molSimplify 1.7.4__py3-none-any.whl

molSimplify/molscontrol/_version.py

@@ -0,0 +1,521 @@
+
+# This file helps to compute a version number in source trees obtained from
+# git-archive tarball (such as those provided by githubs download-from-tag
+# feature). Distribution tarballs (built by setup.py sdist) and build
+# directories (produced by setup.py build) will contain a much shorter file
+# that just contains the computed version number.
+
+# This file is released into the public domain. Generated by
+# versioneer-0.18 (https://github.com/warner/python-versioneer)
+
+"""Git implementation of _version.py."""
+
+import errno
+import os
+import re
+import subprocess
+import sys
+from typing import Dict, Any
+
+
+def get_keywords():
+    """Get the keywords needed to look up the version information."""
+    # these strings will be replaced by git during git-archive.
+    # setup.py/versioneer.py will grep for the variable names, so they must
+    # each be defined on a line of their own. _version.py will just call
+    # get_keywords().
+    git_refnames = "$Format:%d$"
+    git_full = "$Format:%H$"
+    git_date = "$Format:%ci$"
+    keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}
+    return keywords
+
+
+class VersioneerConfig:
+    """Container for Versioneer configuration parameters."""
+
+
+def get_config():
+    """Create, populate and return the VersioneerConfig() object."""
+    # these strings are filled in when 'setup.py versioneer' creates
+    # _version.py
+    cfg = VersioneerConfig()
+    cfg.VCS = "git"
+    cfg.style = "pep440"
+    cfg.tag_prefix = ""
+    cfg.parentdir_prefix = "None"
+    cfg.versionfile_source = "molscontrol/_version.py"
+    cfg.verbose = False
+    return cfg
+
+
+class NotThisMethod(Exception):
+    """Exception raised if a method is not valid for the current scenario."""
+
+
+LONG_VERSION_PY: Dict[Any, Any] = {}
+HANDLERS = {}
+
+
+def register_vcs_handler(vcs, method):  # decorator
+    """Decorator to mark a method as the handler for a particular VCS."""
+    def decorate(f):
+        """Store f in HANDLERS[vcs][method]."""
+        if vcs not in HANDLERS:
+            HANDLERS[vcs] = {}
+        HANDLERS[vcs][method] = f
+        return f
+    return decorate
+
+
+def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False,
+                env=None):
+    """Call the given command(s)."""
+    assert isinstance(commands, list)
+    p = None
+    for c in commands:
+        try:
+            dispcmd = str([c] + args)
+            # remember shell=False, so use git.cmd on windows, not just git
+            p = subprocess.Popen([c] + args, cwd=cwd, env=env,
+                                 stdout=subprocess.PIPE,
+                                 stderr=(subprocess.PIPE if hide_stderr
+                                         else None))
+            break
+        except EnvironmentError:
+            e = sys.exc_info()[1]
+            if e.errno == errno.ENOENT:
+                continue
+            if verbose:
+                print(("unable to run %s" % dispcmd))
+                print(e)
+            return None, None
+    else:
+        if verbose:
+            print(("unable to find command, tried %s" % (commands,)))
+        return None, None
+    stdout = p.communicate()[0].strip()
+    if sys.version_info[0] >= 3:
+        stdout = stdout.decode()
+    if p.returncode != 0:
+        if verbose:
+            print(("unable to run %s (error)" % dispcmd))
+            print(("stdout was %s" % stdout))
+        return None, p.returncode
+    return stdout, p.returncode
+
+
+def versions_from_parentdir(parentdir_prefix, root, verbose):
+    """Try to determine the version from the parent directory name.
+
+    Source tarballs conventionally unpack into a directory that includes both
+    the project name and a version string. We will also support searching up
+    two directory levels for an appropriately named parent directory
+    """
+    rootdirs = []
+
+    for i in range(3):
+        dirname = os.path.basename(root)
+        if dirname.startswith(parentdir_prefix):
+            return {"version": dirname[len(parentdir_prefix):],
+                    "full-revisionid": None,
+                    "dirty": False, "error": None, "date": None}
+        else:
+            rootdirs.append(root)
+            root = os.path.dirname(root)  # up a level
+
+    if verbose:
+        print(("Tried directories %s but none started with prefix %s" %
+              (str(rootdirs), parentdir_prefix)))
+    raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
+
+
+@register_vcs_handler("git", "get_keywords")
+def git_get_keywords(versionfile_abs):
+    """Extract version information from the given file."""
