From 320ced14b915d41db5f1f1b894314da62573f82e Mon Sep 17 00:00:00 2001
From: qimingj <qimingj@users.noreply.github.com>
Date: Thu, 8 Dec 2016 17:38:33 -0800
Subject: [PATCH 01/19] Add gcs_copy_file() that is missing but is referenced
 in a couple of places. (#110)

* Add gcs_copy_file() that is missing but is referenced in a couple of places.

* Add DataFlow to pydatalab dependency list.

* Fix travis test errors by reimplementing gcs copy.

* Remove unnecessary shutil import.
---
 datalab/utils/__init__.py |  2 +-
 datalab/utils/_utils.py   | 11 +++++++++++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/datalab/utils/__init__.py b/datalab/utils/__init__.py
index bcf33ea40..fa5434992 100644
--- a/datalab/utils/__init__.py
+++ b/datalab/utils/__init__.py
@@ -21,4 +21,4 @@
 from ._lru_cache import LRUCache
 from ._lambda_job import LambdaJob
 from ._utils import print_exception_with_last_stack, get_item, compare_datetimes, \
-                    pick_unused_port, is_http_running_on
+                    pick_unused_port, is_http_running_on, gcs_copy_file
diff --git a/datalab/utils/_utils.py b/datalab/utils/_utils.py
index 3e453e647..53ba94409 100644
--- a/datalab/utils/_utils.py
+++ b/datalab/utils/_utils.py
@@ -22,6 +22,7 @@
     import httplib
 
 import pytz
+import subprocess
 import socket
 import traceback
 import types
@@ -110,3 +111,13 @@ def is_http_running_on(port):
     return True
   except Exception as e:
     return False
+
+
+def gcs_copy_file(source, dest):
+  """ Copy file from source to destination. The paths can be GCS or local.
+
+  Args:
+    source: the source file path.
+    dest: the destination file path.
+  """
+  subprocess.check_call(['gsutil', '-q', 'cp', source, dest])

From 7320b39553c75fa0b5624eb861a92e800436a326 Mon Sep 17 00:00:00 2001
From: Anthonios Partheniou <apartheniou@electricalengineer.ca>
Date: Sun, 11 Dec 2016 12:42:07 -0500
Subject: [PATCH 02/19] Flake8 configuration. Set max line length to 100.
 Ignore E111, E114 (#102)

---
 setup.cfg | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/setup.cfg b/setup.cfg
index 8c2826799..970f3f031 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,3 +1,11 @@
 [metadata]
 description-file = README.md
 
+[flake8]
+max-line-length = 100
+ignore =
+    # Indentation is not a multiple of four
+    E111,
+    # Indentation is not a multiple of four (comment)
+    E114
+

From f77abd65214af32635f63abafb193136c415bc46 Mon Sep 17 00:00:00 2001
From: qimingj <qimingj@users.noreply.github.com>
Date: Mon, 12 Dec 2016 18:19:52 -0800
Subject: [PATCH 03/19] Add datalab user agent to CloudML trainer and predictor
 requests. (#112)

---
 datalab/mlalpha/_cloud_predictor.py | 1 +
 datalab/mlalpha/_cloud_runner.py    | 1 +
 2 files changed, 2 insertions(+)

diff --git a/datalab/mlalpha/_cloud_predictor.py b/datalab/mlalpha/_cloud_predictor.py
index 6ecc357e6..8209d77a1 100644
--- a/datalab/mlalpha/_cloud_predictor.py
+++ b/datalab/mlalpha/_cloud_predictor.py
@@ -81,6 +81,7 @@ def predict(self, data):
 
     request = self._api.projects().predict(body={'instances': data},
                                            name=self._full_version_name)
+    request.headers['user-agent'] = 'GoogleCloudDataLab/1.0'
     result = request.execute()
     if 'predictions' not in result:
       raise Exception('Invalid response from service. Cannot find "predictions" in response.')
diff --git a/datalab/mlalpha/_cloud_runner.py b/datalab/mlalpha/_cloud_runner.py
index db3630e0a..5da4958d8 100644
--- a/datalab/mlalpha/_cloud_runner.py
+++ b/datalab/mlalpha/_cloud_runner.py
@@ -86,4 +86,5 @@ def run(self, job_id=None):
                               discoveryServiceUrl=_CLOUDML_DISCOVERY_URL)
     request = cloudml.projects().jobs().create(body=job,
                                                parent='projects/' + context.project_id)
+    request.headers['user-agent'] = 'GoogleCloudDataLab/1.0'
     return request.execute()

From 9124c5e37ad9954807de403017d36157fde3fef0 Mon Sep 17 00:00:00 2001
From: Anthonios Partheniou <apartheniou@electricalengineer.ca>
Date: Mon, 19 Dec 2016 18:58:41 -0500
Subject: [PATCH 04/19] Update oauth2client to 2.2.0 to satisfy cloudml in
 Cloud Datalab (#111)

---
 setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/setup.py b/setup.py
index 203783dba..27d32b21f 100644
--- a/setup.py
+++ b/setup.py
@@ -72,7 +72,7 @@
     'futures==3.0.5',
     'google-cloud==0.19.0',
     'httplib2==0.9.2',
-    'oauth2client==2.0.2',
+    'oauth2client==2.2.0',
     'pandas>=0.17.1',
     'pandas-profiling>=1.0.0a2',
     'python-dateutil==2.5.0',

From 7a3399bd49c7944ecc2ba6542895a9a31ea27f16 Mon Sep 17 00:00:00 2001
From: Yasser Elsayed <yebrahim@users.noreply.github.com>
Date: Sat, 31 Dec 2016 01:55:53 -0800
Subject: [PATCH 05/19] Update README.md (#114)

Added docs link.
---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index ffa63d075..c1c860ad4 100644
--- a/README.md
+++ b/README.md
@@ -60,3 +60,5 @@ You will also need to set the project ID to use; either set a `PROJECT_ID`
 environment variable to the project name, or call `set_datalab_project_id(name)`
 from within your notebook.
 
