def __init__(self, backup_dir, node):
# TODO: not cut
# each pending window (or node) only has a single downstream cut,
# otherwise inconsistency occurs during truncating
self.backup_dir = backup_dir
self.node = node
self.hdfs_client = Config().get_client('dev')
self.hdfs_client.makedirs(self.backup_dir)
# each backup file is named by the ending version, so the current writing one is named temporarily
self.current_backup_path = os.path.join(self.backup_dir, 'current')
# touch the file for later appending
self.hdfs_client.write(self.current_backup_path, data='')
# the version that last truncation conducted against
self.safe_version_path = os.path.join(self.backup_dir, 'safe_version')
# special case for initial version
self.hdfs_client.write(self.safe_version_path, data=str(0))
# the latest integral version
self.latest_version_path = os.path.join(self.backup_dir,
'latest_version')
# special case for initial version
self.hdfs_client.write(self.latest_version_path, data=str(0))
if self.node.type != 'sink':
self.version_acks = dict()
for n in self.node.downstream_connectors:
self.version_acks[n] = 0
def __init__(self, sc, spark_session, uri, port):
self.sc = sc
self.spark_session = spark_session
self.df = []
self.models = []
self.graphs = []
self.base_path = uri + ":" + port
self.local_pickle_path = os.path.dirname(
os.path.realpath(__file__)) + '/../pickles/'
self.pickle_path = '/user/hadoop/pickles/'
self.model_path = '/user/hadoop/pickles/models/'
self.dataset_path = self.pickle_path + "dataset/"
self.private_release_path = self.dataset_path + "private/"
self.anon_release_path = self.dataset_path + "github/"
self.prod_release_path = self.dataset_path + "prod/"
self.df_path = self.pickle_path + 'df/'
self.graph_path = self.local_pickle_path + 'graphs/'
self.labelled_df_path = self.df_path + 'labelled/'
self.hdfs_client = Config().get_client('dev')
self.load_df()
self.load_models()
self.load_graphs()
def __init__(self):
self.client = Config().get_client('dev')
try:
self.client.list('datasets')
except:
self.client.makedirs('datasets')
def main():
client = Config(path=hdfscliconf).get_client()
with client.read('/user/orenault/passwd') as input:
#print input.read()
df = pd.read_csv(input, sep=':', header=None)
cols = df.iloc[:, 0]
client.write('/user/orenault/data.avro',
cols.to_csv(sep=":", header=True, index=False),
overwrite=True)
class HDFSLayout(Layout):
def __init__(self,
path,
config=None,
dynamic_getters=False,
absolute_paths=True,
regex_search=False):
"""
A container for all the files and metadata found at the specified path.
Args:
path (str): The root path of the layout.
config (str): The path to the JSON config file that defines the
entities and paths for the current layout.
dynamic_getters (bool): If True, a get_{entity_name}() method will
be dynamically added to the Layout every time a new Entity is
created. This is implemented by creating a partial function of
the get() function that sets the target argument to the
entity name.
absolute_paths (bool): If True, grabbit uses absolute file paths
everywhere (including when returning query results). If False,
the input path will determine the behavior (i.e., relative if
a relative path was passed, absolute if an absolute path was
passed).
regex_search (bool): Whether to require exact matching (True)
or regex search (False, default) when comparing the query
string to each entity in .get() calls. This sets a default for
the instance, but can be overridden in individual .get()
requests.
"""
self._hdfs_client = Config().get_client()
path = abspath(path) if absolute_paths and self._hdfs_client is None \
else path
# Preprocess the config file
if isinstance(config, six.string_types):
config = '/'.join(config.strip('hdfs://').split('/')[1:])
config = config.replace(self._hdfs_client.root[1:], '')
with self._hdfs_client.read(config) as reader:
config = json.load(reader)
super(HDFSLayout, self).__init__(path, config, dynamic_getters,
absolute_paths, regex_search)
def _get_files(self):
self.root = '/'.join(
self.root.strip('hdfs://').split('/')[1:]).replace(
self._hdfs_client.root[1:], '')
return self._hdfs_client.walk(self.root)
def _make_file_object(self, root, f):
filepath = str(psp.join(root, f))
with self._hdfs_client.read(filepath):
return File(filepath)
def read(cls, file_path):
lines = []
try:
client = Config().get_client('dev')
with client.read(file_path, encoding='utf-8', delimiter='\n') as reader:
for line in reader:
lines.append(line) # eventuell unnoetig, kann man auch reader zurueckgeben?
except:
print("ERROR: Could not read from HDFS.")
raise
return lines
def __init__(self):
self.client = Config().get_client('dev')
self.prompt = 'homura_fs $ '
self.name = None
self.local_xml = None
self.hdfs_xml = '.last_sync.xml'
self.hdfs_loc_xml = None
self.mount_root = None #os.getcwd() + '/test'
self.hdfs_root = '/cs219'
self.meta = HomuraMeta()
self.monitor = None
if sys.platform.startswith('darwin'):
logging.basicConfig(filename='mylog.log', level=logging.INFO)
self.monitor = Monitor_Start()
def main():
arg = parsing_options()
client = Config().get_client()
with client.read(arg.input) as inputFile:
# Load file in dataframe
df=pd.read_csv(inputFile, sep=arg.delimiter, header=arg.header)
inputFile.closed
# Open output file
with client.write(arg.output, overwrite=arg.overwrite) as outputFile:
# Flatten the list of columns
column = list(itertools.chain.from_iterable(arg.column))
# open RSA key
key = get_key(arg.RSAkey,arg.operation)
# Extract columns which need to be hashed / encrypted
cols = df.iloc[:,column]
colName = cols.columns
if arg.operation == 'decrypt':
