def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_milsongs_orc.py"))
pass
else:
hdfs_orc_file = "/datasets/orc_parser/milsongs_orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
hdfs_csv_file = "/datasets/orc_parser/milsongs_csv"
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file)
multi_file_csv = h2o.import_file(url_csv)
multi_file_orc = h2o.import_file(url_orc)
multi_file_csv.summary()
csv_summary = h2o.frame(multi_file_csv.frame_id)["frames"][0]["columns"]
multi_file_orc.summary()
orc_summary = h2o.frame(multi_file_orc.frame_id)["frames"][0]["columns"]
pyunit_utils.compare_frame_summary(csv_summary, orc_summary)
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
# run a quick test to determine if the hive-exec is too old.
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_prostate_orc.py"))
pass
else:
tol_time = 200 # comparing in ms or ns
tol_numeric = 1e-5 # tolerance for comparing other numeric fields
numElements2Compare = 10 # choose number of elements per column to compare. Save test time.
hdfs_orc_file = "/datasets/orc_parser/orc/prostate_NA.orc"
hdfs_csv_file = "/datasets/orc_parser/csv/prostate_NA.csv"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file)
h2oOrc = h2o.import_file(url_orc)
h2oCsv = h2o.import_file(url_csv)
# compare the two frames
assert pyunit_utils.compare_frames(h2oOrc, h2oCsv, numElements2Compare, tol_time, tol_numeric), \
"H2O frame parsed from orc and csv files are different!"
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_iris_import_types_orc.py"))
pass
else:
numElements2Compare = 100
tol_time = 200
tol_numeric = 1e-5
hdfs_orc_file = "/datasets/orc_parser/orc/iris.orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
hdfs_csv_file = "/datasets/orc_parser/csv/iris.csv"
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file)
h2oframe_csv = h2o.import_file(url_csv)
data_types = ['real', 'real', 'real', 'real', 'enum']
h2oframe_orc = h2o.import_file(url_orc, col_types = data_types)
# compare the two frames
assert pyunit_utils.compare_frames(h2oframe_orc, h2oframe_csv, numElements2Compare, tol_time, tol_numeric,
True), "H2O frame parsed from orc and csv files are different!"
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible(
)
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(
hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_milsongs_orc.py"))
pass
else:
hdfs_orc_file = "/datasets/orc_parser/milsongs_orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
hdfs_csv_file = "/datasets/orc_parser/milsongs_csv"
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file)
multi_file_csv = h2o.import_file(url_csv)
multi_file_orc = h2o.import_file(url_orc)
multi_file_csv.summary()
csv_summary = h2o.frame(
multi_file_csv.frame_id)["frames"][0]["columns"]
multi_file_orc.summary()
orc_summary = h2o.frame(
multi_file_orc.frame_id)["frames"][0]["columns"]
pyunit_utils.compare_frame_summary(csv_summary, orc_summary)
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_import_folder_airline_05_orc.py"))
pass
else:
hdfs_orc_file = "/datasets/orc_parser/air05_orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
hdfs_csv_file = "/datasets/orc_parser/air05_csv"
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file)
startcsv = time.time()
multi_file_csv = h2o.import_file(url_csv, na_strings=['\\N'])
endcsv = time.time()
csv_type_dict = multi_file_csv.types
multi_file_csv.summary()
csv_summary = h2o.frame(multi_file_csv.frame_id)["frames"][0]["columns"]
col_ind_name = dict()
# change column types from real to enum according to multi_file_csv column types
for key_name in list(csv_type_dict):
col_ind = key_name.split('C')
new_ind = int(str(col_ind[1]))-1
col_ind_name[new_ind] = key_name
col_types = []
for ind in range(len(col_ind_name)):
