Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://docs.databricks.com/aws/en/getting-started/data-pipeline-get-started below:

Tutorial: Build an ETL pipeline with Lakeflow Declarative Pipelines

import dlt
from pyspark.sql.functions import *
from pyspark.sql.types import DoubleType, IntegerType, StringType, StructType, StructField


file_path = f"/databricks-datasets/songs/data-001/"


schema = StructType(
  [
    StructField("artist_id", StringType(), True),
    StructField("artist_lat", DoubleType(), True),
    StructField("artist_long", DoubleType(), True),
    StructField("artist_location", StringType(), True),
    StructField("artist_name", StringType(), True),
    StructField("duration", DoubleType(), True),
    StructField("end_of_fade_in", DoubleType(), True),
    StructField("key", IntegerType(), True),
    StructField("key_confidence", DoubleType(), True),
    StructField("loudness", DoubleType(), True),
    StructField("release", StringType(), True),
    StructField("song_hotnes", DoubleType(), True),
    StructField("song_id", StringType(), True),
    StructField("start_of_fade_out", DoubleType(), True),
    StructField("tempo", DoubleType(), True),
    StructField("time_signature", DoubleType(), True),
    StructField("time_signature_confidence", DoubleType(), True),
    StructField("title", StringType(), True),
    StructField("year", IntegerType(), True),
    StructField("partial_sequence", IntegerType(), True)
  ]
)

@dlt.table(
  comment="Raw data from a subset of the Million Song Dataset; a collection of features and metadata for contemporary music tracks."
)
def songs_raw():
  return (spark.readStream
    .format("cloudFiles")
    .schema(schema)
    .option("cloudFiles.format", "csv")
    .option("sep","\t")
    .load(file_path))


@dlt.table(
  comment="Million Song Dataset with data cleaned and prepared for analysis."
)
@dlt.expect("valid_artist_name", "artist_name IS NOT NULL")
@dlt.expect("valid_title", "song_title IS NOT NULL")
@dlt.expect("valid_duration", "duration > 0")
def songs_prepared():
  return (
    spark.read.table("songs_raw")
      .withColumnRenamed("title", "song_title")
      .select("artist_id", "artist_name", "duration", "release", "tempo", "time_signature", "song_title", "year")
  )


@dlt.table(
  comment="A table summarizing counts of songs released by the artists who released the most songs each year."
)
def top_artists_by_year():
  return (
    spark.read.table("songs_prepared")
      .filter(expr("year > 0"))
      .groupBy("artist_name", "year")
      .count().withColumnRenamed("count", "total_number_of_songs")
      .sort(desc("total_number_of_songs"), desc("year"))
  )

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4