Merge pull request #56 from ntucllab/chkoar-pep8

Chkoar pep8

Author: yangarbiter

.pylintrc

@@ -0,0 +1,139 @@
+[REPORTS]
+
+# Set the output format. Available formats are text, parseable, colorized, msvs
+# (visual studio) and html.
+output-format=colorized
+
+# Tells whether to display a full report or only the messages
+reports=yes
+
+# Python expression which should return a note less than 10 (10 is the highest
+# note). You have access to the variables errors warning, statement which
+# respectively contain the number of errors / warnings messages and the total
+# number of statements analyzed. This is used by the global evaluation report
+# (RP0004).
+evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)
+
+
+[VARIABLES]
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid to define new builtins when possible.
+additional-builtins=zip
+
+# List of strings which can identify a callback function by name. A callback
+# name must start or end with one of those strings.
+callbacks=cb_,_cb
+
+
+[BASIC]
+
+# List of builtins function names that should not be used, separated by a comma
+bad-functions=map,filter
+
+# Good variable names which should always be accepted, separated by a comma
+# x, y, X, Y - vector maxtrix of features and labels.
+# P, p - probability distribution
+# qs - query strategry
+# w, W - weight vector
+# N - number of instances
+# T, K - number of iterations
+good-names=i,j,k,_,X,Y,x,y,P,p,qs,w,W,N,T,K
+
+# Regular expression matching correct attribute names
+attr-rgx=[a-z_][a-z0-9_]{2,30}$
+
+# Naming hint for attribute names
+attr-name-hint=[a-z_][a-z0-9_]{2,30}$
+
+# Regular expression matching correct variable names
+# start with X imply its a matrix for features
+variable-rgx=[a-z_X][a-z0-9_]{2,30}$
+
+# Naming hint for variable names
+variable-name-hint=[a-z_X][a-z0-9_]{2,30}$
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=^_
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=-1
+
+
+[TYPECHECK]
+
+# List of module names for which member attributes should not be checked
+# (useful for modules/projects where namespaces are manipulated during runtime
+# and thus existing member attributes cannot be deduced by static analysis. It
+# supports qualified module names, as well as Unix pattern matching.
+ignored-modules=numpy,matplotlib,future_builtins
+
+# List of classes names for which member attributes should not be checked
+# (useful for classes with attributes dynamically set). This supports can work
+# with qualified names.
+ignored-classes=
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E1101 when accessed. Python regular
+# expressions are accepted.
+generated-members=
+
+
+[FORMAT]
+
+# Maximum number of characters on a single line.
+max-line-length=79
+
+# List of optional constructs for which whitespace checking is disabled. `dict-
+# separator` is used to allow tabulation in dicts, etc.: {1  : 1,\n222: 2}.
+# `trailing-comma` allows a space between comma and closing bracket: (a, ).
+# `empty-line` allows space-only lines.
+no-space-check=trailing-comma,dict-separator
+
+# Maximum number of lines in a module
+max-module-lines=1000
+
+# String used as indentation unit. This is usually "    " (4 spaces) or "\t" (1
+# tab).
+indent-string='    '
+
+# Number of spaces of indent required inside a hanging or continued line.
+indent-after-paren=4
+
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+expected-line-ending-format=LF
+
+
+[DESIGN]
+
+# Maximum number of arguments for function / method
+max-args=15
+
+# sometimes more locals can handle computation more efficiently
+max-locals=30
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=15
+
+
+[MESSAGES CONTROL]
+
+# R0903 - Not enough public methods
+# E0611 - No name %r in module %r (countless false-positives)
+# E1101, E1103 - %s %r has no %r member (countless false-positives)
+# F0401 - Unable to import %r (error for c extensions)
+disable=R0903,E0611,E1101,E1103,F0401
+
+
+[CLASSES]
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,__new__,setUp
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=mcs

.travis.yml

@@ -34,11 +34,13 @@ before_install:
   - travis_wait 20 pip install -r requirements.txt
   - pip install coverage
   - pip install codecov
+  - pip install pylint
 install:
   - ./setup.py build_ext --inplace
 script:
   - python -m unittest -v
   - coverage run --source libact --omit */tests/* setup.py test
   - coverage report
 after_success:
+  - pylint libact
   - codecov

README.md

@@ -26,58 +26,51 @@ Documentation for the latest release is hosted [here](http://libact.readthedocs.
 
