신은섭(Shin Eun Seop) / Detecting_fraud_clicks

Go to a project
Toggle navigation Toggle navigation pinning
신은섭(Shin Eun Seop)
1a6fada6 2 parents b40afe35 98173ec8

Merge branch 'feature/#3' into calcDelta

Inline Side-by-side
Showing 8 changed files with 335 additions and 17 deletions
1 +<?xml version="1.0" encoding="UTF-8"?>
2 +<module org.jetbrains.idea.maven.project.MavenProjectsManager.isMavenModule="true" type="JAVA_MODULE" version="4">
3 + <component name="NewModuleRootManager" LANGUAGE_LEVEL="JDK_1_8">
4 + <output url="file://$MODULE_DIR$/target/classes" />
5 + <output-test url="file://$MODULE_DIR$/target/test-classes" />
6 + <content url="file://$MODULE_DIR$">
7 + <sourceFolder url="file://$MODULE_DIR$/src/main/resources" type="java-resource" />
8 + <sourceFolder url="file://$MODULE_DIR$/src/test/resources" type="java-test-resource" />
9 + <sourceFolder url="file://$MODULE_DIR$/src/main/java" isTestSource="false" />
10 + <sourceFolder url="file://$MODULE_DIR$/src/test/java" isTestSource="true" />
11 + <excludeFolder url="file://$MODULE_DIR$/target" />
12 + </content>
13 + <orderEntry type="inheritedJdk" />
14 + <orderEntry type="sourceFolder" forTests="false" />
15 + <orderEntry type="library" name="Maven: com.databricks:spark-csv_2.11:1.5.0" level="project" />
16 + <orderEntry type="library" name="Maven: org.apache.commons:commons-csv:1.1" level="project" />
17 + <orderEntry type="library" name="Maven: org.apache.spark:spark-core_2.11:2.3.0" level="project" />
18 + <orderEntry type="library" name="Maven: org.apache.avro:avro:1.7.7" level="project" />
19 + <orderEntry type="library" name="Maven: org.codehaus.jackson:jackson-core-asl:1.9.13" level="project" />
20 + <orderEntry type="library" name="Maven: org.codehaus.jackson:jackson-mapper-asl:1.9.13" level="project" />
21 + <orderEntry type="library" name="Maven: com.thoughtworks.paranamer:paranamer:2.3" level="project" />
22 + <orderEntry type="library" name="Maven: org.apache.commons:commons-compress:1.4.1" level="project" />
23 + <orderEntry type="library" name="Maven: org.tukaani:xz:1.0" level="project" />
24 + <orderEntry type="library" name="Maven: org.apache.avro:avro-mapred:hadoop2:1.7.7" level="project" />
25 + <orderEntry type="library" name="Maven: org.apache.avro:avro-ipc:1.7.7" level="project" />
26 + <orderEntry type="library" name="Maven: org.apache.avro:avro-ipc:tests:1.7.7" level="project" />
27 + <orderEntry type="library" name="Maven: com.twitter:chill_2.11:0.8.4" level="project" />
28 + <orderEntry type="library" name="Maven: com.esotericsoftware:kryo-shaded:3.0.3" level="project" />
29 + <orderEntry type="library" name="Maven: com.esotericsoftware:minlog:1.3.0" level="project" />
30 + <orderEntry type="library" name="Maven: org.objenesis:objenesis:2.1" level="project" />
31 + <orderEntry type="library" name="Maven: com.twitter:chill-java:0.8.4" level="project" />
32 + <orderEntry type="library" name="Maven: org.apache.xbean:xbean-asm5-shaded:4.4" level="project" />
33 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-client:2.6.5" level="project" />
34 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-common:2.6.5" level="project" />
35 + <orderEntry type="library" name="Maven: commons-cli:commons-cli:1.2" level="project" />
36 + <orderEntry type="library" name="Maven: xmlenc:xmlenc:0.52" level="project" />