+## Documentation
+You can read the Sphinx generated docs at: [http://googledatalab.github.io/pydatalab/](http://googledatalab.github.io/pydatalab/)

From 4c18e19187f483bc339d7eaa5aa6bdf08262f8cc Mon Sep 17 00:00:00 2001
From: Yasser Elsayed <yebrahim@users.noreply.github.com>
Date: Sat, 31 Dec 2016 01:59:13 -0800
Subject: [PATCH 06/19] Generate reST documentation for magic commands (#113)

Auto generate docs for any added magics by searching through the source files for lines with register_line_cell_magic, capturing the names for those magics, and calling them inside an ipython kernel with the -h argument, then storing that output into a generated datalab.magics.rst file.
---
 .gitignore             |  1 +
 docs/Makefile          | 54 +++++++++++++++++++++++-------------------
 docs/README            |  9 ++++---
 docs/conf.py           |  2 +-
 docs/gen-magic-rst.ipy | 39 ++++++++++++++++++++++++++++++
 docs/index.rst         |  1 +
 setup.py               |  2 +-
 7 files changed, 76 insertions(+), 32 deletions(-)
 create mode 100644 docs/gen-magic-rst.ipy

diff --git a/.gitignore b/.gitignore
index fa647c89e..aa484f7a7 100644
--- a/.gitignore
+++ b/.gitignore
@@ -7,3 +7,4 @@ MANIFEST
 build
 .coverage
 dist
+datalab.magics.rst
diff --git a/docs/Makefile b/docs/Makefile
index d10cd1f8d..49388854a 100644
--- a/docs/Makefile
+++ b/docs/Makefile
@@ -55,38 +55,42 @@ help:
 clean:
 	rm -rf $(BUILDDIR)/*
 
-html:
+pre-build:
+	@echo "Generate reST for magic commands:"
+	ipython gen-magic-rst.ipy
+
+html: pre-build
 	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
 	@echo
 	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
 
-dirhtml:
+dirhtml: pre-build
 	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
 	@echo
 	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
 
-singlehtml:
+singlehtml: pre-build
 	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
 	@echo
 	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
 
-pickle:
+pickle: pre-build
 	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
 	@echo
 	@echo "Build finished; now you can process the pickle files."
 
-json:
+json: pre-build
 	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
 	@echo
 	@echo "Build finished; now you can process the JSON files."
 
-htmlhelp:
+htmlhelp: pre-build
 	$(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:
+qthelp: pre-build
 	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
 	@echo
 	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
@@ -95,7 +99,7 @@ qthelp:
 	@echo "To view the help file:"
 	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/api.qhc"
 
-applehelp:
+applehelp: pre-build
 	$(SPHINXBUILD) -b applehelp $(ALLSPHINXOPTS) $(BUILDDIR)/applehelp
 	@echo
 	@echo "Build finished. The help book is in $(BUILDDIR)/applehelp."
@@ -103,7 +107,7 @@ applehelp:
 	      "~/Library/Documentation/Help or install it in your application" \
 	      "bundle."
 
-devhelp:
+devhelp: pre-build
 	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
 	@echo
 	@echo "Build finished."
@@ -112,85 +116,85 @@ devhelp:
 	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/api"
 	@echo "# devhelp"
 
-epub:
+epub: pre-build
 	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
 	@echo
 	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
 
-latex:
+latex: pre-build
 	$(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:
+latexpdf: pre-build
 	$(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:
+latexpdfja: pre-build
 	$(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:
+text: pre-build
 	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
 	@echo
 	@echo "Build finished. The text files are in $(BUILDDIR)/text."
 
-man:
+man: pre-build
 	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
 	@echo
 	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
 
-texinfo:
+texinfo: pre-build
 	$(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:
+info: pre-build
 	$(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:
+gettext: pre-build
 	$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
 	@echo
 	@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
 
-changes:
+changes: pre-build
 	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
 	@echo
 	@echo "The overview file is in $(BUILDDIR)/changes."
 
-linkcheck:
+linkcheck: pre-build
 	$(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:
+doctest: pre-build
 	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
 	@echo "Testing of doctests in the sources finished, look at the " \
 	      "results in $(BUILDDIR)/doctest/output.txt."
 
-coverage:
+coverage: pre-build
 	$(SPHINXBUILD) -b coverage $(ALLSPHINXOPTS) $(BUILDDIR)/coverage
 	@echo "Testing of coverage in the sources finished, look at the " \
 	      "results in $(BUILDDIR)/coverage/python.txt."
 
-xml:
+xml: pre-build
 	$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
 	@echo
 	@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
 
-pseudoxml:
+pseudoxml: pre-build
 	$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
 	@echo
 	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."
@@ -202,7 +206,7 @@ prepublish:
 	cd ../../datalab-docs && git clone https://github.com/GoogleCloudPlatform/datalab.git html && \
 		git checkout gh-pages
 
-publish:
+publish: pre-build
 	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
 	cd ../../datalab-docs/html && git add . && git commit -m "Updated" && git push --force origin gh-pages
 
diff --git a/docs/README b/docs/README
index dcb5afe1f..a4d51aca2 100644
--- a/docs/README
+++ b/docs/README
@@ -1,9 +1,8 @@
-To use, install the prerequisites:
+To use, install the prerequisites and the pydatalab module:
 
   pip install sphinx sphinx_rtd_theme sphinxcontrib-napoleon
+  pip install .. # from docs directory
 
+then in the docs directory, do 'make html' (or epub, or text, etc).
 