+    # the code embedded in _version.py can just fetch the value of these
+    # keywords. When used from setup.py, we don't want to import _version.py,
+    # so we do it with a regexp instead. This function is not used from
+    # _version.py.
+    keywords = {}
+    try:
+        with open(versionfile_abs, "r") as f:
+            lines = f.readlines()
+        for line in lines:
+            if line.strip().startswith("git_refnames ="):
+                mo = re.search(r'=\s*"(.*)"', line)
+                if mo:
+                    keywords["refnames"] = mo.group(1)
+            if line.strip().startswith("git_full ="):
+                mo = re.search(r'=\s*"(.*)"', line)
+                if mo:
+                    keywords["full"] = mo.group(1)
+            if line.strip().startswith("git_date ="):
+                mo = re.search(r'=\s*"(.*)"', line)
+                if mo:
+                    keywords["date"] = mo.group(1)
+    except EnvironmentError:
+        pass
+    return keywords
+
+
+@register_vcs_handler("git", "keywords")
+def git_versions_from_keywords(keywords, tag_prefix, verbose):
+    """Get version information from git keywords."""
+    if not keywords:
+        raise NotThisMethod("no keywords at all, weird")
+    date = keywords.get("date")
+    if date is not None:
+        # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant
+        # datestamp. However we prefer "%ci" (which expands to an "ISO-8601
+        # -like" string, which we must then edit to make compliant), because
+        # it's been around since git-1.5.3, and it's too difficult to
+        # discover which version we're using, or to work around using an
+        # older one.
+        date = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
+    refnames = keywords["refnames"].strip()
+    if refnames.startswith("$Format"):
+        if verbose:
+            print("keywords are unexpanded, not using")
+        raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
+    refs = set([r.strip() for r in refnames.strip("()").split(",")])
+    # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
+    # just "foo-1.0". If we see a "tag: " prefix, prefer those.
+    TAG = "tag: "
+    tags = set([r[len(TAG):] for r in refs if r.startswith(TAG)])
+    if not tags:
+        # Either we're using git < 1.8.3, or there really are no tags. We use
+        # a heuristic: assume all version tags have a digit. The old git %d
+        # expansion behaves like git log --decorate=short and strips out the
+        # refs/heads/ and refs/tags/ prefixes that would let us distinguish
+        # between branches and tags. By ignoring refnames without digits, we
+        # filter out many common branch names like "release" and
+        # "stabilization", as well as "HEAD" and "master".
+        tags = set([r for r in refs if re.search(r'\d', r)])
+        if verbose:
+            print(("discarding '%s', no digits" % ",".join(refs - tags)))
+    if verbose:
+        print(("likely tags: %s" % ",".join(sorted(tags))))
+    for ref in sorted(tags):
+        # sorting will prefer e.g. "2.0" over "2.0rc1"
+        if ref.startswith(tag_prefix):
+            r = ref[len(tag_prefix):]
+            if verbose:
+                print(("picking %s" % r))
+            return {"version": r,
+                    "full-revisionid": keywords["full"].strip(),
+                    "dirty": False, "error": None,
+                    "date": date}
+    # no suitable tags, so version is "0+unknown", but full hex is still there
+    if verbose:
+        print("no suitable tags, using unknown + full revision id")
+    return {"version": "0+unknown",
+            "full-revisionid": keywords["full"].strip(),
+            "dirty": False, "error": "no suitable tags", "date": None}
+
+
+@register_vcs_handler("git", "pieces_from_vcs")
+def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
+    """Get version from 'git describe' in the root of the source tree.
+
+    This only gets called if the git-archive 'subst' keywords were *not*
+    expanded, and _version.py hasn't already been rewritten with a short
+    version string, meaning we're inside a checked out source tree.