col_types.append(csv_type_dict[col_ind_name[ind]])
startorc1 = time.time()
multi_file_orc1 = h2o.import_file(url_orc)
endorc1 = time.time()
h2o.remove(multi_file_orc1)
startorc = time.time()
multi_file_orc = h2o.import_file(url_orc,col_types=col_types)
endorc = time.time()
multi_file_orc.summary()
orc_summary = h2o.frame(multi_file_orc.frame_id)["frames"][0]["columns"]
print("************** CSV parse time is {0}".format(endcsv-startcsv))
print("************** ORC (without column type forcing) parse time is {0}".format(endorc1-startorc1))
print("************** ORC (with column type forcing) parse time is {0}".format(endorc-startorc))
# compare frame read by orc by forcing column type,
pyunit_utils.compare_frame_summary(csv_summary, orc_summary)
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible(
)
if hadoop_namenode_is_accessible:
numElements2Compare = 10
tol_time = 200
tol_numeric = 1e-5
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(
hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_orc_parser.py"))
pass
else:
allOrcFiles = [
"/datasets/orc_parser/orc/TestOrcFile.columnProjection.orc",
"/datasets/orc_parser/orc/bigint_single_col.orc",
"/datasets/orc_parser/orc/TestOrcFile.emptyFile.orc",
"/datasets/orc_parser/orc/bool_single_col.orc",
"/datasets/orc_parser/orc/demo-11-zlib.orc",
"/datasets/orc_parser/orc/TestOrcFile.testDate1900.orc",
"/datasets/orc_parser/orc/demo-12-zlib.orc",
"/datasets/orc_parser/orc/TestOrcFile.testDate2038.orc",
"/datasets/orc_parser/orc/double_single_col.orc",
"/datasets/orc_parser/orc/TestOrcFile.testMemoryManagementV11.orc",
"/datasets/orc_parser/orc/float_single_col.orc",
"/datasets/orc_parser/orc/TestOrcFile.testMemoryManagementV12.orc",
"/datasets/orc_parser/orc/int_single_col.orc",
"/datasets/orc_parser/orc/TestOrcFile.testPredicatePushdown.orc",
"/datasets/orc_parser/orc/nulls-at-end-snappy.orc",
"/datasets/orc_parser/orc/TestOrcFile.testSnappy.orc",
"/datasets/orc_parser/orc/orc_split_elim.orc",
"/datasets/orc_parser/orc/TestOrcFile.testStringAndBinaryStatistics.orc",
"/datasets/orc_parser/orc/TestOrcFile.testStripeLevelStats.orc",
"/datasets/orc_parser/orc/smallint_single_col.orc",
"/datasets/orc_parser/orc/string_single_col.orc",
"/datasets/orc_parser/orc/tinyint_single_col.orc",
"/datasets/orc_parser/orc/TestOrcFile.testWithoutIndex.orc"
]
for fIndex in range(len(allOrcFiles)):
url_orc = "hdfs://{0}{1}".format(hdfs_name_node,
allOrcFiles[fIndex])
tab_test = h2o.import_file(url_orc)
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible(
)
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(
hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format(
"pyunit_INTERNAL_HDFS_timestamp_date_orc.py"))
pass
else:
origTZ = h2o.cluster().timezone
newZone = 'America/Los_Angeles'
h2o.cluster().timezone = newZone
tol_time = 200 # comparing in ms or ns
tol_numeric = 1e-5 # tolerance for comparing other numeric fields
numElements2Compare = 100 # choose number of elements per column to compare. Save test time.
allOrcFiles = [
"/datasets/orc_parser/orc/TestOrcFile.testDate1900.orc",
"/datasets/orc_parser/orc/TestOrcFile.testDate2038.orc",
"/datasets/orc_parser/orc/orc_split_elim.orc"
]
allCsvFiles = [
"/datasets/orc_parser/csv/TestOrcFile.testDate1900.csv",
"/datasets/orc_parser/csv/TestOrcFile.testDate2038.csv",
"/datasets/orc_parser/csv/orc_split_elim.csv"
]
for fIndex in range(len(allOrcFiles)):
url_orc = "hdfs://{0}{1}".format(hdfs_name_node,
allOrcFiles[fIndex])
url_csv = "hdfs://{0}{1}".format(hdfs_name_node,
allCsvFiles[fIndex])
h2oOrc = h2o.import_file(url_orc)
h2oCsv = h2o.import_file(url_csv)
# compare the two frames
assert pyunit_utils.compare_frames(h2oOrc, h2oCsv, numElements2Compare, tol_time, tol_numeric), \
"H2O frame parsed from orc and csv files are different!"
