fixed content type on README + misc reformatting (#84)

.travis.yml

@@ -28,9 +28,6 @@ before_install:
 addons:
   apt:
     packages:
-    # install pandoc for use with pypandoc for converting the README
-    # from markdown to RST
-    - pandoc
     # Even though I'm installing cvxopt via conda, still seem to need these:
     - liblapack-dev
     - libatlas-base-dev
@@ -41,7 +38,6 @@ install:
   - source activate test-environment
   - conda install -c cvxgrp scs=1.2.6
   - pip install tensorflow
-  - pip install pypandoc
   - pip install -r requirements.txt
   - pip install .
   - pip install coveralls

README.md

@@ -13,7 +13,7 @@ from fancyimpute import KNN, NuclearNormMinimization, SoftImpute, IterativeImput
 # X is the complete data matrix
 # X_incomplete has the same values as X except a subset have been replace with NaN
 
-# Model each feature with missing values as a function of other features, and 
+# Model each feature with missing values as a function of other features, and
 # use that estimate for imputation.
 X_filled_ii = IterativeImputer().fit_transform(X_incomplete)
 
@@ -66,10 +66,10 @@ matrix. Not guaranteed to converge but works well in practice. Taken from [Matri
 
 ## Note about Inductive vs Transductive Imputation
 Most imputation algorithms in `fancyimpute` are *transductive*. In the elegant language of `scikit-learn`'s API
-this means that you can only call `solver.fit_transform(X_incomplete)`, but then the "fitted" `solver` will not 
+this means that you can only call `solver.fit_transform(X_incomplete)`, but then the "fitted" `solver` will not
 be able to be applied to new data via a call to `solver.transform`. A simple example is the `MatrixFactorization`
-imputer, which decomposes as follows: `<A,B> = X_incomplete`, such that the product of `A` and `B` is close 
-to `X_incomplete` on its non-missing values. How then, can we apply the learned `A` and `B` matrices to 
+imputer, which decomposes as follows: `<A,B> = X_incomplete`, such that the product of `A` and `B` is close
+to `X_incomplete` on its non-missing values. How then, can we apply the learned `A` and `B` matrices to
 held-out data? It is not doable in general, but there are special cases. `fancyimpute` aims to be of general
 use and we have not implemented an inductive mode for `MatrixFactorization`.
 
