_data,
														 fann_type new_min, fann_type new_max)
{
	fann_scale_data(train_data->output, train_data->num_data, train_data->num_output, new_min,
					new_max);
}

/*
 * Scales the inputs in the training data to the specified range 
 */
FANN_EXTERNAL void FANN_API fann_scale_train_data(struct fann_train_data *train_data,
												  fann_type new_min, fann_type new_max)
{
	fann_scale_data(train_data->input, train_data->num_data, train_data->num_input, new_min,
					new_max);
	fann_scale_data(train_data->output, train_data->num_data, train_data->num_output, new_min,
					new_max);
}

/*
 * merges training data into a single struct. 
 */
FANN_EXTERNAL struct fann_train_data *FANN_API fann_merge_train_data(struct fann_train_data *data1,
																	 struct fann_train_data *data2)
{
	unsigned int i;
	fann_type *data_input, *data_output;
	struct fann_train_data *dest =
		(struct fann_train_data *) malloc(sizeof(struct fann_train_data));

	if(dest == NULL)
	{
		fann_error((struct fann_error*)data1, FANN_E_CANT_ALLOCATE_MEM);
		return NULL;
	}

	if((data1->num_input != data2->num_input) || (data1->num_output != data2->num_output))
	{
		fann_error((struct fann_error*)data1, FANN_E_TRAIN_DATA_MISMATCH);
		return NULL;
	}

	fann_init_error_data((struct fann_error *) dest);
	dest->error_log = data1->error_log;

	dest->num_data = data1->num_data+data2->num_data;
	dest->num_input = data1->num_input;
	dest->num_output = data1->num_output;
	dest->input = (fann_type **) calloc(dest->num_data, sizeof(fann_type *));
	if(dest->input == NULL)
	{
		fann_error((struct fann_error*)data1, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}

	dest->output = (fann_type **) calloc(dest->num_data, sizeof(fann_type *));
	if(dest->output == NULL)
	{
		fann_error((struct fann_error*)data1, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}

	data_input = (fann_type *) calloc(dest->num_input * dest->num_data, sizeof(fann_type));
	if(data_input == NULL)
	{
		fann_error((struct fann_error*)data1, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}
	memcpy(data_input, data1->input[0], dest->num_input * data1->num_data * sizeof(fann_type));
	memcpy(data_input + (dest->num_input*data1->num_data), 
		data2->input[0], dest->num_input * data2->num_data * sizeof(fann_type));

	data_output = (fann_type *) calloc(dest->num_output * dest->num_data, sizeof(fann_type));
	if(data_output == NULL)
	{
		fann_error((struct fann_error*)data1, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}
	memcpy(data_output, data1->output[0], dest->num_output * data1->num_data * sizeof(fann_type));
	memcpy(data_output + (dest->num_output*data1->num_data), 
		data2->output[0], dest->num_output * data2->num_data * sizeof(fann_type));

	for(i = 0; i != dest->num_data; i++)
	{
		dest->input[i] = data_input;
		data_input += dest->num_input;
		dest->output[i] = data_output;
		data_output += dest->num_output;
	}
	return dest;
}

/*
 * return a copy of a fann_train_data struct 
 */
FANN_EXTERNAL struct fann_train_data *FANN_API fann_duplicate_train_data(struct fann_train_data
																		 *data)
{
	unsigned int i;
	fann_type *data_input, *data_output;
	struct fann_train_data *dest =
		(struct fann_train_data *) malloc(sizeof(struct fann_train_data));

	if(dest == NULL)
	{
		fann_error((struct fann_error*)data, FANN_E_CANT_ALLOCATE_MEM);
		return NULL;
	}

	fann_init_error_data((struct fann_error *) dest);
	dest->error_log = data->error_log;

	dest->num_data = data->num_data;
	dest->num_input = data->num_input;
	dest->num_output = data->num_output;
	dest->input = (fann_type **) calloc(dest->num_data, sizeof(fann_type *));
	if(dest->input == NULL)
	{
		fann_error((struct fann_error*)data, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}

	dest->output = (fann_type **) calloc(dest->num_data, sizeof(fann_type *));
	if(dest->output == NULL)
	{
		fann_error((struct fann_error*)data, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}

	data_input = (fann_type *) calloc(dest->num_input * dest->num_data, sizeof(fann_type));
	if(data_input == NULL)
	{
		fann_error((struct fann_error*)data, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}
	memcpy(data_input, data->input[0], dest->num_input * dest->num_data * sizeof(fann_type));

	data_output = (fann_type *) calloc(dest->num_output * dest->num_data, sizeof(fann_type));
	if(data_output == NULL)
	{
		fann_error((struct fann_error*)data, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}
	memcpy(data_output, data->output[0], dest->num_output * dest->num_data * sizeof(fann_type));

	for(i = 0; i != dest->num_data; i++)
	{
		dest->input[i] = data_input;
		data_input += dest->num_input;
		dest->output[i] = data_output;
		data_output += dest->num_output;
	}
	return dest;
}