-then in the docs directory, do 'make html' (or epub, or pdf, etc).
-
-Output will be in the docs/_build directory.
-
+Output will be in $BUILDDIR, defaulting to ../../datalab-docs.
diff --git a/docs/conf.py b/docs/conf.py
index 470e1874d..9f1c1355e 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -145,7 +145,7 @@
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+#html_static_path = []
 
 # Add any extra paths that contain custom files (such as robots.txt or
 # .htaccess) here, relative to this directory. These files are copied
diff --git a/docs/gen-magic-rst.ipy b/docs/gen-magic-rst.ipy
new file mode 100644
index 000000000..a44d6cec0
--- /dev/null
+++ b/docs/gen-magic-rst.ipy
@@ -0,0 +1,39 @@
+import subprocess, pkgutil, importlib, sys
+from cStringIO import StringIO
+
+# ignore mlalpha and tensorboard for now because of their tensorflow dependency
+# until tensorboard is pip installable and can be listed as a pydatalab dependency
+IGNORED_MAGICS = ['mlalpha', 'tensorboard']
+
+# import submodules
+submodules = [s for _,s,_ in pkgutil.iter_modules(['../datalab'])]
+
+for m in submodules:
+  name = 'datalab.' + m + '.commands'
+  try:
+    importlib.import_module(name)
+  except:
+    sys.stderr.write('WARNING, could not find module ' + name + '. Ignoring..\n')
+
+magic_regex = "find ../datalab -name '*.py' -exec perl -e '$f=join(\"\",<>); print \"$1\n\" if $f=~/register_line_cell_magic\ndef ([^\(]+)/m' {} \;"
+magics = subprocess.check_output(magic_regex, shell=True)
+
+reSTfile = open('datalab.magics.rst', 'w')
+indent = '\n  '
+
+reSTfile.write('datalab.magics\n')
+reSTfile.write('=================\n\n')
+
+for m in magics.split():
+  if m in IGNORED_MAGICS:
+    sys.stderr.write('Ignoring magic ' + m + '\n')
+  else:
+    reSTfile.write('.. attribute:: ' + m + '\n')
+    reSTfile.write('.. parsed-literal::\n')
+    # hijack stdout since the ipython kernel call writes to stdout/err directly
+    # and does not return its output
+    tmpStdout, sys.stdout = sys.stdout, StringIO()
+    get_ipython().magic(m + ' -h')
+    resultout = sys.stdout.getvalue().splitlines()
+    sys.stdout = tmpStdout
+    reSTfile.writelines(indent + indent.join(resultout) + '\n\n')
diff --git a/docs/index.rst b/docs/index.rst
index afc3d6f96..1f0167284 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -16,6 +16,7 @@ Contents:
    datalab.data
    datalab.stackdriver.monitoring
    datalab.storage
+   datalab.magics
 
 
 Indices and tables
diff --git a/setup.py b/setup.py
index 27d32b21f..d37838bb3 100644
--- a/setup.py
+++ b/setup.py
@@ -79,8 +79,8 @@
     'pytz>=2015.4',
     'pyyaml==3.11',
     'requests==2.9.1',
-    'scikit-learn==0.17.1',
     'scipy==0.18.0',
+    'scikit-learn==0.17.1',
     'ipykernel==4.4.1',
   ],
   package_data={

From 94c731320fb048dd36bf0fcbc1c9e3b097a7f15f Mon Sep 17 00:00:00 2001
From: qimingj <qimingj@users.noreply.github.com>
Date: Sat, 31 Dec 2016 21:47:14 -0800
Subject: [PATCH 07/19] Fix an issue that %%chart failed with UDF query. (#116)

* Fix an issue that %%chart failed with UDF query.

The problem is that the query is submitted to BQ without replacing variable values from user namespace.

* Fix chart tests by adding ip.user_ns mock.

* Fix charting test.

* Add missing import "mock".

* Fix chart tests.
---
 datalab/utils/commands/_utils.py | 3 ++-
 tests/kernel/chart_data_tests.py | 1 +
 tests/kernel/chart_tests.py      | 2 +-
 3 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/datalab/utils/commands/_utils.py b/datalab/utils/commands/_utils.py
index 4035ae6b8..95b11f26f 100644
--- a/datalab/utils/commands/_utils.py
+++ b/datalab/utils/commands/_utils.py
@@ -207,10 +207,11 @@ def get_data(source, fields='*', env=None, first_row=0, count=-1, schema=None):
     Exception if the request could not be fulfilled.
   """
 
+  ipy = IPython.get_ipython()
   if env is None:
     env = {}
+  env.update(ipy.user_ns)
   if isinstance(source, basestring):
-    ipy = IPython.get_ipython()
     source = datalab.utils.get_item(ipy.user_ns, source, source)
     if isinstance(source, basestring):
       source = datalab.bigquery.Table(source)
diff --git a/tests/kernel/chart_data_tests.py b/tests/kernel/chart_data_tests.py
index be02564d8..52f34562d 100644
--- a/tests/kernel/chart_data_tests.py
+++ b/tests/kernel/chart_data_tests.py
@@ -37,6 +37,7 @@ class TestCases(unittest.TestCase):
 
