Latest Threat Research:SANDWORM_MODE: Shai-Hulud-Style npm Worm Hijacks CI Workflows and Poisons AI Toolchains.Details →
Socket
Book a DemoInstallSign in
Socket
Book a DemoInstallSign in

selfies

Package Overview
Dependencies
Maintainers
1
Versions
16
Alerts
File Explorer

Advanced tools

License
Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

selfies - npm Package Compare versions

Comparing version
1.0.1
 to
1.0.2
+21
-22
PKG-INFO
Metadata-Version: 2.1
Name: selfies
Version: 1.0.1
Version: 1.0.2
Summary: SELFIES (SELF-referencIng Embedded Strings) is a general-purpose, sequence-based, robust representation of semantically constrained graphs.

@@ -39,5 +39,4 @@ Home-page: https://github.com/aspuru-guzik-group/selfies

To check if the correct version of ``selfies`` is installed
(see [CHANGELOG](https://github.com/aspuru-guzik-group/selfies/blob/master/CHANGELOG.md)
to verify the latest version), use the following pip command:
To check if the correct version of ``selfies`` is installed, use
the following pip command.

@@ -49,3 +48,5 @@ ```bash

To upgrade to the latest release of ``selfies`` if you are using an
older version, use the following pip command:
older version, use the following pip command. Please see the
[CHANGELOG](https://github.com/aspuru-guzik-group/selfies/blob/master/CHANGELOG.md)
to review the changes between versions of `selfies`:

@@ -66,3 +67,3 @@ ```bash

The ``selfies`` library has six standard functions:
The ``selfies`` library has eight standard functions:

@@ -77,2 +78,4 @@ | Function | Description |

| ``selfies.get_semantic_robust_alphabet`` | Returns a subset of all SELFIES symbols that are semantically constrained. |
| ``selfies.selfies_to_encoding`` | Converts a SELFIES into a label and/or one-hot encoding. |
| ``selfies.encoding_to_selfies`` | Converts a label or one-hot encoding into a SELFIES. |

@@ -104,6 +107,6 @@ Please read the documentation for more detailed descriptions of these

#### Integer encoding SELFIES:
#### Label (Integer) encoding SELFIES:
In this example we first build an alphabet
from a dataset of SELFIES, and then convert a SELFIES into a
padded, integer-encoded representation. Note that we use the
padded, label-encoded representation. Note that we use the
``'[nop]'`` ([no operation](https://en.wikipedia.org/wiki/NOP_(code) ))

@@ -126,14 +129,10 @@ symbol to pad our SELFIES, which is a special SELFIES symbol that is always