# Do not forget the comma behind the privateRSA
# the correct python grammer for a singleton tuple is (1,) not (1),
# which is just an expr wth the value 1.
df[colName]=df[colName].apply(decrypt, args=(key,), axis=1)
df.to_csv(outputFile, sep=":", header=True, index=False)
else:
# Encrypt then hash - as otherwise we encrypt the hash value
# Call function encrypt w/ RSAkey - Axis=1 for row
encrypted = df[colName].apply(encrypt, args=(key,))#, axis=1)
# Rename header to not clash when merging df + encrypted data frame
new_column=[]
#for i in cols.columns:
for i in colName:
new_column.append(str(i) + '_ENC')
encrypted.columns = new_column
# Concatenate both dataframe
df = pd.concat([df, encrypted], axis=1)
# Generate a hash
df[colName] = df[colName].apply(hash_value).values
# Write to file
df.to_csv(outputFile, sep=":", header=True, index=False)
def main():
conf = SparkConf().setAppName("binarize nifti")
sc = SparkContext(conf=conf)
sc.setLogLevel('ERROR')
parser = argparse.ArgumentParser(description='Binarize images')
parser.add_argument('threshold', type=int, help="binarization threshold")
parser.add_argument('folder_path',
type=str,
help='folder path containing all of the splits')
parser.add_argument('output_path', type=str, help='output folder path')
parser.add_argument('num',
type=int,
choices=[2, 4, 6, 8],
help='number of binarization operations')
parser.add_argument('-m',
'--in_memory',
type=bool,
default=True,
help='in memory computation')
args = parser.parse_args()
nibRDD = sc.binaryFiles(args.folder_path)\
.map(lambda x: get_data(x))
client = Config().get_client('dev')
if args.in_memory == 'True':
print "Performing in-memory computations"
for i in xrange(num - 1):
nibRDD = nibRDD.map(lambda x: binarize(x, args.threshold))
nibRDD = nibRDD.map(lambda x: binarize_and_save(
x, args.threshold, args.output_path, client)).collect()
else:
print "Writing intermediary results to disk and loading from disk"
binRDD = nibRDD.map(lambda x: binarize_and_save(
x, args.threshold, args.output_path + "1", client)).collect()
for i in xrange(num - 1):
binRDD = sc.binaryFiles(args.output_path + "1")\
.map(lambda x: get_data(x))\
.map(lambda x: binarize_and_save(x, args.threshold, args.output_path + "1", client)).collect()
def __init__(self,
deviceInfoTableName,
kind,
dataBaseInfo,
needFields="*",
schema=None):
self.dataBaseInfo = dataBaseInfo
self.prefix = deviceInfoTableName
self.kind = kind
self.initDir = "/user/ct_fota/YangShuxuanNotDelete"
self.iniFileName = self.kind + "/" + self.prefix + ".ini"
self.needFields = needFields
#self.initLog()
self.connectDB()
self.clientHDFS = Config().get_client()
self.changtimes = 0
self.schema = schema
def main():
conf = SparkConf().setAppName("binarize nifti")
sc = SparkContext(conf=conf)
sc.setLogLevel('ERROR')
parser = argparse.ArgumentParser(
description='Binarize images using FSL installed in a Docker container'
)
parser.add_argument('threshold', type=int, help="binarization threshold")
parser.add_argument('folder_path',
type=str,
help='folder path containing all of the splits')
parser.add_argument('output_path', type=str, help='output folder path')
args = parser.parse_args()
print args.folder_path
client = Config().get_client('dev')
nibRDD = sc.binaryFiles(args.folder_path)\
.map(lambda x: get_data(x))\
.map(lambda x: binarize(x, args.threshold))\
.map(lambda x: copy_to_hdfs(x, args.output_path, client)).collect()
#!/usr/bin/python
# -*- coding: utf-8 -*-
import urllib, urllib.request
from pyquery import PyQuery as pq
from mongoconnect import *
import hashlib
from hdfs import Config
client = Config().get_client('dev')
KEY_WORD = 'news'
exec('database=db_' + KEY_WORD)
def fetchData(item):
request = urllib.request.Request(item['href'])
result = urllib.request.urlopen(request, timeout=25)
if result.code == 200 or 204:
ts = str(result.read(), encoding='gbk')
d = pq(ts)
d = d('div#content')
head = d('div.hd h1').text()
clas = d('div.a_Info span.a_catlog').text()
source = d('div.a_Info span.a_source').text()
time = d('div.a_Info span.a_time').text()
body = d('div#Cnt-Main-Article-QQ p').text()
print(time, ' ', clas, ' ', source, ' ', head)
newhashid = hashlib.md5((head + time).encode()).hexdigest()
print(body)
#mongo updata class and source,
def __init__(self, profile):
self.client = Config().get_client(profile)
# In[1]:
import os
from pyspark import SparkContext, SparkConf
from pyspark.streaming import StreamingContext
import hyperloglog
from concurrent.futures import Future
from hdfs import Config
import subprocess
try:
client = Config().get_client()
except:
config_fname = "hdfscli.cfg"
with open(config_fname, "wt") as f:
f.write("""
[global]
default.alias = default
[default.alias]
url = http://mipt-master.atp-fivt.org:50070
user = {user}
""".format(user=os.environ["USER"]))
client = Config(config_fname).get_client()
nn_address = subprocess.check_output('hdfs getconf -confKey dfs.namenode.http-address', shell=True).strip().decode("utf-8")
schema_Freq_DF = typ.StructType([
typ.StructField("CHROM", typ.IntegerType(), False),
typ.StructField("POS", typ.IntegerType(), False),
typ.StructField("N_ALLELES", typ.IntegerType(), False),
typ.StructField("N_CHR", typ.IntegerType(), False),
typ.StructField("ALLELE_FREQ_1", typ.StringType(), False),
typ.StructField("ALLELE_FREQ_2", typ.StringType(), False),
typ.StructField("ID", typ.StringType(), True),
])
###############
### Setting up File Paths and Lists
###############
client = Config().get_client('dev')
workingFolder_Indian = "SgIndian_vcf/dataFreeze_Feb2013/SNP/biAllele/"
workingFolder_Malay = "SgMalay_vcf/2012_05/snps/"
workingFolder_Chinese = "1000G_CDX/Phase3/integrated/"
# Filing number of unique samples found in the working folder...
freqFiles_Indian = [
f for f in client.list(workingFolder_Indian)
if re.match(r'chr\d+_analysis_exome\.frq', f)
]
rsIDFiles_Indian = [
f for f in client.list(workingFolder_Indian)
# encoding: utf-8
"""Sample HdfsCLI script.