@@ -108,13 +108,13 @@ XY_completed = []
 for i in range(n_imputations):
     imputer = IterativeImputer(n_iter=5, sample_posterior=True, random_state=i)
     XY_completed.append(imputer.fit_transform(XY_incomplete))
-    
+
 XY_completed_mean = np.mean(XY_completed, 0)
 XY_completed_std = np.std(XY_completed, 0)
 ```
 
 See [2], chapter 4 for more discussion on multiple
-vs. single imputations. 
+vs. single imputations.
 
 It is still an open problem as to how useful single vs. multiple imputation is in
 the context of prediction and classification when the user is not interested in
@@ -123,6 +123,6 @@ measuring uncertainty due to missing values.
 [1] Stef van Buuren, Karin Groothuis-Oudshoorn (2011). "mice: Multivariate
    Imputation by Chained Equations in R". Journal of Statistical Software 45:
    1-67.
-   
+
 [2] Roderick J A Little and Donald B Rubin (1986). "Statistical Analysis
     with Missing Data". John Wiley & Sons, Inc., New York, NY, USA.

fancyimpute/__init__.py

@@ -11,6 +11,8 @@
 from .knn import KNN
 from .similarity_weighted_averaging import SimilarityWeightedAveraging
 
+__version__ = "0.4.1"
+
 __all__ = [
     "Solver",
     "NuclearNormMinimization",

fancyimpute/iterative_imputer.py

@@ -1,3 +1,15 @@
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
 from __future__ import division
 
 import warnings

fancyimpute/iterative_svd.py

@@ -21,6 +21,7 @@
 
 F32PREC = np.finfo(np.float32).eps
 
+
 class IterativeSVD(Solver):
     def __init__(
             self,

fancyimpute/knn.py

@@ -18,6 +18,7 @@
 
 from .solver import Solver
 
+
 class KNN(Solver):
     """
     k-Nearest Neighbors imputation for arrays with missing data.

fancyimpute/nuclear_norm_minimization.py

@@ -18,6 +18,7 @@
 
 from sklearn.utils import check_array
 
+
 class NuclearNormMinimization(Solver):
     """
     Simple implementation of "Exact Matrix Completion via Convex Optimization"

fancyimpute/scaler.py

@@ -16,6 +16,7 @@
 
 import numpy as np
 
+
 class Scaler(object):
     """
     Iterative estimation of row and column centering/scaling

fancyimpute/soft_impute.py

@@ -22,6 +22,7 @@
 
 F32PREC = np.finfo(np.float32).eps
 
+
 class SoftImpute(Solver):
     """
     Implementation of the SoftImpute algorithm from:

fancyimpute/solver.py

@@ -206,10 +206,11 @@ def fit(self, X, y=None):
         using `fit` or `fit_transform` on `X_train` and then `transform`
         on new `X_test`.
         """
-        raise ValueError("%s.fit not implemented! This imputation algorithm likely "
-                         "doesn't support inductive mode. Only fit_transform is "
-                         "supported at this time." % (
-            self.__class__.__name__,))
+        raise ValueError(
+            "%s.fit not implemented! This imputation algorithm likely "
+            "doesn't support inductive mode. Only fit_transform is "
+            "supported at this time." % (
+                self.__class__.__name__,))
 
     def transform(self, X, y=None):
         """
@@ -220,7 +221,8 @@ def transform(self, X, y=None):
         using `fit` or `fit_transform` on `X_train` and then `transform`
         on new `X_test`.
         """
-        raise ValueError("%s.transform not implemented! This imputation algorithm likely "
-                         "doesn't support inductive mode. Only %s.fit_transform is "
-                         "supported at this time." % (
-            self.__class__.__name__,))
+        raise ValueError(
+            "%s.transform not implemented! This imputation algorithm likely "
+            "doesn't support inductive mode. Only %s.fit_transform is "
+            "supported at this time." % (
+                self.__class__.__name__,))

setup.py

@@ -12,34 +12,37 @@
 
 import os
 import logging
+import re
 
 from setuptools import setup
 
+package_name = "fancyimpute"
+
+
 readme_dir = os.path.dirname(__file__)
 readme_filename = os.path.join(readme_dir, 'README.md')
 
 try:
     with open(readme_filename, 'r') as f:
-        readme = f.read()
+        readme_markdown = f.read()
 except:
     logging.warn("Failed to load %s" % readme_filename)
-    readme = ""
+    readme_markdown = ""
 
-try:
-    import pypandoc
-    readme = pypandoc.convert(readme, to='rst', format='md')
-except:
-    logging.warn("Conversion of long_description from MD to RST failed")
-    pass
+with open('%s/__init__.py' % package_name, 'r') as f:
+    version = re.search(
+        r'^__version__\s*=\s*[\'"]([^\'"]*)[\'"]',
+        f.read(),
+        re.MULTILINE).group(1)
 
 if __name__ == '__main__':
     setup(
-        name='fancyimpute',
-        version="0.4.0",
+        name=package_name,
+        version=version,
         description="Matrix completion and feature imputation algorithms",
         author="Alex Rubinsteyn, Sergey Feldman",
         author_email="alex.rubinsteyn@gmail.com",
-        url="https://github.com/hammerlab/fancyimpute",
+        url="https://github.com/openvax/%s" % package_name,
         license="http://www.apache.org/licenses/LICENSE-2.0.html",
         classifiers=[
             'Development Status :: 3 - Alpha',
@@ -64,6 +67,7 @@
             'np_utils',
             'tensorflow',
         ],
-        long_description=readme,
-        packages=['fancyimpute'],
+        long_description=readme_markdown,
+        long_description_content_type='text/markdown',
+        packages=[package_name],
     )