Fixed typos

README.md

@@ -0,0 +1,6 @@
+# MSAX: Multivariate Symbolic Aggregate Approximation
+
+## Installation
+
+## Usage
+

msax/error.py

@@ -43,7 +43,7 @@ def alphabet_error(paa_x, sax_x, a):
     return np.sum(np.abs(values - paa_x))
 
 
-def sax_error(x, a, w, memory_limit, use_inf=False, l_1 = 1.0):
+def sax_error(x, a, w, memory_limit, use_inf=False, l_1=1.0):
     """
     Calculates the L_1 error with input parameters. If the w < 2, a < 3 or the generated sax does not fit in the memory
     it will return with np.nan. If the use_inf is True, it returns with np.inf instead of np.nan.
@@ -133,7 +133,6 @@ def as_dataframe(self, without_nan=True):
             df = df.dropna()
         return df
 
-
     def __str__(self):
         return "ErrorSurface: min_w: {}, min_a: {}, min_value: {}".format(self.min_w, self.min_a, self.min)
 

msax/msax.py

@@ -18,7 +18,7 @@ def breakpoints(a):
     """
     bps = break_point_cache.get(a, None)
     if bps is None:
-        bps = [np.sqrt(2)* erfinv(2*(j / a) - 1) for j in range(1, a)]
+        bps = [np.sqrt(2) * erfinv(2*(j / a) - 1) for j in range(1, a)]
         break_point_cache[a] = bps
     return bps
 
@@ -35,7 +35,7 @@ def symbol_values(a):
     bps = breakpoints(a)
 
     vals = [bps[0]]
-    vals.extend([(bps[x] + bps[x - 1]) / 2 for x in range(1,a-1)])
+    vals.extend([(bps[x] + bps[x - 1]) / 2 for x in range(1, a-1)])
     vals.append(bps[-1])
     return np.array(vals)
 
@@ -84,7 +84,7 @@ def alphabetize(paa_x, a):
     :return: Symbol indices' list. A symbol index can be interpreted as an alphabet index.
     :rtype: np.ndarray
     """
-    return  np.searchsorted(breakpoints(a), paa_x)
+    return np.searchsorted(breakpoints(a), paa_x)
 
 
 def sax(x, w, a, normalized=False):
@@ -103,9 +103,9 @@ def sax(x, w, a, normalized=False):
     :rtype: np.ndarray
     """
     if not normalized:
-        return alphabetize(paa(normalize(x),w), a)
+        return alphabetize(paa(normalize(x), w), a)
     else:
-        return alphabetize(paa(x,w), a)
+        return alphabetize(paa(x, w), a)
 
 
 def independence_transform(x):

msax/plot.py

@@ -3,19 +3,23 @@
 import numpy as np
 import seaborn as sns
 
+from msax.msax import paa
+
 from mpl_toolkits.mplot3d import Axes3D
 
-def ts_with_hist(x, fig = None, gridsize=(1, 3), bins=50):
+
+def ts_with_hist(x, fig=None, bins=50):
     """
+    Visualizes the input x time series with its histogram.
 
-    :param x:
-    :param fig:
-    :param gridsize:
-    :param bins:
+    :param x: Input array
+    :param fig: Optional, matplotlib figure
+    :param bins: Number of bins on histogram
     :return:
     """
     if fig is None:
         fig = plt.figure(figsize=(18, 6))
+    gridsize = (1, 3)
     ax1 = plt.subplot2grid(gridsize, (0, 0), colspan=2, rowspan=1, fig=fig)
     ax2 = plt.subplot2grid(gridsize, (0, 2), fig=fig)
     ax1.plot(x)
@@ -24,58 +28,57 @@ def ts_with_hist(x, fig = None, gridsize=(1, 3), bins=50):
     return fig, ax1, ax2
 
 
-def plot_paa(orig_x, paa_x, w, fig = None):
+def plot_paa(x, w, fig=None):
     """
+    Visualizes the input x time series with its PAA transformed version.
 
-    :param orig_x:
-    :param paa_x:
-    :param w:
-    :param fig:
+    :param x: Input array
+    :param w: window size parameter for PAA transformation
+    :param fig: Optional, matplotlib figure
     :return:
     """
     if fig is None:
         fig = plt.figure(figsize=(18, 6))
+    x_paa = paa(x, w)
+
     ax = fig.subplots(nrows=1, ncols=1)
-    ax.plot(orig_x, c='blue', label='Original')
-    ax.plot(np.repeat(paa_x, w), c='orange', label='PAA')
+    ax.plot(x, c='blue', label='Original')
+    ax.plot(np.repeat(x_paa, w), c='orange', label='PAA')
     ax.legend()
 
     return fig, ax
 
 
-def plot_2d_error_surface(err_surface, alphabets, windows, fig = None):
+def plot_2d_error_surface(err_surface, fig=None):
     """
+    Visualizes the input ErrorSurface in 2D.
 