+    """
+    GITS = ["git"]
+    if sys.platform == "win32":
+        GITS = ["git.cmd", "git.exe"]
+
+    out, rc = run_command(GITS, ["rev-parse", "--git-dir"], cwd=root,
+                          hide_stderr=True)
+    if rc != 0:
+        if verbose:
+            print(("Directory %s not under git control" % root))
+        raise NotThisMethod("'git rev-parse --git-dir' returned error")
+
+    # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
+    # if there isn't one, this yields HEX[-dirty] (no NUM)
+    describe_out, rc = run_command(GITS, ["describe", "--tags", "--dirty",
+                                          "--always", "--long",
+                                          "--match", "%s*" % tag_prefix],
+                                   cwd=root)
+    # --long was added in git-1.5.5
+    if describe_out is None:
+        raise NotThisMethod("'git describe' failed")
+    describe_out = describe_out.strip()
+    full_out, rc = run_command(GITS, ["rev-parse", "HEAD"], cwd=root)
+    if full_out is None:
+        raise NotThisMethod("'git rev-parse' failed")
+    full_out = full_out.strip()
+
+    pieces = {}
+    pieces["long"] = full_out
+    pieces["short"] = full_out[:7]  # maybe improved later
+    pieces["error"] = None
+
+    # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty]
+    # TAG might have hyphens.
+    git_describe = describe_out
+
+    # look for -dirty suffix
+    dirty = git_describe.endswith("-dirty")
+    pieces["dirty"] = dirty
+    if dirty:
+        git_describe = git_describe[:git_describe.rindex("-dirty")]
+
+    # now we have TAG-NUM-gHEX or HEX
+
+    if "-" in git_describe:
+        # TAG-NUM-gHEX
+        mo = re.search(r'^(.+)-(\d+)-g([0-9a-f]+)$', git_describe)
+        if not mo:
+            # unparseable. Maybe git-describe is misbehaving?
+            pieces["error"] = ("unable to parse git-describe output: '%s'"
+                               % describe_out)
+            return pieces
+
+        # tag
+        full_tag = mo.group(1)
+        if not full_tag.startswith(tag_prefix):
+            if verbose:
+                fmt = "tag '%s' doesn't start with prefix '%s'"
+                print((fmt % (full_tag, tag_prefix)))
+            pieces["error"] = ("tag '%s' doesn't start with prefix '%s'"
+                               % (full_tag, tag_prefix))
+            return pieces
+        pieces["closest-tag"] = full_tag[len(tag_prefix):]
+
+        # distance: number of commits since tag
+        pieces["distance"] = int(mo.group(2))
+
+        # commit: short hex revision ID
+        pieces["short"] = mo.group(3)
+
+    else:
+        # HEX: no tags
+        pieces["closest-tag"] = None
+        count_out, rc = run_command(GITS, ["rev-list", "HEAD", "--count"],
+                                    cwd=root)
+        pieces["distance"] = int(count_out)  # total number of commits
+
+    # commit date: see ISO-8601 comment in git_versions_from_keywords()
+    date = run_command(GITS, ["show", "-s", "--format=%ci", "HEAD"],
+                       cwd=root)[0].strip()
+    pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
+
+    return pieces
+
+
+def plus_or_dot(pieces):
+    """Return a + if we don't already have one, else return a ."""
+    if "+" in pieces.get("closest-tag", ""):
+        return "."
+    return "+"
+
+
+def render_pep440(pieces):
+    """Build up version string, with post-release "local version identifier".
+
+    Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you
+    get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty
+
+    Exceptions:
+    1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            rendered += plus_or_dot(pieces)
+            rendered += "%d.g%s" % (pieces["distance"], pieces["short"])
+            if pieces["dirty"]:
+                rendered += ".dirty"
+    else:
+        # exception #1
+        rendered = "0+untagged.%d.g%s" % (pieces["distance"],
+                                          pieces["short"])
+        if pieces["dirty"]:
+            rendered += ".dirty"
+    return rendered
+
+
+def render_pep440_pre(pieces):
+    """TAG[.post.devDISTANCE] -- No -dirty.