This example shows how to write files to HDFS, read them back, and perform a
few other simple filesystem operations.
"""
from hdfs import Config
from json import dump, load
# Get the default alias' client. (See the quickstart section in the
# documentation to learn more about this.)
client = Config().get_client()
# Some fake data that we are interested in uploading to HDFS.
model = {
'(intercept)': 48.,
'first_feature': 2.,
'second_feature': 12.,
}
# First, we delete any existing `models/` folder on HDFS.
client.delete('models', recursive=True)
# We can now upload the data, first as CSV.
with client.write('models/1.csv', encoding='utf-8') as writer:
for item in model.items():
writer.write(u'%s,%s\n' % item)
class HomuraFS():
def __init__(self):
self.client = Config().get_client('dev')
self.prompt = 'homura_fs $ '
self.name = None
self.local_xml = None
self.hdfs_xml = '.last_sync.xml'
self.hdfs_loc_xml = None
self.mount_root = None #os.getcwd() + '/test'
self.hdfs_root = '/cs219'
self.meta = HomuraMeta()
self.monitor = None
if sys.platform.startswith('darwin'):
logging.basicConfig(filename='mylog.log', level=logging.INFO)
self.monitor = Monitor_Start()
def shell_loop(self):
while True:
cmd = raw_input(self.prompt)
if cmd == 'sync':
print "Current devices attached:"
id_mapping = dict()
count = 1
if len(self.monitor.devs) == 0:
print "No device attached"
continue
for dev in self.monitor.devs:
#print dev
devname = dev['Dname']
manufacture = dev['Man']
hname = dev['Hname']
id_mapping[count] = dev
print "{}) Dname: {}, Hname: {}, Manufacture: {}.\n".format(
count, devname, hname, manufacture)
count += 1
dev_id = int(raw_input("Which device to sync:\n"))
if dev_id == 0:
continue
if dev_id in id_mapping:
#self.name = id_mapping[dev_id]['UID']
self.name = ''
self.mount_root = id_mapping[dev_id]['Path']
self.local_xml = self.mount_root + '/.last_sync.xml'
self.hdfs_loc_xml = self.mount_root + '/.cur_hdfs.xml'
self.meta.myRootpath = self.mount_root
log('Mount root is ' + self.mount_root)
log('Device xml file is ' + self.local_xml)
log('HDFS xml file is ' + self.hdfs_xml)
log('Copy of HDFS xml stored at ' + self.hdfs_loc_xml)
log('Syncing files for device ' +
id_mapping[dev_id]['Dname'])
self.sync_files()
else:
pass
elif cmd == 'test':
pass
#log('Setting up test directory with default config')
#self.__test()
elif cmd == 'download':
pass
elif cmd == 'quit':
if self.monitor:
Monitor_Stop(self.monitor)
return
def download_all(self):
log('Downloading all files from HDFS to local device')
try:
self.create_file(self.mount_root, self.hdfs_root, 1)
for dir_or_file in os.listdir(self.mount_root + self.hdfs_root):
if not dir_or_file.startswith('.'):
shutil.move(
self.mount_root + self.hdfs_root + '/' + dir_or_file,
self.mount_root)
shutil.rmtree(self.mount_root + self.hdfs_root)
except:
log('Something went wrog while downloading files')
try:
shutil.rmtree(self.mount_root + self.hdfs_root)
except:
pass
self.meta.path2Xml(self.mount_root)
self.meta.saveXml(self.local_xml, Xml='temp')
def upload_all(self):
log('Uploading all files from local device to HDFS')
for dir_or_file in os.listdir(self.mount_root):
if not dir_or_file.startswith('.'):
try:
log('Uploading to ' + self.hdfs_root + '/' + dir_or_file)
self.client.upload(self.hdfs_root + '/' + dir_or_file,
self.mount_root + '/' + dir_or_file,
n_threads=0)
except:
log('Warning: could not upload')
def load_HDFS_XML(self):
log("Attempting to fetch HDFS xml")
self.update_file(self.hdfs_loc_xml, self.hdfs_xml, 1)
log("Loading HDFS xml")
self.meta.loadHDFSXml(self.hdfs_loc_xml)
os.remove(self.hdfs_loc_xml)
def sync_files(self):
# check if we have an old snapshot xml
if not os.path.isfile(
self.local_xml
): # snapshot doesn't exist, so download everything
log("No local snapshot file was found at " + self.local_xml)
self.meta.Snapshotdoc = self.meta.emptyXml() # use empty
try:
# fetch HDFS xml and store locally
self.load_HDFS_XML()
except:
self.meta.HDFSdoc = self.meta.emptyXml()
else:
log("Fetching local snapshot xml from " + self.local_xml)
self.meta.loadSnapshotXml(self.local_xml)
try:
# fetch HDFS xml and store locally
self.load_HDFS_XML()
except:
self.meta.HDFSdoc = self.meta.emptyXml()
self.meta.path2Xml(self.mount_root)
self.meta.mydoc = self.meta.tempdoc
#print 'HDFS XML:'
#self.meta.showHDFSXml()
#print '---\nSnapshot Xml'
#self.meta.showSnapshotXml()
#print '---\nLocal Xml'
#self.meta.showMyXml()
# find operations since last sync
(my_creates, my_deletes, my_modifies, hdfs_creates, hdfs_deletes,
hdfs_modifies) = self.meta.getOperations()
root = self.mount_root
name = self.hdfs_root
# apply operations on current device
for path in my_creates:
if path.endswith('/'): # path is a folder we want to create
os.makedirs(root + path)
else:
self.create_file(root + path, name + path, 1)
for path in my_modifies:
self.update_file(root + path, name + path, 1)
for path in my_deletes:
self.delete_file(root + path, 1)
# apply operations on HDFS
for path in hdfs_creates:
if path.endswith('/'): # path is a folder we want to create
self.client.makedirs(name + path)
else:
self.create_file(root + path, name + path, 0)
