Merge branch 'sam-dev' into joe-dev2

This commit is contained in:
joedarby
2016-12-16 12:25:32 +00:00
4 changed files with 250 additions and 74 deletions
+164 -50
View File
@@ -2,8 +2,10 @@
<project version="4">
<component name="ChangeListManager">
<list default="true" id="b41a9788-25b3-4e04-923f-17cde259631b" name="Default" comment="">
<change type="NEW" beforePath="" afterPath="$PROJECT_DIR$/run_project.sh" />
<change type="MODIFICATION" beforePath="$PROJECT_DIR$/.idea/workspace.xml" afterPath="$PROJECT_DIR$/.idea/workspace.xml" />
<change type="MODIFICATION" beforePath="$PROJECT_DIR$/src/main/scala/KMeans.scala" afterPath="$PROJECT_DIR$/src/main/scala/KMeans.scala" />
<change type="MODIFICATION" beforePath="$PROJECT_DIR$/src/main/scala/Main.scala" afterPath="$PROJECT_DIR$/src/main/scala/Main.scala" />
<change type="MODIFICATION" beforePath="$PROJECT_DIR$/src/main/scala/XMLParser.scala" afterPath="$PROJECT_DIR$/src/main/scala/XMLParser.scala" />
</list>
<ignored path="$PROJECT_DIR$/target/" />
<option name="EXCLUDED_CONVERTED_TO_IGNORED" value="true" />
@@ -19,11 +21,11 @@
<component name="ExecutionTargetManager" SELECTED_TARGET="default_target" />
<component name="FileEditorManager">
<leaf SIDE_TABS_SIZE_LIMIT_KEY="300">
<file leaf-file-name="KMeans.scala" pinned="false" current-in-tab="true">
<file leaf-file-name="KMeans.scala" pinned="false" current-in-tab="false">
<entry file="file://$PROJECT_DIR$/src/main/scala/KMeans.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="353">
<caret line="20" column="31" lean-forward="true" selection-start-line="20" selection-start-column="31" selection-end-line="20" selection-end-column="31" />
<state relative-caret-position="684">
<caret line="40" column="3" lean-forward="false" selection-start-line="40" selection-start-column="3" selection-end-line="40" selection-end-column="3" />
<folding>
<element signature="e#23#54#0" expanded="true" />
</folding>
@@ -31,11 +33,11 @@
</provider>
</entry>
</file>
<file leaf-file-name="Main.scala" pinned="false" current-in-tab="false">
<file leaf-file-name="Main.scala" pinned="false" current-in-tab="true">
<entry file="file://$PROJECT_DIR$/src/main/scala/Main.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="209">
<caret line="25" column="0" lean-forward="true" selection-start-line="25" selection-start-column="0" selection-end-line="25" selection-end-column="0" />
<state relative-caret-position="258">
<caret line="38" column="38" lean-forward="false" selection-start-line="38" selection-start-column="38" selection-end-line="38" selection-end-column="38" />
<folding />
</state>
</provider>
@@ -44,8 +46,8 @@
<file leaf-file-name="XMLParser.scala" pinned="false" current-in-tab="false">
<entry file="file://$PROJECT_DIR$/src/main/scala/XMLParser.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="396">
<caret line="52" column="3" lean-forward="true" selection-start-line="52" selection-start-column="3" selection-end-line="52" selection-end-column="3" />
<state relative-caret-position="1044">
<caret line="65" column="35" lean-forward="false" selection-start-line="65" selection-start-column="35" selection-end-line="65" selection-end-column="35" />
<folding>
<element signature="e#23#59#0" expanded="true" />
</folding>
@@ -66,8 +68,9 @@
<component name="IdeDocumentHistory">
<option name="CHANGED_PATHS">
<list>
<option value="$PROJECT_DIR$/src/main/scala/Main.scala" />
<option value="$PROJECT_DIR$/src/main/scala/KMeans.scala" />
<option value="$PROJECT_DIR$/src/main/scala/XMLParser.scala" />
<option value="$PROJECT_DIR$/src/main/scala/Main.scala" />
</list>
</option>
</component>
@@ -79,10 +82,10 @@
</option>
</component>
<component name="ProjectFrameBounds">
<option name="x" value="75" />
<option name="y" value="80" />
<option name="width" value="1275" />
<option name="height" value="611" />
<option name="x" value="65" />
<option name="y" value="24" />
<option name="width" value="1295" />
<option name="height" value="744" />
</component>
<component name="ProjectView">
<navigator currentView="ProjectPane" proportions="" version="1">
@@ -99,7 +102,6 @@
<foldersAlwaysOnTop value="true" />
</navigator>
<panes>
<pane id="Scratches" />
<pane id="ProjectPane">
<subPane>
<PATH>
@@ -112,32 +114,6 @@
