import maxframe.dataframe as md
from maxframe import new_session
from maxframe.config import options
options.sql.enable_mcqa = False

table = o.create_table("test_source_table", "a string, b bigint", if_not_exists=True)
with table.open_writer() as writer:
    writer.write([
        ["value1", 0],
        ["value2", 1],
    ])

# 创建MaxFrame session
session = new_session(o)

df = md.read_odps_table("test_source_table",index_col="b")
df["a"] = "prefix_" + df["a"]

# 打印dataframe数据
print(df.execute().fetch())

# MaxFrame DataFrame数据写入MaxCompute表
md.to_odps_table(df, "test_prefix_source_table").execute()

# 销毁 maxframe session
session.destroy()

from odps import ODPS
from maxframe.session import new_session
import maxframe.dataframe as md
import pandas as pd
import os

o = ODPS(
    # 确保 ALIBABA_CLOUD_ACCESS_KEY_ID 环境变量设置为用户 Access Key ID，
    # ALIBABA_CLOUD_ACCESS_KEY_SECRET 环境变量设置为用户 Access Key Secret，
    # 不建议直接使用AccessKey ID和 AccessKey Secret字符串。
    os.getenv('ALIBABA_CLOUD_ACCESS_KEY_ID'),
    os.getenv('ALIBABA_CLOUD_ACCESS_KEY_SECRET'),
    project='your-default-project',
    endpoint='your-end-point',
)

data_sets = [{
    "table_name": "product",
    "table_schema" : "index bigint, product_id bigint, product_name string, current_price bigint",
    "source_type": "records",
    "records" : [
        [1, 100, 'Nokia', 1000],
        [2, 200, 'Apple', 5000],
        [3, 300, 'Samsung', 9000]
    ],
},
{
    "table_name" : "sales",
    "table_schema" : "index bigint, sale_id bigint, product_id bigint, user_id bigint, year bigint, quantity bigint, price bigint",
    "source_type": "records",
    "records" : [
        [1, 1, 100, 101, 2008, 10, 5000],
        [2, 2, 300, 101, 2009, 7, 4000],
        [3, 4, 100, 102, 2011, 9, 4000],
        [4, 5, 200, 102, 2013, 6, 6000],
        [5, 8, 300, 102, 2015, 10, 9000],
        [6, 9, 100, 102, 2015, 6, 2000]
    ],
    "lifecycle": 5
}]

def prepare_data(o: ODPS, data_sets, suffix="", drop_if_exists=False):
    for index, data in enumerate(data_sets):
        table_name = data.get("table_name")
        table_schema = data.get("table_schema")
        source_type = data.get("source_type")
        
        if not table_name or not table_schema or not source_type:
            raise ValueError(f"Dataset at index {index} is missing one or more required keys: 'table_name', 'table_schema', or 'source_type'.")

        lifecycle = data.get("lifecycle", 5)
        table_name += suffix
        
        print(f"Processing {table_name}...")
        if drop_if_exists:
            print(f"Deleting {table_name}...")
            o.delete_table(table_name, if_exists=True)
        
        o.create_table(name=table_name, table_schema=table_schema, lifecycle=lifecycle, if_not_exists=True)

        if source_type == "local_file":
            file_path = data.get("file")
            if not file_path:
                raise ValueError(f"Dataset at index {index} with source_type 'local_file' is missing the 'file' key.")
            sep = data.get("sep", ",")
            pd_df = pd.read_csv(file_path, sep=sep)
            ODPSDataFrame(pd_df).persist(table_name, drop_table=True)
        elif source_type == 'records':
            records = data.get("records")
            if not records:
                raise ValueError(f"Dataset at index {index} with source_type 'records' is missing the 'records' key.")
            with o.get_table(table_name).open_writer() as writer:
                writer.write(records)
        else:
            raise ValueError(f"Unknown data set source_type: {source_type}")
        
        print(f"Processed {table_name} Done")

prepare_data(o, data_sets, "_maxframe_demo", True)

Executing user script with PyODPS 0.12.1 (wrapper version: 0.12.1spawn)

Processing product_maxframe_demo...
Deleting product_maxframe_demo...

/opt/taobao/tbdpapp/pyodps/pyodpswrapper.py:1191: UserWarning: Global variable __doc__ you are about to set conflicts with pyodpswrapper or builtin variables. It might not be runnable with multiprocessing.
  "It might not be runnable with multiprocessing." % key
2025-01-07 20:34:40,348 WARNING:urllib3.connectionpool:Retrying (Retry(total=3, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x7f48ac8fb198>, 'Connection to service.cn-beijing.maxcompute.aliyun.com timed out. (connect timeout=120)')': /api/tenants?curr_project=user_project_dev