h2o.cluster().timezone = origTZ
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible(
)
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(
hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_baddata_orc.py"))
pass
else:
hdfs_orc_file = "/datasets/orc_parser/orc/TestOrcFile.testStringAndBinaryStatistics.orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
print("Parsing the orc file {0}".format(url_orc))
assert pyunit_utils.expect_warnings(
url_orc,
warn_phrase="UserWarning:",
warn_string_of_interest="Skipping field:",
in_hdfs=True,
number_of_times=1
), "Expect warnings from orc parser for file " + url_orc + "!"
hdfs_orc_file = "/datasets/orc_parser/orc/TestOrcFile.emptyFile.orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
print("Parsing the orc file {0}".format(url_orc))
assert pyunit_utils.expect_warnings(
url_orc,
warn_phrase="UserWarning:",
warn_string_of_interest="Skipping field:",
in_hdfs=True,
number_of_times=1
), "Expect warnings from orc parser for file " + url_orc + "!"
hdfs_orc_file = "/datasets/orc_parser/orc/nulls-at-end-snappy.orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
print("Parsing the orc file {0}".format(url_orc))
assert pyunit_utils.expect_warnings(
url_orc,
warn_phrase="UserWarning:",
warn_string_of_interest="Long.MIN_VALUE:",
in_hdfs=True,
number_of_times=1
), "Expect warnings from orc parser for file " + url_orc + "!"
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
numElements2Compare = 10
tol_time = 200
tol_numeric = 1e-5
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_orc_parser.py"))
pass
else:
allOrcFiles = ["/datasets/orc_parser/orc/TestOrcFile.columnProjection.orc",
"/datasets/orc_parser/orc/bigint_single_col.orc",
"/datasets/orc_parser/orc/TestOrcFile.emptyFile.orc",
"/datasets/orc_parser/orc/bool_single_col.orc",
"/datasets/orc_parser/orc/demo-11-zlib.orc",
"/datasets/orc_parser/orc/TestOrcFile.testDate1900.orc",
"/datasets/orc_parser/orc/demo-12-zlib.orc",
"/datasets/orc_parser/orc/TestOrcFile.testDate2038.orc",
"/datasets/orc_parser/orc/double_single_col.orc",
"/datasets/orc_parser/orc/TestOrcFile.testMemoryManagementV11.orc",
"/datasets/orc_parser/orc/float_single_col.orc",
"/datasets/orc_parser/orc/TestOrcFile.testMemoryManagementV12.orc",
"/datasets/orc_parser/orc/int_single_col.orc",
"/datasets/orc_parser/orc/TestOrcFile.testPredicatePushdown.orc",
"/datasets/orc_parser/orc/nulls-at-end-snappy.orc",
"/datasets/orc_parser/orc/TestOrcFile.testSnappy.orc",
"/datasets/orc_parser/orc/orc_split_elim.orc",
"/datasets/orc_parser/orc/TestOrcFile.testStringAndBinaryStatistics.orc",
"/datasets/orc_parser/orc/TestOrcFile.testStripeLevelStats.orc",
"/datasets/orc_parser/orc/smallint_single_col.orc",
"/datasets/orc_parser/orc/string_single_col.orc",
"/datasets/orc_parser/orc/tinyint_single_col.orc",
"/datasets/orc_parser/orc/TestOrcFile.testWithoutIndex.orc"]
for fIndex in range(len(allOrcFiles)):
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, allOrcFiles[fIndex])
tab_test = h2o.import_file(url_orc)
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible(
)
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(
hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print(
"Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_import_folder_orc.py"))
pass
else:
tol_time = 200 # comparing in ms or ns
tol_numeric = 1e-5 # tolerance for comparing other numeric fields
numElements2Compare = 0 # choose number of elements per column to compare. Save test time.
