Initial commit

.gitignore

@@ -0,0 +1,9 @@
+build/
+*.pyc
+__pycache__
+scratch
+mallet*
+source/_static/
+source/generated
+source/cache
+datasets.zip

Makefile

@@ -0,0 +1,182 @@
+# Makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = /usr/bin/env sphinx-build
+PAPER         = a4
+BUILDDIR      = build
+
+# User-friendly check for sphinx-build
+ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)
+$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/)
+endif
+
+# Internal variables.
+PAPEROPT_a4     = -D latex_paper_size=a4
+PAPEROPT_letter = -D latex_paper_size=letter
+ALLSPHINXOPTS   = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) source
+# the i18n builder cannot share the environment and doctrees with the others
+I18NSPHINXOPTS  = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) source
+
+.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
+
+help:
+	@echo "Please use \`make <target>' where <target> is one of"
+	@echo "  html       to make standalone HTML files"
+	@echo "  dirhtml    to make HTML files named index.html in directories"
+	@echo "  singlehtml to make a single large HTML file"
+	@echo "  pickle     to make pickle files"
+	@echo "  json       to make JSON files"
+	@echo "  htmlhelp   to make HTML files and a HTML help project"
+	@echo "  qthelp     to make HTML files and a qthelp project"
+	@echo "  devhelp    to make HTML files and a Devhelp project"
+	@echo "  epub       to make an epub"
+	@echo "  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
+	@echo "  latexpdf   to make LaTeX files and run them through pdflatex"
+	@echo "  latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
+	@echo "  text       to make text files"
+	@echo "  man        to make manual pages"
+	@echo "  texinfo    to make Texinfo files"
+	@echo "  info       to make Texinfo files and run them through makeinfo"
+	@echo "  gettext    to make PO message catalogs"
+	@echo "  changes    to make an overview of all changed/added/deprecated items"
+	@echo "  xml        to make Docutils-native XML files"
+	@echo "  pseudoxml  to make pseudoxml-XML files for display purposes"
+	@echo "  linkcheck  to check all external links for integrity"
+	@echo "  doctest    to run all doctests embedded in the documentation (if enabled)"
+
+clean:
+	rm -rf $(BUILDDIR)/*
+
+html:
+	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
+
+dirhtml:
+	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
+
+singlehtml:
+	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
+	@echo
+	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
+
+pickle:
+	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
+	@echo
+	@echo "Build finished; now you can process the pickle files."
+
+json:
+	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
+	@echo
+	@echo "Build finished; now you can process the JSON files."
+
+htmlhelp:
+	$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
+	@echo
+	@echo "Build finished; now you can run HTML Help Workshop with the" \
+	      ".hhp project file in $(BUILDDIR)/htmlhelp."
+
+qthelp:
+	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
+	@echo
+	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
+	      ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
+	@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/TextAnalysiswithTopicModelsfortheGeisteswissenschaften.qhcp"
+	@echo "To view the help file:"
+	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/TextAnalysiswithTopicModelsfortheGeisteswissenschaften.qhc"
+
+devhelp:
+	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
+	@echo
+	@echo "Build finished."
+	@echo "To view the help file:"
+	@echo "# mkdir -p $$HOME/.local/share/devhelp/TextAnalysiswithTopicModelsfortheGeisteswissenschaften"
+	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/TextAnalysiswithTopicModelsfortheGeisteswissenschaften"
+	@echo "# devhelp"
+
+epub:
+	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
+	@echo
+	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
+
+latex:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo
+	@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
+	@echo "Run \`make' in that directory to run these through (pdf)latex" \
+	      "(use \`make latexpdf' here to do that automatically)."
+
+latexpdf:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through pdflatex..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+latexpdfja:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through platex and dvipdfmx..."
+	$(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+text:
+	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
+	@echo
+	@echo "Build finished. The text files are in $(BUILDDIR)/text."
+
+man:
+	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
+	@echo
+	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
+
+texinfo:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo
+	@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
+	@echo "Run \`make' in that directory to run these through makeinfo" \
+	      "(use \`make info' here to do that automatically)."
+
+info:
+	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
+	@echo "Running Texinfo files through makeinfo..."
+	make -C $(BUILDDIR)/texinfo info
+	@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
+
+gettext:
+	$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
+	@echo
+	@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
+
+changes:
+	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
+	@echo
+	@echo "The overview file is in $(BUILDDIR)/changes."
+
+linkcheck:
+	$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
+	@echo
+	@echo "Link check complete; look for any errors in the above output " \
+	      "or in $(BUILDDIR)/linkcheck/output.txt."
+
+doctest:
+	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
+	@echo "Testing of doctests in the sources finished, look at the " \
+	      "results in $(BUILDDIR)/doctest/output.txt."
+
+xml:
+	$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
+	@echo
+	@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
+
+pseudoxml:
+	$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
+	@echo
+	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."
+
+rsync:
+	rsync -avz build/html/ abr.webfactional.com:~/webapps/wuerzburg_text_analysis/ 
+	rsync -avz source/ abr.webfactional.com:~/webapps/wuerzburg_text_analysis/source/ 
+

README.rst

@@ -0,0 +1,19 @@
+TAToM: Text Analysis with Topic Models for the Humanities and Social Sciences
+=============================================================================
+
+*TAToM: Text Analysis with Topic Models for the Humanities and Social Sciences*
+consists of a series of tutorials that introduce basic procedures in
+quantitative text analysis with a particular focus on the preparation of a text
+corpus for analysis and on exploratory analysis using topic models and machine
+learning.
+
+These tutorials are addressed to an audience in the humanities and social
+sciences.
+
+Building
+========
+
+The project relies heavily on the ``ipython`` Sphinx directive, which is
+somewhat fragile.
+
+See ``requirements.txt`` for the packages required for building.

