📊 PySpark DataFrames for Kids! 🚀

# Step 1: Load the student data from pyspark.sql import SparkSession spark = SparkSession.builder.appName("StudentAnalysis").getOrCreate() df = spark.read.csv("students.csv", header=True, inferSchema=True) # Step 2: See what we have print("Total students:", df.count()) df.show(5) # Show first 5 rows # Step 3: Find top performers (score > 95) top_students = df.filter(df.Score > 95) print("Top performers:", top_students.count()) # Step 4: Calculate average by subject subject_avg = df.groupBy("Subject").avg("Score") subject_avg.show() # Step 5: Find the best Math students best_math = df.filter(df.Subject == "Math") \ .orderBy(df.Score.desc()) \ .limit(10) best_math.show() # Step 6: Create summary report summary = df.groupBy("Grade", "Subject") \ .agg({"Score": "avg", "*": "count"}) \ .orderBy("Grade", "Subject") summary.show()

# Quick start template from pyspark.sql import SparkSession # Create Spark session (like opening your library) spark = SparkSession.builder \ .appName("MyFirstDataFrame") \ .getOrCreate() # Load data (like importing book catalog) df = spark.read.csv("mydata.csv", header=True, inferSchema=True) # Start exploring! df.show() # See your data df.printSchema() # See column types df.describe().show() # Get statistics