hdfs_csv_file1 = "/datasets/orc_parser/csv/balunbal.csv"
url_csv1 = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file1)
multi_file_csv1 = h2o.import_file(url_csv1)
hdfs_csv_file2 = "/datasets/orc_parser/csv/unbalbal.csv"
url_csv2 = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file2)
multi_file_csv2 = h2o.import_file(url_csv2)
hdfs_orc_file = "/datasets/orc_parser/synthetic_perfect_separation_orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
multi_file_orc = h2o.import_file(url_orc)
# make sure orc multi-file and single big file create same H2O frame
try:
assert pyunit_utils.compare_frames(multi_file_orc , multi_file_csv1, numElements2Compare,
tol_time=tol_time, tol_numeric=tol_numeric, strict=True), \
"H2O frame parsed from multiple orc and single orc files are different!"
except:
assert pyunit_utils.compare_frames(multi_file_orc , multi_file_csv2, numElements2Compare,
tol_time=tol_time, tol_numeric=tol_numeric, strict=True), \
"H2O frame parsed from multiple orc and single orc files are different!"
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_import_folder_orc.py"))
pass
else:
mix_folder = "/datasets/orc_csv_same_milsongs"
url_csv1 = "hdfs://{0}{1}".format(hdfs_name_node, mix_folder)
multi_file_mixed = h2o.import_file(url_csv1)
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_import_folder_orc.py"))
pass
else:
mix_folder = "/datasets/milsongs_orc_air_csv"
url_csv1 = "hdfs://{0}{1}".format(hdfs_name_node, mix_folder)
multi_file_mixed = h2o.import_file(url_csv1)
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_import_folder_orc.py"))
pass
else:
tol_time = 200 # comparing in ms or ns
tol_numeric = 1e-5 # tolerance for comparing other numeric fields
numElements2Compare = 0 # choose number of elements per column to compare. Save test time.
hdfs_csv_file1 = "/datasets/orc_parser/csv/balunbal.csv"
url_csv1 = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file1)
multi_file_csv1 = h2o.import_file(url_csv1)
hdfs_csv_file2 = "/datasets/orc_parser/csv/unbalbal.csv"
url_csv2 = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file2)
multi_file_csv2 = h2o.import_file(url_csv2)
hdfs_orc_file = "/datasets/orc_parser/synthetic_perfect_separation_orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
multi_file_orc = h2o.import_file(url_orc)
# make sure orc multi-file and single big file create same H2O frame
try:
assert pyunit_utils.compare_frames(multi_file_orc , multi_file_csv1, numElements2Compare,
tol_time=tol_time, tol_numeric=tol_numeric, strict=True), \
"H2O frame parsed from multiple orc and single orc files are different!"
except:
assert pyunit_utils.compare_frames(multi_file_orc , multi_file_csv2, numElements2Compare,
tol_time=tol_time, tol_numeric=tol_numeric, strict=True), \
"H2O frame parsed from multiple orc and single orc files are different!"
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_timestamp_date_orc.py"))
pass
else:
tol_time = 200 # comparing in ms or ns
tol_numeric = 1e-5 # tolerance for comparing other numeric fields
numElements2Compare = 100 # choose number of elements per column to compare. Save test time.
allOrcFiles = ["/datasets/orc_parser/orc/TestOrcFile.testDate1900.orc",
"/datasets/orc_parser/orc/TestOrcFile.testDate2038.orc",
"/datasets/orc_parser/orc/orc_split_elim.orc"]
allCsvFiles = ["/datasets/orc_parser/csv/TestOrcFile.testDate1900.csv",
"/datasets/orc_parser/csv/TestOrcFile.testDate2038.csv",
"/datasets/orc_parser/csv/orc_split_elim.csv"]
for fIndex in range(len(allOrcFiles)):
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, allOrcFiles[fIndex])
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, allCsvFiles[fIndex])
h2oOrc = h2o.import_file(url_orc)
h2oCsv = h2o.import_file(url_csv)
# compare the two frames
assert pyunit_utils.compare_frames(h2oOrc, h2oCsv, numElements2Compare, tol_time, tol_numeric), \
"H2O frame parsed from orc and csv files are different!"