   @mock.patch('datalab.utils.get_item')
   def test_get_chart_data(self, mock_get_item):
+    IPython.get_ipython().user_ns = {}
     t = [
         {'country': 'US', 'quantity': 100},
         {'country': 'ZA', 'quantity': 50},
diff --git a/tests/kernel/chart_tests.py b/tests/kernel/chart_tests.py
index 260d1a615..0f6a16dc3 100644
--- a/tests/kernel/chart_tests.py
+++ b/tests/kernel/chart_tests.py
@@ -28,7 +28,6 @@ def noop_decorator(func):
 IPython.core.display.HTML = lambda x: x
 IPython.core.display.JSON = lambda x: x
 
-
 import datalab.utils.commands
 
 
@@ -36,6 +35,7 @@ class TestCases(unittest.TestCase):
 
   def test_chart_cell(self):
     t = [{'country': 'US', 'quantity': 100}, {'country': 'ZA', 'quantity': 50}]
+    IPython.get_ipython().user_ns = {}
     chart = datalab.utils.commands._chart._chart_cell({'chart': 'geo', 'data': t, 'fields': None}, '')
     self.assertTrue(chart.find('charts.render(') > 0)
     self.assertTrue(chart.find('\'geo\'') > 0)

From 23e9e21ba9c3b083e0ef20c16865f0531dd8557f Mon Sep 17 00:00:00 2001
From: qimingj <qimingj@users.noreply.github.com>
Date: Wed, 4 Jan 2017 11:15:04 -0800
Subject: [PATCH 08/19] Fix "%%bigquery schema" issue --  the command generates
 nothing in output. (#119)

---
 datalab/bigquery/commands/_bigquery.py | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/datalab/bigquery/commands/_bigquery.py b/datalab/bigquery/commands/_bigquery.py
index 9731965ab..032f1e56c 100644
--- a/datalab/bigquery/commands/_bigquery.py
+++ b/datalab/bigquery/commands/_bigquery.py
@@ -1009,6 +1009,14 @@ def _repr_html_table_schema(schema):
   _HTML_TEMPLATE = """
     <div class="bqsv" id="%s"></div>
     <script>
+      require.config({
+        map: {
+          '*': {
+            datalab: 'nbextensions/gcpdatalab'
+          }
+        },
+      });
+
       require(['datalab/bigquery', 'datalab/element!%s',
           'datalab/style!/nbextensions/gcpdatalab/bigquery.css'],
         function(bq, dom) {

From 3a6f471dadd797dd6920300032416e161454d0ff Mon Sep 17 00:00:00 2001
From: Eyad Sibai <eyadsibai@users.noreply.github.com>
Date: Thu, 12 Jan 2017 06:18:07 +0100
Subject: [PATCH 09/19] Add some missing dependencies, remove some unused ones
 (#122)

* Remove scikit-learn and scipy as dependencies
* add more required packages
* Add psutil as dependency
* Update packages versions
---
 setup.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/setup.py b/setup.py
index d37838bb3..e9b464f5a 100644
--- a/setup.py
+++ b/setup.py
@@ -71,16 +71,18 @@
     'future==0.15.2',
     'futures==3.0.5',
     'google-cloud==0.19.0',
+    'google-api-python-client==1.5.1',
+    'seaborn==0.7.0',
+    'plotly==1.12.5',
     'httplib2==0.9.2',
     'oauth2client==2.2.0',
+    'psutil==4.3.0',
     'pandas>=0.17.1',
     'pandas-profiling>=1.0.0a2',
     'python-dateutil==2.5.0',
     'pytz>=2015.4',
     'pyyaml==3.11',
     'requests==2.9.1',
-    'scipy==0.18.0',
-    'scikit-learn==0.17.1',
     'ipykernel==4.4.1',
   ],
   package_data={

From 75fb7e3e4d07c013e77b80e41fdf6078c89fc581 Mon Sep 17 00:00:00 2001
From: Eyad Sibai <eyadsibai@users.noreply.github.com>
Date: Thu, 12 Jan 2017 19:21:12 +0100
Subject: [PATCH 10/19] Cleanup (#123)

* Remove unnecessary semicolons

* remove unused imports

* remove unncessary defined variable
---
 datalab/mlalpha/_dataset.py          | 2 +-
 datalab/mlalpha/commands/_mlalpha.py | 5 ++---
 datalab/storage/_item.py             | 1 -
 3 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/datalab/mlalpha/_dataset.py b/datalab/mlalpha/_dataset.py
index 2837ef326..e9b5b01ef 100644
--- a/datalab/mlalpha/_dataset.py
+++ b/datalab/mlalpha/_dataset.py
@@ -294,7 +294,7 @@ def _scatter3d_plot(self, names, x, y, z, color):
     iplot(fig)
 
   def _plot_x(self, names, x):
-    self._histogram(names, x);
+    self._histogram(names, x)
     if x != self._target_name:
       self._scatter_plot(names, x, self._target_name, self._target_name)
 
diff --git a/datalab/mlalpha/commands/_mlalpha.py b/datalab/mlalpha/commands/_mlalpha.py
index dd8c2e324..4bcfa4127 100644
--- a/datalab/mlalpha/commands/_mlalpha.py
+++ b/datalab/mlalpha/commands/_mlalpha.py
@@ -18,14 +18,13 @@
 
 
 import collections
-import datetime
 import fnmatch
 import google.cloud.ml
 import json
 import math
 import os
 import plotly.graph_objs as go
-from plotly.offline import init_notebook_mode, iplot
+from plotly.offline import iplot
 import urllib
 import yaml
 
