getting started samples for Rservices added

Author: negust-microsoft

samples/features/r-services/gettingstarted/customerclustering/CustomerClustering.R

@@ -0,0 +1,86 @@
+
+# Input Query
+input_query <- "
+	SELECT
+  ss_customer_sk AS customer,
+  round(CASE WHEN ((orders_count = 0) OR (returns_count IS NULL) OR (orders_count IS NULL) OR ((returns_count / orders_count) IS NULL) ) THEN 0.0 ELSE (cast(returns_count as nchar(10)) / orders_count) END, 7) AS orderRatio,
+  round(CASE WHEN ((orders_items = 0) OR(returns_items IS NULL) OR (orders_items IS NULL) OR ((returns_items / orders_items) IS NULL) ) THEN 0.0 ELSE (cast(returns_items as nchar(10)) / orders_items) END, 7) AS itemsRatio,
+  round(CASE WHEN ((orders_money = 0) OR (returns_money IS NULL) OR (orders_money IS NULL) OR ((returns_money / orders_money) IS NULL) ) THEN 0.0 ELSE (cast(returns_money as nchar(10)) / orders_money) END, 7) AS monetaryRatio,
+  round(CASE WHEN ( returns_count IS NULL                                                                        ) THEN 0.0 ELSE  returns_count                 END, 0) AS frequency
+ 
+FROM
+  (
+    SELECT
+      ss_customer_sk, 
+      -- return order ratio
+      COUNT(distinct(ss_ticket_number)) AS orders_count,
+      -- return ss_item_sk ratio
+      COUNT(ss_item_sk) AS orders_items,
+      -- return monetary amount ratio
+      SUM( ss_net_paid ) AS orders_money
+    FROM store_sales s
+    GROUP BY ss_customer_sk
+  ) orders
+  LEFT OUTER JOIN
+  (
+    SELECT
+      sr_customer_sk,
+      -- return order ratio
+      count(distinct(sr_ticket_number)) as returns_count,
+      -- return ss_item_sk ratio
+      COUNT(sr_item_sk) as returns_items,
+      -- return monetary amount ratio
+      SUM( sr_return_amt ) AS returns_money
+    FROM store_returns
+    GROUP BY sr_customer_sk
+  ) returned ON ss_customer_sk=sr_customer_sk 
+"
+
+# Define the connection string
+connStr <- paste("Driver=SQL Server;Server=", "NELLIELAPTOP", ";Database=", "tpcx1b", ";Trusted_Connection=true;", sep = "");
+
+# Input customer data that needs to be classified
+customer_returns <- RxSqlServerData(sqlQuery = input_query,
+                                        colClasses = c(customer = "numeric", orderRatio = "numeric", itemsRatio = "numeric", monetaryRatio = "numeric", frequency = "numeric"),
+                                    connectionString = connStr);
+
+
+# Transform the data from an input dataset to an output dataset
+customer_data <- rxDataStep(customer_returns);
+#Look at the data we just loaded from SQL Server
+head(customer_data, n = 5);
+
+# Determine number of clusters
+#Using a plot of the within groups sum of squares by number of clusters extracted can help determine the appropriate number of clusters.
+#We are looking for a bend in the plot. It is at this "elbow" in the plot that we have the appropriate number of clusters 
+wss <- (nrow(customer_data) - 1) * sum(apply(customer_data, 2, var))
+for (i in 2:20) { 
+xt = kmeans(customer_data, centers = i)
+    print(xt$ifault)
+wss[i] <- sum(kms = kmeans(customer_data, centers = i)$withinss)
+    }
+plot(1:20, wss, type = "b", xlab = "Number of Clusters", ylab = "Within groups sum of squares")
+
+# Output table to hold the customer group mappings
+return_cluster = RxSqlServerData(table = "return_cluster", connectionString = connStr);
+
+# Set.seed for random number generator for predicatability
+set.seed(10);
+
+# Generate clusters using rxKmeans and output key / cluster to a table in SQL Server called return_cluster
+clust <- rxKmeans( ~ orderRatio + itemsRatio + monetaryRatio + frequency, customer_returns, numClusters = 4
+                    , outFile = return_cluster, outColName = "cluster", extraVarsToWrite = c("customer"), overwrite = TRUE);
+
+# Read the custome returns cluster table
+customer_cluster <- rxDataStep(return_cluster);
+
+#Plot the clusters (need to install library "cluster")
+#install.packages("cluster")
+library("cluster");
+clusplot(customer_data, customer_cluster$cluster, color=TRUE, shade=TRUE, labels=4, lines=0, plotchar = TRUE);
+
+#Look at the clustering details and analyze results
+clust
+
+
+

samples/features/r-services/gettingstarted/customerclustering/CustomerClustering.sql