<option name="myItemType" value="com.intellij.ide.projectView.impl.nodes.PsiDirectoryNode" />
</PATH_ELEMENT>
</PATH>
<PATH>
<PATH_ELEMENT>
<option name="myItemId" value="KMeans" />
<option name="myItemType" value="com.intellij.ide.projectView.impl.nodes.ProjectViewProjectNode" />
</PATH_ELEMENT>
<PATH_ELEMENT>
<option name="myItemId" value="Big_Data_Assignment_2" />
<option name="myItemType" value="com.intellij.ide.projectView.impl.nodes.PsiDirectoryNode" />
</PATH_ELEMENT>
<PATH_ELEMENT>
<option name="myItemId" value="src" />
<option name="myItemType" value="com.intellij.ide.projectView.impl.nodes.PsiDirectoryNode" />
</PATH_ELEMENT>
<PATH_ELEMENT>
<option name="myItemId" value="main" />
<option name="myItemType" value="com.intellij.ide.projectView.impl.nodes.PsiDirectoryNode" />
</PATH_ELEMENT>
<PATH_ELEMENT>
<option name="myItemId" value="scala" />
<option name="myItemType" value="com.intellij.ide.projectView.impl.nodes.PsiDirectoryNode" />
</PATH_ELEMENT>
<PATH_ELEMENT>
<option name="myItemId" value="XMLParser.scala" />
<option name="myItemType" value="org.jetbrains.plugins.scala.components.ScalaDefsProjectViewProvider$ScalaFileTreeNode" />
</PATH_ELEMENT>
</PATH>
<PATH>
<PATH_ELEMENT>
<option name="myItemId" value="KMeans" />
@@ -163,6 +139,7 @@
</subPane>
</pane>
<pane id="PackagesPane" />
<pane id="Scratches" />
<pane id="Scope" />
</panes>
</component>
@@ -436,7 +413,7 @@
<servers />
</component>
<component name="ToolWindowManager">
<frame x="75" y="80" width="1275" height="611" extended-state="0" />
<frame x="65" y="24" width="1295" height="744" extended-state="6" />
<editor active="true" />
<layout>
<window_info id="Palette" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="3" side_tool="false" content_ui="tabs" />
@@ -447,19 +424,19 @@
<window_info id="Capture Analysis" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="3" side_tool="false" content_ui="tabs" />
<window_info id="Event Log" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="7" side_tool="true" content_ui="tabs" />
<window_info id="Maven Projects" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="3" side_tool="false" content_ui="tabs" />
<window_info id="Version Control" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="7" side_tool="false" content_ui="tabs" />
<window_info id="Run" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="2" side_tool="false" content_ui="tabs" />
<window_info id="Version Control" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="7" side_tool="false" content_ui="tabs" />
<window_info id="Properties" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="3" side_tool="false" content_ui="tabs" />
<window_info id="Terminal" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="7" side_tool="false" content_ui="tabs" />
<window_info id="Capture Tool" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="2" side_tool="false" content_ui="tabs" />
<window_info id="Designer" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="2" side_tool="false" content_ui="tabs" />
<window_info id="Project" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="true" show_stripe_button="true" weight="0.24941176" sideWeight="0.5" order="0" side_tool="false" content_ui="combo" />
<window_info id="Project" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="true" show_stripe_button="true" weight="0.24555984" sideWeight="0.5" order="0" side_tool="false" content_ui="combo" />
<window_info id="Structure" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="1" side_tool="false" content_ui="tabs" />
<window_info id="Ant Build" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="1" side_tool="false" content_ui="tabs" />
<window_info id="UI Designer" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="2" side_tool="false" content_ui="tabs" />
<window_info id="Theme Preview" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="3" side_tool="false" content_ui="tabs" />
<window_info id="Favorites" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="2" side_tool="true" content_ui="tabs" />
<window_info id="Debug" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.4" sideWeight="0.5" order="3" side_tool="false" content_ui="tabs" />
<window_info id="Favorites" active="false" anchor="left" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="2" side_tool="true" content_ui="tabs" />
