sws-spark-dissemination-helper 0.0.166__py3-none-any.whl → 0.0.169__py3-none-any.whl

sws_spark_dissemination_helper/SWSBronzeIcebergSparkHelper.py

@@ -158,7 +158,7 @@ class SWSBronzeIcebergSparkHelper:
 
         return dfs_dimension
 
-    def _prepare_element_uom(self) -> DataFrame:
+    def _prepare_element_uom(self) -> Union[DataFrame, None]:
         """Prepare the element and unit of measure join."""
 
         # Get the element DataFrame
@@ -170,23 +170,24 @@ class SWSBronzeIcebergSparkHelper:
             if dimension_column == self.element_column
         )
 
-        # Join the element and the unit_of_measure
-        df_element_uom = (
-            df_element.alias("e")
-            .join(
-                self.df_unit_of_measure.alias("u"),
-                col("e.unit_of_measure") == col("u.id"),
-            )
-            .select(
-                col("e.code").alias("element_code"),
-                col("u.code").alias("unit_of_measure"),
-                col("u.symbol").alias("unit_of_measure_symbol"),
-                col("u.base_unit").alias("unit_of_measure_base_unit"),
-                col("u.multiplier").alias("unit_of_measure_multiplier"),
+        if any("unit_of_measure" == column.lower() for column in df_element.columns):
+            # Join the element and the unit_of_measure
+            df_element_uom = (
+                df_element.alias("e")
+                .join(
+                    self.df_unit_of_measure.alias("u"),
+                    col("e.unit_of_measure") == col("u.id"),
+                )
+                .select(
+                    col("e.code").alias("element_code"),
+                    col("u.code").alias("unit_of_measure"),
+                    col("u.symbol").alias("unit_of_measure_symbol"),
+                    col("u.base_unit").alias("unit_of_measure_base_unit"),
+                    col("u.multiplier").alias("unit_of_measure_multiplier"),
+                )
             )
-        )
 
-        return df_element_uom
+            return df_element_uom
 
     def _gen_denormalized_observation(self) -> DataFrame:
         """Original query upon which the below computation is based
@@ -278,15 +279,16 @@ class SWSBronzeIcebergSparkHelper:
                 .withColumnRenamed("code", dimension_column)
             )
 
-        df_intermediate = (
-            df_intermediate.alias("d")
-            .join(
-                F.broadcast(df_element_uom).alias("e"),
-                col(f"d.{self.element_column}") == col("e.element_code"),
-                "left",
+        if df_element_uom is not None:
+            df_intermediate = (
+                df_intermediate.alias("d")
+                .join(
+                    F.broadcast(df_element_uom).alias("e"),
+                    col(f"d.{self.element_column}") == col("e.element_code"),
+                    "left",
+                )
+                .drop("element_code")
             )
-            .drop("element_code")
-        )
 
         df_obs_denorm = df_intermediate
 
@@ -364,16 +366,17 @@ class SWSBronzeIcebergSparkHelper:
             )
             logging.debug(f"After join count: {df_obs_denorm.count()}")
 
-        df_obs_denorm = (
-            df_obs_denorm.alias("d")
-            .join(
-                F.broadcast(df_element_uom).alias("e"),
-                col(f"d.{self.element_column}") == col("e.element_code"),
-                "left",
+        if df_element_uom is not None:
+            df_obs_denorm = (
+                df_obs_denorm.alias("d")
+                .join(
+                    F.broadcast(df_element_uom).alias("e"),
+                    col(f"d.{self.element_column}") == col("e.element_code"),
+                    "left",
+                )
+                .drop("element_code")
             )
-            .drop("element_code")
-        )
-        logging.debug(f"After uom count: {df_obs_denorm.count()}")
+            logging.debug(f"After uom count: {df_obs_denorm.count()}")
 
         return df_obs_denorm
 
@@ -766,3 +769,29 @@ class SWSBronzeIcebergSparkHelper:
         logging.debug(f"Tag with Added csv Table: {tag}")
 