37 + <orderEntry type="library" name="Maven: commons-httpclient:commons-httpclient:3.1" level="project" />
38 + <orderEntry type="library" name="Maven: commons-io:commons-io:2.4" level="project" />
39 + <orderEntry type="library" name="Maven: commons-collections:commons-collections:3.2.2" level="project" />
40 + <orderEntry type="library" name="Maven: commons-configuration:commons-configuration:1.6" level="project" />
41 + <orderEntry type="library" name="Maven: commons-digester:commons-digester:1.8" level="project" />
42 + <orderEntry type="library" name="Maven: commons-beanutils:commons-beanutils:1.7.0" level="project" />
43 + <orderEntry type="library" name="Maven: commons-beanutils:commons-beanutils-core:1.8.0" level="project" />
44 + <orderEntry type="library" name="Maven: com.google.code.gson:gson:2.2.4" level="project" />
45 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-auth:2.6.5" level="project" />
46 + <orderEntry type="library" name="Maven: org.apache.directory.server:apacheds-kerberos-codec:2.0.0-M15" level="project" />
47 + <orderEntry type="library" name="Maven: org.apache.directory.server:apacheds-i18n:2.0.0-M15" level="project" />
48 + <orderEntry type="library" name="Maven: org.apache.directory.api:api-asn1-api:1.0.0-M20" level="project" />
49 + <orderEntry type="library" name="Maven: org.apache.directory.api:api-util:1.0.0-M20" level="project" />
50 + <orderEntry type="library" name="Maven: org.apache.curator:curator-client:2.6.0" level="project" />
51 + <orderEntry type="library" name="Maven: org.htrace:htrace-core:3.0.4" level="project" />
52 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-hdfs:2.6.5" level="project" />
53 + <orderEntry type="library" name="Maven: org.mortbay.jetty:jetty-util:6.1.26" level="project" />
54 + <orderEntry type="library" name="Maven: xerces:xercesImpl:2.9.1" level="project" />
55 + <orderEntry type="library" name="Maven: xml-apis:xml-apis:1.3.04" level="project" />
56 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-mapreduce-client-app:2.6.5" level="project" />
57 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-mapreduce-client-common:2.6.5" level="project" />
58 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-yarn-client:2.6.5" level="project" />
59 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-yarn-server-common:2.6.5" level="project" />
60 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-mapreduce-client-shuffle:2.6.5" level="project" />
61 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-yarn-api:2.6.5" level="project" />
62 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-mapreduce-client-core:2.6.5" level="project" />
63 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-yarn-common:2.6.5" level="project" />
64 + <orderEntry type="library" name="Maven: javax.xml.bind:jaxb-api:2.2.2" level="project" />
65 + <orderEntry type="library" name="Maven: javax.xml.stream:stax-api:1.0-2" level="project" />
66 + <orderEntry type="library" name="Maven: org.codehaus.jackson:jackson-jaxrs:1.9.13" level="project" />
67 + <orderEntry type="library" name="Maven: org.codehaus.jackson:jackson-xc:1.9.13" level="project" />
68 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-mapreduce-client-jobclient:2.6.5" level="project" />