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_baddata_orc.py"))
pass
else:
hdfs_orc_file = "/datasets/orc_parser/orc/TestOrcFile.testStringAndBinaryStatistics.orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
print("Parsing the orc file {0}".format(url_orc))
assert pyunit_utils.expect_warnings(url_orc, warn_phrase="UserWarning:",
warn_string_of_interest="Skipping field:", in_hdfs=True,
number_of_times=1), "Expect warnings from orc parser for file "+url_orc+"!"
hdfs_orc_file = "/datasets/orc_parser/orc/TestOrcFile.emptyFile.orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
print("Parsing the orc file {0}".format(url_orc))
assert pyunit_utils.expect_warnings(url_orc, warn_phrase="UserWarning:",
warn_string_of_interest="Skipping field:", in_hdfs=True,
number_of_times=1), "Expect warnings from orc parser for file "+url_orc+"!"
hdfs_orc_file = "/datasets/orc_parser/orc/nulls-at-end-snappy.orc"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
print("Parsing the orc file {0}".format(url_orc))
assert pyunit_utils.expect_warnings(url_orc, warn_phrase="UserWarning:",
warn_string_of_interest="Long.MIN_VALUE:", in_hdfs=True,
number_of_times=1), "Expect warnings from orc parser for file "+url_orc+"!"
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible(
)
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
# run a quick test to determine if the hive-exec is too old.
if pyunit_utils.cannaryHDFSTest(
hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_prostate_orc.py"))
pass
else:
tol_time = 200 # comparing in ms or ns
tol_numeric = 1e-5 # tolerance for comparing other numeric fields
numElements2Compare = 10 # choose number of elements per column to compare. Save test time.
hdfs_orc_file = "/datasets/orc_parser/orc/prostate_NA.orc"
hdfs_csv_file = "/datasets/orc_parser/csv/prostate_NA.csv"
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file)
h2oOrc = h2o.import_file(url_orc)
h2oCsv = h2o.import_file(url_csv)
# compare the two frames
assert pyunit_utils.compare_frames(h2oOrc, h2oCsv, numElements2Compare, tol_time, tol_numeric), \
"H2O frame parsed from orc and csv files are different!"
else:
raise EnvironmentError
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible(
)
if hadoop_namenode_is_accessible:
numElements2Compare = 10
tol_time = 200
tol_numeric = 1e-5
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(
hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_airlines_orc.py"))
pass
else:
hdfs_orc_file = "/datasets/airlines_all_orc_parts"
hdfs_csv_file = "/datasets/air_csv_part"
col_types = [
'real', 'real', 'real', 'real', 'real', 'real', 'real', 'real',
'enum', 'real', 'enum', 'real', 'real', 'enum', 'real', 'real',
'enum', 'enum', 'real', 'enum', 'enum', 'real', 'real', 'real',
'enum', 'enum', 'enum', 'enum', 'enum', 'enum', 'enum'
]
# import CSV file
print(
"Import airlines 116M dataset in original csv format from HDFS"
)
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file)
startcsv = time.time()
multi_file_csv = h2o.import_file(url_csv,
na_strings=['\\N'],
col_types=col_types)
endcsv = time.time()
startcsv1 = time.time()
multi_file_csv1 = h2o.import_file(url_csv)
endcsv1 = time.time()
h2o.remove(multi_file_csv1)
multi_file_csv.summary()
csv_summary = h2o.frame(
multi_file_csv.frame_id)["frames"][0]["columns"]