         logging.info("Bronze Disseminated tag with selection successfully written")
+
+
+1
+frozenset({"8", "4", "2", "5", "9", "1", "7", "6", "0", "3"})
+1
+1
+2
+frozenset({"8", "4", "2", "5", "9", "1", "7", "6", "0", "3"})
+2
+1
+1
+frozenset({"8", "4", "2", "5", "9", "1", "7", "6", "0", "3"})
+1
+1
+2
+frozenset({"8", "4", "2", "5", "9", "1", "7", "6", "0", "3"})
+2
+1
+1
+frozenset({"8", "4", "2", "5", "9", "1", "7", "6", "0", "3"})
+1
+1
+1
+frozenset({"8", "4", "2", "5", "9", "1", "7", "6", "0", "3"})
+1
+1

sws_spark_dissemination_helper/SWSGoldIcebergSparkHelper.py

@@ -296,6 +296,35 @@ class SWSGoldIcebergSparkHelper:
 
         return df
 
+    def write_gold_faostat_unfiltered_data_to_iceberg_and_csv(
+        self, df: DataFrame
+    ) -> DataFrame:
+        """The expected input to this function is the output of the sws disseminated function"""
+        df.writeTo(
+            self.iceberg_tables.GOLD_FAOSTAT_UNFILTERED.iceberg_id
+        ).createOrReplace()
+
+        logging.info(
+            f"Gold FAOSTAT unfiltered table written to {self.iceberg_tables.GOLD_FAOSTAT.iceberg_id}"
+        )
+
+        self.spark.sql(
+            f"ALTER TABLE {self.iceberg_tables.GOLD_FAOSTAT_UNFILTERED.iceberg_id} CREATE OR REPLACE TAG `{self.tag_name}`"
+        )
+
+        logging.info(f"gold FAOSTAT unfiltered tag '{self.tag_name}' created")
+
+        df_1 = df.coalesce(1)
+
+        save_cache_csv(
+            df=df_1,
+            bucket=self.bucket,
+            prefix=self.iceberg_tables.GOLD_FAOSTAT_UNFILTERED.csv_prefix,
+            tag_name=self.tag_name,
+        )
+
+        return df
+
     def write_gold_sws_validated_sws_dissemination_tag(
         self, df: DataFrame, tags: Tags
     ) -> DataFrame:
@@ -589,3 +618,52 @@ class SWSGoldIcebergSparkHelper:
         logging.debug(f"Tag with Added csv Table: {tag}")
 
         return df
+
+    def write_gold_faostat_unfiltered_dissemination_tag(
+        self, df: DataFrame, tags: Tags
+    ) -> DataFrame:
+        # Get or create a new tag
+        tag = get_or_create_tag(tags, self.dataset_id, self.tag_name, self.tag_name)
+        logging.debug(f"Tag: {tag}")
+
+        new_iceberg_table = BaseDisseminatedTagTable(
+            id=f"{self.domain_code.lower()}_gold_faostat_unfiltered_iceberg",
+            name=f"{self.domain_code} gold FAOSTAT unfiltered Iceberg",
+            description="Gold table containing all the tag data in FAOSTAT format",
+            layer=TableLayer.GOLD,
+            private=True,
+            type=TableType.ICEBERG,
+            database=IcebergDatabases.GOLD_DATABASE,
+            table=self.iceberg_tables.GOLD_FAOSTAT_UNFILTERED.table,
+            path=self.iceberg_tables.GOLD_FAOSTAT_UNFILTERED.path,
+            structure={"columns": df.schema.jsonValue()["fields"]},
+        )
+        tag = upsert_disseminated_table(
+            sws_tags=tags,
+            tag=tag,
+            dataset_id=self.dataset_id,
+            tag_name=self.tag_name,
+            table=new_iceberg_table,
+        )
+        logging.debug(f"Tag with Added Iceberg Table: {tag}")
+
+        new_diss_table = BaseDisseminatedTagTable(
+            id=f"{self.domain_code.lower()}_gold_faostat_unfiltered_csv",
+            name=f"{self.domain_code} gold FAOSTAT unfiltered csv",
+            description="Gold table containing the tag data in FAOSTAT format in csv",
+            layer=TableLayer.GOLD,
+            private=True,
+            type=TableType.CSV,
+            path=self.iceberg_tables.GOLD_FAOSTAT_UNFILTERED.csv_path,
+            structure={"columns": df.schema.jsonValue()["fields"]},
+        )
+        tag = upsert_disseminated_table(
+            sws_tags=tags,
+            tag=tag,
+            dataset_id=self.dataset_id,
+            tag_name=self.tag_name,
+            table=new_diss_table,
+        )
+        logging.debug(f"Tag with Added csv Table: {tag}")
+
+        return df