+
+    Exceptions:
+    1: no tags. 0.post.devDISTANCE
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"]:
+            rendered += ".post.dev%d" % pieces["distance"]
+    else:
+        # exception #1
+        rendered = "0.post.dev%d" % pieces["distance"]
+    return rendered
+
+
+def render_pep440_post(pieces):
+    """TAG[.postDISTANCE[.dev0]+gHEX] .
+
+    The ".dev0" means dirty. Note that .dev0 sorts backwards
+    (a dirty tree will appear "older" than the corresponding clean one),
+    but you shouldn't be releasing software with -dirty anyways.
+
+    Exceptions:
+    1: no tags. 0.postDISTANCE[.dev0]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            rendered += ".post%d" % pieces["distance"]
+            if pieces["dirty"]:
+                rendered += ".dev0"
+            rendered += plus_or_dot(pieces)
+            rendered += "g%s" % pieces["short"]
+    else:
+        # exception #1
+        rendered = "0.post%d" % pieces["distance"]
+        if pieces["dirty"]:
+            rendered += ".dev0"
+        rendered += "+g%s" % pieces["short"]
+    return rendered
+
+
+def render_pep440_old(pieces):
+    """TAG[.postDISTANCE[.dev0]] .
+
+    The ".dev0" means dirty.
+
+    Eexceptions:
+    1: no tags. 0.postDISTANCE[.dev0]
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"] or pieces["dirty"]:
+            rendered += ".post%d" % pieces["distance"]
+            if pieces["dirty"]:
+                rendered += ".dev0"
+    else:
+        # exception #1
+        rendered = "0.post%d" % pieces["distance"]
+        if pieces["dirty"]:
+            rendered += ".dev0"
+    return rendered
+
+
+def render_git_describe(pieces):
+    """TAG[-DISTANCE-gHEX][-dirty].
+
+    Like 'git describe --tags --dirty --always'.
+
+    Exceptions:
+    1: no tags. HEX[-dirty]  (note: no 'g' prefix)
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        if pieces["distance"]:
+            rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
+    else:
+        # exception #1
+        rendered = pieces["short"]
+    if pieces["dirty"]:
+        rendered += "-dirty"
+    return rendered
+
+
+def render_git_describe_long(pieces):
+    """TAG-DISTANCE-gHEX[-dirty].
+
+    Like 'git describe --tags --dirty --always -long'.
+    The distance/hash is unconditional.
+
+    Exceptions:
+    1: no tags. HEX[-dirty]  (note: no 'g' prefix)
+    """
+    if pieces["closest-tag"]:
+        rendered = pieces["closest-tag"]
+        rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
+    else:
+        # exception #1
+        rendered = pieces["short"]
+    if pieces["dirty"]:
+        rendered += "-dirty"
+    return rendered
+
+
+def render(pieces, style):
+    """Render the given version pieces into the requested style."""
+    if pieces["error"]:
+        return {"version": "unknown",
+                "full-revisionid": pieces.get("long"),
+                "dirty": None,
+                "error": pieces["error"],
+                "date": None}
+
+    if not style or style == "default":
+        style = "pep440"  # the default
+
+    if style == "pep440":
+        rendered = render_pep440(pieces)
+    elif style == "pep440-pre":
+        rendered = render_pep440_pre(pieces)
+    elif style == "pep440-post":
+        rendered = render_pep440_post(pieces)
+    elif style == "pep440-old":
+        rendered = render_pep440_old(pieces)
+    elif style == "git-describe":
+        rendered = render_git_describe(pieces)
+    elif style == "git-describe-long":
+        rendered = render_git_describe_long(pieces)
+    else:
+        raise ValueError("unknown style '%s'" % style)
+
+    return {"version": rendered, "full-revisionid": pieces["long"],
+            "dirty": pieces["dirty"], "error": None,
+            "date": pieces.get("date")}
+
+
+def get_versions():
+    """Get version information or return default if unable to do so."""
+    # I am in _version.py, which lives at ROOT/VERSIONFILE_SOURCE. If we have
+    # __file__, we can work backwards from there to the root. Some
+    # py2exe/bbfreeze/non-CPython implementations don't do __file__, in which
+    # case we can only use expanded keywords.
