Merge b471f2179a into bc3598b1cd

[spark/en] Spark Tutorial

qsharp.html.markdown

@@ -4,6 +4,7 @@ contributors:
     - ["Vincent van Wingerden", "https://github.com/vivanwin"]
     - ["Mariia Mykhailova", "https://github.com/tcNickolas"]
     - ["Andrew Ryan Davis", "https://github.com/AndrewDavis1191"]
+    - ["Alex Hansen", "https://github.com/sezna"]
 filename: LearnQSharp.qs
 ---
 
@@ -19,13 +20,14 @@ Q# is a high-level domain-specific language which enables developers to write qu
 // The most important part of quantum programs is qubits.
 // In Q# type Qubit represents the qubits which can be used.
 // This will allocate an array of two new qubits as the variable qs.
-using (qs = Qubit[2]) {
+operation QuantumDataTypes() : Unit {
+    use qs = Qubit[2];
 
     // The qubits have internal state that you cannot access to read or modify directly.
     // You can inspect the current state of your quantum program
     // if you're running it on a classical simulator.
     // Note that this will not work on actual quantum hardware!
-    DumpMachine();
+    Std.Diagnostics.DumpMachine();
 
     // If you want to change the state of a qubit
     // you have to do this by applying quantum gates to the qubit.
@@ -58,97 +60,102 @@ using (qs = Qubit[2]) {
 /////////////////////////////////////
 // 2. Classical data types and operators
 
-// Numbers in Q# can be stored in Int, BigInt or Double.
-let i = 1;            // This defines an Int variable i equal to 1
-let bi = 1L;          // This defines a BigInt variable bi equal to 1
-let d = 1.0;          // This defines a Double variable d equal to 1
+function ClassicalDataTypes() : Unit {
+    // Numbers in Q# can be stored in Int, BigInt or Double.
+    let i = 1;            // This defines an Int variable i equal to 1
+    let bi = 1L;          // This defines a BigInt variable bi equal to 1
+    let d = 1.0;          // This defines a Double variable d equal to 1
 
-// Arithmetic is done as expected, as long as the types are the same
-let n = 2 * 10;                // = 20
-// Q# does not have implicit type cast, 
-// so to perform arithmetic on values of different types, 
-// you need to cast type explicitly
-let nd = IntAsDouble(2) * 1.0; // = 20.0
+    // Arithmetic is done as expected, as long as the types are the same
+    let n = 2 * 10;                // = 20
+    // Q# does not have implicit type cast,
+    // so to perform arithmetic on values of different types,
+    // you need to cast type explicitly
+    let nd = Std.Convert.IntAsDouble(2) * 1.0; // = 20.0
 
-// Boolean type is called Bool
-let trueBool = true;
-let falseBool = false;
+    // Boolean type is called Bool
+    let trueBool = true;
+    let falseBool = false;
 
-// Logic operators work as expected
-let andBool = true and false;
-let orBool = true or false;
-let notBool = not false;
+    // Logic operators work as expected
+    let andBool = true and false;
+    let orBool = true or false;
+    let notBool = not false;
 
-// Strings
-let str = "Hello World!";
+    // Strings
+    let str = "Hello World!";
 
-// Equality is ==
-let x = 10 == 15; // is false
+    // Equality is ==
+    let x = 10 == 15; // is false
 
-// Range is a sequence of integers and can be defined like: start..step..stop
-let xi = 1..2..7; // Gives the sequence 1,3,5,7
+    // Range is a sequence of integers and can be defined like: start..step..stop
+    let xi = 1..2..7; // Gives the sequence 1,3,5,7
 
-// Assigning new value to a variable:
-// by default all Q# variables are immutable;
-// if the variable was defined using let, you cannot reassign its value.
+    // Assigning new value to a variable:
+    // by default all Q# variables are immutable;
+    // if the variable was defined using let, you cannot reassign its value.
 
