submit

.gitattributes

@@ -0,0 +1,22 @@
+# Auto detect text files and perform LF normalization
+* text=auto
+
+# Custom for Visual Studio
+*.cs     diff=csharp
+*.sln    merge=union
+*.csproj merge=union
+*.vbproj merge=union
+*.fsproj merge=union
+*.dbproj merge=union
+
+# Standard to msysgit
+*.doc	 diff=astextplain
+*.DOC	 diff=astextplain
+*.docx diff=astextplain
+*.DOCX diff=astextplain
+*.dot  diff=astextplain
+*.DOT  diff=astextplain
+*.pdf  diff=astextplain
+*.PDF	 diff=astextplain
+*.rtf	 diff=astextplain
+*.RTF	 diff=astextplain

.gitignore

@@ -0,0 +1,215 @@
+#################
+## Eclipse
+#################
+
+*.pydevproject
+.project
+.metadata
+bin/
+tmp/
+*.tmp
+*.bak
+*.swp
+*~.nib
+local.properties
+.classpath
+.settings/
+.loadpath
+
+# External tool builders
+.externalToolBuilders/
+
+# Locally stored "Eclipse launch configurations"
+*.launch
+
+# CDT-specific
+.cproject
+
+# PDT-specific
+.buildpath
+
+
+#################
+## Visual Studio
+#################
+
+## Ignore Visual Studio temporary files, build results, and
+## files generated by popular Visual Studio add-ons.
+
+# User-specific files
+*.suo
+*.user
+*.sln.docstates
+
+# Build results
+
+[Dd]ebug/
+[Rr]elease/
+x64/
+build/
+[Bb]in/
+[Oo]bj/
+
+# MSTest test Results
+[Tt]est[Rr]esult*/
+[Bb]uild[Ll]og.*
+
+*_i.c
+*_p.c
+*.ilk
+*.meta
+*.obj
+*.pch
+*.pdb
+*.pgc
+*.pgd
+*.rsp
+*.sbr
+*.tlb
+*.tli
+*.tlh
+*.tmp
+*.tmp_proj
+*.log
+*.vspscc
+*.vssscc
+.builds
+*.pidb
+*.log
+*.scc
+
+# Visual C++ cache files
+ipch/
+*.aps
+*.ncb
+*.opensdf
+*.sdf
+*.cachefile
+
+# Visual Studio profiler
+*.psess
+*.vsp
+*.vspx
+
+# Guidance Automation Toolkit
+*.gpState
+
+# ReSharper is a .NET coding add-in
+_ReSharper*/
+*.[Rr]e[Ss]harper
+
+# TeamCity is a build add-in
+_TeamCity*
+
+# DotCover is a Code Coverage Tool
+*.dotCover
+
+# NCrunch
+*.ncrunch*
+.*crunch*.local.xml
+
+# Installshield output folder
+[Ee]xpress/
+
+# DocProject is a documentation generator add-in
+DocProject/buildhelp/
+DocProject/Help/*.HxT
+DocProject/Help/*.HxC
+DocProject/Help/*.hhc
+DocProject/Help/*.hhk
+DocProject/Help/*.hhp
+DocProject/Help/Html2
+DocProject/Help/html
+
+# Click-Once directory
+publish/
+
+# Publish Web Output
+*.Publish.xml
+*.pubxml
+
+# NuGet Packages Directory
+## TODO: If you have NuGet Package Restore enabled, uncomment the next line
+#packages/
+
+# Windows Azure Build Output
+csx
+*.build.csdef
+
+# Windows Store app package directory
+AppPackages/
+
+# Others
+sql/
+*.Cache
+ClientBin/
+[Ss]tyle[Cc]op.*
+~$*
+*~
+*.dbmdl
+*.[Pp]ublish.xml
+*.pfx
+*.publishsettings
+
+# RIA/Silverlight projects
+Generated_Code/
+
+# Backup & report files from converting an old project file to a newer
+# Visual Studio version. Backup files are not needed, because we have git ;-)
+_UpgradeReport_Files/
+Backup*/
+UpgradeLog*.XML
+UpgradeLog*.htm
+
+# SQL Server files
+App_Data/*.mdf
+App_Data/*.ldf
+
+#############
+## Windows detritus
+#############
+
+# Windows image file caches
+Thumbs.db
+ehthumbs.db
+
+# Folder config file
+Desktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Mac crap
+.DS_Store
+
+
+#############
+## Python
+#############
+
+*.py[co]
+
+# Packages
+*.egg
+*.egg-info
+dist/
+build/
+eggs/
+parts/
+var/
+sdist/
+develop-eggs/
+.installed.cfg
+
+# Installer logs
+pip-log.txt
+
+# Unit test / coverage reports
+.coverage
+.tox
+
+#Translations
+*.mo
+
+#Mr Developer
+.mr.developer.cfg

