HCP_S1200数据集下载

HCP_dataset
Mapping the human brain is one of the great scientific challenges of the 21st century.
The HCP( The Human Connectome Project) is mapping the healthy human connectome by collecting and freely distributing neuroimaging and behavioral data on 1,200 normal young adults, aged 22-35. Using greatly improved methods for data acquisition, analysis, and sharing, the HCP has provided the scientific community with data and discoveries that greatly enhance our understanding of human brain structure, function, and connectivity and their relationships to behavior. Also ,it is providing a treasure trove of neuroimaging and behavioral data at an unprecedented level of detail.
About Questions

import boto3
import os
import logging
import datetime
from boto3.session import Session

bucketName = 'hcp-openaccess'
prefix = 'HCP_1200'
outputPath = '/home/ec2-user/SageMaker/HCP_dataset'
access_key = 'AKIAXO65CT57HVRCTMH4'# [你的 aws_access_key]
secret_key = 'XA6zzMixA9ci15pEZ24zjgLCOuoiWdiSRUdaPDkv' # [你的 aws_secret_key]
bucketName = 'hcp-openaccess'
if not os.path.exists(outputPath):
    os.makedirs(outputPath)
session = Session(aws_access_key_id=access_key,aws_secret_access_key=secret_key)
s3 = session.resource('s3')
theTime = datetime.datetime.now().strftime('%Y_%m_%d-%H-%M_%S')
#os.makedirs(theTime)

logger = logging.getLogger('script')
formatter = logging.Formatter('%(asctime)s[line:%(lineno)d] - %(levelname)s: %(message)s')
logger.setLevel(level = logging.DEBUG)
logger.propagate = False

stream_handler = logging.StreamHandler()
stream_handler.setLevel(logging.INFO)
stream_handler.setFormatter(formatter)

logger.addHandler(stream_handler)

bucket = s3.Bucket(bucketName)
logger.info('Bucket built!')

with open('./subjects.txt', 'r') as fr:
        for subject_number in fr.readlines():
            subject_number = subject_number.strip()
            keyList = bucket.objects.filter(Prefix = prefix + '/{}/MNINonLinear/Results/tfMRI'.format(subject_number))
            keyList = [key.key for key in keyList]
            keyList = [x for x in keyList if '_LR.nii.gz' in x ]
            totalNumber = len(keyList)
            for idx,tarPath in enumerate(keyList):
                downloadPath = os.path.join(outputPath,tarPath)
                #downloadDir = os.path.dirname(downloadPath)
                downloadPath1 = os.path.join(outputPath,subject_number+'_'+tarPath.split('/')[-1].split('_')[1]+'.nii.gz')
                #if not os.path.exists(downloadDir):
                 #   os.makedirs(downloadDir)
                try:
                    if not os.path.exists(downloadPath1):
                        bucket.download_file(tarPath,downloadPath1)
                        logger.info('%s: %s downloaded! %d/%d',subject_number,tarPath.split('/')[-1],idx+1,totalNumber)
                    else :
                        logger.info('%s: %s already exists! %d/%d',subject_number,tarPath.split('/')[-1],idx+1,totalNumber)
                except Exception as exc:
                    logger.error('{}'.format(str(exc)))
            logger.info('%s completed!', subject_number)

with open('./subjects.txt', 'r') as fr:
    with open('/home/ec2-user/SageMaker/Models_HCP/dt1.txt', 'w') as fr2:
        for subject_number in fr.readlines():
            subject_number = subject_number.strip()
            keyList = bucket.objects.filter(Prefix = prefix + '/{}/MNINonLinear/Results/tfMRI'.format(subject_number))
            keyList = [key.key for key in keyList]
            keyList = [x for x in keyList if '_LR.nii.gz' in x ]
            totalNumber = len(keyList)
            for idx,tarPath in enumerate(keyList):
                downloadPath1 = os.path.join(outputPath,subject_number+'_'+tarPath.split('/')[-1].split('_')[1]+'.nii.gz')
                fr2.write(subject_number+'_'+tarPath.split('/')[-1].split('_')[1]+'.nii.gz\n')

for i in $(ls *.gz);do gzip -d $i;done
for i in $(ls *.gz);do rm $i;done