def load_csv(self,
path=None,
provider=None,
*args,
sep=None,
header=None,
**kwargs):
#return None
obj = None
md = Resource(path, provider, sep=sep, header=header, **kwargs)
# download if necessary
md = get_local(md)
options = md['options']
# after collecting from metadata, or method call, define csv defaults
options['header'] = options.get('header') or True
options['inferSchema'] = options.get('inferSchema') or True
options['sep'] = options.get('sep') or ','
local = self.is_spark_local()
# start the timer for logging
ts_start = timer()
try:
#three approaches: local, cluster, and service
if md['service'] == 'file' and local:
obj = self.context.read.options(**options).csv(md['url'])
elif md['service'] == 'file':
logging.warning(
f'local file + spark cluster: loading using pandas reader',
extra={'md': to_dict(md)})
df = pd.read_csv(md['url'],
sep=options['sep'],
header=options['header'])
obj = self.context.createDataFrame(df)
elif md['service'] in ['hdfs', 's3a']:
obj = self.context.read.options(**options).csv(md['url'])
else:
logging.error(f'Unknown resource service "{md["service"]}"',
extra={'md': to_dict(md)})
except AnalysisException as e:
logging.error(str(e), extra={'md': md})
except Exception as e:
logging.error(e, extra={'md': md})
self.load_log(md, options, ts_start)
return obj
def load_parquet(self,
path=None,
provider=None,
*args,
mergeSchema=None,
**kwargs):
obj = None
md = Resource(path,
provider,
format='parquet',
mergeSchema=mergeSchema,
**kwargs)
# download if necessary
md = get_local(md)
options = md['options']
# after collecting from metadata, or method call, define csv defaults
options['mergeSchema'] = options.get('mergeSchema') or True
local = self.is_spark_local()
try:
#three approaches: local, cluster, and service
if md['service'] == 'file' and local:
obj = self.context.read.options(**options).parquet(md['url'])
elif md['service'] == 'file':
logging.warning(
f'local file + spark cluster: loading using pandas reader',
extra={'md': to_dict(md)})
#fallback to the pandas reader, then convert to spark
df = pd.read_parquet(md['url'])
obj = self.context.createDataFrame(df)
elif md['service'] in ['hdfs', 's3a']:
obj = self.context.read.options(**options).parquet(md['url'])
else:
logging.error(f'Unknown resource service "{md["service"]}"',
extra={'md': to_dict(md)})
return obj
except AnalysisException as e:
logging.error(str(e), extra={'md': md})
except Exception as e:
logging.error(str(e), extra={'md': md})
return obj