+
+    cfg = get_config()
+    verbose = cfg.verbose
+
+    try:
+        return git_versions_from_keywords(get_keywords(), cfg.tag_prefix,
+                                          verbose)
+    except NotThisMethod:
+        pass
+
+    try:
+        root = os.path.realpath(__file__)
+        # versionfile_source is the relative path from the top of the source
+        # tree (where the .git directory might live) to this file. Invert
+        # this to find the root from __file__.
+        for _ in cfg.versionfile_source.split('/'):
+            root = os.path.dirname(root)
+    except NameError:
+        return {"version": "0+unknown", "full-revisionid": None,
+                "dirty": None,
+                "error": "unable to find root of source tree",
+                "date": None}
+
+    try:
+        pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose)
+        return render(pieces, cfg.style)
+    except NotThisMethod:
+        pass
+
+    try:
+        if cfg.parentdir_prefix:
+            return versions_from_parentdir(cfg.parentdir_prefix, root, verbose)
+    except NotThisMethod:
+        pass
+
+    return {"version": "0+unknown", "full-revisionid": None,
+            "dirty": None,
+            "error": "unable to compute version", "date": None}

molSimplify/molscontrol/clf_tools.py

@@ -0,0 +1,144 @@
+import numpy as np
+from sklearn.metrics.pairwise import pairwise_distances
+from packaging import version
+from tensorflow.keras import backend as K
+import tensorflow as tf
+from sklearn.neighbors import BallTree
+from tensorflow.keras import Model
+
+"""
+tools for ML models.
+"""
+
+
+def get_layer_outputs(model, layer_index, input,
+                      training_flag=False):
+    if not version.parse(tf.__version__) >= version.parse('2.0.0'):
+        get_outputs = K.function([model.layers[0].input, K.learning_phase()],
+                                 [model.layers[layer_index].output])
+        nn_outputs = get_outputs([input, training_flag])[0]
+    else:
+        partial_model = Model(model.inputs, model.layers[layer_index].output)
+        nn_outputs = partial_model([input], training=training_flag).numpy()  # runs the model in training mode
+    return nn_outputs
+
+
+def _dist_neighbor(fmat1, fmat2, labels, l=5, dist_ref=1):  # noqa E741
+    dist_mat = pairwise_distances(fmat1, fmat2, 'manhattan')
+    dist_mat = dist_mat * 1.0 / dist_ref
+    dist_avrg, dist_list, labels_list = [], [], []
+    for ele in dist_mat:
+        dist_arr = np.round(np.array(ele), 4)
+        if not dist_ref == 1:
+            _count = (dist_arr < 10).sum()
+            _count = l if _count < l else _count
+            _count = _count if _count < 300 else 300
+        else:
+            _count = l
+        ind = dist_arr.argsort()[:_count]
+        _dist = dist_arr[ind]
+        dist_list.append(_dist)
+        _labels = np.array([labels[x] for x in ind])
+        labels_list.append(_labels)
+        if _dist.all() > 1e-4:
+            dist_avrg.append(np.mean(_dist[:l]))
+        else:
+            dist_avrg.append(np.mean(_dist[:l]) * float(l) / (l - 1))
+    # print('-----mean: %f, std: %f---' % (np.mean(dist_avrg), np.std(dist_avrg)))
+    dist_avrg = np.array(dist_avrg)
+    dist_list = np.array(dist_list)
+    labels_list = np.array(labels_list)
+    return dist_avrg, dist_list, labels_list
+
+
+def dist_neighbor(fmat1, fmat2, labels, l=10, dist_ref=1):  # noqa E741
+    tree = BallTree(fmat2, leaf_size=2, metric='cityblock')
+    dist_mat, inds = tree.query(fmat1, l)
+    dist_mat = dist_mat * 1.0 / dist_ref
+    dist_avrg = np.mean(dist_mat, axis=1)
+    labels_list = labels[inds]
+    return dist_avrg, dist_mat, labels_list
+
+
+def _get_entropy(dists, neighbor_targets):
+    entropies = []
+    _sum = 0
+    for ii, _neighbor_targets in enumerate(neighbor_targets):
+        p0, p1 = dist_penalty(2), dist_penalty(2)