69 + <orderEntry type="library" name="Maven: org.apache.hadoop:hadoop-annotations:2.6.5" level="project" />
70 + <orderEntry type="library" name="Maven: org.apache.spark:spark-launcher_2.11:2.3.0" level="project" />
71 + <orderEntry type="library" name="Maven: org.apache.spark:spark-kvstore_2.11:2.3.0" level="project" />
72 + <orderEntry type="library" name="Maven: org.fusesource.leveldbjni:leveldbjni-all:1.8" level="project" />
73 + <orderEntry type="library" name="Maven: com.fasterxml.jackson.core:jackson-core:2.6.7" level="project" />
74 + <orderEntry type="library" name="Maven: com.fasterxml.jackson.core:jackson-annotations:2.6.7" level="project" />
75 + <orderEntry type="library" name="Maven: org.apache.spark:spark-network-common_2.11:2.3.0" level="project" />
76 + <orderEntry type="library" name="Maven: org.apache.spark:spark-network-shuffle_2.11:2.3.0" level="project" />
77 + <orderEntry type="library" name="Maven: org.apache.spark:spark-unsafe_2.11:2.3.0" level="project" />
78 + <orderEntry type="library" name="Maven: net.java.dev.jets3t:jets3t:0.9.4" level="project" />
79 + <orderEntry type="library" name="Maven: org.apache.httpcomponents:httpcore:4.4.1" level="project" />
80 + <orderEntry type="library" name="Maven: org.apache.httpcomponents:httpclient:4.5" level="project" />
81 + <orderEntry type="library" name="Maven: commons-codec:commons-codec:2.0-SNAPSHOT" level="project" />
82 + <orderEntry type="library" name="Maven: javax.activation:activation:1.1.1" level="project" />
83 + <orderEntry type="library" name="Maven: org.bouncycastle:bcprov-jdk15on:1.52" level="project" />
84 + <orderEntry type="library" name="Maven: com.jamesmurty.utils:java-xmlbuilder:1.1" level="project" />
85 + <orderEntry type="library" name="Maven: net.iharder:base64:2.3.8" level="project" />
86 + <orderEntry type="library" name="Maven: org.apache.curator:curator-recipes:2.6.0" level="project" />
87 + <orderEntry type="library" name="Maven: org.apache.curator:curator-framework:2.6.0" level="project" />
88 + <orderEntry type="library" name="Maven: org.apache.zookeeper:zookeeper:3.4.6" level="project" />
89 + <orderEntry type="library" name="Maven: com.google.guava:guava:16.0.1" level="project" />
90 + <orderEntry type="library" name="Maven: javax.servlet:javax.servlet-api:3.1.0" level="project" />
91 + <orderEntry type="library" name="Maven: org.apache.commons:commons-lang3:3.5" level="project" />
92 + <orderEntry type="library" name="Maven: org.apache.commons:commons-math3:3.4.1" level="project" />
93 + <orderEntry type="library" name="Maven: com.google.code.findbugs:jsr305:1.3.9" level="project" />
94 + <orderEntry type="library" name="Maven: org.slf4j:slf4j-api:1.7.16" level="project" />
95 + <orderEntry type="library" name="Maven: org.slf4j:jul-to-slf4j:1.7.16" level="project" />
96 + <orderEntry type="library" name="Maven: org.slf4j:jcl-over-slf4j:1.7.16" level="project" />
97 + <orderEntry type="library" name="Maven: log4j:log4j:1.2.17" level="project" />
98 + <orderEntry type="library" name="Maven: org.slf4j:slf4j-log4j12:1.7.16" level="project" />
99 + <orderEntry type="library" name="Maven: com.ning:compress-lzf:1.0.3" level="project" />
100 + <orderEntry type="library" name="Maven: org.xerial.snappy:snappy-java:1.1.2.6" level="project" />