@@ -255,7 +254,7 @@ def _train(args, cell):
         urllib.urlencode(log_url_query_strings)
     html += '<p>Click <a href="%s" target="_blank">here</a> to view cloud log. <br/>' % log_url
     html += 'Start TensorBoard by running "%tensorboard start --logdir=&lt;YourLogDir&gt;".</p>'
-    return IPython.core.display.HTML(html);
+    return IPython.core.display.HTML(html)
   else:
     # local training
     package_path = None
diff --git a/datalab/storage/_item.py b/datalab/storage/_item.py
index dba54b619..57729f3be 100644
--- a/datalab/storage/_item.py
+++ b/datalab/storage/_item.py
@@ -196,7 +196,6 @@ def read_lines(self, max_lines=None):
 
     max_to_read = self.metadata.size
     bytes_to_read = min(100 * max_lines, self.metadata.size)
-    lines = []
     while True:
       content = self.read_from(byte_count=bytes_to_read)
 

From 57dbbc5ea21d671c354ed13476024300cf193573 Mon Sep 17 00:00:00 2001
From: Yasser Elsayed <yebrahim@users.noreply.github.com>
Date: Tue, 17 Jan 2017 10:40:16 -0800
Subject: [PATCH 11/19] Fix query_metadata tests (#128)

Fix query_metadata tests
---
 .travis.yml                                       | 2 +-
 datalab/stackdriver/monitoring/_query_metadata.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.travis.yml b/.travis.yml
index f3f210d6b..be16d27da 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,7 +1,7 @@
 language: python
 python:
   - "2.7"
-  - "3.4"
+  - "3.5"
 
 before_install:
   - npm install -g typescript
diff --git a/datalab/stackdriver/monitoring/_query_metadata.py b/datalab/stackdriver/monitoring/_query_metadata.py
index b78be767b..2cfe99fbe 100644
--- a/datalab/stackdriver/monitoring/_query_metadata.py
+++ b/datalab/stackdriver/monitoring/_query_metadata.py
@@ -64,7 +64,7 @@ def as_dataframe(self, max_rows=None):
       """
       max_rows = len(self._timeseries_list) if max_rows is None else max_rows
       headers = [{
-          'resource': ts.resource.__dict__, 'metric': ts.metric.__dict__}
+          'resource': ts.resource._asdict(), 'metric': ts.metric._asdict()}
           for ts in self._timeseries_list[:max_rows]]
 
       if not headers:

From c67ac4f5f83122706cc18e75d57d04200793be60 Mon Sep 17 00:00:00 2001
From: Yasser Elsayed <yebrahim@users.noreply.github.com>
Date: Tue, 17 Jan 2017 11:23:46 -0800
Subject: [PATCH 12/19] Make the library pip-installable (#125)

This PR adds tensorflow and cloudml in setup.py to make the lib pip-installable. I had to install them explicitly using pip from inside the setup.py script, even though it's not a clean way to do it, it gets around the two issues we have at the moment with these two packags:
- Pypi has Tensorflow version 0.12, while we need 0.11 for the current version of pydatalab. According to the Cloud ML docs, that version exists as a pip package for three supported platforms.
- Cloud ML SDK exists as a pip package, but also not on Pypi, and while we could add it as a dependency link, there exists another package on Pypi called cloudml, and pip ends up installing that instead (see #124). I cannot find a way to force pip to install the package from the link I included.
---
 .travis.yml |  6 ++++--
 setup.py    | 26 ++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/.travis.yml b/.travis.yml
index be16d27da..adc180ab2 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,12 +1,14 @@
 language: python
 python:
-  - "2.7"
-  - "3.5"
+  - 2.7
+  - 3.5
 
 before_install:
+  - sudo apt-get install -y python-setuptools
   - npm install -g typescript
   - tsc --module amd --noImplicitAny --outdir datalab/notebook/static datalab/notebook/static/*.ts
   - pip install -U pip
+  - pip install -U setuptools
   - pip install .
 
 script: python ./tests/main.py
diff --git a/setup.py b/setup.py
index e9b464f5a..b0c4a18f9 100644
--- a/setup.py
+++ b/setup.py
@@ -13,8 +13,13 @@
 # To publish to PyPi use: python setup.py bdist_wheel upload -r pypi
 
 import datetime
+import sys
 from setuptools import setup
 
+if sys.version_info[0] == 2:
+  import platform
+  import pip
+
 minor = datetime.datetime.now().strftime("%y%m%d%H%M")
 version = '0.1.' + minor
 
@@ -104,3 +109,24 @@
       ]
   }
 )
+
+# for python2 only, install tensorflow and cloudml
+if sys.version_info[0] == 2:
+  tensorflow_path = None
+  if platform.system() == 'Darwin':
+    tensorflow_path = 'https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-0.11.0-py2-none-any.whl'
+  elif platform.system() == 'Linux':
+    if platform.linux_distribution()[0] == 'Ubuntu':
+      tensorflow_path = 'https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.11.0-cp27-none-linux_x86_64.whl'
+    elif platform.linux_distribution()[0] == 'Debian':
+      tensorflow_path = 'https://storage.googleapis.com/tensorflow/linux/cpu/debian/jessie/tensorflow-0.11.0-cp27-none-linux_x86_64.whl'
+
+  # install tensorflow
+  if not tensorflow_path:
+    print("""Warning: could not find tensorflow build for your OS.
+    Please go to https://www.tensorflow.org/get_started/os_setup to see install options""")
+  else:
+    pip.main(['install', tensorflow_path])
+
+  # install cloud ml sdk
+  pip.main(['install', 'https://storage.googleapis.com/cloud-ml/sdk/cloudml.latest.tar.gz'])

