def table(self, table): """Returns the provided Spark SQL table as a L{DataFrame} Parameters ---------- table: string The name of the Spark SQL table to turn into a L{DataFrame} Returns ------- Sparkling Pandas DataFrame. """ return DataFrame.from_spark_rdd(self.sql_ctx.table(table), self.sql_ctx)
def table(self, table): """Returns the provided Spark SQL table as a L{DataFrame} Parameters ---------- table: string The name of the Spark SQL table to turn into a L{DataFrame} Returns ------- Sparkling Pandas DataFrame. """ return DataFrame.from_spark_rdd(self.sql_ctx.table(table), self.sql_ctx)
def from_spark_rdd(self, spark_rdd): """ Translates a Spark DataFrame into a Sparkling Pandas Dataframe. Currently, no checking or validation occurs. Parameters ---------- spark_rdd: Spark DataFrame Input Spark DataFrame. Returns ------- Sparkling Pandas DataFrame. """ return DataFrame.from_spark_rdd(spark_rdd, self.sql_ctx)
def sql(self, query): """Perform a SQL query and create a L{DataFrame} of the result. The SQL query is run using Spark SQL. This is not intended for querying arbitrary databases, but rather querying Spark SQL tables. Parameters ---------- query: string The SQL query to pass to Spark SQL to execute. Returns ------- Sparkling Pandas DataFrame. """ return DataFrame.from_spark_rdd(self.sql_ctx.sql(query), self.sql_ctx)
def from_spark_rdd(self, spark_rdd): """ Translates a Spark DataFrame into a Sparkling Pandas Dataframe. Currently, no checking or validation occurs. Parameters ---------- spark_rdd: Spark DataFrame Input Spark DataFrame. Returns ------- Sparkling Pandas DataFrame. """ return DataFrame.from_spark_rdd(spark_rdd, self.sql_ctx)
def sql(self, query): """Perform a SQL query and create a L{DataFrame} of the result. The SQL query is run using Spark SQL. This is not intended for querying arbitrary databases, but rather querying Spark SQL tables. Parameters ---------- query: string The SQL query to pass to Spark SQL to execute. Returns ------- Sparkling Pandas DataFrame. """ return DataFrame.from_spark_rdd(self.sql_ctx.sql(query), self.sql_ctx)