@@ -0,0 +1,102 @@
+USE [tpcx1b]
+
+DROP PROC IF EXISTS generate_customer_return_clusters;
+GO
+CREATE procedure [dbo].[generate_customer_return_clusters]
+AS
+/* 
+  This procedure uses R to classify customers into different groups based on their
+  purchase & return history.
+*/
+BEGIN
+	DECLARE @duration FLOAT
+	, @predict_duration FLOAT
+	, @instance_name NVARCHAR(100) = @@SERVERNAME
+	, @database_name NVARCHAR(128) = db_name()
+
+-- Input query to generate the purchase history & return metrics
+	, @input_query NVARCHAR(MAX) = N'
+SELECT
+  ss_customer_sk AS customer,
+  round(CASE WHEN ((orders_count = 0) OR (returns_count IS NULL) OR (orders_count IS NULL) OR ((returns_count / orders_count) IS NULL) ) THEN 0.0 ELSE (cast(returns_count as nchar(10)) / orders_count) END, 7) AS orderRatio,
+  round(CASE WHEN ((orders_items = 0) OR(returns_items IS NULL) OR (orders_items IS NULL) OR ((returns_items / orders_items) IS NULL) ) THEN 0.0 ELSE (cast(returns_items as nchar(10)) / orders_items) END, 7) AS itemsRatio,
+  round(CASE WHEN ((orders_money = 0) OR (returns_money IS NULL) OR (orders_money IS NULL) OR ((returns_money / orders_money) IS NULL) ) THEN 0.0 ELSE (cast(returns_money as nchar(10)) / orders_money) END, 7) AS monetaryRatio,
+  round(CASE WHEN ( returns_count IS NULL                                                                        ) THEN 0.0 ELSE  returns_count                 END, 0) AS frequency
+  
+FROM
+  (
+    SELECT
+      ss_customer_sk,
+      -- return order ratio
+      COUNT(distinct(ss_ticket_number)) AS orders_count,
+      -- return ss_item_sk ratio
+      COUNT(ss_item_sk) AS orders_items,
+      -- return monetary amount ratio
+      SUM( ss_net_paid ) AS orders_money
+    FROM store_sales s
+    GROUP BY ss_customer_sk
+  ) orders
+  LEFT OUTER JOIN
+  (
+    SELECT
+      sr_customer_sk,
+      -- return order ratio
+      count(distinct(sr_ticket_number)) as returns_count,
+      -- return ss_item_sk ratio
+      COUNT(sr_item_sk) as returns_items,
+      -- return monetary amount ratio
+      SUM( sr_return_amt ) AS returns_money
+    FROM store_returns
+    GROUP BY sr_customer_sk
+  ) returned ON ss_customer_sk=sr_customer_sk 
+ '
+
+EXEC sp_execute_external_script
+	  @language = N'R'
+	, @script = N'
+# Define the connection string
+connStr <- paste("Driver=SQL Server;Server=", instance_name, ";Database=", database_name, ";Trusted_Connection=true;", sep="");
+
+
+# Input customer data that needs to be classified. This is the result we get from our query
+customer_returns <- RxSqlServerData(sqlQuery = input_query,
+									colClasses = c(customer = "numeric", orderRatio = "numeric", itemsRatio = "numeric", monetaryRatio = "numeric", frequency = "numeric"),
+									connectionString = connStr);
+
+# Output table to hold the customer cluster mappings
+return_cluster = RxSqlServerData(table = "customer_return_clusters", connectionString = connStr);
+
+# set.seed for random number generator for predicatability
+set.seed(10);
+
+# generate clusters using rxKmeans and output clusters to a table called "customer_return_clusters". 
+clust <- rxKmeans( ~ orderRatio + itemsRatio + monetaryRatio + frequency, customer_returns, numClusters = 4
+                    , outFile = return_cluster, outColName = "cluster", writeModelVars = TRUE , extraVarsToWrite = c("customer"), overwrite = TRUE);
+'
+	, @input_data_1 = N''
+	, @params = N'@instance_name nvarchar(100), @database_name nvarchar(128), @input_query nvarchar(max), @duration float OUTPUT'
+	, @instance_name = @instance_name
+	, @database_name = @database_name
+	, @input_query = @input_query
+	, @duration = @duration OUTPUT;
+END;
+
+GO
+
+
+--Empty table of the results before running the stored procedure
+TRUNCATE TABLE customer_return_clusters;
+
+--Execute the clustering. This will load the table customer_return_clusters with cluster mappings
+EXEC [dbo].[generate_customer_return_clusters];
+
+--Now select data from table customer_return_clusters to verify that the clustering data was loaded
+SELECT * FROM customer_return_clusters;
+
+--Select email addresses of customers in cluster 1
+SELECT customer.[c_email_address], customer.c_customer_sk
+  FROM dbo.customer
+  JOIN 
+  [dbo].[customer_return_clusters] as r
+  ON r.customer = customer.c_customer_sk
+  WHERE r.cluster = 1

