So bauen Sie mit Apache Spark und PySpark eine Finish-to-Finish-Pipeline für Datentechnik und maschinelles Lernen auf

!pip set up -q pyspark==3.5.1
from pyspark.sql import SparkSession, capabilities as F, Window
from pyspark.sql.varieties import IntegerType, StringType, StructType, StructField, FloatType
from pyspark.ml.function import StringIndexer, VectorAssembler
from pyspark.ml.classification import LogisticRegression
from pyspark.ml.analysis import MulticlassClassificationEvaluator


spark = (SparkSession.builder.appName("ColabSparkAdvancedTutorial")
        .grasp("native(*)")
        .config("spark.sql.shuffle.partitions", "4")
        .getOrCreate())
print("Spark model:", spark.model)


information = (
   (1, "Alice", "IN", "2025-10-01", 56000.0, "premium"),
   (2, "Bob", "US", "2025-10-03", 43000.0, "normal"),
   (3, "Carlos", "IN", "2025-09-27", 72000.0, "premium"),
   (4, "Diana", "UK", "2025-09-30", 39000.0, "normal"),
   (5, "Esha", "IN", "2025-10-02", 85000.0, "premium"),
   (6, "Farid", "AE", "2025-10-02", 31000.0, "primary"),
   (7, "Gita", "IN", "2025-09-29", 46000.0, "normal"),
   (8, "Hassan", "PK", "2025-10-01", 52000.0, "premium"),
)
schema = StructType((
   StructField("id", IntegerType(), False),
   StructField("title", StringType(), True),
   StructField("nation", StringType(), True),
   StructField("signup_date", StringType(), True),
   StructField("revenue", FloatType(), True),
   StructField("plan", StringType(), True),
))
df = spark.createDataFrame(information, schema)
df.present()