for path in hdfs_modifies:
self.update_file(root + path, name + path, 0)
for path in hdfs_deletes:
self.delete_file(name + path, 0)
# update last sync for both HDFS and current device
self.meta.path2Xml(self.mount_root)
self.meta.saveXml(self.local_xml, Xml='temp')
self.update_file(self.local_xml, self.hdfs_xml, 0)
return
# in this set of functions, when kyuubey = 0, the operation goes
# from loc to hdfs (i.e. local becomes the "master")
# when kyuubey = 1, the operation goes from hdfs to loc
# (i.e. hdfs becomes the "master")
def create_file(self, loc_path, hdfs_path, kyuubey):
if kyuubey == 0:
log('Creating ' + hdfs_path + ' on HDFS')
self.client.upload(hdfs_path, loc_path, n_threads=0)
elif kyuubey == 1:
log('Creating ' + loc_path + ' locally')
self.client.download(hdfs_path, loc_path, n_threads=0)
def update_file(self, loc_path, hdfs_path, kyuubey):
if kyuubey == 0: # updating file on HDFS
log('Updating file ' + hdfs_path + ' on HDFS')
with open(loc_path) as reader:
with self.client.write(hdfs_path, overwrite=True) as writer:
for line in reader:
writer.write(line)
elif kyuubey == 1:
log('Updating file ' + loc_path + ' locally')
with open(loc_path, 'w') as writer:
with self.client.read(hdfs_path) as reader:
data = reader.read()
writer.write(data)
def delete_file(self, path, kyuubey):
if kyuubey == 0: # delete file on HDFS
log('Deleting file ' + path + ' from HDFS')
self.client.delete(path, recursive=True)
elif kyuubey == 1: # delete file locally
log('Deleting file ' + path + ' locally')
os.remove(path)
def move_file(self, src_path, dst_path, kyuubey):
if kyuubey == 0: # move file on HDFS
log('Moving file from ' + src_path + ' to ' + dst_path +
' on HDFS')
self.client.rename(src_path, dst_path)
elif kyuubey == 1: # move file locally
os.rename(src_path, dst_path)
log('Moving file from ' + src_path + ' to ' + dst_path +
' locally')
def __test(self, test_no=1):
self.__reset_test()
if test_no == 1:
self.__config_basic()
elif test_no == 2:
self.__config_outer_empty()
def __reset_test(self):
root = self.mount_root
log('Resetting mount directory')
if os.path.exists(root):
shutil.rmtree(root)
os.makedirs(root)
def __config_basic(self):
root = self.mount_root
log('Config 1: default')
with open(root + '/test1.txt', 'w') as writer:
writer.write('hi\nthere\n!\n')
with open(root + '/test2.txt', 'w') as writer:
writer.write('one-liner')
with open(root + '/test3.txt', 'w') as writer:
writer.write('')
os.makedirs(root + '/subdir')
with open(root + '/subdir/test1.txt', 'w') as writer:
writer.write('a different\ntest1.txt\nfile!\n')
os.makedirs(root + '/subdir/subsubdir')
with open(root + '/subdir/subsubdir/test1.txt', 'w') as writer:
writer.write('yet another different\ntest1.txt\nfile!\n')
def __config_outer_empty(self):
root = self.mount_root
log('Config 2: outer directory empty')
os.makedirs(root + '/subdir')
with open(root + '/subdir/test1.txt', 'w') as writer:
writer.write('a different\ntest1.txt\nfile!\n')
os.makedirs(root + '/subdir/subsubdir')
with open(root + '/subdir/subsubdir/test1.txt', 'w') as writer:
writer.write('yet another different\ntest1.txt\nfile!\n')
class Pickler:
def __init__(self, sc, spark_session, uri, port):
self.sc = sc
self.spark_session = spark_session
self.df = []
self.models = []
self.graphs = []
self.base_path = uri + ":" + port
self.local_pickle_path = os.path.dirname(
os.path.realpath(__file__)) + '/../pickles/'
self.pickle_path = '/user/hadoop/pickles/'
self.model_path = '/user/hadoop/pickles/models/'
self.dataset_path = self.pickle_path + "dataset/"
self.private_release_path = self.dataset_path + "private/"
self.anon_release_path = self.dataset_path + "github/"
self.prod_release_path = self.dataset_path + "prod/"
self.df_path = self.pickle_path + 'df/'
self.graph_path = self.local_pickle_path + 'graphs/'
self.labelled_df_path = self.df_path + 'labelled/'
self.hdfs_client = Config().get_client('dev')
self.load_df()
self.load_models()
self.load_graphs()
#TODO: Implement generic methods for read dataset / model ONLY
def read(self):
pass
def save(self):
pass
def getLabelledFiles(self):
return self.hdfs_client.list(self.prod_release_path)
def readCSVToDF(self, date, folder):
return self.spark_session.read.option(
"header",
True).csv(self.base_path + self.dataset_path + folder + "/" + date)
def getLabelledTelemetry(self):
return self.hdfs_client.list(self.private_release_path)
def existsModel(self, name):
res = self.hdfs_client.list(self.model_path)
file_extension = '.model'
if name + file_extension in res:
return True
def getModel(self, name):
return PipelineModel.load(self.base_path + self.model_path + name +
".model")
def isDateLabelled(self, date):
res = self.hdfs_client.list(self.prod_release_path)
file_extension = ".csv"
if date + file_extension in res:
return True
return False
def load_graphs(self):
for file in os.listdir(self.graph_path):
if file.endswith(".pickle"):
self.graphs.append(file[:-7])
def existsGraph(self, date):
if date in self.graphs:
return True
return False
def getGraph(self, date):
if date in self.graphs:
with open(self.graph_path + date + ".pickle", 'rb') as pickle_file:
content = pickle.load(pickle_file)
return content
def saveGraph(self, G, date):
if date in self.graphs:
return False
nx.write_gpickle(G, self.graph_path + date + ".pickle")
self.graphs.append(date)
def existsDF(self, date, source):
#2020.03.01_joy
hash = self.getHash(date, source)
if hash in self.df:
return True
return False
def load_df(self):
#Load Joy Data
res = self.hdfs_client.list(self.df_path + 'joy')
# print(f"Joy Items in directory: {res}")
for file in res:
if file.endswith(".parquet"):
self.df.append(sha256(file[:-8].encode('utf-8')).hexdigest())
#Load graph features DF
res = self.hdfs_client.list(self.df_path + 'graph')
# print(f"Graph DF Items in directory: {res}")
for file in res:
if file.endswith(".parquet"):
self.df.append(sha256(file[:-8].encode('utf-8')).hexdigest())
res = self.hdfs_client.list(self.df_path + 'labelled')
# print(f"Labelled Items in directory: {res}")
for file in res:
if file.endswith(".parquet"):
self.df.append(sha256(file[:-8].encode('utf-8')).hexdigest())
# TODO : Load others?
def saveModel(self, model, name):
model.save(self.base_path + self.model_path + name + ".model")
def load_models(self):
res = self.hdfs_client.list(self.model_path)
for file in res:
if file.endswith(".model"):
self.models.append(file.split('.')[0])
def saveDFToCSV(self, df, date, folder, coalesced=False):
if coalesced:
df.coalesce(1).write.csv(self.base_path + self.pickle_path +
"dataset/" + folder + '/' + date + '.csv',
header=True)
else:
df.write.csv(self.base_path + self.pickle_path + "dataset/" +
folder + '/' + date + '.csv',
header=True)
df.write.parquet(self.base_path + self.pickle_path + "dataset/" +
folder + '/' + date + '.parquet')
def saveDF(self, df, date, source):
hash = self.getHash(date, source)
if hash in self.df:
return False
else:
df.write.parquet(self.base_path + self.df_path + source + '/' +
date + "_" + source + '.parquet')
self.df.append(hash)
def getDF(self, date, source):
hash = self.getHash(date, source)
if hash in self.df:
df = self.spark_session.read.parquet(self.base_path +
self.df_path + source + '/' +
date + "_" + source +
'.parquet')
return df
return False
def getHash(self, date, source):
id = date + "_" + source
hash = sha256(id.encode('utf-8')).hexdigest()
return hash
HDFS_OUTPUT_DIR = "/OUTPUT/"
HDFS_BASE_URL = "hdfs://bdrenfdludcf01:9000"
if __name__ == "__main__":
# Folder creation for placing all the spark data
cmd_a = "mkdir -p " + "/tmp/SPARK_PROCESS/"
os.system(cmd_a)
# Configure Spark
conf = SparkConf().setAppName(APP_NAME).set("spark.local.dir",
"/tmp/SPARK_PROCESS/")
sc = SparkContext(conf=conf)
sqlContext = SQLContext(sc)
client = Config().get_client('bdrenhdfs')
files = client.list(HDFS_RAWFILE_DIR)
totalfilecount = len(files)
if totalfilecount == 0:
print("There is no files to be processed, application exiting...")
sys.exit(0)
filecount = 0
for filename in files:
print(filename)
if filename.find("Covid_Analysis_DataSet.csv") >= 0:
filecount = filecount + 1
df_covid = sqlContext.read.format("csv").option(
"delimiter",
def get_hdfs(alias='lake'):
# https://hdfscli.readthedocs.io/en/latest/api.html
from hdfs import Config
client = Config().get_client(alias)
return client
from hdfs import Config from sys import argv from math import ceil script, filename = argv client = Config().get_client() status = client.status(filename) print(ceil(status['length'] / status['blockSize']))
def __init__(self, debug=False):
path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'.hdfscli.cfg')
self.client = Config(path).get_client()
self.debug = debug
class HadoopWebExplorer:
def __init__(self, debug=False):
path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'.hdfscli.cfg')
self.client = Config(path).get_client()
self.debug = debug
def print(self, *args):
if self.debug:
print(*args)
def path_exists(self, path):
"""
Checks whether such path already exists
:param path: path to check
:type path: unicode
:return: boolean flag indicating whether path already exists or not
:rtype: bool
"""
return self.client.status(path, strict=False) is not None
@catch_hdfs_error
def create_folder(self, folder_name):
"""
Creates folder with the given name if it does not exist
:param folder_name: the name of the folder we want to add
:type folder_name: unicode
:return: returns true if created folder or it already exists, otherwise false
:rtype: bool
"""
if self.path_exists(folder_name):
print(f'Folder already exists: {folder_name}')
return True
self.print(f'Folder does not exist: {folder_name}')
self.client.makedirs(folder_name)
self.print(f'Folder created: {folder_name}')
@catch_hdfs_error
def write_to_file(self,
folder_name,
file_name,
data,
overwrite=False,
append=False):
"""
Writes provided data into file in the specified folder
:param folder_name: name of the folder where file is located
:type folder_name: unicode
:param file_name: name of the file where data should be written to
:type file_name: unicode
:param data: data to be written
:type data: unicode
:param overwrite: overwrite any existing file or directory
:type overwrite: bool
:param append: append to a file rather than create a new one.