101 + <orderEntry type="library" name="Maven: org.lz4:lz4-java:1.4.0" level="project" />
102 + <orderEntry type="library" name="Maven: com.github.luben:zstd-jni:1.3.2-2" level="project" />
103 + <orderEntry type="library" name="Maven: org.roaringbitmap:RoaringBitmap:0.5.11" level="project" />
104 + <orderEntry type="library" name="Maven: commons-net:commons-net:2.2" level="project" />
105 + <orderEntry type="library" name="Maven: org.scala-lang:scala-library:2.11.8" level="project" />
106 + <orderEntry type="library" name="Maven: org.json4s:json4s-jackson_2.11:3.2.11" level="project" />
107 + <orderEntry type="library" name="Maven: org.json4s:json4s-core_2.11:3.2.11" level="project" />
108 + <orderEntry type="library" name="Maven: org.json4s:json4s-ast_2.11:3.2.11" level="project" />
109 + <orderEntry type="library" name="Maven: org.scala-lang:scalap:2.11.0" level="project" />
110 + <orderEntry type="library" name="Maven: org.scala-lang:scala-compiler:2.11.0" level="project" />
111 + <orderEntry type="library" name="Maven: org.scala-lang.modules:scala-xml_2.11:1.0.1" level="project" />
112 + <orderEntry type="library" name="Maven: org.glassfish.jersey.core:jersey-client:2.22.2" level="project" />
113 + <orderEntry type="library" name="Maven: javax.ws.rs:javax.ws.rs-api:2.0.1" level="project" />
114 + <orderEntry type="library" name="Maven: org.glassfish.hk2:hk2-api:2.4.0-b34" level="project" />
115 + <orderEntry type="library" name="Maven: org.glassfish.hk2:hk2-utils:2.4.0-b34" level="project" />
116 + <orderEntry type="library" name="Maven: org.glassfish.hk2.external:aopalliance-repackaged:2.4.0-b34" level="project" />
117 + <orderEntry type="library" name="Maven: org.glassfish.hk2.external:javax.inject:2.4.0-b34" level="project" />
118 + <orderEntry type="library" name="Maven: org.glassfish.hk2:hk2-locator:2.4.0-b34" level="project" />
119 + <orderEntry type="library" name="Maven: org.javassist:javassist:3.18.1-GA" level="project" />
120 + <orderEntry type="library" name="Maven: org.glassfish.jersey.core:jersey-common:2.22.2" level="project" />
121 + <orderEntry type="library" name="Maven: javax.annotation:javax.annotation-api:1.2" level="project" />
122 + <orderEntry type="library" name="Maven: org.glassfish.jersey.bundles.repackaged:jersey-guava:2.22.2" level="project" />
123 + <orderEntry type="library" name="Maven: org.glassfish.hk2:osgi-resource-locator:1.0.1" level="project" />
124 + <orderEntry type="library" name="Maven: org.glassfish.jersey.core:jersey-server:2.22.2" level="project" />
125 + <orderEntry type="library" name="Maven: org.glassfish.jersey.media:jersey-media-jaxb:2.22.2" level="project" />
126 + <orderEntry type="library" name="Maven: javax.validation:validation-api:1.1.0.Final" level="project" />
127 + <orderEntry type="library" name="Maven: org.glassfish.jersey.containers:jersey-container-servlet:2.22.2" level="project" />
128 + <orderEntry type="library" name="Maven: org.glassfish.jersey.containers:jersey-container-servlet-core:2.22.2" level="project" />
129 + <orderEntry type="library" name="Maven: io.netty:netty-all:4.1.17.Final" level="project" />
130 + <orderEntry type="library" name="Maven: io.netty:netty:3.9.9.Final" level="project" />
131 + <orderEntry type="library" name="Maven: com.clearspring.analytics:stream:2.7.0" level="project" />