+        for idx, tar in enumerate(_neighbor_targets):
+            tar = int(tar)
+            d = dists[ii][idx]
+            if d <= 10:
+                if d != 0:
+                    if tar == 0:
+                        p0 += dist_penalty(d)
+                    elif tar == 1:
+                        p1 += dist_penalty(d)
+                else:
+                    if tar == 0:
+                        p0 += 100
+                    elif tar == 1:
+                        p1 += 100
+            _sum = p0 + p1
+        p0 = p0 / _sum
+        p1 = p1 / _sum
+        if p1 == 0 or p0 == 0:
+            entropies.append(0)
+        else:
+            entropies.append(-(p0 * np.log(p0) + p1 * np.log(p1)))
+    return np.array(entropies)
+
+
+def get_entropy(dists, neighbor_targets, nclasses=2):
+    entropies = []
+    for ii, _neighbor_targets in enumerate(neighbor_targets):
+        p = [dist_penalty(2) for ii in range(nclasses)]
+        for idx, tar in enumerate(_neighbor_targets):
+            tar = int(tar)
+            d = dists[ii][idx]
+            if d <= 10:
+                p[tar] += dist_penalty(d) if d > 1e-6 else 100
+        p = [x/np.sum(p) for x in p]
+        _entropy = 0
+        for ii in range(nclasses):
+            _entropy += -p[ii] * np.log(p[ii])
+        entropies.append(_entropy)
+    return np.array(entropies)
+
+
+def dist_penalty(d):
+    return np.exp(-1 * d ** 2)
+
+
+def find_closest_model(step, allowed_steps):
+    step_chosen = 0
+    for _s in allowed_steps:
+        delta = step - _s
+        if ("mindelta" not in list(locals().keys())):
+            mindelta = abs(delta)
+            step_chosen = _s
+        elif (abs(delta) < mindelta):
+            mindelta = abs(delta)
+            step_chosen = _s
+    return step_chosen, mindelta
+
+
+def get_lsd(model, X_train, X, labels_train=None):
+    '''
+    Get latent space distance
+    inputs:
+        model: ANN model
+        X_train: np.array, training features
+        X: features for target point(s)
+        labels_train: np.array, names for training poinst (optional)
+    outputs:
+        dist_avrg: np.array, lsd for target points
+    '''
+    if labels_train is None:
+        labels_train = np.array([0 for _ in X_train])
+    ls_train = get_layer_outputs(model, layer_index=-3, input=X_train, training_flag=False)
+    ls = get_layer_outputs(model, layer_index=-3, input=X, training_flag=False)
+    _dist_avrg, _, _ = dist_neighbor(fmat1=ls_train, fmat2=ls_train, labels=labels_train, l=10, dist_ref=1)
+    avrg_ls_train = np.mean(_dist_avrg)
+    dist_avrg, _, _ = dist_neighbor(fmat1=ls, fmat2=ls_train, labels=labels_train, l=10, dist_ref=avrg_ls_train)
+    return dist_avrg

molSimplify/molscontrol/data/README.md

@@ -0,0 +1,21 @@
+# Sample Package Data
+
+This directory contains sample additional data you may want to include with your package.
+This is a place where non-code related additional information (such as data files, molecular structures,  etc.) can
+go that you want to ship alongside your code.
+
+Please note that it is not recommended to place large files in your git directory. If your project requires files larger
+than a few megabytes in size it is recommended to host these files elsewhere. This is especially true for binary files
+as the `git` structure is unable to correctly take updates to these files and will store a complete copy of every version
+in your `git` history which can quickly add up. As a note most `git` hosting services like GitHub have a 1 GB per repository
+cap.
+
+## Including package data
+
+Modify your package's `setup.py` file and the `setup()` command. Include the
+[`package_data`](http://setuptools.readthedocs.io/en/latest/setuptools.html#basic-use) keyword and point it at the
+correct files.
+
+## Manifest
+
+* `look_and_say.dat`: first entries of the "Look and Say" integer series, sequence [A005150](https://oeis.org/A005150)