<window_info id="Cvs" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.25" sideWeight="0.5" order="4" side_tool="false" content_ui="tabs" />
<window_info id="Message" active="false" anchor="bottom" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.33" sideWeight="0.5" order="0" side_tool="false" content_ui="tabs" />
<window_info id="Commander" active="false" anchor="right" auto_hide="false" internal_type="DOCKED" type="DOCKED" visible="false" show_stripe_button="true" weight="0.4" sideWeight="0.5" order="0" side_tool="false" content_ui="tabs" />
@@ -476,6 +453,34 @@
<watches-manager />
</component>
<component name="editorHistoryManager">
<entry file="file://$PROJECT_DIR$/src/main/scala/KMeans.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="720">
<caret line="40" column="3" lean-forward="false" selection-start-line="40" selection-start-column="3" selection-end-line="40" selection-end-column="3" />
<folding>
<element signature="e#23#54#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/Main.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="684">
<caret line="38" column="38" lean-forward="true" selection-start-line="38" selection-start-column="38" selection-end-line="38" selection-end-column="38" />
<folding />
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/XMLParser.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="1170">
<caret line="65" column="35" lean-forward="false" selection-start-line="65" selection-start-column="35" selection-end-line="65" selection-end-column="35" />
<folding>
<element signature="e#23#59#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/KMeans.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="0">
@@ -500,13 +505,30 @@
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="168">
<caret line="15" column="6" lean-forward="false" selection-start-line="15" selection-start-column="6" selection-end-line="15" selection-end-column="6" />
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/Main.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="245">
<caret line="27" column="27" lean-forward="true" selection-start-line="27" selection-start-column="27" selection-end-line="27" selection-end-column="27" />
<folding />
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/KMeans.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="396">
<caret line="40" column="3" lean-forward="true" selection-start-line="40" selection-start-column="3" selection-end-line="40" selection-end-column="3" />
<folding>
<element signature="e#23#54#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/XMLParser.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="396">
<state relative-caret-position="612">
<caret line="52" column="3" lean-forward="true" selection-start-line="52" selection-start-column="3" selection-end-line="52" selection-end-column="3" />
<folding>
<element signature="e#23#59#0" expanded="true" />
@@ -514,24 +536,116 @@
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/KMeans.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="0">
<caret line="0" column="0" lean-forward="false" selection-start-line="0" selection-start-column="0" selection-end-line="0" selection-end-column="0" />
<folding>
<element signature="e#23#54#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/XMLParser.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="270">
<caret line="15" column="7" lean-forward="false" selection-start-line="15" selection-start-column="7" selection-end-line="15" selection-end-column="7" />
<folding>
<element signature="e#23#59#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="jar://$MAVEN_REPOSITORY$/org/scala-lang/scala-library/2.10.5/scala-library-2.10.5.jar!/scala/collection/TraversableLike.class">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="168">
<caret line="15" column="6" lean-forward="false" selection-start-line="15" selection-start-column="6" selection-end-line="15" selection-end-column="6" />
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/XMLParser.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="537">
<caret line="84" column="5" lean-forward="true" selection-start-line="84" selection-start-column="5" selection-end-line="84" selection-end-column="5" />
<folding>