132 + <orderEntry type="library" name="Maven: io.dropwizard.metrics:metrics-core:3.1.5" level="project" />
133 + <orderEntry type="library" name="Maven: io.dropwizard.metrics:metrics-jvm:3.1.5" level="project" />
134 + <orderEntry type="library" name="Maven: io.dropwizard.metrics:metrics-json:3.1.5" level="project" />
135 + <orderEntry type="library" name="Maven: io.dropwizard.metrics:metrics-graphite:3.1.5" level="project" />
136 + <orderEntry type="library" name="Maven: com.fasterxml.jackson.core:jackson-databind:2.6.7.1" level="project" />
137 + <orderEntry type="library" name="Maven: com.fasterxml.jackson.module:jackson-module-scala_2.11:2.6.7.1" level="project" />
138 + <orderEntry type="library" name="Maven: org.scala-lang:scala-reflect:2.11.8" level="project" />
139 + <orderEntry type="library" name="Maven: com.fasterxml.jackson.module:jackson-module-paranamer:2.7.9" level="project" />
140 + <orderEntry type="library" name="Maven: org.apache.ivy:ivy:2.4.0" level="project" />
141 + <orderEntry type="library" name="Maven: oro:oro:2.0.8" level="project" />
142 + <orderEntry type="library" name="Maven: net.razorvine:pyrolite:4.13" level="project" />
143 + <orderEntry type="library" name="Maven: net.sf.py4j:py4j:0.10.6" level="project" />
144 + <orderEntry type="library" name="Maven: org.apache.spark:spark-tags_2.11:2.3.0" level="project" />
145 + <orderEntry type="library" name="Maven: org.apache.commons:commons-crypto:1.0.0" level="project" />
146 + <orderEntry type="library" name="Maven: org.spark-project.spark:unused:1.0.0" level="project" />
147 + <orderEntry type="library" name="Maven: org.apache.spark:spark-sql_2.11:2.3.0" level="project" />
148 + <orderEntry type="library" name="Maven: com.univocity:univocity-parsers:2.5.9" level="project" />
149 + <orderEntry type="library" name="Maven: org.apache.spark:spark-sketch_2.11:2.3.0" level="project" />
150 + <orderEntry type="library" name="Maven: org.apache.spark:spark-catalyst_2.11:2.3.0" level="project" />
151 + <orderEntry type="library" name="Maven: org.scala-lang.modules:scala-parser-combinators_2.11:1.0.4" level="project" />
152 + <orderEntry type="library" name="Maven: org.codehaus.janino:janino:3.0.8" level="project" />
153 + <orderEntry type="library" name="Maven: org.codehaus.janino:commons-compiler:3.0.8" level="project" />
154 + <orderEntry type="library" name="Maven: org.antlr:antlr4-runtime:4.7" level="project" />
155 + <orderEntry type="library" name="Maven: org.apache.orc:orc-core:nohive:1.4.1" level="project" />
156 + <orderEntry type="library" name="Maven: com.google.protobuf:protobuf-java:2.5.0" level="project" />
157 + <orderEntry type="library" name="Maven: commons-lang:commons-lang:2.6" level="project" />
158 + <orderEntry type="library" name="Maven: io.airlift:aircompressor:0.8" level="project" />
159 + <orderEntry type="library" name="Maven: org.apache.orc:orc-mapreduce:nohive:1.4.1" level="project" />
160 + <orderEntry type="library" name="Maven: org.apache.parquet:parquet-column:1.8.2" level="project" />
161 + <orderEntry type="library" name="Maven: org.apache.parquet:parquet-common:1.8.2" level="project" />
162 + <orderEntry type="library" name="Maven: org.apache.parquet:parquet-encoding:1.8.2" level="project" />