# SELFIES to integer encode
# SELFIES to label encode
dimethyl_ether = dataset[0] # '[C][O][C]'
# pad the SELFIES
dimethyl_ether += '[nop]' * (pad_to_len - sf.len_selfies(dimethyl_ether))
# integer encode the SELFIES
int_encoded = []
for symbol in sf.split_selfies(dimethyl_ether):
int_encoded.append(symbol_to_idx[symbol])
print(int_encoded) # [1, 3, 1, 4, 4]
# [1, 3, 1, 4, 4]
print(sf.selfies_to_encoding(dimethyl_ether,
vocab_stoi=symbol_to_idx,
pad_to_len=pad_to_len,
enc_type='label'))
```

@@ -163,3 +162,3 @@

* 130K molecules from [QM9](https://www.nature.com/articles/sdata201422)
* 250K molecules from [ZINC](https://en.wikipedia.org/wiki/ZINC_database),
* 250K molecules from [ZINC](https://en.wikipedia.org/wiki/ZINC_database)
* 50K molecules from [non-fullerene acceptors for organic solar cells](https://www.sciencedirect.com/science/article/pii/S2542435117301307)

@@ -189,5 +188,5 @@ * 8K molecules from [Tox21](http://moleculenet.ai/datasets-1) in MoleculeNet

We thank Kevin Ryan (LeanAndMean@github), Theophile Gaudin, Andrew Brereton,
Benjamin Sanchez-Lengeling, and Zhenpeng Yao for their suggestions and
bug reports.
We thank Jacques Boitreaud, Andrew Brereton, Matthew Carbone (x94carbone), Nathan Frey (ncfrey), Theophile Gaudin,
Hyunmin Kim (hmkim), Minjie Li, Vincent Mallet, Kevin Ryan (LeanAndMean), Benjamin Sanchez-Lengeling,
and Zhenpeng Yao for their suggestions and bug reports, and Robert Pollice for chemistry advices.

@@ -194,0 +193,0 @@ ## License

+20
-21
README.md

@@ -31,5 +31,4 @@ # SELFIES

To check if the correct version of ``selfies`` is installed
(see [CHANGELOG](https://github.com/aspuru-guzik-group/selfies/blob/master/CHANGELOG.md)
to verify the latest version), use the following pip command:
To check if the correct version of ``selfies`` is installed, use
the following pip command.

@@ -41,3 +40,5 @@ ```bash

To upgrade to the latest release of ``selfies`` if you are using an
older version, use the following pip command:
older version, use the following pip command. Please see the
[CHANGELOG](https://github.com/aspuru-guzik-group/selfies/blob/master/CHANGELOG.md)
to review the changes between versions of `selfies`:

@@ -58,3 +59,3 @@ ```bash

The ``selfies`` library has six standard functions:
The ``selfies`` library has eight standard functions:

@@ -69,2 +70,4 @@ | Function | Description |

| ``selfies.get_semantic_robust_alphabet`` | Returns a subset of all SELFIES symbols that are semantically constrained. |
| ``selfies.selfies_to_encoding`` | Converts a SELFIES into a label and/or one-hot encoding. |
| ``selfies.encoding_to_selfies`` | Converts a label or one-hot encoding into a SELFIES. |

@@ -96,6 +99,6 @@ Please read the documentation for more detailed descriptions of these

#### Integer encoding SELFIES:
#### Label (Integer) encoding SELFIES:
In this example we first build an alphabet
from a dataset of SELFIES, and then convert a SELFIES into a
padded, integer-encoded representation. Note that we use the
padded, label-encoded representation. Note that we use the
``'[nop]'`` ([no operation](https://en.wikipedia.org/wiki/NOP_(code) ))

@@ -118,14 +121,10 @@ symbol to pad our SELFIES, which is a special SELFIES symbol that is always

# SELFIES to integer encode
# SELFIES to label encode
dimethyl_ether = dataset[0] # '[C][O][C]'
# pad the SELFIES
dimethyl_ether += '[nop]' * (pad_to_len - sf.len_selfies(dimethyl_ether))
# integer encode the SELFIES
int_encoded = []
for symbol in sf.split_selfies(dimethyl_ether):
int_encoded.append(symbol_to_idx[symbol])
print(int_encoded) # [1, 3, 1, 4, 4]
# [1, 3, 1, 4, 4]
print(sf.selfies_to_encoding(dimethyl_ether,
vocab_stoi=symbol_to_idx,
pad_to_len=pad_to_len,
enc_type='label'))
```

@@ -155,3 +154,3 @@

* 130K molecules from [QM9](https://www.nature.com/articles/sdata201422)
* 250K molecules from [ZINC](https://en.wikipedia.org/wiki/ZINC_database),
* 250K molecules from [ZINC](https://en.wikipedia.org/wiki/ZINC_database)
* 50K molecules from [non-fullerene acceptors for organic solar cells](https://www.sciencedirect.com/science/article/pii/S2542435117301307)

@@ -181,5 +180,5 @@ * 8K molecules from [Tox21](http://moleculenet.ai/datasets-1) in MoleculeNet

We thank Kevin Ryan (LeanAndMean@github), Theophile Gaudin, Andrew Brereton,
Benjamin Sanchez-Lengeling, and Zhenpeng Yao for their suggestions and
bug reports.
We thank Jacques Boitreaud, Andrew Brereton, Matthew Carbone (x94carbone), Nathan Frey (ncfrey), Theophile Gaudin,
Hyunmin Kim (hmkim), Minjie Li, Vincent Mallet, Kevin Ryan (LeanAndMean), Benjamin Sanchez-Lengeling,
and Zhenpeng Yao for their suggestions and bug reports, and Robert Pollice for chemistry advices.

@@ -186,0 +185,0 @@ ## License

+21
-22
selfies.egg-info/PKG-INFO
Metadata-Version: 2.1
Name: selfies
Version: 1.0.1
Version: 1.0.2
Summary: SELFIES (SELF-referencIng Embedded Strings) is a general-purpose, sequence-based, robust representation of semantically constrained graphs.

