MaxCompute:Manage tables

from odps.models import Schema, Column, Partition
columns = [
    Column(name='num', type='bigint', comment='the column'),
    Column(name='num2', type='double', comment='the column2'),
]
partitions = [Partition(name='pt', type='string', comment='the partition')]
schema = Schema(columns=columns, partitions=partitions)

from odps.models import Schema
schema = Schema.from_lists(['num', 'num2'], ['bigint', 'double'], ['pt'], ['string'])
print(schema.columns)

[<column num, type bigint>,
 <column num2, type double>,
 <partition pt, type string>]

# Create a table schema.
from odps.models import Schema
schema = Schema.from_lists(['num', 'num2'], ['bigint', 'double'], ['pt'], ['string'])

# Create a table by using the schema that you created.
table = o.create_table('my_new_table', schema)

# Create a table only if no table with the same name exists.
table = o.create_table('my_new_table', schema, if_not_exists=True)

# Configure the lifecycle of the table.
table = o.create_table('my_new_table', schema, lifecycle=7)

print(o.exist_table('my_new_table'))

# Create a partitioned table named my_new_table with specified common columns and partition key columns.
table = o.create_table('my_new_table', ('num bigint, num2 double', 'pt string'), if_not_exists=True)

# Create a non-partitioned table named my_new_table02.
table = o.create_table('my_new_table02', 'num bigint, num2 double', if_not_exists=True)

print(o.exist_table('my_new_table'))

from odps import options
options.sql.use_odps2_extension = True
table = o.create_table('my_new_table', 'cat smallint, content struct<title:varchar(100), body:string>')

table = o.get_table('my_new_table')
if table.schema.partitions:
    print('Table %s is partitioned.' % table.name)

table = o.get_table('my_new_table')
for partition in table.partitions:  # Iterate over all partitions.
    print(partition.name)  # An iteration step. In this step, the partition name is displayed.
for partition in table.iterate_partitions(spec='pt=test'):  # Iterate over level-2 partitions in the partition named test.
    print(partition.name)  # An iteration step. In this step, the partition name is displayed.
for partition in table.iterate_partitions(spec='dt>20230119'):  # Iterate over level-2 partitions in the partitions that meet the dt>20230119 condition.
    print(partition.name)  # An iteration step. In this step, the partition name is displayed.

table = o.get_table('my_new_table')
table.exist_partition('pt=test,sub=2015')

table = o.get_table('my_new_table')
partition = table.get_partition('pt=test')
print(partition.creation_time)
partition.size

t = o.get_table('my_new_table')
t.create_partition('pt=test', if_not_exists=True)  # Create a partition only if no partition with the same name exists.

t = o.get_table('my_new_table')
t.delete_partition('pt=test', if_exists=True)  # Set the if_exists parameter to True. This ensures that a partition is deleted only if the partition exists.
partition.drop()  # Call the drop() method to drop a partition if the partition exists.

from odps import ODPS
t = o.get_table('dual')
for record in t.head(3):
    # Process each record.

with t.open_reader(partition='pt=test') as reader:
count = reader.count
for record in reader[5:10]  # You can execute the statement multiple times until all records are read. The number of records is specified by count. You can change the code to parallel-operation code.
    # Process one record.

reader = t.open_reader(partition='pt=test')
count = reader.count
for record in reader[5:10]  # You can execute the statement multiple times until all records are read. The number of records is specified by count. You can change the code to parallel-operation code.
    # Process one record.

with t.open_reader(partition='pt=test') as reader:
pd_df = reader.to_pandas()

with t.open_writer(partition='pt=test') as writer:
	  records = [[111, 'aaa', True],                 # A list can be used.
	             [222, 'bbb', False],
	             [333, 'ccc', True],
	             [444, 'Chinese', False]]
    writer.write(records)  # Records can be iterable objects.

records = [t.new_record([111, 'aaa', True]),   # Record objects can be used.
           t.new_record([222, 'bbb', False]),
           t.new_record([333, 'ccc', True]),
           t.new_record([444, 'Chinese', False])]
writer.write(records)

with t.open_writer(partition='pt=test', create_partition=True) as writer:
    records = [[111, 'aaa', True],                 # A list can be used.
               [222, 'bbb', False],
               [333, 'ccc', True],
               [444, 'Chinese', False]]
    writer.write(records)  # Records can be iterable objects.

records = [[111, 'aaa', True],                 # A list can be used.
           [222, 'bbb', False],
           [333, 'ccc', True],
           [444, 'Chinese', False]]
o.write_table('test_table', records, partition='pt=test', create_partition=True)