163 + <orderEntry type="library" name="Maven: org.apache.parquet:parquet-hadoop:1.8.2" level="project" />
164 + <orderEntry type="library" name="Maven: org.apache.parquet:parquet-format:2.3.1" level="project" />
165 + <orderEntry type="library" name="Maven: org.apache.parquet:parquet-jackson:1.8.2" level="project" />
166 + <orderEntry type="library" name="Maven: org.apache.arrow:arrow-vector:0.8.0" level="project" />
167 + <orderEntry type="library" name="Maven: org.apache.arrow:arrow-format:0.8.0" level="project" />
168 + <orderEntry type="library" name="Maven: org.apache.arrow:arrow-memory:0.8.0" level="project" />
169 + <orderEntry type="library" name="Maven: joda-time:joda-time:2.9.9" level="project" />
170 + <orderEntry type="library" name="Maven: com.carrotsearch:hppc:0.7.2" level="project" />
171 + <orderEntry type="library" name="Maven: com.vlkan:flatbuffers:1.2.0-3f79e055" level="project" />
172 + <orderEntry type="library" name="Maven: com.databricks:spark-csv_2.11:1.5.0" level="project" />
173 + <orderEntry type="library" name="Maven: org.apache.commons:commons-csv:1.1" level="project" />
174 + </component>
175 +</module>
...\ No newline at end of file ...\ No newline at end of file
1 +<?xml version="1.0" encoding="UTF-8"?>
2 +<project version="4">
3 + <component name="MarkdownExportedFiles">
4 + <htmlFiles />
5 + <imageFiles />
6 + <otherFiles />
7 + </component>
8 +</project>
...\ No newline at end of file ...\ No newline at end of file
1 +<?xml version="1.0" encoding="UTF-8"?>
2 +<project version="4">
3 + <component name="MarkdownProjectSettings">
4 + <PreviewSettings splitEditorLayout="SPLIT" splitEditorPreview="PREVIEW" useGrayscaleRendering="false" zoomFactor="1.0" maxImageWidth="0" showGitHubPageIfSynced="false" allowBrowsingInPreview="false" synchronizePreviewPosition="true" highlightPreviewType="NONE" highlightFadeOut="5" highlightOnTyping="true" synchronizeSourcePosition="true" verticallyAlignSourceAndPreviewSyncPosition="true" showSearchHighlightsInPreview="false" showSelectionInPreview="true">
5 + <PanelProvider>
6 + <provider providerId="com.vladsch.idea.multimarkdown.editor.swing.html.panel" providerName="Default - Swing" />
7 + </PanelProvider>
8 + </PreviewSettings>
9 + <ParserSettings gitHubSyntaxChange="false">
10 + <PegdownExtensions>
11 + <option name="ABBREVIATIONS" value="false" />
12 + <option name="ANCHORLINKS" value="true" />
13 + <option name="ASIDE" value="false" />
14 + <option name="ATXHEADERSPACE" value="true" />
15 + <option name="AUTOLINKS" value="true" />
16 + <option name="DEFINITIONS" value="false" />
17 + <option name="DEFINITION_BREAK_DOUBLE_BLANK_LINE" value="false" />
18 + <option name="FENCED_CODE_BLOCKS" value="true" />
19 + <option name="FOOTNOTES" value="false" />
20 + <option name="HARDWRAPS" value="false" />
21 + <option name="HTML_DEEP_PARSER" value="false" />
22 + <option name="INSERTED" value="false" />
23 + <option name="QUOTES" value="false" />
24 + <option name="RELAXEDHRULES" value="true" />
25 + <option name="SMARTS" value="false" />
26 + <option name="STRIKETHROUGH" value="true" />
27 + <option name="SUBSCRIPT" value="false" />
28 + <option name="SUPERSCRIPT" value="false" />
29 + <option name="SUPPRESS_HTML_BLOCKS" value="false" />
30 + <option name="SUPPRESS_INLINE_HTML" value="false" />
31 + <option name="TABLES" value="true" />