data/austen-brontë-split/Austen_Emma0000.txt

@@ -0,0 +1,102 @@
+EMMA
+BY
+JANE AUSTEN
+VOLUME I
+CHAPTER I
+Emma Woodhouse, handsome, clever, and rich, with a comfortable home and
+happy disposition, seemed to unite some of the best blessings of
+existence; and had lived nearly twenty-one years in the world with very
+little to distress or vex her.
+She was the youngest of the two daughters of a most affectionate,
+indulgent father; and had, in consequence of her sister's marriage,
+been mistress of his house from a very early period. Her mother had
+died too long ago for her to have more than an indistinct remembrance
+of her caresses; and her place had been supplied by an excellent woman
+as governess, who had fallen little short of a mother in affection.
+Sixteen years had Miss Taylor been in Mr. Woodhouse's family, less as a
+governess than a friend, very fond of both daughters, but particularly
+of Emma. Between _them_ it was more the intimacy of sisters. Even
+before Miss Taylor had ceased to hold the nominal office of governess,
+the mildness of her temper had hardly allowed her to impose any
+restraint; and the shadow of authority being now long passed away, they
+had been living together as friend and friend very mutually attached,
+and Emma doing just what she liked; highly esteeming Miss Taylor's
+judgment, but directed chiefly by her own.
+The real evils, indeed, of Emma's situation were the power of having
+rather too much her own way, and a disposition to think a little too
+well of herself; these were the disadvantages which threatened alloy to
+her many enjoyments. The danger, however, was at present so
+unperceived, that they did not by any means rank as misfortunes with
+her.
+Sorrow came--a gentle sorrow--but not at all in the shape of any
+disagreeable consciousness.--Miss Taylor married. It was Miss Taylor's
+loss which first brought grief. It was on the wedding-day of this
+beloved friend that Emma first sat in mournful thought of any
+continuance. The wedding over, and the bride-people gone, her father
+and herself were left to dine together, with no prospect of a third to
+cheer a long evening. Her father composed himself to sleep after
+dinner, as usual, and she had then only to sit and think of what she
+had lost.
+The event had every promise of happiness for her friend. Mr. Weston
+was a man of unexceptionable character, easy fortune, suitable age, and
+pleasant manners; and there was some satisfaction in considering with
+what self-denying, generous friendship she had always wished and
+promoted the match; but it was a black morning's work for her. The
+want of Miss Taylor would be felt every hour of every day. She
+recalled her past kindness--the kindness, the affection of sixteen
+years--how she had taught and how she had played with her from five
+years old--how she had devoted all her powers to attach and amuse her
+in health--and how nursed her through the various illnesses of
+childhood. A large debt of gratitude was owing here; but the
+intercourse of the last seven years, the equal footing and perfect
+unreserve which had soon followed Isabella's marriage, on their being
+left to each other, was yet a dearer, tenderer recollection. She had
+been a friend and companion such as few possessed: intelligent,
+well-informed, useful, gentle, knowing all the ways of the family,
+interested in all its concerns, and peculiarly interested in herself,
+in every pleasure, every scheme of hers--one to whom she could speak
+every thought as it arose, and who had such an affection for her as
+could never find fault.
+How was she to bear the change?--It was true that her friend was going
+only half a mile from them; but Emma was aware that great must be the
+difference between a Mrs. Weston, only half a mile from them, and a
+Miss Taylor in the house; and with all her advantages, natural and
+domestic, she was now in great danger of suffering from intellectual
+solitude. She dearly loved her father, but he was no companion for
+her. He could not meet her in conversation, rational or playful.
+The evil of the actual disparity in their ages (and Mr. Woodhouse had
+not married early) was much increased by his constitution and habits;
+for having been a valetudinarian all his life, without activity of mind
+or body, he was a much older man in ways than in years; and though
+everywhere beloved for the friendliness of his heart and his amiable
+temper, his talents could not have recommended him at any time.
+Her sister, though comparatively but little removed by matrimony, being
+settled in London, only sixteen miles off, was much beyond her daily
+reach; and many a long October and November evening must be struggled
+through at Hartfield, before Christmas brought the next visit from
+Isabella and her husband, and their little children, to fill the house,
+and give her pleasant society again.
+Highbury, the large and populous village, almost amounting to a town,
+to which Hartfield, in spite of its separate lawn, and shrubberies, and
+name, did really belong, afforded her no equals. The Woodhouses were
+first in consequence there. All looked up to them. She had many
+acquaintance in the place, for her father was universally civil, but
+not one among them who could be accepted in lieu of Miss Taylor for
+even half a day. It was a melancholy change; and Emma could not but
+sigh over it, and wish for impossible things, till her father awoke,
+and made it necessary to be cheerful. His spirits required support.
+He was a nervous man, easily depressed; fond of every body that he was
+used to, and hating to part with them; hating change of every kind.
+Matrimony, as the origin of change, was always disagreeable; and he was
+by no means yet reconciled to his own daughter's marrying, nor could
+ever speak of her but with compassion, though it had been entirely a
+match of affection, when he was now obliged to part with Miss Taylor
+too; and from his habits of gentle selfishness, and of being never able
+to suppose that other people could feel differently from himself, he
+was very much disposed to think Miss Taylor had done as sad a thing for
+herself as for them, and would have been a great deal happier if she
+had spent all the rest of her life at Hartfield. Emma smiled and
+chatted as cheerfully as she could, to keep him from such thoughts; but
+when tea came, it was impossible for him not to say exactly as he had
+said at dinner,
+"Poor Miss