@@ -39,5 +39,4 @@ Home-page: https://github.com/aspuru-guzik-group/selfies

To check if the correct version of ``selfies`` is installed
(see [CHANGELOG](https://github.com/aspuru-guzik-group/selfies/blob/master/CHANGELOG.md)
to verify the latest version), use the following pip command:
To check if the correct version of ``selfies`` is installed, use
the following pip command.

@@ -49,3 +48,5 @@ ```bash

To upgrade to the latest release of ``selfies`` if you are using an
older version, use the following pip command:
older version, use the following pip command. Please see the
[CHANGELOG](https://github.com/aspuru-guzik-group/selfies/blob/master/CHANGELOG.md)
to review the changes between versions of `selfies`:

@@ -66,3 +67,3 @@ ```bash

The ``selfies`` library has six standard functions:
The ``selfies`` library has eight standard functions:

@@ -77,2 +78,4 @@ | Function | Description |

| ``selfies.get_semantic_robust_alphabet`` | Returns a subset of all SELFIES symbols that are semantically constrained. |
| ``selfies.selfies_to_encoding`` | Converts a SELFIES into a label and/or one-hot encoding. |
| ``selfies.encoding_to_selfies`` | Converts a label or one-hot encoding into a SELFIES. |

@@ -104,6 +107,6 @@ Please read the documentation for more detailed descriptions of these

#### Integer encoding SELFIES:
#### Label (Integer) encoding SELFIES:
In this example we first build an alphabet
from a dataset of SELFIES, and then convert a SELFIES into a
padded, integer-encoded representation. Note that we use the
padded, label-encoded representation. Note that we use the
``'[nop]'`` ([no operation](https://en.wikipedia.org/wiki/NOP_(code) ))

@@ -126,14 +129,10 @@ symbol to pad our SELFIES, which is a special SELFIES symbol that is always