32 + <option name="TASKLISTITEMS" value="true" />
33 + <option name="TOC" value="false" />
34 + <option name="WIKILINKS" value="true" />
35 + </PegdownExtensions>
36 + <ParserOptions>
37 + <option name="COMMONMARK_LISTS" value="true" />
38 + <option name="DUMMY" value="false" />
39 + <option name="EMOJI_SHORTCUTS" value="true" />
40 + <option name="FLEXMARK_FRONT_MATTER" value="false" />
41 + <option name="GFM_LOOSE_BLANK_LINE_AFTER_ITEM_PARA" value="false" />
42 + <option name="GFM_TABLE_RENDERING" value="true" />
43 + <option name="GITBOOK_URL_ENCODING" value="false" />
44 + <option name="GITHUB_EMOJI_URL" value="false" />
45 + <option name="GITHUB_LISTS" value="false" />
46 + <option name="GITHUB_WIKI_LINKS" value="true" />
47 + <option name="JEKYLL_FRONT_MATTER" value="false" />
48 + <option name="SIM_TOC_BLANK_LINE_SPACER" value="true" />
49 + </ParserOptions>
50 + </ParserSettings>
51 + <HtmlSettings headerTopEnabled="false" headerBottomEnabled="false" bodyTopEnabled="false" bodyBottomEnabled="false" embedUrlContent="false" addPageHeader="true">
52 + <GeneratorProvider>
53 + <provider providerId="com.vladsch.idea.multimarkdown.editor.swing.html.generator" providerName="Default Swing HTML Generator" />
54 + </GeneratorProvider>
55 + <headerTop />
56 + <headerBottom />
57 + <bodyTop />
58 + <bodyBottom />
59 + </HtmlSettings>
60 + <CssSettings previewScheme="UI_SCHEME" cssUri="" isCssUriEnabled="false" isCssTextEnabled="false" isDynamicPageWidth="true">
61 + <StylesheetProvider>
62 + <provider providerId="com.vladsch.idea.multimarkdown.editor.swing.html.css" providerName="Default Swing Stylesheet" />
63 + </StylesheetProvider>
64 + <ScriptProviders />
65 + <cssText />
66 + </CssSettings>
67 + <HtmlExportSettings updateOnSave="false" parentDir="$ProjectFileDir$" targetDir="$ProjectFileDir$" cssDir="" scriptDir="" plainHtml="false" imageDir="" copyLinkedImages="false" imageUniquifyType="0" targetExt="" useTargetExt="false" noCssNoScripts="false" linkToExportedHtml="true" exportOnSettingsChange="true" regenerateOnProjectOpen="false" />
68 + <LinkMapSettings>
69 + <textMaps />
70 + </LinkMapSettings>
71 + </component>
72 +</project>
...\ No newline at end of file ...\ No newline at end of file
1 +<component name="MarkdownNavigator.ProfileManager">
2 + <settings default="" pdf-export="" />
3 +</component>
...\ No newline at end of file ...\ No newline at end of file
...@@ -11,4 +11,14 @@ ...@@ -11,4 +11,14 @@
11 <component name="ProjectRootManager" version="2" languageLevel="JDK_1_8" project-jdk-name="1.8" project-jdk-type="JavaSDK"> 11 <component name="ProjectRootManager" version="2" languageLevel="JDK_1_8" project-jdk-name="1.8" project-jdk-type="JavaSDK">
12 <output url="file://$PROJECT_DIR$/out" /> 12 <output url="file://$PROJECT_DIR$/out" />
13 </component> 13 </component>
14 + <component name="MavenProjectsManager">
15 + <option name="originalFiles">
16 + <list>
17 + <option value="$PROJECT_DIR$/pom.xml" />
18 + </list>
19 + </option>
20 + </component>
21 + <component name="ProjectRootManager" version="2" languageLevel="JDK_1_8" default="false" project-jdk-name="1.8" project-jdk-type="JavaSDK">
22 + <output url="file:///tmp" />
23 + </component>
14 </project> 24 </project>
...\ No newline at end of file ...\ No newline at end of file
......