From 2395c61a0568ea4676355002eb8b66623a28f4ce Mon Sep 17 00:00:00 2001
From: qimingj <qimingj@users.noreply.github.com>
Date: Tue, 17 Jan 2017 17:05:40 -0800
Subject: [PATCH 13/19] Set command description so it is displayed in --help.
 argparser's format_help() prints description but not help. (#131)

---
 datalab/utils/commands/_commands.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/datalab/utils/commands/_commands.py b/datalab/utils/commands/_commands.py
index 5eac09ae0..48363bd1d 100644
--- a/datalab/utils/commands/_commands.py
+++ b/datalab/utils/commands/_commands.py
@@ -79,4 +79,4 @@ def subcommand(self, name, help):
     """Creates a parser for a sub-command. """
     if self._subcommands is None:
       self._subcommands = self.add_subparsers(help='commands')
-    return self._subcommands.add_parser(name, help=help)
+    return self._subcommands.add_parser(name, description=help, help=help)

From 31e7486c1a860c64afd700779a337b1aa2c74d90 Mon Sep 17 00:00:00 2001
From: qimingj <qimingj@users.noreply.github.com>
Date: Fri, 20 Jan 2017 10:01:46 -0800
Subject: [PATCH 14/19] Fix an issue that setting project id from datalab does
 not set gcloud default project. (#136)

---
 datalab/context/_utils.py | 33 +++++++++++++++++++++++++--------
 1 file changed, 25 insertions(+), 8 deletions(-)

diff --git a/datalab/context/_utils.py b/datalab/context/_utils.py
index 01d958ee3..577289831 100644
--- a/datalab/context/_utils.py
+++ b/datalab/context/_utils.py
@@ -19,6 +19,7 @@
 import oauth2client.client
 import json
 import os
+import subprocess
 
 
 # TODO(ojarjur): This limits the APIs against which Datalab can be called
@@ -90,14 +91,19 @@ def save_project_id(project_id):
   Args:
     project_id: the project_id to save.
   """
-  config_file = os.path.join(get_config_dir(), 'config.json')
-  config = {}
-  if os.path.exists(config_file):
-    with open(config_file) as f:
-      config = json.loads(f.read())
-  config['project_id'] = project_id
-  with open(config_file, 'w') as f:
-    f.write(json.dumps(config))
+  # Try gcloud first. If gcloud fails (probably because it does not exist), then
+  # write to a config file.
+  try:
+    subprocess.call(['gcloud', 'config', 'set', 'project', project_id])
+  except:
+    config_file = os.path.join(get_config_dir(), 'config.json')
+    config = {}
+    if os.path.exists(config_file):
+      with open(config_file) as f:
+        config = json.loads(f.read())
+    config['project_id'] = project_id
+    with open(config_file, 'w') as f:
+      f.write(json.dumps(config))
 
 
 def get_project_id():
@@ -105,6 +111,17 @@ def get_project_id():
 
   Returns: the project id if available, or None.
   """
+  # Try getting default project id from gcloud. If it fails try config.json.
+  try:
+    proc = subprocess.Popen(['gcloud', 'config', 'list', '--format', 'value(core.project)'],
+                            stdout=subprocess.PIPE)
+    stdout, _ = proc.communicate()
+    value = stdout.strip()
+    if proc.poll() == 0 and value:
+      return value
+  except:
+    pass
+
   config_file = os.path.join(get_config_dir(), 'config.json')
   if os.path.exists(config_file):
     with open(config_file) as f:

From 220d8047e901f9c85359d6b29c973d30cdf6ef16 Mon Sep 17 00:00:00 2001
From: Yasser Elsayed <yebrahim@users.noreply.github.com>
Date: Mon, 30 Jan 2017 13:45:51 -0800
Subject: [PATCH 15/19] Add future==0.16.0 as a dependency since it's required
 by CloudML SDK (#143)

As of the latest release of CloudML Python SDK, that package seems to require future==0.16.0, so until it's fixed, we'll take it as a dependency.
---
 setup.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/setup.py b/setup.py
index b0c4a18f9..d0fd1da09 100644
--- a/setup.py
+++ b/setup.py
@@ -73,7 +73,7 @@
 for accessing Google's Cloud Platform services such as Google BigQuery.
   """,
   install_requires=[
-    'future==0.15.2',
+    'future==0.16.0',
     'futures==3.0.5',
     'google-cloud==0.19.0',
     'google-api-python-client==1.5.1',

From 15abddff2d74b77375010a89769b1f6022c61fa6 Mon Sep 17 00:00:00 2001
From: qimingj <qimingj@users.noreply.github.com>
Date: Wed, 1 Feb 2017 09:14:06 -0800
Subject: [PATCH 16/19] Remove tensorflow and CloudML SDK from setup.py (#144)

* Install TensorFlow 0.12.1.

* Remove TensorFlow and CloudML SDK from setup.py.