# import ORC file with same column types as CSV file
print("Import airlines 116M dataset in ORC format from HDFS")
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
startorc1 = time.time()
multi_file_orc1 = h2o.import_file(url_orc)
endorc1 = time.time()
h2o.remove(multi_file_orc1)
startorc = time.time()
multi_file_orc = h2o.import_file(url_orc, col_types=col_types)
endorc = time.time()
multi_file_orc.summary()
orc_summary = h2o.frame(
multi_file_orc.frame_id)["frames"][0]["columns"]
print(
"************** CSV (without column type forcing) parse time is {0}"
.format(endcsv1 - startcsv1))
print(
"************** CSV (with column type forcing) parse time is {0}"
.format(endcsv - startcsv))
print(
"************** ORC (without column type forcing) parse time is {0}"
.format(endorc1 - startorc1))
print(
"************** ORC (with column type forcing) parse time is {0}"
.format(endorc - startorc))
# compare frame read by orc by forcing column type,
pyunit_utils.compare_frame_summary(csv_summary, orc_summary)
else:
raise EnvironmentError
def import_folder_orc():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_airlines_orc.py"))
pass
else:
hdfs_orc_file = "/datasets/orc_parser/prostate_NA.orc"
hdfs_csv_file = "/datasets/orc_parser/prostate_NA.csv"
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file)
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
csv = h2o.import_file(url_csv, na_strings=['\\N'])
multi_file_orc1 = h2o.import_file(url_orc)
pyunit_utils.compare_frames_local(csv, multi_file_orc1, prob=1) # should be the same here.
path = url_orc
skip_all = list(range(csv.ncol))
skip_even = list(range(0, csv.ncol, 2))
skip_odd = list(range(1, csv.ncol, 2))
skip_start_end = [0, csv.ncol - 1]
skip_except_last = list(range(0, csv.ncol - 2))
skip_except_first = list(range(1, csv.ncol))
temp = list(range(0, csv.ncol))
random.shuffle(temp)
skip_random = []
for index in range(0, csv.ncol / 2):
skip_random.append(temp[index])
skip_random.sort()
try:
loadFileSkipAll = h2o.upload_file(path, skipped_columns=skip_all)
sys.exit(1) # should have failed here
except:
pass
try:
importFileSkipAll = h2o.import_file(path, skipped_columns=skip_all)
sys.exit(1) # should have failed here
except:
pass
# skip even columns
pyunit_utils.checkCorrectSkips(csv, path, skip_even)
# skip odd columns
pyunit_utils.checkCorrectSkips(csv, path, skip_odd)
# skip the very beginning and the very end.
pyunit_utils.checkCorrectSkips(csv, path, skip_start_end)
# skip all except the last column
pyunit_utils.checkCorrectSkips(csv, path, skip_except_last)
# skip all except the very first column
pyunit_utils.checkCorrectSkips(csv, path, skip_except_first)
# randomly skipped half the columns
pyunit_utils.checkCorrectSkips(csv, path, skip_random)
def import_folder_orc():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible(
)
if hadoop_namenode_is_accessible:
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(
hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_airlines_orc.py"))
pass
else:
hdfs_orc_file = "/datasets/orc_parser/prostate_NA.orc"
hdfs_csv_file = "/datasets/orc_parser/prostate_NA.csv"
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file)
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
csv = h2o.import_file(url_csv, na_strings=['\\N'])
multi_file_orc1 = h2o.import_file(url_orc)
pyunit_utils.compare_frames_local(csv, multi_file_orc1,
prob=1) # should be the same here.