 # Basic Dependencies
 
-Python3 dependencies
+* Python 2.7, 3.3, 3.4, 3.5
+
+* Python dependencies
 ```
-pip3 install -r requirements.txt
+pip install -r requirements.txt
 ```
 
-Debian (>= 7) / Ubuntu (>= 14.04)
+* Debian (>= 7) / Ubuntu (>= 14.04)
 ```
 sudo apt-get install build-essential gfortran libatlas-base-dev liblapacke-dev python3-dev
 ```
 
-MacOS
+* MacOS
 ```
 brew tap homebrew/science
 brew install openblas
 ```
 
 # Installation
 
-One of the query strategies (`hintsvm`) depends on the HintSVM package that requires special installation. If you are not using the strategy, please simply follow the section on general installation. Otherwise please follow the section on HintSVM.
-
-## General Installation
-After resolving the dependencies, it should be fairly simple to install the package in your home directory:
-
+After resolving the dependencies, you may install the package via pip (for all users):
 ```
-python setup.py install --user
+sudo pip install libact
 ```
 
-To install for all users on Unix/Linux:
+or pip install in home directory:
 ```
-python setup.py build
-sudo python setup.py install
+pip install --user libact
 ```
 
-Or via pip: (for all users):
+or pip install from github repository for latest source:
 ```
-sudo pip install libact
+pip install git+https://github.com/ntucllab/libact.git
 ```
 
-Pip install in home directory:
+To build and install from souce in your home directory:
 ```
-pip install --user libact
+python setup.py install --user
 ```
 
-## Special Installation for HintSVM
-
-For HintSVM, you would have to install the [hintsvm package](https://github.com/ntucllab/hintsvm) first.
-
-Before running, you need to make sure the path to the library and
-python code of `hintsvm` are set in the environment variables:
-
-    export LD_LIBRARY_PATH=/path/to/hintsvm:$LD_LIBRARY_PATH
-    export PYTHONPATH=/path/to/hintsvm/python:$PYTHONPATH
+To build and install from souce for all users on Unix/Linux:
+```
+python setup.py build
+sudo python setup.py install
+```
 
 # Usage
 
@@ -103,6 +96,27 @@ Available examples:
   - `examples/label_digits.py`: This example shows how to use libact in the case
     that you want a human to label the selected sample for your algorithm.
 
+# Running tests
+
+To run the test suite:
+
+```
+python setup.py test
+```
+
+To run pylint, install pylint through ```pip install pylint``` and run the following command in root directory:
+
+```
+pylint libact
+```
+
+To measure the test code coverage, install coverage through ```pip install coverage``` and run the following commands in root directory:
+
+```
+coverage run --source libact --omit */tests/* setup.py test
+coverage report
+```
+
 # Acknowledgments
 
 The authors thank Chih-Wei Chang and other members of the [Computational Learning Lab](https://learner.csie.ntu.edu.tw/) at National Taiwan University for valuable discussions and various contributions to making this package better.

docs/conf.py

@@ -19,7 +19,9 @@
 import sys
 from unittest.mock import MagicMock
 
+
 class Mock(MagicMock):
+
     @classmethod
     def __getattr__(cls, name):
         return Mock()
@@ -239,25 +241,25 @@ def __getattr__(cls, name):
 # -- Options for LaTeX output ---------------------------------------------
 
 latex_elements = {
-# The paper size ('letterpaper' or 'a4paper').
-#'papersize': 'letterpaper',
+    # The paper size ('letterpaper' or 'a4paper').
+    #'papersize': 'letterpaper',
 
-# The font size ('10pt', '11pt' or '12pt').
-#'pointsize': '10pt',
+    # The font size ('10pt', '11pt' or '12pt').
+    #'pointsize': '10pt',
 