<element signature="e#23#59#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/Main.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="209">
<caret line="25" column="0" lean-forward="true" selection-start-line="25" selection-start-column="0" selection-end-line="25" selection-end-column="0" />
<state relative-caret-position="245">
<caret line="27" column="27" lean-forward="true" selection-start-line="27" selection-start-column="27" selection-end-line="27" selection-end-column="27" />
<folding />
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/KMeans.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="353">
<caret line="20" column="31" lean-forward="true" selection-start-line="20" selection-start-column="31" selection-end-line="20" selection-end-column="31" />
<state relative-caret-position="396">
<caret line="40" column="3" lean-forward="false" selection-start-line="40" selection-start-column="3" selection-end-line="40" selection-end-column="3" />
<folding>
<element signature="e#23#54#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/KMeans.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="0">
<caret line="0" column="0" lean-forward="false" selection-start-line="0" selection-start-column="0" selection-end-line="0" selection-end-column="0" />
<folding>
<element signature="e#23#54#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/XMLParser.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="270">
<caret line="15" column="7" lean-forward="false" selection-start-line="15" selection-start-column="7" selection-end-line="15" selection-end-column="7" />
<folding>
<element signature="e#23#59#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="jar://$MAVEN_REPOSITORY$/org/scala-lang/scala-library/2.10.5/scala-library-2.10.5.jar!/scala/collection/TraversableLike.class">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="168">
<caret line="15" column="6" lean-forward="false" selection-start-line="15" selection-start-column="6" selection-end-line="15" selection-end-column="6" />
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/KMeans.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="684">
<caret line="40" column="3" lean-forward="false" selection-start-line="40" selection-start-column="3" selection-end-line="40" selection-end-column="3" />
<folding>
<element signature="e#23#54#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/XMLParser.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="1044">
<caret line="65" column="35" lean-forward="false" selection-start-line="65" selection-start-column="35" selection-end-line="65" selection-end-column="35" />
<folding>
<element signature="e#23#59#0" expanded="true" />
</folding>
</state>
</provider>
</entry>
<entry file="file://$PROJECT_DIR$/src/main/scala/Main.scala">
<provider selected="true" editor-type-id="text-editor">
<state relative-caret-position="258">
<caret line="38" column="38" lean-forward="false" selection-start-line="38" selection-start-column="38" selection-end-line="38" selection-end-column="38" />
<folding />
</state>
</provider>
</entry>
</component>
<component name="masterDetails">
<states>
Executable
+4
View File
@@ -0,0 +1,4 @@
#!/usr/bin/env bash
cd target
spark-submit --class ClusterSOData.Main --master local KMeans-0.0.1.jar
+19 -2
View File
@@ -22,13 +22,30 @@ object Main {
def main(args: Array[String]) {
// Retrieve data from StackOverflow dataset XMLs. Format into DataFrames
// for easy access to data elements.
val df = DataParser.ParseData()
val dataFrames = DataParser.ParseData()
// get the users XML file
val users = df("users")
val users = dataFrames("users")
val centres = KMeans.train(users)
val centresArray = centres.collect()
val unwrap = centresArray.map(x => x._2)
unwrap.foreach(println)
/*val users = dataFrames("users")
users.persist()
// Show 20 entries from the user dataset
users.show()
// Show types for the user dataset
users.printSchema()
users.show()
// create new dataframe with only the reputation of the users
users.select("CreationDate").show()
// Info on using DataFrames here: https://www.mapr.com/blog/using-apache-spark-dataframes-processing-tabular-data
*/
}
}
+63 -22
View File
@@ -23,28 +23,29 @@ object DataParser {
// Define XML file locations and a string of attribute tags to retrieve
// from each xml element.