* Add comments why we ignore errors when importing mlalpha.
---
 datalab/kernel/__init__.py | 12 +++++++++++-
 setup.py                   | 21 ---------------------
 2 files changed, 11 insertions(+), 22 deletions(-)

diff --git a/datalab/kernel/__init__.py b/datalab/kernel/__init__.py
index 9f900b906..d500c0fd0 100644
--- a/datalab/kernel/__init__.py
+++ b/datalab/kernel/__init__.py
@@ -31,11 +31,21 @@
 import datalab.bigquery.commands
 import datalab.context.commands
 import datalab.data.commands
-import datalab.mlalpha.commands
 import datalab.stackdriver.commands
 import datalab.storage.commands
 import datalab.utils.commands
 
+# mlalpha modules require TensorFlow, CloudML SDK, and DataFlow (installed with CloudML SDK).
+# These are big dependencies and users who want to use Bigquery/Storage features may not
+# want to install them.
+# This __init__.py file is called when Jupyter/Datalab loads magics on startup. We don't want
+# Jupyter+pydatalab fail to start because of missing TensorFlow/DataFlow. So we ignore import
+# errors on mlalpha commands.
+try:
+  import datalab.mlalpha.commands
+except:
+  print('TensorFlow and CloudML SDK are required.')
+
 
 _orig_request = _httplib2.Http.request
 _orig_init = _requests.Session.__init__
diff --git a/setup.py b/setup.py
index d0fd1da09..b5ad744a1 100644
--- a/setup.py
+++ b/setup.py
@@ -109,24 +109,3 @@
       ]
   }
 )
-
-# for python2 only, install tensorflow and cloudml
-if sys.version_info[0] == 2:
-  tensorflow_path = None
-  if platform.system() == 'Darwin':
-    tensorflow_path = 'https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-0.11.0-py2-none-any.whl'
-  elif platform.system() == 'Linux':
-    if platform.linux_distribution()[0] == 'Ubuntu':
-      tensorflow_path = 'https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.11.0-cp27-none-linux_x86_64.whl'
-    elif platform.linux_distribution()[0] == 'Debian':
-      tensorflow_path = 'https://storage.googleapis.com/tensorflow/linux/cpu/debian/jessie/tensorflow-0.11.0-cp27-none-linux_x86_64.whl'
-
-  # install tensorflow
-  if not tensorflow_path:
-    print("""Warning: could not find tensorflow build for your OS.
-    Please go to https://www.tensorflow.org/get_started/os_setup to see install options""")
-  else:
-    pip.main(['install', tensorflow_path])
-
-  # install cloud ml sdk
-  pip.main(['install', 'https://storage.googleapis.com/cloud-ml/sdk/cloudml.latest.tar.gz'])

From 62716e923b78cdc80bca42080123cd37772c36be Mon Sep 17 00:00:00 2001
From: Dan Brown <jdanbrown@gmail.com>
Date: Tue, 14 Feb 2017 09:53:51 -0800
Subject: [PATCH 17/19] Fix project_id from `gcloud config` in py3 (#194)

- `Popen.stdout` is a `bytes` in py3, needs `.decode()`

- Before:
```py
>>> %%sql -d standard
... select 3
Your active configuration is: [test]

HTTP request failed: Invalid project ID 'b'foo-bar''. Project IDs must contain 6-63 lowercase letters, digits, or dashes. IDs must start with a letter and may not end with a dash.
```
```sh
$ for p in python2 python3; do $p -c 'from datalab.context._utils import get_project_id; print(get_project_id())'; done
Your active configuration is: [test]

foo-bar
Your active configuration is: [test]

b'foo-bar'
```

- After:
```py
>>> %%sql -d standard
... select 3
Your active configuration is: [test]

QueryResultsTable job_1_bZNbAUtk8QzlK7bqWD5fz7S5o
```
```sh
$ for p in python2 python3; do $p -c 'from datalab.context._utils import get_project_id; print(get_project_id())'; done
Your active configuration is: [test]

foo-bar
Your active configuration is: [test]

foo-bar
```
---
 datalab/context/_utils.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/datalab/context/_utils.py b/datalab/context/_utils.py
index 577289831..c5dec5832 100644
--- a/datalab/context/_utils.py
+++ b/datalab/context/_utils.py
@@ -116,7 +116,7 @@ def get_project_id():
     proc = subprocess.Popen(['gcloud', 'config', 'list', '--format', 'value(core.project)'],
                             stdout=subprocess.PIPE)
     stdout, _ = proc.communicate()
-    value = stdout.strip()
+    value = stdout.decode().strip()
     if proc.poll() == 0 and value:
       return value
   except:

From 7ff0b3c50e1eda3d49f8565d81e0fcfdc0bf517e Mon Sep 17 00:00:00 2001
From: Dan Brown <jdanbrown@gmail.com>
Date: Tue, 14 Feb 2017 11:10:26 -0800
Subject: [PATCH 18/19] Use http Keep-Alive, else BigQuery queries are ~seconds
 slower than necessary (#195)

- Before (without Keep-Alive): ~3-7s for BigQuery `select 3` with an already cached result
- After (with Keep-Alive): ~1.5-3s
- Query sends these 6 http requests and runtime appears to be dominated by network RTT
---
 datalab/utils/_http.py    | 21 ++++++++++++---------
 tests/_util/http_tests.py | 16 ++++++++--------
 2 files changed, 20 insertions(+), 17 deletions(-)

diff --git a/datalab/utils/_http.py b/datalab/utils/_http.py
index a161da14c..a07f51db7 100644
--- a/datalab/utils/_http.py
+++ b/datalab/utils/_http.py
@@ -53,6 +53,16 @@ class Http(object):
   """A helper class for making HTTP requests.
   """
 
+  # Reuse one Http object across requests to take advantage of Keep-Alive, e.g.
+  # for BigQuery queries that requires at least ~5 sequential http requests.
+  #
+  # TODO(nikhilko):
+  # SSL cert validation seemingly fails, and workarounds are not amenable
+  # to implementing in library code. So configure the Http object to skip
+  # doing so, in the interim.
+  http = httplib2.Http()
+  http.disable_ssl_certificate_validation = True
+
   def __init__(self):
     pass
 
@@ -109,15 +119,8 @@ def request(url, args=None, data=None, headers=None, method=None,
     if method is None:
       method = 'GET'
 