sws_spark_dissemination_helper/constants.py

@@ -254,37 +254,37 @@ class IcebergTables:
         self.__tag_name = tag_name
 
         # TODO Fix later with a more appropriate DATABASE
-        self.DENORMALIZED_OBSERVATION = self._create_iceberg_table("BRONZE", suffix="denormalized_observation")
-        self.DENORMALIZED_METADATA = self._create_iceberg_table("BRONZE", suffix="denormalized_metadata")
-        self.GROUPED_METADATA = self._create_iceberg_table("BRONZE", suffix="grouped_metadata")
-        self.TABLE = self._create_iceberg_table("BRONZE")
-        self.TABLE_FILTERED = self._create_iceberg_table("BRONZE", suffix="filtered")
-        self.BRONZE = self._create_iceberg_table("BRONZE")
-        self.BRONZE_DISS_TAG = self._create_iceberg_table("BRONZE", suffix="diss_tag")
-        self.SILVER = self._create_iceberg_table("SILVER", prefix=domain)
+        self.DENORMALIZED_OBSERVATION = self.create_iceberg_table("BRONZE", suffix="denormalized_observation")
+        self.DENORMALIZED_METADATA = self.create_iceberg_table("BRONZE", suffix="denormalized_metadata")
+        self.GROUPED_METADATA = self.create_iceberg_table("BRONZE", suffix="grouped_metadata")
+        self.TABLE = self.create_iceberg_table("BRONZE")
+        self.TABLE_FILTERED = self.create_iceberg_table("BRONZE", suffix="filtered")
+        self.BRONZE = self.create_iceberg_table("BRONZE")
+        self.BRONZE_DISS_TAG = self.create_iceberg_table("BRONZE", suffix="diss_tag")
+        self.SILVER = self.create_iceberg_table("SILVER", prefix=domain)
 
         # GOLD tables with specific suffixes
-        self.GOLD_SWS = self._create_iceberg_table("GOLD", prefix=domain, suffix="sws")
-        self.GOLD_SDMX = self._create_iceberg_table(
+        self.GOLD_SWS = self.create_iceberg_table("GOLD", prefix=domain, suffix="sws")
+        self.GOLD_SDMX = self.create_iceberg_table(
             "GOLD", prefix=domain, suffix="sdmx_disseminated"
         )
-        self.GOLD_SWS_VALIDATED = self._create_iceberg_table(
+        self.GOLD_SWS_VALIDATED = self.create_iceberg_table(
             "GOLD", prefix=domain, suffix="sws_validated"
         )
-        self.GOLD_SWS_DISSEMINATED = self._create_iceberg_table(
+        self.GOLD_SWS_DISSEMINATED = self.create_iceberg_table(
             "GOLD", prefix=domain, suffix="sws_disseminated"
         )
-        self.GOLD_PRE_SDMX = self._create_iceberg_table(
+        self.GOLD_PRE_SDMX = self.create_iceberg_table(
             "GOLD", prefix=domain, suffix="pre_sdmx"
         )
-        self.GOLD_FAOSTAT = self._create_iceberg_table(
+        self.GOLD_FAOSTAT = self.create_iceberg_table(
             "GOLD", prefix=domain, suffix="faostat"
         )
-        self.GOLD_FAOSTAT_UNFILTERED = self._create_iceberg_table(
+        self.GOLD_FAOSTAT_UNFILTERED = self.create_iceberg_table(
             "GOLD", prefix=domain, suffix="faostat_unfiltered"
         )
 
