illy’s gists

illy / reordering1.r

Last active December 15, 2015 14:59

recording in ggplot

	sample <- read.table("~/Dropbox/sample.txt", header=T, sep="\t")

	p <- ggplot(sample)
	p <- p + geom_boxplot(aes(x=factor(Type), y=Word, fill=factor(Type)), notch=T, outlier.shape = NA) +
	theme(axis.text.x=element_text(angle=15, hjust=0.8, vjust=1, size=12),
	axis.text.y=element_text(size=12)) +
	guides(fill=F) + scale_fill_grey() +
	scale_y_continuous(limits = c(0, 30))
	print(p)

illy / reordering2.r

Last active December 15, 2015 14:59

	sample <- read.table("~/Dropbox/sample.txt", header=T, sep="\t")

	p <- ggplot(sample)
	p <- p + geom_boxplot(aes(x=factor(Type), y=Word, fill=factor(Type)), notch=T, outlier.shape = NA) +
	theme(axis.text.x=element_text(angle=15, hjust=0.8, vjust=1, size=12),
	axis.text.y=element_text(size=12)) +
	guides(fill=F) + scale_fill_grey() +
	scale_x_discrete(limits=c("NSR", "stock-related", "NTR", "ticker-related", "NEG", "NEU", "POS")) +
	scale_y_continuous(limits = c(0, 30))
	print(p)

illy / reordering3.r

Last active December 15, 2015 14:59

	sample <- read.table("~/Dropbox/sample.txt", header=T, sep="\t")
	sample$Type <- factor(sample$Type, levels = c("NSR", "stock-related", "NTR", "ticker-related", "NEG", "NEU", "POS"))

	p <- ggplot(sample)
	p <- p + geom_boxplot(aes(x=factor(Type), y=Word, fill=factor(Type)), notch=T, outlier.shape = NA) +
	theme(axis.text.x=element_text(angle=15, hjust=0.8, vjust=1, size=12),
	axis.text.y=element_text(size=12))
	guides(fill=F) + scale_fill_grey() +
	scale_y_continuous(limits = c(0, 30))
	print(p)

illy / reordering4.r

Created March 30, 2013 23:27

	sample <- read.table("~/Dropbox/sample.txt", header=T, sep="\t")

	p <- ggplot(sample)
	p <- p + geom_boxplot(aes(x=factor(Type), y=Word, fill=factor(Type)), notch=T, outlier.shape = NA) +
	theme(axis.text.x=element_text(angle=15, hjust=0.8, vjust=1, size=12),
	axis.text.y=element_text(size=12)) +
	guides(fill=F) +
	scale_x_discrete(limits=c("NSR", "stock-related", "NTR", "ticker-related", "NEG", "NEU", "POS")) +
	scale_fill_manual(values=c("grey60", "grey60", "skyblue1", "grey60", "grey60", "skyblue1", "grey60" ), guide=FALSE) +
	scale_y_continuous(limits = c(0, 30))

illy / reordering5.r

Created March 30, 2013 23:28

	sample <- read.table("~/Dropbox/sample.txt", header=T, sep="\t")
	sample$Type <- factor(sample$Type, levels = c("NSR", "stock-related", "NTR", "ticker-related", "NEG", "NEU", "POS"))

	p <- ggplot(sample)
	p <- p + geom_boxplot(aes(x=factor(Type), y=Word, fill=factor(Type)), notch=T, outlier.shape = NA) +
	theme(axis.text.x=element_text(angle=15, hjust=0.8, vjust=1, size=12),
	axis.text.y=element_text(size=12)) +
	guides(fill=F) +
	scale_fill_manual(values=c("skyblue1", "skyblue1", "grey60", "grey60", "grey60", "grey60", "grey60" ), guide=FALSE) +
	scale_y_continuous(limits = c(0, 30))

illy / LM_POS.txt

Last active December 15, 2015 15:59

awk script for generating a matrix for PCA

illy / price_sample.tsv

Created April 25, 2013 12:25

We can make this file beautiful and searchable if this error is corrected: No tabs found in this TSV file in line 0.

illy / dataframeA.tsv

Last active December 17, 2015 08:59

We can make this file beautiful and searchable if this error is corrected: No tabs found in this TSV file in line 0.

illy / twitter_lib.bib

Last active December 22, 2015 06:09

my current collection of papers on Twitter and tweets, including 253 papers.

	%% This BibTeX bibliography file in UTF-8 format was created using Papers.
	%% http://mekentosj.com/papers/

	@article{turner_praise_2012,
	author = {Julia Turner},
	journal = {The New York Times},
	title = {In Praise of the Hashtag},
	chapter = {Magazine},
	year = {2012},
	keywords = {Twitter},

illy / twitter_ling.bib

Created September 3, 2013 20:29

This sub-library contains the papers about linguistics and Twitter, including 43 papers.

	%% This BibTeX bibliography file in UTF-8 format was created using Papers.
	%% http://mekentosj.com/papers/

	@article{Williams:2012p29780,
	author = {J Williams},
	journal = {Proceedings of the 2012 Student Research Workshop, EMNLP2012},
	title = {Extracting fine-grained durations for verbs from Twitter},
	abstract = {We seek to automatically estimate typical durations for events and habits described in Twitter tweets. A corpus of more than 14 million tweets containing temporal du- ration information was collected. These tweets were classified as to their habituality status using a bootstrapped, decision tree. For each verb lemma, associated duration information was collected for episodic and habitual uses of the verb. Summary statis- tics for 483 verb lemmas and their typical habit and episode durations has been com- piled and made available. This automati- cally generated duration information is broadly comparable to hand-annotation.},
	pages = {49},
	year = {2012},