-// When you want to make a variable mutable, you have to declare it as such, 
-// and use the set word to update value
-mutable xii = true;
-set xii = false;
+    // When you want to make a variable mutable, you have to declare it as such,
+    // and use the set word to update value
+    mutable xii = true;
+    set xii = false;
 
-// You can create an array for any data type like this
-let xiii = new Double[10];
+    // You can create an array for any data type like this
+    let xiii = [0.0, size = 10];
 
-// Getting an element from an array 
-let xiv = xiii[8];
+    // Getting an element from an array
+    let xiv = xiii[8];
 
-// Assigning a new value to an array element
-mutable xv = new Double[10];
-set xv w/= 5 <- 1;
+    // Assigning a new value to an array element
+    mutable xv = [0.0, size = 10];
+    set xv w/= 5 <- 1.0;
+}
 
 
 /////////////////////////////////////
 // 3. Control flow
 
-// If structures work a little different than most languages
-if (a == 1) {
+operation ControlFlow() : Unit {
+    let a = 1;
+    // If expressions support a true branch, elif, and else.
+    if (a == 1) {
         // ...
-} elif (a == 2) {
+    } elif (a == 2) {
         // ...
-} else {
+    } else {
         // ...
-}
+    }
+    use qubits = Qubit[2];
 
-// Foreach loops can be used to iterate over an array
-for (qubit in qubits) {
+    // For loops can be used to iterate over an array
+    for qubit in qubits {
         X(qubit);
-}
+    }
 
-// Regular for loops can be used to iterate over a range of numbers
-for (index in 0 .. Length(qubits) - 1) {
+    // Regular for loops can be used to iterate over a range of numbers
+    for index in 0..Length(qubits) - 1 {
         X(qubits[index]);
-}
+    }
 
-// While loops are restricted for use in classical context only
-mutable index = 0;
-while (index < 10) {
+    // While loops are restricted for use in classical context only
+    mutable index = 0;
+    while (index < 10) {
         set index += 1;
-}
+    }
 
-// Quantum equivalent of a while loop is a repeat-until-success loop.
-// Because of the probabilistic nature of quantum computing sometimes
-// you want to repeat a certain sequence of operations 
-// until a specific condition is achieved; you can use this loop to express this.
-repeat {
+    let success_criteria = true;
+    // Quantum equivalent of a while loop is a repeat-until-success loop.
+    // Because of the probabilistic nature of quantum computing sometimes
+    // you want to repeat a certain sequence of operations
+    // until a specific condition is achieved; you can use this loop to express this.
+    repeat {
         // Your operation here
-}
-until (success criteria) // This could be a measurement to check if the state is reached
-fixup {
+    } until (success_criteria) // This could be a measurement to check if the state is reached
+    fixup {
         // Resetting to the initial conditions, if required
+    }
 }
 
-
 /////////////////////////////////////
 // 4. Putting it all together
 
@@ -161,7 +168,7 @@ operation ApplyXGate(source : Qubit) : Unit {
 // adjoint and controlled variants of it.
 // The easiest way to do that is to add "is Adj + Ctl" after Unit.
 // This will tell the compiler to generate the variants automatically.
-operation ApplyXGateCA (source : Qubit) : Unit is Adj + Ctl {
+operation ApplyXGateCA(source : Qubit) : Unit is Adj + Ctl {
     X(source);
 }
 
@@ -169,20 +176,21 @@ operation ApplyXGateCA (source : Qubit) : Unit is Adj + Ctl {
 
 
 // To run Q# code, you can put @EntryPoint() before the operation you want to run first
-@EntryPoint()
 operation XGateDemo() : Unit {
-    using (q = Qubit()) {
+    use q = Qubit();
     ApplyXGate(q);
-    }
 }
 
 // Here is a simple example: a quantum random number generator.
 // We will generate a classical array of random bits using quantum code.
-@EntryPoint()
-operation QRNGDemo() : Unit {
-    mutable bits = new Int[5];                // Array we'll use to store bits
-    using (q = Qubit()) {                     // Allocate a qubit
-        for (i in 0 .. 4) {                   // Generate each bit independently
+// Callables (functions or operations) named `Main` are used as entry points.
+operation Main() : Unit {
+    mutable bits = [0, size = 5];                // Array we'll use to store bits
+    use q  = Qubit();
+    {
+        // Allocate a qubit
+        for i in 0..4 {
+            // Generate each bit independently
             H(q);                             // Hadamard gate sets equal superposition
             let result = M(q);                // Measure qubit gets 0|1 with 50/50 prob
             let bit = result == Zero ? 0 | 1; // Convert measurement result to integer
@@ -196,9 +204,6 @@ operation QRNGDemo() : Unit {
 
 ## Further Reading
 
-The [Quantum Katas][1] offer great self-paced tutorials and programming exercises to learn quantum computing and Q#. 
+The Quantum Katas ([repo](https://github.com/microsoft/qsharp/tree/main/katas) [hosted tutorials](https://quantum.microsoft.com/en-us/tools/quantum-katas) offer great self-paced tutorials and programming exercises to learn quantum computing and Q#. 
 
