mike-luabase commented on issue #208:
URL: https://github.com/apache/iceberg-python/issues/208#issuecomment-2156618883
Here's what I've been trying (sorry for long example, but thought the
context would help)
```python
iowa_sales_df =
pcsv.read_csv("/Users/mritchie712/blackbird/demoData/Iowa_Liquor_Sales_20240607.csv")
date_column = pc.strptime(iowa_sales_df['date'], format='%m/%d/%Y',
unit='us')
# Replace the old 'date' column with the new date column
iowa_sales_df =
iowa_sales_df.set_column(iowa_sales_df.schema.get_field_index('date'), 'date',
date_column)
iceberg_schema = Schema(
NestedField(1, "invoice_item_number", StringType(), required=True),
NestedField(2, "date", TimestampType(), required=True),
NestedField(3, "store_number", LongType(), required=True),
NestedField(4, "store_name", StringType(), required=True),
NestedField(5, "address", StringType(), required=True),
NestedField(6, "city", StringType(), required=True),
NestedField(7, "zip_code", StringType(), required=True),
NestedField(8, "store_location", StringType(), required=True),
NestedField(9, "county_number", LongType(), required=True),
NestedField(10, "county", StringType(), required=True),
NestedField(11, "category", LongType(), required=True),
NestedField(12, "category_name", StringType(), required=True),
NestedField(13, "vendor_number", LongType(), required=True),
NestedField(14, "vendor_name", StringType(), required=True),
NestedField(15, "item_number", StringType(), required=True),
NestedField(16, "item_description", StringType(), required=True),
NestedField(17, "pack", LongType(), required=True),
NestedField(18, "bottle_volume_ml", LongType(), required=True),
NestedField(19, "state_bottle_cost", DoubleType(), required=True),
NestedField(20, "state_bottle_retail", DoubleType(), required=True),
NestedField(21, "bottles_sold", LongType(), required=True),
NestedField(22, "sale_dollars", DoubleType(), required=True),
NestedField(23, "volume_sold_liters", DoubleType(), required=True),
NestedField(24, "volume_sold_gallons", DoubleType(), required=True)
)
from pyiceberg.partitioning import PartitionSpec, PartitionField
from pyiceberg.transforms import DayTransform
PARTITION_FIELD_ID_START = 1000
source_id = iowa_sales_df.schema.get_field_index('date')
partition_spec = PartitionSpec(
PartitionField(
source_id=source_id, # ID of the "date" field in the schema
(0-based index)
field_id=PARTITION_FIELD_ID_START, # Unique ID for the partition
field, starting from 1000
transform=DayTransform(),
name="date_day"
)
)
table = catalog.create_table(
"default.iowa_liquor_sales",
schema=iceberg_schema,
partition_spec=partition_spec,
)
table.append(iowa_sales_df)
len(table.scan().to_arrow())
```
```
{
"name": "ValueError",
"message": "Cannot write to partitioned tables",
"stack":
"---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[17], line 1
----> 1 table.overwrite(iowa_sales_df)
2 # table.append(iowa_sales_df)
3 len(table.scan().to_arrow())
File
~/blackbird/notebooks/.venv/lib/python3.12/site-packages/pyiceberg/table/__init__.py:1094,
in Table.overwrite(self, df, overwrite_filter)
1091 raise NotImplementedError(\"Cannot overwrite a subset of a
table\")
1093 if len(self.spec().fields) > 0:
-> 1094 raise ValueError(\"Cannot write to partitioned tables\")
1096 from pyiceberg.io.pyarrow import schema_to_pyarrow
1098 _check_schema_compatible(self.schema(), other_schema=df.schema)
ValueError: Cannot write to partitioned tables"
}
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