path = url_orc
skip_all = list(range(csv.ncol))
skip_even = list(range(0, csv.ncol, 2))
skip_odd = list(range(1, csv.ncol, 2))
skip_start_end = [0, csv.ncol - 1]
skip_except_last = list(range(0, csv.ncol - 2))
skip_except_first = list(range(1, csv.ncol))
temp = list(range(0, csv.ncol))
random.shuffle(temp)
skip_random = []
for index in range(0, csv.ncol / 2):
skip_random.append(temp[index])
skip_random.sort()
try:
loadFileSkipAll = h2o.upload_file(path, skipped_columns=skip_all)
sys.exit(1) # should have failed here
except:
pass
try:
importFileSkipAll = h2o.import_file(path, skipped_columns=skip_all)
sys.exit(1) # should have failed here
except:
pass
# skip even columns
pyunit_utils.checkCorrectSkips(csv, path, skip_even)
# skip odd columns
pyunit_utils.checkCorrectSkips(csv, path, skip_odd)
# skip the very beginning and the very end.
pyunit_utils.checkCorrectSkips(csv, path, skip_start_end)
# skip all except the last column
pyunit_utils.checkCorrectSkips(csv, path, skip_except_last)
# skip all except the very first column
pyunit_utils.checkCorrectSkips(csv, path, skip_except_first)
# randomly skipped half the columns
pyunit_utils.checkCorrectSkips(csv, path, skip_random)
def hdfs_orc_parser():
# Check if we are running inside the H2O network by seeing if we can touch
# the namenode.
hadoop_namenode_is_accessible = pyunit_utils.hadoop_namenode_is_accessible()
if hadoop_namenode_is_accessible:
numElements2Compare = 10
tol_time = 200
tol_numeric = 1e-5
hdfs_name_node = pyunit_utils.hadoop_namenode()
if pyunit_utils.cannaryHDFSTest(hdfs_name_node, "/datasets/orc_parser/orc/orc_split_elim.orc"):
print("Your hive-exec version is too old. Orc parser test {0} is "
"skipped.".format("pyunit_INTERNAL_HDFS_airlines_orc.py"))
pass
else:
hdfs_orc_file = "/datasets/airlines_all_orc_parts"
hdfs_csv_file = "/datasets/air_csv_part"
col_types = ['real', 'real', 'real', 'real', 'real', 'real', 'real', 'real', 'enum', 'real', 'enum', 'real',
'real', 'enum', 'real', 'real', 'enum', 'enum', 'real', 'enum', 'enum', 'real', 'real', 'real',
'enum', 'enum', 'enum', 'enum', 'enum', 'enum', 'enum']
# import CSV file
print("Import airlines 116M dataset in original csv format from HDFS")
url_csv = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_csv_file)
startcsv = time.time()
multi_file_csv = h2o.import_file(url_csv, na_strings=['\\N'], col_types=col_types)
endcsv = time.time()
startcsv1 = time.time()
multi_file_csv1 = h2o.import_file(url_csv)
endcsv1 = time.time()
h2o.remove(multi_file_csv1)
multi_file_csv.summary()
csv_summary = h2o.frame(multi_file_csv.frame_id)["frames"][0]["columns"]
# import ORC file with same column types as CSV file
print("Import airlines 116M dataset in ORC format from HDFS")
url_orc = "hdfs://{0}{1}".format(hdfs_name_node, hdfs_orc_file)
startorc1 = time.time()
multi_file_orc1 = h2o.import_file(url_orc)
endorc1 = time.time()
h2o.remove(multi_file_orc1)
startorc = time.time()
multi_file_orc = h2o.import_file(url_orc, col_types=col_types)
endorc = time.time()
multi_file_orc.summary()
orc_summary = h2o.frame(multi_file_orc.frame_id)["frames"][0]["columns"]
print("************** CSV (without column type forcing) parse time is {0}".format(endcsv1-startcsv1))
print("************** CSV (with column type forcing) parse time is {0}".format(endcsv-startcsv))
print("************** ORC (without column type forcing) parse time is {0}".format(endorc1-startorc1))
print("************** ORC (with column type forcing) parse time is {0}".format(endorc-startorc))
# compare frame read by orc by forcing column type,
pyunit_utils.compare_frame_summary(csv_summary, orc_summary)
else:
raise EnvironmentError