-[Q# Documentation][2] is official Q# documentation, including language reference and user guides.
-
-[1]: https://github.com/microsoft/QuantumKatas
-[2]: https://docs.microsoft.com/quantum/
+[Q# Documentation](https://docs.microsoft.com/quantum/) is official Q# documentation, including language reference and user guides.

spark.html.markdown

@@ -0,0 +1,106 @@
+---
+language: Spark
+category: tool
+tool: Spark
+filename: learnspark-en.spark
+contributors:
+    - ["Scronge", "https://github.com/Scronge"]
+---
+
+[Spark](https://spark.apache.org/) is an open-source distributed data processing framework that enables large-scale data processing across clusters. This guide covers the basics of **Apache Spark** using PySpark, the Python API.
+
+```python
+# Setting Up Spark
+from pyspark.sql import SparkSession
+
+spark = SparkSession.builder \
+    .appName("RealWorldExampleApp") \
+    .getOrCreate()
+
+# Working with Larger DataFrames
+# Sample data for a retail dataset with multiple columns for complex queries
+data = [
+    ("Alice", "Electronics", 30, 200),
+    ("Bob", "Clothing", 40, 150),
+    ("Carol", "Electronics", 25, 300),
+    ("Dave", "Home Goods", 35, 100),
+    ("Eve", "Clothing", 28, 80),
+    ("Frank", "Home Goods", 40, 120)
+]
+columns = ["Name", "Category", "Age", "PurchaseAmount"]
+
+df = spark.createDataFrame(data, columns)
+df.show()
+# +-----+-----------+---+--------------+
+# | Name|   Category|Age|PurchaseAmount|
+# +-----+-----------+---+--------------+
+# |Alice|Electronics| 30|           200|
+# |  Bob|   Clothing| 40|           150|
+# |Carol|Electronics| 25|           300|
+# | Dave| Home Goods| 35|           100|
+# |  Eve|   Clothing| 28|            80|
+# |Frank| Home Goods| 40|           120|
+# +-----+-----------+---+--------------+
+
+# Transformations and Actions
+
+# Filtering data to select customers over 30 with purchases above $100
+filtered_df = df.filter((df.Age > 30) & (df.PurchaseAmount > 100))
+filtered_df.show()
+# +-----+-----------+---+--------------+
+# | Name|   Category|Age|PurchaseAmount|
+# +-----+-----------+---+--------------+
+# |  Bob|   Clothing| 40|           150|
+# |Frank| Home Goods| 40|           120|
+# +-----+-----------+---+--------------+
+
+# Grouping and Aggregations
+# Calculate total purchases by category
+category_totals = df.groupBy("Category").sum("PurchaseAmount")
+category_totals.show()
+# +-----------+------------------+
+# |   Category|sum(PurchaseAmount)|
+# +-----------+------------------+
+# |Electronics|               500|
+# |   Clothing|               230|
+# | Home Goods|               220|
+# +-----------+------------------+
+
+# SQL Queries
+
+# Registering DataFrame as a SQL temporary view
+df.createOrReplaceTempView("customers")
+high_spenders = spark.sql("SELECT Name, Category, PurchaseAmount FROM customers WHERE PurchaseAmount > 100")
+high_spenders.show()
+# +-----+-----------+--------------+
+# | Name|   Category|PurchaseAmount|
+# +-----+-----------+--------------+
+# |Alice|Electronics|           200|
+# |  Bob|   Clothing|           150|
+# |Carol|Electronics|           300|
+# |Frank| Home Goods|           120|
+# +-----+-----------+--------------+
+
+# Reading and Writing Files
+
+# Reading from CSV with additional options
+csv_df = spark.read.csv("path/to/large_retail_data.csv", header=True, inferSchema=True, sep=",")
+csv_df.show(5)  # Display only first 5 rows for preview
+
+# Writing DataFrame to Parquet format for optimized storage and access
+df.write.parquet("output/retail_data")
+
+# RDD Basics
+
+# Creating an RDD and performing complex transformations
+sales_data = [(1, 100), (2, 150), (3, 200), (4, 250)]
+rdd = spark.sparkContext.parallelize(sales_data)
+
+# Transformations to calculate discounts for each sale
+discounted_sales_rdd = rdd.map(lambda x: (x[0], x[1] * 0.9))
+print(discounted_sales_rdd.collect())
+# Output: [(1, 90.0), (2, 135.0), (3, 180.0), (4, 225.0)]
+
+# Ending the Spark Session
+
+spark.stop()