-    # Create an Http object to issue requests. Associate the credentials
-    # with it if specified to perform authorization.
-    #
-    # TODO(nikhilko):
-    # SSL cert validation seemingly fails, and workarounds are not amenable
-    # to implementing in library code. So configure the Http object to skip
-    # doing so, in the interim.
-    http = httplib2.Http()
-    http.disable_ssl_certificate_validation = True
+    # Authorize with credentials if given.
+    http = Http.http
     if credentials is not None:
       http = credentials.authorize(http)
     if stats is not None:
diff --git a/tests/_util/http_tests.py b/tests/_util/http_tests.py
index 371a1e8a4..b620ffb9e 100644
--- a/tests/_util/http_tests.py
+++ b/tests/_util/http_tests.py
@@ -23,7 +23,7 @@
 class TestCases(unittest.TestCase):
 
   @mock.patch('httplib2.Response')
-  @mock.patch('httplib2.Http.request')
+  @mock.patch('datalab.utils._http.Http.http.request')
   def test_get_request_is_invoked(self, mock_request, mock_response):
     TestCases._setup_mocks(mock_request, mock_response, '{}')
 
@@ -32,7 +32,7 @@ def test_get_request_is_invoked(self, mock_request, mock_response):
     self.assertEqual(mock_request.call_args[1]['method'], 'GET')
 
   @mock.patch('httplib2.Response')
-  @mock.patch('httplib2.Http.request')
+  @mock.patch('datalab.utils._http.Http.http.request')
   def test_post_request_is_invoked(self, mock_request, mock_response):
     TestCases._setup_mocks(mock_request, mock_response, '{}')
 
@@ -40,7 +40,7 @@ def test_post_request_is_invoked(self, mock_request, mock_response):
     self.assertEqual(mock_request.call_args[1]['method'], 'POST')
 
   @mock.patch('httplib2.Response')
-  @mock.patch('httplib2.Http.request')
+  @mock.patch('datalab.utils._http.Http.http.request')
   def test_explicit_post_request_is_invoked(self, mock_request, mock_response):
     TestCases._setup_mocks(mock_request, mock_response, '{}')
 
@@ -48,7 +48,7 @@ def test_explicit_post_request_is_invoked(self, mock_request, mock_response):
     self.assertEqual(mock_request.call_args[1]['method'], 'POST')
 
   @mock.patch('httplib2.Response')
-  @mock.patch('httplib2.Http.request')
+  @mock.patch('datalab.utils._http.Http.http.request')
   def test_query_string_format(self, mock_request, mock_response):
     TestCases._setup_mocks(mock_request, mock_response, '{}')
 
@@ -59,7 +59,7 @@ def test_query_string_format(self, mock_request, mock_response):
     self.assertTrue('b=a+b+c' in parts[1:])
 
   @mock.patch('httplib2.Response')
-  @mock.patch('httplib2.Http.request')
+  @mock.patch('datalab.utils._http.Http.http.request')
   def test_formats_json_request(self, mock_request, mock_response):
     TestCases._setup_mocks(mock_request, mock_response, '{}')
 
@@ -71,7 +71,7 @@ def test_formats_json_request(self, mock_request, mock_response):
                      'application/json')
 
   @mock.patch('httplib2.Response')
-  @mock.patch('httplib2.Http.request')
+  @mock.patch('datalab.utils._http.Http.http.request')
   def test_supports_custom_content(self, mock_request, mock_response):
     TestCases._setup_mocks(mock_request, mock_response, '{}')
 
@@ -83,7 +83,7 @@ def test_supports_custom_content(self, mock_request, mock_response):
     self.assertEqual(mock_request.call_args[1]['headers']['Content-Type'], 'text/plain')
 
   @mock.patch('httplib2.Response')
-  @mock.patch('httplib2.Http.request')
+  @mock.patch('datalab.utils._http.Http.http.request')
   def test_parses_json_response(self, mock_request, mock_response):
     TestCases._setup_mocks(mock_request, mock_response, '{"abc":123}')
 
@@ -91,7 +91,7 @@ def test_parses_json_response(self, mock_request, mock_response):
     self.assertEqual(data['abc'], 123)
 
   @mock.patch('httplib2.Response')
-  @mock.patch('httplib2.Http.request')
+  @mock.patch('datalab.utils._http.Http.http.request')
   def test_raises_http_error(self, mock_request, mock_response):
     TestCases._setup_mocks(mock_request, mock_response, 'Not Found', 404)
 

From 6a6344ec228d950689e6331fc75485fcd9f61097 Mon Sep 17 00:00:00 2001
From: benopendoor <ben.rifkind@opendoor.com>
Date: Tue, 21 Feb 2017 15:50:33 -0800
Subject: [PATCH 19/19] cast string to int (#217)

`table.insert_data(df)` inserts data correctly but raises TypeError: unorderable types: str() > int()
---
 datalab/bigquery/_table.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/datalab/bigquery/_table.py b/datalab/bigquery/_table.py
index 6467eb305..6b6203521 100644
--- a/datalab/bigquery/_table.py
+++ b/datalab/bigquery/_table.py
@@ -401,7 +401,7 @@ def insert_data(self, data, include_index=False, index_name=None):
       self._info = self._api.tables_get(self._name_parts)
       if 'streamingBuffer' not in self._info or \
               'estimatedRows' not in self._info['streamingBuffer'] or \
-              self._info['streamingBuffer']['estimatedRows'] > 0:
+              int(self._info['streamingBuffer']['estimatedRows']) > 0:
         break
       time.sleep(2)