Merge pull request #6 from metamx/docs

Docs

.gitignore

@@ -1,4 +1,5 @@
 *.pyc
 test.py
 pydruid/bard.py
-.idea/
+.DS_store
+.idea/

README.md

@@ -0,0 +1,128 @@
+#pydruid
+pydruid exposes a simple API to create, execute, and analyze [Druid](http://druid.io/) queries. pydruid can parse query results into [Pandas](http://pandas.pydata.org/) DataFrame objects for subsequent data analysis -- this offers a tight integration between [Druid](http://druid.io/), the [SciPy](http://www.scipy.org/stackspec.html) stack (for scientific computing) and [scikit-learn](http://scikit-learn.org/stable/) (for machine learning). Additionally, pydruid can export query results into TSV or JSON for further processing with your favorite tool, e.g., R, Julia, Matlab, Excel.
+
+#examples
+
+The following exampes show how to execute and analyze the results of three types of queries: timeseries, topN, and groupby. We will use these queries to ask simple questions about twitter's public data set.
+
+## timeseries 
+
+What was the average tweet length, per day, surrounding the 2014 Sochi olympics?
+
+```python
+from pydruid.client import *
+from pylab import plt
+
+query = PyDruid(bard_url_goes_here, 'druid/v2')
+
+ts = query.timeseries(
+    datasource='twitterstream',
+    granularity='day',
+    intervals='2014-02-02/p4w',
+    aggregations={'length': doublesum('tweet_length'), 'count': doublesum('count')},
+    post_aggregations={'avg_tweet_length': (Field('length') / Field('count'))},
+    filter=Dimension('first_hashtag') == 'sochi2014'
+)
+df = query.export_pandas()
+df['timestamp'] = df['timestamp'].map(lambda x: x.split('T')[0])
+df.plot(x='timestamp', y='avg_tweet_length', ylim=(80, 140), rot=20,
+        title='Sochi 2014')
+plt.ylabel('avg tweet length (chars)')
+plt.show()
+```
+
+![alt text](https://github.com/metamx/pydruid/raw/docs/docs/figures/avg_tweet_length.png "Avg. tweet length")
+
+## topN 
+
+Who were the top ten mentions (@user_name) during the 2014 Oscars?
+
+```python
+top = query.topn(
+    datasource='twitterstream',
+    granularity='all',
+    intervals='2014-03-03/p1d',  # utc time of 2014 oscars
+    aggregations={'count': doublesum('count')},
+    dimension='user_mention_name',
+    filter=(Dimension('user_lang') == 'en') & (Dimension('first_hashtag') == 'oscars') &
+           (Dimension('user_time_zone') == 'Pacific Time (US & Canada)') &
+           ~(Dimension('user_mention_name') == 'No Mention'),
+    metric='count',
+    threshold=10
+)
+
+df = query.export_pandas()
+print df
+
+   count                 timestamp user_mention_name
+0   1303  2014-03-03T00:00:00.000Z      TheEllenShow
+1     44  2014-03-03T00:00:00.000Z        TheAcademy
+2     21  2014-03-03T00:00:00.000Z               MTV
+3     21  2014-03-03T00:00:00.000Z         peoplemag
+4     17  2014-03-03T00:00:00.000Z               THR
+5     16  2014-03-03T00:00:00.000Z      ItsQueenElsa
+6     16  2014-03-03T00:00:00.000Z           eonline
+7     15  2014-03-03T00:00:00.000Z       PerezHilton
+8     14  2014-03-03T00:00:00.000Z     realjohngreen
+9     12  2014-03-03T00:00:00.000Z       KevinSpacey
+
+```
+
+## groupby
+
+What does the social network of users replying to other users look like?
+
+```python
+from igraph import *
+from cairo import *
+from pandas import concat
+
+group = query.groupby(
+    datasource='twitterstream',
+    granularity='hour',
+    intervals='2013-10-04/pt12h',
+    dimensions=["user_name", "reply_to_name"],
+    filter=(~(Dimension("reply_to_name") == "Not A Reply")) &
+           (Dimension("user_location") == "California"),
+    aggregations={"count": doublesum("count")}
+)
+
+df = query.export_pandas()
+
+# map names to categorical variables with a lookup table
+names = concat([df['user_name'], df['reply_to_name']]).unique()
+nameLookup = dict([pair[::-1] for pair in enumerate(names)])
+df['user_name_lookup'] = df['user_name'].map(nameLookup.get)
+df['reply_to_name_lookup'] = df['reply_to_name'].map(nameLookup.get)
+
+# create the graph with igraph
+g = Graph(len(names), directed=False)
+vertices = zip(df['user_name_lookup'], df['reply_to_name_lookup'])
+g.vs["name"] = names
+g.add_edges(vertices)
+layout = g.layout_fruchterman_reingold()
+plot(g, "tweets.png", layout=layout, vertex_size=2, bbox=(400, 400), margin=25, edge_width=1, vertex_color="blue")
+```
+
+![alt text](https://github.com/metamx/pydruid/raw/docs/docs/figures/twitter_graph.png "Social Network")
+
+
+#documentation
+
+pydruid is a [Sphinx](http://sphinx-doc.org/) project. You can view documentation locally by opening the following with a web browser: 
+
+```python
+pydruid/docs/build/html/index.html
+```
+
+The docstrings are written in [ReStructuredText](http://docutils.sourceforge.net/rst.html). If edited, documentation can be re-generated by running:
+
+```python
+make html
+```
+
+from within the docs directory, assuming Sphinx is installed on your machine.
+
+
+
+

docs/Makefile

@@ -0,0 +1,177 @@
+# Makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+PAPER         =
+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/PyDruid.qhcp"
+	@echo "To view the help file:"
+	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/PyDruid.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/PyDruid"
+	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/PyDruid"
+	@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."

docs/build/html/.buildinfo

@@ -0,0 +1,4 @@
+# Sphinx build info version 1
+# This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
+config: e0a9069122c14226639caf781d513013
+tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/build/html/_sources/index.txt

@@ -0,0 +1,25 @@
+.. PyDruid documentation master file, created by
+   sphinx-quickstart on Mon Mar  3 16:38:17 2014.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to PyDruid's documentation!
+===================================
+
+Contents:
+
+.. toctree::
+   :maxdepth: 2
+
+.. automodule:: pydruid
+
+.. autoclass:: client.PyDruid
+    :members:
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
+