def h2oset_timezone(): """ Python API test: h2o.set_timezone(value) Deprecated, set h2o.cluster().timezone instead. Copy from pyunit_get_set_list_timezones.py """ try: origTZ = h2o.get_timezone() print("Original timezone: {0}".format(origTZ)) timezones = h2o.list_timezones() # don't use the first one..it's a header for the table print("timezones[0]:", timezones[0]) zone = timezones[random.randint(1, timezones.nrow - 1), 0].split(" ")[1].split(",")[0] print("Setting the timezone: {0}".format(zone)) h2o.set_timezone(zone) newTZ = h2o.get_timezone() assert newTZ == zone, "Expected new timezone to be {0}, but got {01}".format( zone, newTZ) print("Setting the timezone back to original: {0}".format(origTZ)) h2o.set_timezone(origTZ) except Exception as e: assert False, "h2o.set_timezone() command is not working."
def get_set_list_timezones(ip,port): # Connect to h2o h2o.init(ip,port) origTZ = h2o.get_timezone() print "Original timezone: {0}".format(origTZ) timezones = h2o.list_timezones() zone = timezones[random.randint(0,timezones.nrow()-1),0].split(" ")[1].split(",")[0] print "Setting the timezone: {0}".format(zone) h2o.set_timezone(zone) newTZ = h2o.get_timezone() assert newTZ == zone, "Expected new timezone to be {0}, but got {01}".format(zone, newTZ) print "Setting the timezone back to original: {0}".format(origTZ) h2o.set_timezone(origTZ)
def get_set_list_timezones(): origTZ = h2o.get_timezone() print "Original timezone: {0}".format(origTZ) timezones = h2o.list_timezones() # don't use the first one..it's a header for the table print "timezones[0]:", timezones[0] zone = timezones[random.randint(1,timezones.nrow-1),0].split(" ")[1].split(",")[0] print "Setting the timezone: {0}".format(zone) h2o.set_timezone(zone) newTZ = h2o.get_timezone() assert newTZ == zone, "Expected new timezone to be {0}, but got {01}".format(zone, newTZ) print "Setting the timezone back to original: {0}".format(origTZ) h2o.set_timezone(origTZ)
def get_set_list_timezones(): origTZ = h2o.get_timezone() print "Original timezone: {0}".format(origTZ) timezones = h2o.list_timezones() # don't use the first one..it's a header for the table print "timezones[0]:", timezones[0] zone = timezones[random.randint(1, timezones.nrow - 1), 0].split(" ")[1].split(",")[0] print "Setting the timezone: {0}".format(zone) h2o.set_timezone(zone) newTZ = h2o.get_timezone() assert newTZ == zone, "Expected new timezone to be {0}, but got {01}".format( zone, newTZ) print "Setting the timezone back to original: {0}".format(origTZ) h2o.set_timezone(origTZ)
def h2oset_timezone(): """ Python API test: h2o.set_timezone(value) Deprecated, set h2o.cluster().timezone instead. Copy from pyunit_get_set_list_timezones.py """ origTZ = h2o.get_timezone() print("Original timezone: {0}".format(origTZ)) timezones = h2o.list_timezones() # don't use the first one..it's a header for the table print("timezones[0]:", timezones[0]) zone = timezones[random.randint(1,timezones.nrow-1),0].split(" ")[1].split(",")[0] print("Setting the timezone: {0}".format(zone)) h2o.set_timezone(zone) newTZ = h2o.get_timezone() assert newTZ == zone, "Expected new timezone to be {0}, but got {01}".format(zone, newTZ) print("Setting the timezone back to original: {0}".format(origTZ)) h2o.set_timezone(origTZ)
# Transform census table # Remove all spaces from column names (causing problems in Spark SQL) col_names = map(lambda s: s.strip().replace(' ', '_').replace('+', '_'), f_census.col_names) # Update column names in the table # f_weather.names = col_names f_census.names = col_names # Transform crimes table # Drop useless columns f_crimes = f_crimes[2:] # Set time zone to UTC for date manipulation h2o.set_timezone("Etc/UTC") # Replace ' ' by '_' in column names col_names = map(lambda s: s.replace(' ', '_'), f_crimes.col_names) f_crimes.names = col_names refine_date_col(f_crimes, "Date", "%m/%d/%Y %I:%M:%S %p") f_crimes = f_crimes.drop("Date") # Expose H2O frames as Spark DataFrame df_weather = h2oContext.as_spark_frame(f_weather) df_census = h2oContext.as_spark_frame(f_census) df_crimes = h2oContext.as_spark_frame(f_crimes) # Use Spark SQL to join datasets