diff --git a/.gitignore b/.gitignore
index 1fe62cb..14e6d03 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,16 +1,62 @@
-bin/
-local/
-include/
-share/
-lib/
-*~
-*.pyc
-classification-hourlyResultsAll.txt
-*.csv
-*.msg
-datasets/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
 env/
-.ipynb_checkpoints
-MANIFEST
 build/
+develop-eggs/
 dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Project development
+.idea/
+ignore/
+venv/
diff --git a/.travis.yml b/.travis.yml
new file mode 100644
index 0000000..f3b493a
--- /dev/null
+++ b/.travis.yml
@@ -0,0 +1,28 @@
+language: python
+sudo: false
+
+cache:
+  directories:
+    - "~/.cache/pip"
+
+addons:
+  apt:
+    sources:
+      - ubuntu-toolchain-r-test
+    packages:
+      - libfreetype6-dev
+      - libatlas-dev
+      - gfortran
+
+python:
+  - 2.7
+
+install:
+  - pip install pip setuptools wheel --upgrade
+  - pip install -e .\[dev\]
+
+script:
+  - python -c "import vessel_scoring"
+
+after_success:
+  - coveralls || echo "!! intermittent coveralls failure"
diff --git a/README.md b/README.md
index 482c860..9fe305f 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,7 @@
+[![Build Status](https://travis-ci.org/GlobalFishingWatch/vessel-scoring.svg?branch=master)](https://travis-ci.org/GlobalFishingWatch/vessel-scoring)
+
+[![Coverage Status](https://coveralls.io/repos/github/GlobalFishingWatch/vessel-scoring/badge.svg?branch=master)](https://coveralls.io/github/GlobalFishingWatch/vessel-scoring?branch=master)
+
 # About
 This repository contains fishing scoring heuristics and evaluation of their effectiveness,
 as well as development of supervised-ML scoring algorithms.
diff --git a/requirements.txt b/requirements.txt
deleted file mode 100644
index 5ef7a86..0000000
--- a/requirements.txt
+++ /dev/null
@@ -1,40 +0,0 @@
-Jinja2==2.8
-MarkupSafe==0.23
-Pygments==2.0.2
-backports-abc==0.4
-backports.ssl-match-hostname==3.5.0.1
-certifi==2015.11.20.1
-cycler==0.9.0
-decorator==4.0.6
-functools32==3.2.3-2
-ipykernel==4.2.2
-ipython==4.0.1
-ipython-genutils==0.1.0
-ipywidgets==4.1.1
-jsonschema==2.5.1
-jupyter==1.0.0
-jupyter-client==4.1.1
-jupyter-console==4.0.3
-jupyter-core==4.0.6
-matplotlib==1.5.0
-mistune==0.7.1
-nbconvert==4.1.0
-nbformat==4.0.1
-notebook==4.0.6
-numpy==1.10.2
-path.py==8.1.2
-pexpect==4.0.1
-pickleshare==0.5
-ptyprocess==0.5
-pyparsing==2.0.7
-python-dateutil==2.4.2
-pytz==2015.7
-pyzmq==15.1.0
-qtconsole==4.1.1
-simplegeneric==0.8.1
-singledispatch==3.4.0.3
-six==1.10.0
-terminado==0.6
-tornado==4.3
-traitlets==4.0.0
-gpsdio==0.0.7
diff --git a/setup.py b/setup.py
index 9f25e40..916c69b 100644
--- a/setup.py
+++ b/setup.py
@@ -42,8 +42,11 @@ def run(self):
     packages=[
         'vessel_scoring',
     ],
-    package_data={'vessel_scoring': ['models/*']},
-    install_requires=["numpy", "scikit_learn", "scipy", "matplotlib", "ipython"],
+    package_data={
+        'vessel_scoring': ['models/*']},
+    install_requires=["numpy", "scikit-learn", "scipy", "rolling_measures"],
+    extras_require={
+        'dev': ['matplotlib', 'ipython', 'coveralls']},
     version='1.0',
     author='Egil Moeller, Timothy Hochberg',
     author_email='egil@skytruth.org, tim@skytruth.org',
diff --git a/vessel_scoring/evaluate_model.py b/vessel_scoring/evaluate_model.py
index 86ff37c..cfbef1f 100644
--- a/vessel_scoring/evaluate_model.py
+++ b/vessel_scoring/evaluate_model.py
@@ -1,9 +1,5 @@
-import matplotlib.pyplot as plt
 from vessel_scoring import utils
-import numpy as np
 from sklearn import metrics
-from IPython.core.display import display, HTML
-
 
 
 def train_model(model, train_data):
@@ -22,12 +18,17 @@ def train_model(model, train_data):
 
 # TODO break this into a plotting and a text part
 def evaluate_model(model, test_data, name=None):
-    """Plot some graphs and compute some metrics on a model
+    """Plot some graphs and compute some metrics on a model.  Requires
+    matplotlib and IPython.
 
     model - a trained model
     test_data - data to use on the evalutions
 
     """
+
+    import matplotlib.pyplot as plt
+    from IPython.core.display import display, HTML
+
     is_fishy = utils.is_fishy(test_data)
 
     score = model.predict_proba(test_data)[:,1]
@@ -91,6 +92,7 @@ def convert_range(ax_f):
     overlap = total - non_overlap
     error = overlap / total
 
+
 def compare_models(models, test_data):
     is_fishy = utils.is_fishy(test_data)