README.md

@@ -0,0 +1,6 @@
+# PLSA (Probabilistic Latent Semantic Analysis) implementation via the EM (Expectation-Maximization) algorithm
+
+# lipiji.sdu@gmail.com
+
+# Reference:
+	[1] https://github.com/hitalex/PLSA

data/events_2010/GulfOilSpill/0091.txt

@@ -0,0 +1,33 @@
+From 'static kill' to 'bottom kill��: next steps in Gulf oil spill
+
+BP readies plans to permanently seal the ruptured well in the Gulf oil spill through two operations in the next two weeks �C the initial ��static kill�� followed by the final ��bottom kill.��
+
+
+A response vessel is seen along a line of emulsified oil between the Deepwater Horizon oil spill site and the Louisiana coast in the Gulf of Mexico, off the Louisiana coast, Monday.
+
+With the operation to permanently seal the runaway well at the center of the Gulf oil spill set to begin as early as the week after next, relief efforts are already casting an eye to the longer-term future to determine "how clean is clean" and when they will begin to draw down resources.
+
+
+A coordinated effort to clean up residual oil left standing in marshes and beaches will continue through September, said retired Coast Guard Adm. Thad Allen, who is overseeing the federal effort, in a press briefing Monday.
+
+This week BP and Coast Guard officials are preparing what they call a ��bottom kill�� �C the permanent sealing of the runaway Macondo well through one of the two relief wells drilled 13,000 feet below the seafloor. According to Allen, BP will deposit through the relief well a combination of drilling mud, cement, liquids, and nitrogen to stop the flow of oil �C perhaps as early as Aug. 7.
+
+That operation will come after ��static kill,�� which has a tentative start date of next Monday. Static kill would deposit the same mixture of materials into the top of the well. Unlike ��top kill�� in late May, which employed the same tactic, static kill is considered a more realistic solution to preventing oil flow because the container cap, installed in mid-July, is providing a tighter seal around the wellhead and therefore won't allow oil and gas to escape.
+
+Both operations are being prepared simultaneously. Monday the well lines are being reattached to the riser pipes that extend from the seafloor to near the surface, after they were temporarily abandoned this weekend due to the threat of tropical storm Bonnie. Both lines will be flushed to remove sediments.
+
+Starting Wednesday and continuing through Sunday, the lines will each be fitted with a 2,000-foot internal casing pipe that will carry the materials downward. Once they are in place, the static kill operation will occur, likely Monday. The entire endeavor is set to prepare the launch of the relief well operation.
+
+��The week after next we will have the potential �� to begin killing the well,�� he said.
+
+Despite the tight time schedule, Allen said the Coast Guard is starting to transition resources to address cleanup efforts long past the moment the well is permanently shut down.
+
+Aerial surveillance from this past weekend shows there are at least ��hundreds of thousands of [oil] patches�� on the surface of Gulf waters and, because the oil can biodegrade into small fragments, locating their residual forms is expected to take between four to six weeks after the well is sealed, Allen said.
+
+��We��re going to have [oil] tarballs and other impacts going on for a long, long time and we have to prepare,�� he said.
+
+Allen said he is starting to meet with local government officials to establish guidelines for ��how clean is clean�� regarding oil findings in their communities. Because the most elusive oil will end up out of sight, he wants to create a protocol for addressing oil should it be discovered in coming months.
+
+He envisioned a scenario where oil might be discovered underneath a beach. In that case, the oil would be tested to determine if it originated from the Macondo well. If it did, BP would be alerted to clean the area.
+
+��When I say there��s hundreds of thousands of patches, it is literally that, but they��re not as large as they used to be, so they��re harder to locate,�� Allen said. ��There��s definitely oil out there and we need to be able to deal with it.��

data/events_2010/GulfOilSpill/0092.txt

@@ -0,0 +1,23 @@
+Gulf oil spill: Will Obama regret his '90 percent' promise?
+
+President Obama said in his Oval Office address that he wants "up to 90 percent" of the Gulf oil spill leak contained by the end of the month. He is putting his faith in an uncertain BP plan.
+
+President Barack Obama speaks in the White House's State Dining Room Wednesday after meeting with BP executives. Obama has said that he wants to see 'up to 90 percent' of the Gulf oil spill geyser contained in the next few weeks. 
+
+President Obama's declaration that he'd like to see "up to 90 percent" of the Gulf oil spill geyser contained in the next few weeks is a best-case scenario in a worst-case kind of disaster.
+
+
+From the beginning, BP has failed to meet expectations either to kill the well or contain the oil flowing from it. The containment dome clogged. The "top kill" failed. The "junk shot" accomplished nothing. Even the relatively successful "top cap" operation is apparently still leaking as much as 42,000 barrels (1.8 million gallons) of oil into the Gulf of Mexico daily.
+
+BP and its promises to stem the oil are firmly in "the boy who cried wolf" territory. Yet Mr. Obama, in one of the most important speeches of his presidency, pinned no small amount of his credibility in the crisis on a plan that BP itself is trying to downplay.
+
+Given BP's performance, it was unwise �C and unnecessary, to boot, says Alan Abramowitz, a political scientist at Emory University in Atlanta.
+
+"The '90 percent' line reminds me about the promise that if the stimulus bill is passed, unemployment will peak at 8 percent," says Mr. Abramowitz. "He could've said, 'We'll be able to capture more of it,' but when you put out a number, then people are going to come back and say, 'How come this didn't happen?' From everything that's happened so far, I'd be surprised if they can actually achieve that."
+Obama's victories
+
+On Wednesday, Obama won major concessions from BP, including a $20 billion escrow fund and a promise by the company to suspend stockholder dividend payments. But for the Gulf Coast �C and much of America �C the primary question remains: When is the oil going to stop?
+
+"His promise of '90 percent containment' right around the corner was a huge risk to buy short-term traction," writes Rodger Jones, editorial writer for the Dallas Morning News, on the Dallas Morning Views blog.
+
+The president's statement came only a few days after BP had to backtrack on executive Doug Suttles's comment that the flow at the Macondo well would close to "a trickle" soon. Moreover, they've had to defend early decisions not to calculate the flow rate accurately �C saying it wasn't important. 