val xmlInfos = Array(
("badges", "../stackoverflow_dataset/badges.txt", "Id UserId Name Date"),
("comments", "../stackoverflow_dataset/comments.txt", "Id PostId Score Text CreationDate UserId"),
("posts", "../stackoverflow_dataset/posts.txt", "Id PostTypeId ParentID AcceptedAnswerId CreationDate Score ViewCount Body OwnerUserId LastEditorUserId LastEditorDisplayName LastEditDate LastActivityDate CommunityOwnedDate ClosedDate Title Tags AnswerCount CommentCount FavoriteCount"),
("postHistory", "../stackoverflow_dataset/postHistory.txt","Id PostHistoryTypeId PostId RevisionGUID CreationDate UserId UserDisplayName Comment Text CloseReasonId"),
("postLinks", "../stackoverflow_dataset/postLinks.txt", "Id CreationDate PostId RelatedPostId PostLinkTypeId"),
("users", "../stackoverflow_dataset/users.txt", "Reputation CreationDate DisplayName EmailHash LastAccessDate WebsiteUrl Location Age AboutMe Views UpVotes DownVotes"),
("votes", "../stackoverflow_dataset/votes.txt", "Id PostId VoteTypeId UserId CreationDate")
("badges", "../stackoverflow_dataset/badges.txt", "Id UserId Name Date", Array[DataType](IntegerType, IntegerType, StringType, DateType)),
("comments", "../stackoverflow_dataset/comments.txt", "Id PostId Score Text CreationDate UserId", Array[DataType](IntegerType, IntegerType, IntegerType, StringType, DateType, IntegerType)),
("posts", "../stackoverflow_dataset/posts.txt", "Id PostTypeId ParentID AcceptedAnswerId CreationDate Score ViewCount Body OwnerUserId LastEditorUserId LastEditorDisplayName LastEditDate LastActivityDate CommunityOwnedDate ClosedDate Title Tags AnswerCount CommentCount FavoriteCount", Array[DataType](IntegerType, IntegerType, IntegerType, IntegerType, DateType, IntegerType, IntegerType, StringType, IntegerType, IntegerType, StringType, DateType, DateType, DateType, DateType, StringType, StringType, IntegerType, IntegerType, IntegerType)),
("postHistory", "../stackoverflow_dataset/postHistory.txt","Id PostHistoryTypeId PostId RevisionGUID CreationDate UserId UserDisplayName Comment Text CloseReasonId", Array[DataType](IntegerType, IntegerType, IntegerType,IntegerType, DateType, IntegerType, StringType, StringType, StringType, IntegerType)),
("postLinks", "../stackoverflow_dataset/postLinks.txt", "Id CreationDate PostId RelatedPostId PostLinkTypeId", Array[DataType](IntegerType, DateType, IntegerType, IntegerType, IntegerType)),
("users", "../stackoverflow_dataset/users.txt", "Reputation CreationDate DisplayName EmailHash LastAccessDate WebsiteUrl Location Age AboutMe Views UpVotes DownVotes", Array[DataType](IntegerType, DateType, StringType, StringType, DateType, StringType, StringType, IntegerType, StringType, IntegerType, IntegerType, IntegerType)),
("votes", "../stackoverflow_dataset/votes.txt", "Id PostId VoteTypeId UserId CreationDate", Array[DataType](IntegerType, IntegerType, IntegerType, IntegerType, DateType))
)
// Store each file's DataFrame in an array of DataFrames.