:type append: bool
:return: returns true if it successfully wrote the data, otherwise false
:rtype: bool
"""
path = os.path.join(folder_name, file_name)
if append and not self.path_exists(path):
self.client.write(path,
data,
encoding='utf-8',
overwrite=overwrite)
else:
self.client.write(path,
data,
encoding='utf-8',
overwrite=overwrite,
append=append)
self.print("Written data to HDFS file")
@catch_hdfs_error
def read_from_file(self, folder_name, file_name):
"""
Reads from file in the specified folder
:param folder_name: name of the folder where file is located
:type folder_name: unicode
:param file_name: name of the file where data should be read from
:type file_name: unicode
"""
path = os.path.join(folder_name, file_name)
if not self.path_exists(path):
self.print(f'File does not exists: {path}')
return None
return self.client.read(path)
@catch_hdfs_error
def delete_file(self, folder_name, file_name):
"""
Deletes file in the specified folder
:param folder_name: name of the folder where file is located
:type folder_name: unicode
:param file_name: name of the file to be deleted
:type file_name: unicode
:return: returns true if it successfully deleted the file, otherwise false
:rtype: bool
"""
path = os.path.join(folder_name, file_name)
return self.client.delete(path)
@catch_hdfs_error
def delete_folder(self, folder_name):
"""
Deletes the specified folder
:param folder_name: name of the folder where file is located
:type folder_name: unicode
:return: returns true if it successfully deleted the folder, otherwise false
:rtype: bool
"""
return self.client.delete(folder_name, recursive=True)
@catch_hdfs_error
def explore_folder(self, folder_name):
"""
Explores the specified folder
:param folder_name: name of the folder to be observed
:type folder_name: unicode
"""
if not self.path_exists(folder_name):
self.print(f'Folder does not exists: {folder_name}')
self.print(f'Exploring folder: {folder_name}')
for path, dirs, files in self.client.walk(folder_name, status=True):
for file in files:
block_size = file[1]['blockSize']
size = file[1]['length']
owner = file[1]['owner']
self.print(
f'\tFile: {file[0]}, blockSize: {block_size}, size: {size}, owner: {owner}'
)
from hdfs import Config, InsecureClient
import cPickle as pickle
from tuple import Tuple
client = Config().get_client('dev')
client.write('a/p', 'aaa', overwrite=True)
print client.status('a')
def main():
arg = parsing_options()
krb_client = Config(path=arg.hdfsConf).get_client()
az_conf = read_conf(arg.azureConf)
az_client = az_key_vault_connection(az_conf['azure_client_id'],
az_conf['azure_client_secret'],
az_conf['azure_tenant_id'])
az_rsa_key = az_get_rsa_key_info(az_client, az_conf['key_vault'],
az_conf['key_name'])
column = list(itertools.chain.from_iterable(arg.column))
with krb_client.read(arg.input) as inputFile:
with krb_client.write(arg.output,
overwrite=arg.overwrite) as outputFile:
if arg.operation == 'encrypt':
aes_key = generate_aes_key()
az_conf['uuid'] = str(uuid.uuid4())
encrypt_and_store_aes_key(az_client, az_conf,
az_rsa_key['version'],
base64.b64encode(aes_key))
df = pd.read_csv(inputFile,
sep=arg.delimiter,
header=arg.header,
dtype=str,
chunksize=10000)
num_chunk = 0
for chunk in df:
# Generate new column name and hash in place
new_column = []
for i in column:
new_column.append(str(i) + '_HASH')
chunk[new_column] = chunk[column].apply(hash_value)
# Encrypt in place
chunk[column] = chunk[column].apply(encrypt,
args=(aes_key,
az_conf['uuid']))
if num_chunk == 0:
chunk.to_csv(outputFile,
sep=arg.delimiter,
header=True,
index=False)
num_chunk += 1
else:
chunk.to_csv(outputFile,
sep=arg.delimiter,
header=False,
index=False)
else:
df = pd.read_csv(inputFile,
sep=arg.delimiter,
header=arg.header,
dtype=str,
chunksize=1000)
num_chunk = 0
for chunk in df:
if num_chunk == 0:
# spliting only the first column - grabbing the 3rd field (key) and grabbing the value [0]
key = base64.b64decode(chunk[column[0]].str.split(
pat='-', n=3, expand=True)[3][0])
aes_key = retrieve_and_decrypt_aes_key(
az_client, az_conf, az_rsa_key['version'], key)
chunk[column] = chunk[column].apply(decrypt,
args=(aes_key, ))
if num_chunk == 0:
chunk.to_csv(outputFile,
sep=arg.delimiter,
header=True,
index=False)
num_chunk += 1
else:
chunk.to_csv(outputFile,
sep=arg.delimiter,
header=False,
index=False)
#! /user/bin/env python3
from hdfs import Config
import sys
client = Config().get_client()
filename = sys.argv[1]
with client.read(filename) as reader:
ans = reader.read(10)
print(ans.decode())
def main(argv):
# Validamos entrada
try:
opts, args = getopt.getopt(argv, "hd:n:l:m:")
except getopt.GetoptError:
print(
'usage: spark-submit \\ \n --master <master> \\ \n <path>/ClasificacionImagenes.py \\'
)
print(' [-d <directorio_salida] [-n <numero_imagenes>] \\ \n ')
print(' [-l <tamaño_lote] [-m max_etiquetas] [-s url_images]')
sys.exit(2)
for opt, arg in opts:
if opt == '-h':
print(
'usage: spark-submit \\ \n --master <master> \\ \n <path>/ClasificacionImagenes.py \\'
)
print(' [-d <directorio_salida] [-n <numero_imagenes>] \\ \n ')
print(' [-l <tamaño_lote] [-m max_etiquetas] [-s url_images]')
sys.exit()
elif opt == "-s":
C.images_index_url = arg
elif opt == "-d":
C.dir_classification = arg
elif opt == "-n":
C.numero_imagenes_proceso = int(arg)