# SELFIES to integer encode
# SELFIES to label encode
dimethyl_ether = dataset[0] # '[C][O][C]'
# pad the SELFIES
dimethyl_ether += '[nop]' * (pad_to_len - sf.len_selfies(dimethyl_ether))
# integer encode the SELFIES
int_encoded = []
for symbol in sf.split_selfies(dimethyl_ether):
int_encoded.append(symbol_to_idx[symbol])
print(int_encoded) # [1, 3, 1, 4, 4]
# [1, 3, 1, 4, 4]
print(sf.selfies_to_encoding(dimethyl_ether,
vocab_stoi=symbol_to_idx,
pad_to_len=pad_to_len,
enc_type='label'))
```

@@ -163,3 +162,3 @@

* 130K molecules from [QM9](https://www.nature.com/articles/sdata201422)
* 250K molecules from [ZINC](https://en.wikipedia.org/wiki/ZINC_database),
* 250K molecules from [ZINC](https://en.wikipedia.org/wiki/ZINC_database)
* 50K molecules from [non-fullerene acceptors for organic solar cells](https://www.sciencedirect.com/science/article/pii/S2542435117301307)

@@ -189,5 +188,5 @@ * 8K molecules from [Tox21](http://moleculenet.ai/datasets-1) in MoleculeNet

We thank Kevin Ryan (LeanAndMean@github), Theophile Gaudin, Andrew Brereton,
Benjamin Sanchez-Lengeling, and Zhenpeng Yao for their suggestions and
bug reports.
We thank Jacques Boitreaud, Andrew Brereton, Matthew Carbone (x94carbone), Nathan Frey (ncfrey), Theophile Gaudin,
Hyunmin Kim (hmkim), Minjie Li, Vincent Mallet, Kevin Ryan (LeanAndMean), Benjamin Sanchez-Lengeling,
and Zhenpeng Yao for their suggestions and bug reports, and Robert Pollice for chemistry advices.

@@ -194,0 +193,0 @@ ## License

+28
-7
selfies/__init__.py

@@ -30,11 +30,32 @@ #!/usr/bin/env python

__all__ = ['encoder', 'decoder',
'get_semantic_robust_alphabet', 'get_semantic_constraints',
'set_semantic_constraints',
'len_selfies', 'split_selfies', 'get_alphabet_from_selfies']
__all__ = [
"encoder",
"decoder",
"get_semantic_robust_alphabet",
"get_semantic_constraints",
"set_semantic_constraints",
"len_selfies",
"split_selfies",
"get_alphabet_from_selfies",
"selfies_to_encoding",
"batch_selfies_to_flat_hot",
"encoding_to_selfies",
"batch_flat_hot_to_selfies",
]
from .decoder import decoder
from .encoder import encoder
from .grammar_rules import get_semantic_robust_alphabet, \
get_semantic_constraints, set_semantic_constraints
from .utils import get_alphabet_from_selfies, len_selfies, split_selfies
from .grammar_rules import (
get_semantic_robust_alphabet,
get_semantic_constraints,
set_semantic_constraints,
)
from .utils import (
get_alphabet_from_selfies,
len_selfies,
split_selfies,
selfies_to_encoding,
batch_selfies_to_flat_hot,
encoding_to_selfies,
batch_flat_hot_to_selfies,
)
+7
-2
selfies/decoder.py

@@ -19,4 +19,4 @@ from collections import OrderedDict

:param selfies: The SELFIES to be translated.
:param print_error: If True, error messages will be printed to console.
:param selfies: the SELFIES to be translated.
:param print_error: if True, error messages will be printed to console.
Defaults to False.

@@ -66,2 +66,7 @@ :return: the SMILES translation of ``selfies``. If an error occurs,

right_idx = selfies.find(']', left_idx + 1)
if (selfies[left_idx] != '[') or (right_idx == -1):
raise ValueError("malformed SELIFES, "
"misplaced or missing brackets")
next_symbol = selfies[left_idx: right_idx + 1]

@@ -68,0 +73,0 @@ left_idx = right_idx + 1

+5
-2
selfies/encoder.py

@@ -35,4 +35,4 @@ from typing import Dict, Iterable, List, Optional, Tuple

:param smiles: The SMILES to be translated.
:param print_error: If True, error messages will be printed to console.
:param smiles: the SMILES to be translated.
:param print_error: if True, error messages will be printed to console.
Defaults to False.

@@ -130,2 +130,5 @@ :return: the SELFIES translation of ``smiles``. If an error occurs,

if r_idx == -1:
raise ValueError("malformed SMILES, missing ']'")
# quick chirality specification check

@@ -132,0 +135,0 @@ chiral_i = symbol.find('@')

+7
-7
selfies/grammar_rules.py

@@ -6,7 +6,7 @@ from itertools import product

'H': 1, 'F': 1, 'Cl': 1, 'Br': 1, 'I': 1,
'O': 2,
'N': 3,
'C': 4,
'P': 5,
'S': 6,
'O': 2, 'O+1': 3, 'O-1': 1,
'N': 3, 'N+1': 4, 'N-1': 2,
'C': 4, 'C+1': 5, 'C-1': 3,
'S': 6, 'S+1': 7, 'S-1': 5,
'P': 7, 'P+1': 8, 'P-1': 6,
'?': 8,

@@ -67,3 +67,3 @@ }

:return: The bond constraints :mod:`selfies` is currently operating on.
:return: the bond constraints :mod:`selfies` is currently operating on.
"""

@@ -166,3 +166,3 @@