-    def _create_iceberg_table(
+    def create_iceberg_table(
         self, level: str, prefix: str = "", suffix: str = ""
     ) -> IcebergTable:
         database = getattr(IcebergDatabases, f"{level}_DATABASE")

{sws_spark_dissemination_helper-0.0.166.dist-info → sws_spark_dissemination_helper-0.0.169.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sws-spark-dissemination-helper
-Version: 0.0.166
+Version: 0.0.169
 Summary: A Python helper package providing streamlined Spark functions for efficient data dissemination processes
 Project-URL: Repository, https://github.com/un-fao/fao-sws-it-python-spark-dissemination-helper
 Author-email: Daniele Mansillo <danielemansillo@gmail.com>

{sws_spark_dissemination_helper-0.0.166.dist-info → sws_spark_dissemination_helper-0.0.169.dist-info}/RECORD

@@ -1,13 +1,13 @@
-sws_spark_dissemination_helper/SWSBronzeIcebergSparkHelper.py,sha256=ocuau0WtpyRwui0qwdQ_Rxh4nYPOyZoHpGKaWRa6B3Q,28868
+sws_spark_dissemination_helper/SWSBronzeIcebergSparkHelper.py,sha256=N0eQ2LXtpPeZQCWYi85sMLmpXRzLA2erECiba8tqOAY,29595
 sws_spark_dissemination_helper/SWSDatatablesExportHelper.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sws_spark_dissemination_helper/SWSEasyIcebergSparkHelper.py,sha256=csqKyYglBkJSBvEkEa1_keHarZZAIJHaV0d64gGJy98,26379
-sws_spark_dissemination_helper/SWSGoldIcebergSparkHelper.py,sha256=USEIiPZuPcKxzJdesz-N3PsBSEPpkGk8aavDNUPmb80,22092
+sws_spark_dissemination_helper/SWSGoldIcebergSparkHelper.py,sha256=0dxbVkrhdaASapEffF5PFcgKwAMyJoWBxzgymjZ4JyY,25049
 sws_spark_dissemination_helper/SWSPostgresSparkReader.py,sha256=KpG8gp8Ai9pHDiKhUOTcXWxxmFGeKEE3XKlI_Y-SveU,18453
 sws_spark_dissemination_helper/SWSSilverIcebergSparkHelper.py,sha256=qioLv3SlJEfk0LzTiwfXRtZXVImPOJUeh9k1XwHC-pA,26225
 sws_spark_dissemination_helper/__init__.py,sha256=42TPbk7KxAud_qY3Sr_F4F7VjyofUlxEJkUXAFQsjRo,327
-sws_spark_dissemination_helper/constants.py,sha256=zviO6huxWTWonHv4v2M8zKr7HXCDMBGqjHx-eTfGT2A,13487
+sws_spark_dissemination_helper/constants.py,sha256=vQmalAqInwPAybgJOfYx99jn47KsKp8jeD8eqmjw-Rs,13471
 sws_spark_dissemination_helper/utils.py,sha256=G7lQqNRrvqZpgm9WmddD7fWsI8IVn09x1p3cV3458EA,21963
-sws_spark_dissemination_helper-0.0.166.dist-info/METADATA,sha256=tseBASNGGEO46T902JN85SquzCKuVrlILT4W5iPU9Ws,2824
-sws_spark_dissemination_helper-0.0.166.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-sws_spark_dissemination_helper-0.0.166.dist-info/licenses/LICENSE,sha256=zFzeb_j_6pXEHwH8Z0OpIkKFJk7vmhZjdem-K0d4zU4,1073
-sws_spark_dissemination_helper-0.0.166.dist-info/RECORD,,
+sws_spark_dissemination_helper-0.0.169.dist-info/METADATA,sha256=1gUttuBzd1iSvoe2zEdyGFjk2ZuXPS5IXqQjuv0dAWQ,2824
+sws_spark_dissemination_helper-0.0.169.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+sws_spark_dissemination_helper-0.0.169.dist-info/licenses/LICENSE,sha256=zFzeb_j_6pXEHwH8Z0OpIkKFJk7vmhZjdem-K0d4zU4,1073
+sws_spark_dissemination_helper-0.0.169.dist-info/RECORD,,