data/events_2010/GulfOilSpill/0093.txt

@@ -0,0 +1,71 @@
+President Barack Obama meets fishermen affected by the oil spill in Venice, Louisiana. Source: AP
+
+THE Obama administration, facing growing public anger over the Gulf of Mexico oil spill, plans to ask BP to establish an independently administered fund for reimbursing victims -- in effect, taking some of the compensation decisions out of the company's hands.
+
+The calls came as BP said over the weekend it was now collecting about 15,000 barrels of oil a day at the site, due to a special cap installed over the leaking pipe. US officials upped their leak estimate last week to as much as 40,000 barrels a day, although yesterday, Coast Guard Admiral Thad Allen said they believe the leak was closer to 35,000 barrels a day.
+
+White House officials yesterday said they wanted BP to put "substantial" funds into an escrow account to cover claims by Gulf Coast businesses and residents affected by the spill.
+
+President Barack Obama plans to bring up the idea at a White House meeting Wednesday with top BP executives, including chairman Carl-Henric Svanberg. 
+
+The call was echoed by congressional leaders and state officials.
+
+In a June 10 letter to BP released yesterday, Senate Majority Leader Harry Reid and other Democrats asked BP to establish a $US20 billion ($23.4bn) account, administered by an independent trustee, that would be used to pay the damages and clean-up costs associated with the spill. Florida Governor Charlie Crist and other officials in the Gulf Coast region joined the chorus.
+
+It remained unclear how any such funds would be supervised, in particular who would oversee the compensation decisions. Administration officials yesterday didn't comment on the size of the escrow account they will seek, or on where money might come from. Nor did officials detail the legal status of the proposal.
+
+Such a fund would provide a measure of security, proponents argue, for people concerned BP might file for bankruptcy protection or otherwise stop paying claims at some point in the future. It also has the potential to give the government or its designees control of distributing a significant pool of relief money.
+
+People familiar with BP said that the company understood any such account wouldn't include money originally earmarked for dividend payments.
+
+A BP spokesman said yesterday the company expects to discuss the escrow account proposal with President Obama on Wednesday. "We're preparing our response and we want to respond constructively," he said.
+While not opposed to the idea of the fund, BP objects to the implication that if it isn't required to set money aside, it might try to avoid paying it in full, according to a person familiar with the company's position.
+
+BP insists it has the financial muscle to settle the final bill for the clean-up, as well as pay to its dividend.
+
+Legal experts struggled to come up with a precedent for such a move. Examples of government-run funds exist, but they differ from the proposal facing BP.
+
+In the early 1980s the government passed Superfund legislation that would create a fund to pay for the cleanup of hazardous-waste dump sites.
+
+Through the law, the Environmental Protection Agency can compel the polluter to clean up the site or pay for it through the Superfund and sue for reimbursement.
+
+Around the same time, the first of about 40 trust funds were set up with court approval by Johns Manville Corporation and later other companies with asbestos liability to alleviate some of the problems of lengthy asbestos-related litigation. But their creation stemmed from bankruptcy proceedings for Johns Manville. The trusts now oversee about $US20bn in assets, a sum that has nearly tripled since 2005, consultants say.
+
+Richard Nagareda, a law professor at Vanderbilt University, said the numerous civil lawsuits relating to the Gulf oil spill could be in jeopardy, because BP could argue victims can't have double compensation. But it could be advantageous for BP to agree to the President's idea if the company gets some kind of liability protection.
+
+"This really is sort of like a gigantic class settlement but with the government representing the victims," he said. "What affect does this have on the oodles and oodles of private lawsuits already on file?"
+
+Over the weekend, US officials told BP to devise a more effective plan for containing the oil that has been gushing from its deepwater well since April 20. They also demanded the company put more ships and other resources in the Gulf in case of additional equipment failures.
+
+BP said it would respond to the Coast Guard by the US-set deadline to lay out a more-aggressive plan, but declined further comment.
+
+Last week, Mr Obama suggested BP suspend its second-quarter dividend payout so the company could pay claims by Gulf Coast residents.
+
+Many Americans say the company shouldn't be rewarding shareholders while oil continues to spill into the Gulf and wash onto US shores.
+
+On Saturday, Mr Obama spoke with British Prime Minister David Cameron during a 30-minute phone call designed to lessen tensions on both sides of the Atlantic over the oil leak.
+
+BP has proposed installing new systems to collect more oil spilling from the site. However the most effective of those systems -- which could collect an estimated 40,000 to 50,000 barrels a day -- wouldn't be completed until mid-July.
+
+The escrow-fund and other demands come as anger continues to grow in the US over the failure by BP and US officials alike to stop the leak, which has started to wash ashore, killing wildlife and threatening the livelihoods of residents in coastal states.
+
+BP's directors were expected to discuss the idea of a clean-up fund in London at their weekly board meeting today. It will be one of the options that they will be asked to look at ahead of the White House meeting. Other options under consideration include cutting or deferring the company's second-quarter dividend, or paying it in scrip -- a kind of IOU -- as a way of easing the pressure on the company from the Obama administration.
+
+Last month, BP said it was appointing an independent mediator to review and assist with claims, a step which it says shows it understands the need for external oversight. "It's important that there's a set of rules that allow people to have confidence in the claims process," said a person familiar with the company.
+
+In Alabama, frustration about cleanup and containment efforts mounted yesterday as oil washed up on stretches of white beaches for a second straight day and threatened inlets.
+
+Authorities ramped up efforts to limit the damage but struggled in big tourist towns such as Orange Beach and Gulf Shores, where oil that was alternately thick and gooey or fine like ground-up coffee gathered in the surf and spread across the sand.
+
+"It's disgusting. They ought to have the military out here," said Becky Sutton, 63, an Orange Beach resident, as she stood on one stretch of beach that had turned brown at the water's edge.
+
+Tourists typically spend more than $US1.5bn along the state's coast between Memorial Day and Labor Day.
+Authorities said more than 1900 workers were deployed to help clean up the state's beaches yesterday, up from about 1200 a few days ago. BP is paying for the clean-up efforts through private contractors.
+
+A Federal Reserve report on the US economy last week said business contacts indicated that the potential impact on the tourism industry along the coastlines of Louisiana, Mississippi, Alabama and western Florida could be substantial.
+
+President Obama is expected to try to keep up the pressure on the oil giant this week, after heading back to the Gulf Coast for his third visit today and tomorrow to assess cleanup efforts in Mississippi, Alabama and Florida.
+
+He will address the nation tomorrow night after he returns from his trip to the Gulf, White House aides said.
+
+Additional reporting Dionne Searcey, Andrew Morse, Mike Esterl and Perry Stein