samples/features/r-services/gettingstarted/predictivemodel/PredictiveModel.R

@@ -0,0 +1,54 @@
+#Connection string to connect to SQL Server
+connStr <- paste("Driver=SQL Server; Server=", "MyServer",
+                 ";Database=", "tutorialdb", ";Trusted_Connection=true;", sep = "");
+
+#Get the data from SQL Server Table
+SQL_rentaldata <- RxSqlServerData(table = "dbo.rental_data",
+                              connectionString = connStr, returnDataFrame = TRUE);
+
+#Import the data into a data frame
+rentaldata <- rxImport(SQL_rentaldata);
+
+#Let's see the structure of the data and the top rows
+head(rentaldata);
+str(rentaldata);
+
+#Changing the three factor columns to factor types
+#This helps when building the model because we are explicitly saying that these values are categorical
+rentaldata$Holiday <- factor(rentaldata$Holiday);
+rentaldata$Snow <- factor(rentaldata$Snow);
+rentaldata$WeekDay <- factor(rentaldata$WeekDay);
+
+#Visualize the dataset after the change
+str(rentaldata);
+
+#Now let's split the dataset into 2 different sets
+#One set for training the model and the other for validating it
+train_data = rentaldata[rentaldata$Year < 2015,];
+test_data = rentaldata[rentaldata$Year == 2015,];
+
+#Use this column to check the quality of the prediction against actual values
+actual_counts <- test_data$RentalCount;
+
+#Model 1: Use rxLinMod to create a linear regression model. We are training the data using the training data set
+model_linmod <- rxLinMod(RentalCount ~ Month + Day + WeekDay + Snow + Holiday, data = train_data);
+
+#Model 2: Use rxDTree to create a decision tree model. We are training the data using the training data set
+model_dtree <- rxDTree(RentalCount ~ Month + Day + WeekDay + Snow + Holiday, data = train_data);
+
+#Use the models we just created to predict using the test data set.
+#That enables us to compare actual values of RentalCount from the two models and compare to the actual values in the test data set
+predict_linmod <- rxPredict(model_linmod, test_data, writeModelVars = TRUE);
+
+predict_dtree <- rxPredict(model_dtree, test_data, writeModelVars = TRUE);
+
+#Look at the top rows of the two prediction data sets.
+head(predict_linmod);
+head(predict_dtree);
+
+#Now we will use the plotting functionality in R to viusalize the results from the predictions
+#We are plotting the difference between actual and predicted values for both models to compare accuracy
+par(mfrow = c(2, 1));
+plot(predict_linmod$RentalCount_Pred - predict_linmod$RentalCount, main = "Difference between actual and predicted. rxLinmod");
+plot(predict_dtree$RentalCount_Pred - predict_dtree$RentalCount, main = "Difference between actual and predicted. rxDTree");
+