val parsedData = xmlInfos.map(x => (x._1, ParseXMLInfo((x._2, x._3)))).toMap
val parsedData = xmlInfos.map(x => (x._1, ParseXMLInfo((x._2, x._3, x._4)))).toMap
return parsedData
}
private def ParseXMLInfo(xmlInfo: (String, String)) : DataFrame = {
private def ParseXMLInfo(xmlInfo: (String, String, Array[DataType])) : DataFrame = {
// Get the XML attributes used for generating the table columns
var schemaString = xmlInfo._2
val schemaType = xmlInfo._3
// Generate schema using XML attribute string
var schema = GenerateSchemaFromString(schemaString)
var schema = GenerateSchemaFromString(schemaString, schemaType)
// Generate RDD of data from the XML file
var rdd = ParseInput(xmlInfo._1, schemaString)
var rdd = ParseInput(xmlInfo._1, schemaString, schemaType)
// Convert RDD to DataFrame for easier processing
var data = Main.sqlContext.createDataFrame(rdd, schema)
@@ -55,9 +56,13 @@ object DataParser {
/*
* Generate a schema based on the string of XML attributes
*/
private def GenerateSchemaFromString(schemaString: String) : StructType = {
val fields = schemaString.split(" ")
.map(fieldName => StructField(fieldName, StringType, nullable = true))
private def GenerateSchemaFromString(schemaString: String, schemaType: Array[DataType]) : StructType = {
// Replace all DateTypes with Longs as date will now be stored as longs.
val sT = schemaType.map(i => if (i==DateType) LongType else i)
val schemaPairs = schemaString.split(" ") zip sT
// Create schema for columns and set their datatypes for DataFrame based on attribute names.
val fields = schemaPairs.map{case (fieldName: String, dataType: DataType) => StructField(fieldName, dataType, nullable = true)}
val schema = StructType(fields)
return schema
}
@@ -68,12 +73,14 @@ object DataParser {
* inputFilepath: Filepath to XML file
* schemaString: Space seperated attribute values
*/
private def ParseInput(inputFilepath: String, schemaString: String) : RDD[Row] = {
private def ParseInput(inputFilepath: String, schemaString: String, schemaType: Array[DataType]) : RDD[Row] = {
// Create spark text file object
val inputFile = Main.sc.textFile(inputFilepath)
// Map the input file data to an RDD
val Data = inputFile.map(line => ParsingFunc(line, schemaString))
val Data = inputFile.collect {
case line if !SantizeLine(line) => ParsingFunc(line, schemaString, schemaType)
}
return Data
}
@@ -83,13 +90,47 @@ object DataParser {
* line: XML file line
* schemaString: Space seperated attribute values
*/
private def ParsingFunc(line: String, schemaString: String) : Row = {
// Parse line of XML using Scala's built in XML library
val xmlLine = scala.xml.XML.loadString(line)
// Create array of values with element for each attribute in schemaString
var lineData = schemaString.split(" ").map(fieldName => getXMLAttribute(xmlLine, fieldName))
return Row.fromSeq(lineData)
private def SantizeLine(line: String) : Boolean = {
val invalidLines = Array("<?xml version=\"1.0\" encoding=\"utf-8\"?>", "<users>", "</users>")
return invalidLines contains line
}
private def ParsingFunc(line: String, schemaString: String, schemaType: Array[DataType]) : Row = {
// Parse line of XML using Scala's built in XML library
try {
val xmlLine = scala.xml.XML.loadString(line)
var schemaPairs = schemaString.split(" ") zip schemaType
// Create array of values with element for each attribute in schemaString
var lineData = schemaPairs.map { case (fieldName: String, dType: DataType) => castToDType(getXMLAttribute(xmlLine, fieldName), dType) }
return Row.fromSeq(lineData)
} catch {
case e:Exception=>
println(line)
throw new Exception("failed to load")
}
}
/*
* Cast attribute data to relevant datatype.
*/
private def castToDType(attribute: String, dType: DataType) : Any = {
dType match {
case StringType => return attribute
case IntegerType =>
try {
return attribute.toInt
} catch {
// If the string was not castable to integer then it is not a number.
// In this case, return a placeholder value of -1.
case e: Exception => return -1
}
case DateType =>
// If the string is a date, convert from date string to long.
var format = new java.text.SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSS")
return format.parse(attribute).getTime()
}
}
/*