Study index finngen

@dataclass
class StudyIndexFinnGen(StudyIndex):
    """Study index dataset from FinnGen.

    The following information is aggregated/extracted:

    - Study ID in the special format (FINNGEN_R9_*)
    - Trait name (for example, Amoebiasis)
    - Number of cases and controls
    - Link to the summary statistics location

    Some fields are also populated as constants, such as study type and the initial sample size.
    """

    @classmethod
    def get_schema(cls: type[StudyIndexFinnGen]) -> StructType:
        """Provides the schema for the StudyIndexFinnGen dataset.

        This method is a duplication from the parent class, but by definition, the use of abstract methods require that every child class implements them.

        Returns:
            StructType: Spark schema for the StudyIndexFinnGen dataset.
        """
        return parse_spark_schema("studies.json")

    @classmethod
    def from_source(
        cls: type[StudyIndexFinnGen],
        finngen_studies: DataFrame,
        finngen_release_prefix: str,
        finngen_sumstat_url_prefix: str,
        finngen_sumstat_url_suffix: str,
    ) -> StudyIndexFinnGen:
        """This function ingests study level metadata from FinnGen.

        Args:
            finngen_studies (DataFrame): FinnGen raw study table
            finngen_release_prefix (str): Release prefix pattern.
            finngen_sumstat_url_prefix (str): URL prefix for summary statistics location.
            finngen_sumstat_url_suffix (str): URL prefix suffix for summary statistics location.

        Returns:
            StudyIndexFinnGen: Parsed and annotated FinnGen study table.
        """
        return cls(
            _df=finngen_studies.select(
                f.concat(f.lit(f"{finngen_release_prefix}_"), f.col("phenocode")).alias(
                    "studyId"
                ),
                f.col("phenostring").alias("traitFromSource"),
                f.col("num_cases").alias("nCases"),
                f.col("num_controls").alias("nControls"),
                f.lit(finngen_release_prefix).alias("projectId"),
                f.lit("gwas").alias("studyType"),
                f.lit(True).alias("hasSumstats"),
                f.lit("377,277 (210,870 females and 166,407 males)").alias(
                    "initialSampleSize"
                ),
            )
            .withColumn("nSamples", f.col("nCases") + f.col("nControls"))
            .withColumn(
                "summarystatsLocation",
                f.concat(
                    f.lit(finngen_sumstat_url_prefix),
                    f.col("studyId"),
                    f.lit(finngen_sumstat_url_suffix),
                ),
            ),
            _schema=cls.get_schema(),
        )