-# Additional stuff for the LaTeX preamble.
-#'preamble': '',
+    # Additional stuff for the LaTeX preamble.
+    #'preamble': '',
 
-# Latex figure (float) alignment
-#'figure_align': 'htbp',
+    # Latex figure (float) alignment
+    #'figure_align': 'htbp',
 }
 
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-  (master_doc, 'libact.tex', 'libact Documentation',
-   'Y.-A. Chung, S.-C. Lee, T.-E. Wu, Y.-Y. Yang, H.-T. Lin', 'manual'),
+    (master_doc, 'libact.tex', 'libact Documentation',
+     'Y.-A. Chung, S.-C. Lee, T.-E. Wu, Y.-Y. Yang, H.-T. Lin', 'manual'),
 ]
 
 # The name of an image file (relative to this directory) to place at the top of
@@ -300,9 +302,9 @@ def __getattr__(cls, name):
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-  (master_doc, 'libact', 'libact Documentation',
-   author, 'libact', 'One line description of project.',
-   'Miscellaneous'),
+    (master_doc, 'libact', 'libact Documentation',
+     author, 'libact', 'One line description of project.',
+     'Miscellaneous'),
 ]
 
 # Documents to append as an appendix to all manuals.

examples/label_digits.py

@@ -29,14 +29,15 @@ def split_train_test(n_classes):
     from sklearn.datasets import load_digits
 
     n_labeled = 5
-    digits = load_digits(n_class=n_classes) # consider binary case
+    digits = load_digits(n_class=n_classes)  # consider binary case
     X = digits.data
     y = digits.target
     print(np.shape(X))
 
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
     while len(np.unique(y_train[:n_labeled])) < n_classes:
-        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33)
+        X_train, X_test, y_train, y_test = train_test_split(
+            X, y, test_size=0.33)
 
     trn_ds = Dataset(X_train, np.concatenate(
         [y_train[:n_labeled], [None] * (len(y_train) - n_labeled)]))
@@ -98,9 +99,9 @@ def main():
         model.train(trn_ds2)
         E_out2 = np.append(E_out2, 1 - model.score(tst_ds))
 
-        ax.set_xlim((0, i+1))
+        ax.set_xlim((0, i + 1))
         ax.set_ylim((0, max(max(E_out1), max(E_out2)) + 0.2))
-        query_num = np.arange(0, i+2)
+        query_num = np.arange(0, i + 2)
         p1.set_xdata(query_num)
         p1.set_ydata(E_out1)
         p2.set_xdata(query_num)

examples/plot.py

@@ -55,7 +55,7 @@ def main():
     dataset_filepath = os.path.join(
         os.path.dirname(os.path.realpath(__file__)), 'diabetes.txt')
     test_size = 0.33    # the percentage of samples in the dataset that will be
-                        # randomly selected and assigned to the test set
+    # randomly selected and assigned to the test set
     n_labeled = 10      # number of samples that are initially labeled
 
     # Load dataset

libact/base/dataset.py

@@ -13,6 +13,7 @@
 
 
 class Dataset(object):
+
     """libact dataset object
 
     Parameters
@@ -31,7 +32,9 @@ class Dataset(object):
 
     """
 
-    def __init__(self, X=[], y=[]):
+    def __init__(self, X=None, y=None):
+        if X is None: X = []
+        if y is None: y = []
         self.data = list(zip(X, y))
         self.modified = True
         self._update_callback = set()
@@ -176,7 +179,7 @@ def get_unlabeled_entries(self):
         return [
             (idx, entry[0]) for idx, entry in enumerate(self.data)
             if entry[1] is None
-            ]
+        ]
 
     def labeled_uniform_sample(self, sample_size, replace=True):
         """Returns a Dataset object with labeled data only, which is
@@ -191,7 +194,7 @@ def labeled_uniform_sample(self, sample_size, replace=True):
             samples = [
                 random.choice(self.get_labeled_entries())
                 for _ in range(sample_size)
-                ]
+            ]
         else:
             samples = random.sample(self.get_labeled_entries(), sample_size)
         return Dataset(*zip(*samples))