...@@ -2,7 +2,7 @@ ...@@ -2,7 +2,7 @@
2 <project xmlns="http://maven.apache.org/POM/4.0.0" 2 <project xmlns="http://maven.apache.org/POM/4.0.0"
3 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" 3 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
4 xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> 4 xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
5 - <modelVersion>4.0.0</modelVersion> 5 + <modelVersion>1.0.0</modelVersion>
6 6
7 <groupId>cesco</groupId> 7 <groupId>cesco</groupId>
8 <artifactId>Detecting_fraud_clicks</artifactId> 8 <artifactId>Detecting_fraud_clicks</artifactId>
...@@ -16,7 +16,7 @@ ...@@ -16,7 +16,7 @@
16 <artifactId>spark-core_2.11</artifactId> 16 <artifactId>spark-core_2.11</artifactId>
17 <version>2.3.0</version> 17 <version>2.3.0</version>
18 </dependency> 18 </dependency>
19 - <!-- https://mavnrepository.com/artifact/org.apache.spark/spark-sql --> 19 +
20 <dependency> 20 <dependency>
21 <groupId>org.apache.spark</groupId> 21 <groupId>org.apache.spark</groupId>
22 <artifactId>spark-sql_2.11</artifactId> 22 <artifactId>spark-sql_2.11</artifactId>
...@@ -28,21 +28,22 @@ ...@@ -28,21 +28,22 @@
28 <artifactId>spark-csv_2.11</artifactId> 28 <artifactId>spark-csv_2.11</artifactId>
29 <version>1.5.0</version> 29 <version>1.5.0</version>
30 </dependency> 30 </dependency>
31 - </dependencies>
32 31
32 + </dependencies>
33 33
34 - <!--maven-compiler-plugin-->
35 <build> 34 <build>
36 - <plugins> 35 + <plugins>
37 - <plugin> 36 + <plugin>
38 - <groupId>org.apache.maven.plugins</groupId> 37 + <groupId>org.apache.maven.plugins</groupId>
39 - <artifactId>maven-compiler-plugin</artifactId> 38 + <artifactId>maven-compiler-plugin</artifactId>
40 - <version>3.1</version> 39 + <version>3.6.1</version>
41 - <configuration> 40 + <configuration>
42 - <source>1.8</source> 41 + <source>1.8</source>
43 - <target>1.8</target> 42 + <target>1.8</target>
44 - </configuration> 43 + </configuration>
45 - </plugin> 44 + </plugin>
46 - </plugins> 45 + </plugins>
47 - </build> 46 + </build>
48 -</project> 47 +
48 +
49 +</project>
...\ No newline at end of file ...\ No newline at end of file
......
1 +import org.apache.spark.sql.Dataset;
2 +import org.apache.spark.sql.Row;
3 +import org.apache.spark.sql.SparkSession;
4 +import org.apache.spark.sql.expressions.Window;
5 +import org.apache.spark.sql.expressions.WindowSpec;
6 +
7 +import static org.apache.spark.sql.functions.col;
8 +import static org.apache.spark.sql.functions.count;
9 +import static org.apache.spark.sql.functions.sum;
10 +
11 +
12 +public class AvgAdvTime {
13 +
14 + public static void main(String[] args) throws Exception {
15 +
16 + // Start Spark Session
17 + SparkSession spark = SparkSession
18 + .builder()
19 + .master("local")
20 + .appName("Java Spark SQL basic example")
21 + .getOrCreate();
22 +
23 + // Read SCV to DataSet
24 + Dataset<Row> df = spark.read().format("csv")
25 + .option("inferSchema", "true")
26 + .option("header", "true")
27 + .load("train_sample.csv");
28 +
29 + // cast timestamp to long
30 + Dataset<Row> newdf = df.withColumn("utc_click_time", df.col("click_time").cast("long"));
31 + newdf = newdf.withColumn("utc_attributed_time", df.col("attributed_time").cast("long"));
32 + newdf = newdf.drop("click_time").drop("attributed_time");
33 +
34 + // set Window partition by 'ip' and 'app' order by 'utc_click_time' select rows between 1st row to current row
35 + WindowSpec w = Window.partitionBy("ip", "app")
36 + .orderBy("utc_click_time")
37 + .rowsBetween(Window.unboundedPreceding(), Window.currentRow());
38 +
39 + // aggregation
40 + newdf = newdf.withColumn("cum_count_click", count("utc_click_time").over(w));
41 + newdf = newdf.withColumn("cum_sum_attributed", sum("is_attributed").over(w));
42 + newdf = newdf.withColumn("avg_efficient", col("cum_sum_attributed").divide(col("cum_count_click")));
43 +
44 + // print example
45 + newdf.where("ip == '5348' and app == '19'").show();
46 + newdf.printSchema();
47 +
48 + }
49 +}
...\ No newline at end of file ...\ No newline at end of file
This diff could not be displayed because it is too large.