FANN_EXTERNAL struct fann_train_data *FANN_API fann_subset_train_data(struct fann_train_data
																		 *data, unsigned int pos,
																		 unsigned int length)
{
	unsigned int i;
	fann_type *data_input, *data_output;
	struct fann_train_data *dest =
		(struct fann_train_data *) malloc(sizeof(struct fann_train_data));

	if(dest == NULL)
	{
		fann_error((struct fann_error*)data, FANN_E_CANT_ALLOCATE_MEM);
		return NULL;
	}
	
	if(pos > data->num_data || pos+length > data->num_data)
	{
		fann_error((struct fann_error*)data, FANN_E_TRAIN_DATA_SUBSET, pos, length, data->num_data);
		return NULL;
	}

	fann_init_error_data((struct fann_error *) dest);
	dest->error_log = data->error_log;

	dest->num_data = length;
	dest->num_input = data->num_input;
	dest->num_output = data->num_output;
	dest->input = (fann_type **) calloc(dest->num_data, sizeof(fann_type *));
	if(dest->input == NULL)
	{
		fann_error((struct fann_error*)data, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}

	dest->output = (fann_type **) calloc(dest->num_data, sizeof(fann_type *));
	if(dest->output == NULL)
	{
		fann_error((struct fann_error*)data, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}

	data_input = (fann_type *) calloc(dest->num_input * dest->num_data, sizeof(fann_type));
	if(data_input == NULL)
	{
		fann_error((struct fann_error*)data, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}
	memcpy(data_input, data->input[pos], dest->num_input * dest->num_data * sizeof(fann_type));

	data_output = (fann_type *) calloc(dest->num_output * dest->num_data, sizeof(fann_type));
	if(data_output == NULL)
	{
		fann_error((struct fann_error*)data, FANN_E_CANT_ALLOCATE_MEM);
		fann_destroy_train(dest);
		return NULL;
	}
	memcpy(data_output, data->output[pos], dest->num_output * dest->num_data * sizeof(fann_type));

	for(i = 0; i != dest->num_data; i++)
	{
		dest->input[i] = data_input;
		data_input += dest->num_input;
		dest->output[i] = data_output;
		data_output += dest->num_output;
	}
	return dest;
}

FANN_EXTERNAL unsigned int FANN_API fann_length_train_data(struct fann_train_data *data)
{
	return data->num_data;
}

FANN_EXTERNAL unsigned int FANN_API fann_num_input_train_data(struct fann_train_data *data)
{
	return data->num_input;
}

FANN_EXTERNAL unsigned int FANN_API fann_num_output_train_data(struct fann_train_data *data)
{
	return data->num_output;
}

/* INTERNAL FUNCTION
   Save the train data structure.
 */
int fann_save_train_internal(struct fann_train_data *data, const char *filename,
							  unsigned int save_as_fixed, unsigned int decimal_point)
{
	int retval = 0;
	FILE *file = fopen(filename, "w");

	if(!file)
	{
		fann_error((struct fann_error *) data, FANN_E_CANT_OPEN_TD_W, filename);
		return -1;
	}
	retval = fann_save_train_internal_fd(data, file, filename, save_as_fixed, decimal_point);
	fclose(file);
	
	return retval;
}

/* INTERNAL FUNCTION
   Save the train data structure.
 */
int fann_save_train_internal_fd(struct fann_train_data *data, FILE * file, const char *filename,
								 unsigned int save_as_fixed, unsigned int decimal_point)
{
	unsigned int num_data = data->num_data;
	unsigned int num_input = data->num_input;
	unsigned int num_output = data->num_output;
	unsigned int i, j;
	int retval = 0;

#ifndef FIXEDFANN
	unsigned int multiplier = 1 << decimal_point;
#endif

	fprintf(file, "%u %u %u\n", data->num_data, data->num_input, data->num_output);

	for(i = 0; i < num_data; i++)
	{
		for(j = 0; j < num_input; j++)
		{
#ifndef FIXEDFANN
			if(save_as_fixed)
			{
				fprintf(file, "%d ", (int) (data->input[i][j] * multiplier));
			}
			else
			{
				if(((int) floor(data->input[i][j] + 0.5) * 1000000) ==
				   ((int) floor(data->input[i][j] * 1000000.0 + 0.5)))
				{
					fprintf(file, "%d ", (int) data->input[i][j]);
				}
				else
				{
					fprintf(file, "%f ", data->input[i][j]);
				}
			}
#else
			fprintf(file, FANNPRINTF " ", data->input[i][j]);
#endif
		}
		fprintf(file, "\n");

		for(j = 0; j < num_output; j++)
		{
#ifndef FIXEDFANN
			if(save_as_fixed)
			{
				fprintf(file, "%d ", (int) (data->output[i][j] * multiplier));
			}
			else
			{
				if(((int) floor(data->output[i][j] + 0.5) * 1000000) ==
				   ((int) floor(data->output[i][j] * 1000000.0 + 0.5)))
				{
					fprintf(file, "%d ", (int) data->output[i][j]);
				}
				else
				{
					fprintf(file, "%f ", data->output[i][j]);
				}
			}
#else
			fprintf(file, FANNPRINTF " ", data->output[i][j]);
#endif
		}
		fprintf(file, "\n");
	}
	
	return retval;
}


/*
 * INTERNAL FUNCTION Reads training data from a file descriptor. 
 */
struct fann_train_data *fann_read_train_from_fd(FILE * file, const char *filename)
{
	unsigned int num_input, num_output, num_data, i, j;
	unsigned int line = 1;
	fann_type *data_input, *data_output;
	struct fann_train_data *data =
		(struct fann_train_data *) malloc(sizeof(struct fann_train_data));

	if(data == NULL)
	{
		fann_error(NULL, FANN_E_CANT_ALLOCATE_MEM);
		return NULL;
	}

	if(fscanf(file, "%u %u %u\n", &num_data, &num_input, &num_output) != 3)
	{
		fann_error(NULL, FANN_E_CANT_READ_TD, filename, line);
		fann_destroy_train(data);
		return NULL;
	}
	line++;