samples/features/r-services/gettingstarted/predictivemodel/PredictiveModel.sql

@@ -0,0 +1,103 @@
+--Before we start, we need to restore the DB for this tutorial.
+--Step1:Download the compressed backup file
+--Save the file on a location where SQL Server can access it. For example:C:\Program Files \Microsoft SQL Server \MSSQL13.MSSQLSERVER\MSSQL\Backup\
+--In a new query window in SSMS, execute the following restore statement, but REMEMBER TO CHANGE THE FILE PATHS
+--to match the directories of your installation!
+USE master;
+GO
+RESTORE DATABASE TutorialDB
+FROM DISK = 'C:\Program Files\Microsoft SQL Server\MSSQL13.MSSQLSERVER\MSSQL\Backup\TutorialDB.bak'
+WITH
+MOVE 'TutorialDB' TO 'C:\Program Files\Microsoft SQL Server\MSSQL13.MSSQLSERVER\MSSQL\DATA\TutorialDB.mdf'
+                , MOVE 'TutorialDB_log' TO 'C:\Program Files\Microsoft SQL Server\MSSQL13.MSSQLSERVER\MSSQL\DATA\TutorialDB.ldf';
+GO
+
+USE tutorialdb;
+SELECT * FROM [dbo].[rental_data];
+
+
+-- Operationalize
+USE tutorialdb;
+GO
+-- Setup model table
+DROP TABLE IF EXISTS rental_rx_models;
+GO
+CREATE TABLE rental_rx_models (
+                model_name VARCHAR(30) NOT NULL DEFAULT('default model') PRIMARY KEY,
+                model VARBINARY(MAX) NOT NULL
+);
+GO
+
+-- Stored procedure that trains and generates a model using the rental_data and a decision tree algorithm
+DROP PROCEDURE IF EXISTS generate_rental_rx_model;
+go
+CREATE PROCEDURE generate_rental_rx_model (@trained_model varbinary(max) OUTPUT)
+AS
+BEGIN
+    EXECUTE sp_execute_external_script
+      @language = N'R'
+    , @script = N'
+        require("RevoScaleR");
+
+        rental_train_data$Holiday = factor(rental_train_data$Holiday);
+            rental_train_data$Snow = factor(rental_train_data$Snow);
+            rental_train_data$WeekDay = factor(rental_train_data$WeekDay);
+
+        #Create a dtree model and train it using the training data set
+        model_dtree <- rxDTree(RentalCount ~ Month + Day + WeekDay + Snow + Holiday, data = rental_train_data);
+        #Before saving the model to the DB table, we need to serialize it
+        trained_model <- as.raw(serialize(model_dtree, connection=NULL));'
+
+    , @input_data_1 = N'select "RentalCount", "Month", "Day", "WeekDay", "Snow", "Holiday" from dbo.rental_data where Year < 2015'
+    , @input_data_1_name = N'rental_train_data'
+    , @params = N'@trained_model varbinary(max) OUTPUT'
+    , @trained_model = @trained_model OUTPUT;
+END;
+GO
+TRUNCATE TABLE rental_rx_models;
+--Script to call the stored procedure that generates the rxDTree model and save the model in a table in SQL Server
+DECLARE @model VARBINARY(MAX);
+EXEC generate_rental_rx_model @model OUTPUT;
+INSERT INTO rental_rx_models (model_name, model) VALUES('rxDTree', @model);
+SELECT * FROM rental_rx_models;
+GO
+
+--Stored procedure that takes model name and new data as inout parameters and predicts the rental count for the new data
+DROP PROCEDURE IF EXISTS predict_rentals;
+GO
+CREATE PROCEDURE predict_rentals (@model VARCHAR(100),@q NVARCHAR(MAX))
+AS
+BEGIN
+    DECLARE @rx_model VARBINARY(MAX) = (SELECT model FROM rental_rx_models WHERE model_name = @model);
+    EXECUTE sp_execute_external_script
+        @language = N'R'
+        , @script = N'
+            require("RevoScaleR");
+
+            #The InputDataSet contains the new data passed to this stored proc. We will use this data to predict.
+            rentals = InputDataSet;
+
+        #Convert types to factors
+            rentals$Holiday = factor(rentals$Holiday);
+            rentals$Snow = factor(rentals$Snow);
+            rentals$WeekDay = factor(rentals$WeekDay);
+
+            #Before using the model to predict, we need to unserialize it
+            rental_model = unserialize(rx_model);
+
+            #Call prediction function
+            rental_predictions = rxPredict(rental_model, rentals);'
+                , @input_data_1 = @q
+        , @output_data_1_name = N'rental_predictions'
+                , @params = N'@rx_model varbinary(max)'
+                , @rx_model = @rx_model
+                WITH RESULT SETS (("RentalCount_Predicted" FLOAT));
+
+END;
+GO
+
+--Execute the predict_rentals stored proc and pass the modelname and a query string with a set of features we want to use to predict the rental count
+EXEC dbo.predict_rentals @model = 'rxDTree',
+       @q ='SELECT CONVERT(INT, 3) AS Month, CONVERT(INT, 24) AS Day, CONVERT(INT, 4) AS WeekDay, CONVERT(INT, 1) AS Snow, CONVERT(INT, 1) AS Holiday';
+GO
+