elif opt == "-l":
C.lote_size = int(arg)
elif opt == "-m":
C.max_etiquetas = int(arg)
print("Directorio : ", C.dir_classification)
print("Num Imagenes a procesar: ", C.numero_imagenes_proceso)
print("Imagenes por lote: ", C.lote_size)
print("Max etiquetas a guardar: ", C.max_etiquetas)
# ***************************************************************************
# Inicio del proceso
# ***************************************************************************
global node_lookup_bc
global model_data_bc
# Iniciamos SparkContext
print("Inicio: ",
datetime.fromtimestamp(time()).strftime('%Y-%m-%d %H:%M:%S'))
sc = SparkContext(
appName='Clasificacion MirFlickr con TensorFlow',
pyFiles=[
'/home/utad/TFM/Fuentes/TensorFlowMirFlickr/Constantes.py',
'/home/utad/TFM/Fuentes/TensorFlowMirFlickr/NodeLookup.py'
])
get_tensorflow_model()
# Cargamos el modelo y lo distribuimos
model_path = os.path.join(C.model_dir, 'classify_image_graph_def.pb')
with tf.gfile.FastGFile(model_path, 'rb') as f:
model_data = f.read()
model_data_bc = sc.broadcast(model_data)
# Distribuimos node lookup para ser utilizado en los workers
node_lookup = NodeLookup().node_lookup
node_lookup_bc = sc.broadcast(node_lookup)
# Obtenemos una lista de las imágenes a procesar y las agrupamos en lotes
servicio_imagenes = None
try:
servicio_imagenes = urllib.urlopen(C.images_index_url)
except Exception as e:
print(e)
print("Servidor de imágenes no disponible")
exit(404)
imagenes = servicio_imagenes.read().split(
'<li>')[2:C.numero_imagenes_proceso + 2]
lote_imagenes = [
imagenes[i:i + C.lote_size]
for i in range(0, len(imagenes), C.lote_size)
]
# Paralelizamos los lotes de imagenes y procesamos
rdd_imagenes = sc.parallelize(lote_imagenes).map(
lambda x: map(obtener_nombre_imagen, x))
inception_rdd = rdd_imagenes.flatMap(procesar_lote_imagenes)
# Borramos directorio categorias del hdfs por si existiera
client = Config().get_client()
client.delete('inception', recursive=True)
# Salvamos los ficheros obtenidos en formato json. Para ello usamos un dataframe
print("Procesamos:",
datetime.fromtimestamp(time()).strftime('%Y-%m-%d %H:%M:%S'))
spark = SparkSession(sc)
inception_df = inception_rdd.toDF()
inception_df.write.json(C.dir_classification)
print("Fin:", datetime.fromtimestamp(time()).strftime('%Y-%m-%d %H:%M:%S'))
#!/usr/bin/env python
# encoding: utf-8
"""Avro extension example."""
from hdfs import Config
from hdfs.ext.avro import AvroReader, AvroWriter
# Get the default alias' client.
client = Config().get_client()
# Some sample data.
records = [
{
'name': 'Ann',
'age': 23
},
{
'name': 'Bob',
'age': 22
},
]
# Write an Avro File to HDFS (since our records' schema is very simple, we let
# the writer infer it automatically, otherwise we would pass it as argument).
with AvroWriter(client, 'names.avro', overwrite=True) as writer:
for record in records:
writer.write(record)
# Read it back.
with AvroReader(client, 'names.avro') as reader:
schema = reader.schema # The inferred schema.
class SparkHDFSClient(object):
def __init__(self, datasource):
self.datasource = datasource
self.client = Config().get_client("dev")
def get_file_list(self, folder):
files = self.client.list(folder.strip())
files = [folder + '/' + file for file in files]
return files
def list_collections(self):
results = []
status = self.client.status(self.datasource.url, strict=False)
print(status, self.datasource.url)
if status is not None:
if status['type'] == "DIRECTORY":
files = self.get_file_list(self.datasource.url)
while len(files) > 0:
file = files.pop()
status = self.client.status(os.path.join(
self.datasource.url, file),
strict=False)
if status is None:
continue
if status['type'] == "DIRECTORY":
subfiles = self.get_file_list(
os.path.join(self.datasource.url, file))
files.extend(subfiles)
continue
else:
if self.datasource.dstype == DataSourceType.SPARK_CSV and file[-2:] != 'sv' \
or self.datasource.dstype == DataSourceType.SPARK_TSV and file[-2:] != 'sv'\
or self.datasource.dstype == DataSourceType.SPARK_XML and file[-3:] != 'xml'\
or self.datasource.dstype == DataSourceType.SPARK_JSON and file[-4:] != 'json':
continue
row = {
"db":
file[:file.rfind('/')]
if '/' in file else self.datasource.url,
"document":
file[file.rfind('/') +
1:] if '/' in file else file,
"count":
-1
}
results.append(row)
return results
else:
return [{
"db": self.datasource.url,
"document": self.datasource.url,
"count": -1
}]
else:
return results
def get_documents(self, filename, limit=10):
results = []
delimiter = "\n"
header = None
rows = 0
if self.datasource.dstype == DataSourceType.SPARK_CSV or \
self.datasource.dstype == DataSourceType.SPARK_TSV:
delimiter = "\n"
with self.client.read(filename,
encoding='utf-8',
delimiter=delimiter) as reader:
for line in reader:
if len(line.strip()) == 0 or line[0] == '#':
continue
if filename[-3:] == "csv":
line = line.split(',')
else:
line = line.split('\t')
if header is None:
header = line
continue
res = {
header[i]: line[i]
for i in range(len(line)) if i < len(header)
}
results.append(res)
rows += 1
if rows > limit + 1:
break
elif self.datasource.dstype == DataSourceType.SPARK_XML:
with self.client.read(filename, encoding='utf-8',
chunk_size=2048) as reader:
header = ['content']
for chunk in reader:
res = {'content': str(chunk)}
results.append(res)
print(results)
break
elif self.datasource.dstype == DataSourceType.SPARK_JSON:
with self.client.read(filename, encoding='utf-8') as reader:
model = load(reader)
if isinstance(model, list):
model = [{
p:
str(list(md[p][0].keys())) if isinstance(md[p], list)
and isinstance(md[p][0], dict) else str(model[p])
if isinstance(md[p], list) else str(list(md[p].keys()))
if isinstance(md[p], dict) else md[p]
for p in md
} for md in model]
results.extend(model)
else:
model = {
p: str(list(model[p][0].keys()))
if isinstance(model[p], list) and isinstance(
model[p][0], dict) else model[p] if isinstance(
model[p], list) else str(list(model[p].keys()))
if isinstance(model[p], dict) else model[p]
for p in model
}
results.append(model)
return results[:limit], limit
class PendingWindow(object):
"""docstring for PendingWindow"""
def __init__(self, backup_dir, node):
# TODO: not cut
# each pending window (or node) only has a single downstream cut,
# otherwise inconsistency occurs during truncating
self.backup_dir = backup_dir
self.node = node
self.hdfs_client = Config().get_client('dev')
self.hdfs_client.makedirs(self.backup_dir)
# each backup file is named by the ending version, so the current writing one is named temporarily
self.current_backup_path = os.path.join(self.backup_dir, 'current')
# touch the file for later appending
self.hdfs_client.write(self.current_backup_path, data='')
# the version that last truncation conducted against
self.safe_version_path = os.path.join(self.backup_dir, 'safe_version')
# special case for initial version
self.hdfs_client.write(self.safe_version_path, data=str(0))
# the latest integral version
self.latest_version_path = os.path.join(self.backup_dir,
'latest_version')
# special case for initial version
self.hdfs_client.write(self.latest_version_path, data=str(0))
if self.node.type != 'sink':
self.version_acks = dict()
for n in self.node.downstream_connectors:
self.version_acks[n] = 0
def append(self, tuple_):
"""Make an output tuple persistent, and complete a version if necessary
"""
self.hdfs_client.write(self.current_backup_path,
data=pickle.dumps(tuple_),
append=True)
if isinstance(tuple_, BarrierTuple):
self.hdfs_client.rename(
self.current_backup_path,
os.path.join(self.backup_dir, str(tuple_.version)))
self.hdfs_client.write(self.latest_version_path,
data=str(tuple_.version),
overwrite=True)
self.hdfs_client.write(self.current_backup_path, data='')
def extend(self, tuples):
# TODO: can be improved
with self.hdfs_client.write(self.current_backup_path,
append=True) as f:
for t in tuples:
pickle.dump(t, f)
if isinstance(tuples[-1], BarrierTuple):
self.hdfs_client.rename(
self.current_backup_path,
os.path.join(self.backup_dir, str(tuples[-1].version)))
self.hdfs_client.write(self.latest_version_path,
data=str(tuples[-1].version),
overwrite=True)
self.hdfs_client.write(self.current_backup_path, data='')
def truncate(self, version):
"""Delete files with filename <= version
"""
# with self.hdfs_client.read(self.safe_version_path) as f:
# safe_version = int(f.read())
#
# # only = condition can occur
# if version <= safe_version:
# return
for f in self.hdfs_client.list(self.backup_dir):
if f.isdigit() and int(f) <= version:
self.hdfs_client.delete(os.path.join(self.backup_dir, f))
# self.node.LOGGER.info('truncated version %d' % version)
def handle_version_ack(self, version_ack):
old_safe_version = min(self.version_acks.values())
self.version_acks[version_ack.sent_from] = version_ack.version
new_safe_version = min(self.version_acks.values())
if new_safe_version > old_safe_version:
self.hdfs_client.write(self.safe_version_path,
data=str(new_safe_version),
overwrite=True)
self.truncate(new_safe_version)
def get_latest_version(self):
with self.hdfs_client.read(self.latest_version_path) as f:
latest_version = int(f.read())
return latest_version
def rewind(self, version=None):
"""Delete files with filename > version (including current file)
"""
if version == None:
self.hdfs_client.write(self.current_backup_path,
data='',
overwrite=True)
return
# TODO: underflow
# assert version == 0 or
for f in self.hdfs_client.list(self.backup_dir):
if f.isdigit() and int(f) > version:
self.hdfs_client.delete(os.path.join(self.backup_dir, f))
self.hdfs_client.write(self.current_backup_path,
data='',
overwrite=True)
self.hdfs_client.write(self.latest_version_path,
data=str(version),
overwrite=True)
def replay(self):
"""When both the node and pending window state are ready, replay the pending window before resuming
"""
for v in sorted(
map(
int,
filter(unicode.isdigit,
self.hdfs_client.list(self.backup_dir)))):
# filter out the faster nodes
tuples = []
with self.hdfs_client.read(os.path.join(self.backup_dir,
str(v))) as f:
while True:
try:
t = pickle.load(f)
tuples.append(t)
except EOFError:
self.node.LOGGER.debug(
'reached EOF, send this version')
break
# Spout needs version too, so that data source can resend from a version
# except pickle.UnpickleableError:
# self.node.LOGGER.debug('spout reached partial dump location, send this incomplete version')
# break
self.node.multicast(self.node.downstream_nodes, tuples)
def __init__(self, datasource):
self.datasource = datasource
self.client = Config().get_client("dev")