-    :param err_surface:
-    :param alphabets:
-    :param windows:
-    :param fig:
+    :param err_surface: Input error surface. Must be an instance of ErrorSurface (msax.error.ErrorSurface)
+    :type err_surface: msax.error.ErrorSurface
+    :param fig: Optional, matplotlib figure
     :return:
     """
     if fig is None:
         fig = plt.figure(figsize=(18, 12))
 
-    from msax.error import ErrorSurface
-    if isinstance(err_surface, ErrorSurface):
-        err_surface = err_surface.values
+    err_surface_vals = err_surface.values
 
     ax = fig.add_subplot(111)
-    ax.text()
-    sns.heatmap(err_surface, xticklabels=alphabets, yticklabels=windows, ax=ax)
+    sns.heatmap(err_surface_vals, xticklabels=err_surface.alphabets, yticklabels=err_surface.windows, ax=ax)
     ax.set_ylabel('window size')
     ax.set_xlabel('alphabet size')
     ax.set_title('Cost of SAX')
-    sns.jointplot()
     return fig, ax
 
 
 def plot_3d_error_surface(err_surface, ax=None, title=None):
     """
+    Visualizes the input ErrorSurface in 3D.
 
-    :param title:
-    :param ax:
-    :param err_surface:
+    :param err_surface: Input error surface
     :type err_surface: msax.error.ErrorSurface
+    :param title: Optional. The title of the figure
+    :param ax: Optional. matplotlib axes.
     :return:
     """
     if ax is None:

setup.py

@@ -0,0 +1,130 @@
+import io
+import os
+import sys
+from shutil import rmtree
+
+from setuptools import find_packages, setup, Command
+
+# Package meta-data.
+NAME = 'msax'
+DESCRIPTION = 'Implementation of Multivariate Symbolic Aggregate Approximation (MSAX)'
+URL = 'https://github.com/nagyatka/msax'
+EMAIL = '[email protected]'
+AUTHOR = 'Attila M. Nagy'
+REQUIRES_PYTHON = '>=3.6.0'
+KEYWORDS = 'sax msax timeseries '
+
+MAJOR               = 0
+MINOR               = 1
+MICRO               = 0
+VERSION             = '%d.%d.%d' % (MAJOR, MINOR, MICRO)
+
+# What packages are required for this module to be executed?
+REQUIRED = [
+    'numpy', 'scipy', 'pandas'
+]
+
+# What packages are optional?
+EXTRAS = {
+    # 'fancy feature': ['django'],
+}
+
+# The rest you shouldn't have to touch too much :)
+# ------------------------------------------------
+# Except, perhaps the License and Trove Classifiers!
+# If you do change the License, remember to change the Trove Classifier for that!
+
+here = os.path.abspath(os.path.dirname(__file__))
+
+# Import the README and use it as the long-description.
+# Note: this will only work if 'README.md' is present in your MANIFEST.in file!
+try:
+    with io.open(os.path.join(here, 'README.md'), encoding='utf-8') as f:
+        long_description = '\n' + f.read()
+except FileNotFoundError:
+    long_description = DESCRIPTION
+
+
+# Load the package's __version__.py module as a dictionary.
+about = {}
+if not VERSION:
+    project_slug = NAME.lower().replace("-", "_").replace(" ", "_")
+    with open(os.path.join(here, project_slug, '__version__.py')) as f:
+        exec(f.read(), about)
+else:
+    about['__version__'] = VERSION
+
+class UploadCommand(Command):
+    """Support setup.py upload."""
+
+    description = 'Build and publish the package.'
+    user_options = []
+
+    @staticmethod
+    def status(s):
+        """Prints things in bold."""
+        print('\033[1m{0}\033[0m'.format(s))
+
+    def initialize_options(self):
+        pass
+
+    def finalize_options(self):
+        pass
+
+    def run(self):
+        try:
+            self.status('Removing previous builds…')
+            rmtree(os.path.join(here, 'dist'))
+        except OSError:
+            pass
+
+        self.status('Building Source and Wheel (universal) distribution…')
+        os.system('{0} setup.py sdist bdist_wheel --universal'.format(sys.executable))
+
+        self.status('Uploading the package to PyPI via Twine…')
+        os.system('twine upload dist/*')
+
+        self.status('Pushing git tags…')
+        os.system('git tag v{0}'.format(about['__version__']))
+        os.system('git push --tags')
+
+        sys.exit()
+
+
+# Where the magic happens:
+setup(
+    name=NAME,
+    version=about['__version__'],
+    description=DESCRIPTION,
+    long_description=long_description,
+    long_description_content_type='text/markdown',
+    author=AUTHOR,
+    author_email=EMAIL,
+    python_requires=REQUIRES_PYTHON,
+    url=URL,
+    packages=find_packages(exclude=["tests", "*.tests", "*.tests.*", "tests.*"]),
+    # If your package is a single module, use this instead of 'packages':
+    # py_modules=['mypackage'],
+
+    # entry_points={
+    #     'console_scripts': ['mycli=mymodule:cli'],
+    # },
+    install_requires=REQUIRED,
+    extras_require=EXTRAS,
+    include_package_data=True,
+    license='MIT',
+    classifiers=[
+        'License :: OSI Approved :: MIT License',
+        'Programming Language :: Python',
+        'Programming Language :: Python :: 3',
+        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: Implementation :: CPython',
+        'Programming Language :: Python :: Implementation :: PyPy',
+        'Topic :: Scientific/Engineering :: Artificial Intelligence',
+        'Topic :: Scientific/Engineering :: Information Analysis'
+    ],
+    # $ setup.py publish support.
+    cmdclass={
+        'upload': UploadCommand,
+    },
+)