if h_count >= max_bonds:
if (h_count > max_bonds) or (h_count == max_bonds and state > 0):
raise ValueError("too many Hs in symbol '{}'; consider "

@@ -169,0 +169,0 @@ "adjusting bond constraints".format(symbol))

+6
-2
selfies/kekulize.py

@@ -130,3 +130,3 @@ from typing import Dict, Iterable, List, Set, Tuple, Union

'b': 3, 'c': 4, 'n': 5, 'p': 5, 'as': 5,
'o': 6, 's': 6, 'se': 6
'o': 6, 's': 6, 'se': 6, 'te': 6
}

@@ -197,3 +197,7 @@

# e.g. c1ccccc1
if (atom == 'c') and (h_count == charge == 0) and (len(bonds) == 2):
# this also covers the neutral carbon radical case (e.g. C1=[C]NC=C1),
# which is treated equivalently to a 1-H carbon (e.g. C1=[CH]NC=C1)
if (atom == 'c') and (h_count == charge == 0) \
and (len(bonds) == 2) and ('#' not in bonds):
h_count += 1 # implied bonded hydrogen

@@ -200,0 +204,0 @@ 

+213
-13
selfies/utils.py

@@ -1,2 +0,2 @@

from typing import Iterable, Set
from typing import Dict, Iterable, List, Set, Tuple, Union

@@ -10,4 +10,4 @@

:param selfies: A SELFIES.
:return: The symbol length of ``selfies``.
:param selfies: a SELFIES.
:return: the symbol length of ``selfies``.

@@ -23,3 +23,3 @@ :Example:

return selfies.count('[') + selfies.count('.')
return selfies.count("[") + selfies.count(".")

@@ -35,4 +35,4 @@

:param selfies: The SELFIES to be read.
:return: An iterable of the symbols of ``selfies`` in the same order
:param selfies: the SELFIES to be read.
:return: an iterable of the symbols of ``selfies`` in the same order
they appear in the string.

@@ -49,6 +49,6 @@

left_idx = selfies.find('[')
left_idx = selfies.find("[")
while 0 <= left_idx < len(selfies):
right_idx = selfies.find(']', left_idx + 1)
right_idx = selfies.find("]", left_idx + 1)
next_symbol = selfies[left_idx: right_idx + 1]

@@ -58,4 +58,4 @@ yield next_symbol

left_idx = right_idx + 1
if selfies[left_idx: left_idx + 1] == '.':
yield '.'
if selfies[left_idx: left_idx + 1] == ".":
yield "."
left_idx += 1

@@ -73,4 +73,4 @@

:param selfies_iter: An iterable of SELFIES.
:return: The SElFIES alphabet built from the SELFIES in ``selfies_iter``.
:param selfies_iter: an iterable of SELFIES.
:return: the SElFIES alphabet built from the SELFIES in ``selfies_iter``.

@@ -92,4 +92,204 @@ :Example:

alphabet.discard('.')
alphabet.discard(".")
return alphabet
def selfies_to_encoding(
selfies: str,
vocab_stoi: Dict[str, int],
pad_to_len: int = -1,
enc_type: str = 'both'
) -> Union[List[int], List[List[int]], Tuple[List[int], List[List[int]]]]:
"""Converts a SELFIES into its label (integer) and/or one-hot encoding.
A label encoded output will be a list of size ``(N,)`` and a
one-hot encoded output will be a list of size ``(N, len(vocab_stoi))``;
where ``N`` is the symbol length of the (potentially padded) SELFIES.
Note that SELFIES uses the special padding symbol ``[nop]``.
:param selfies: the SELFIES to be encoded.
:param vocab_stoi: a dictionary that maps SELFIES symbols (the keys)
to a non-negative index. The indices of the dictionary
must contiguous, starting from 0.
:param pad_to_len: the length the SELFIES is be padded to.
If ``pad_to_len`` is less than or equal to the symbol
length of the SELFIES, then no padding is added. Defaults to ``-1``.
:param enc_type: the type of encoding of the output:
``label`` or ``one_hot`` or ``both``.
If the value is ``both``, then a tuple of the label and one-hot
encoding are returned (in that order). Defaults to ``both``.
:return: the label encoded and/or one-hot encoded SELFIES.
:Example:
>>> import selfies as sf
>>> sf.selfies_to_encoding('[C][F]', {'[C]': 0, '[F]': 1})
([0, 1], [[1, 0], [0, 1]])
"""
# some error checking
if enc_type not in ('label', 'one_hot', 'both'):
raise ValueError("enc_type must be in ('label', 'one_hot', 'both')")
# pad with [nop]
if pad_to_len > len_selfies(selfies):
selfies += "[nop]" * (pad_to_len - len_selfies(selfies))
# integer encode
char_list = split_selfies(selfies)
integer_encoded = [vocab_stoi[char] for char in char_list]
if enc_type == 'label':
return integer_encoded
# one-hot encode
onehot_encoded = list()
for index in integer_encoded:
letter = [0] * len(vocab_stoi)
letter[index] = 1
onehot_encoded.append(letter)
if enc_type == 'one_hot':
return onehot_encoded
return integer_encoded, onehot_encoded
def encoding_to_selfies(
encoded: Union[List[int], List[List[int]]],
vocab_itos: Dict[int, str],
enc_type: str,
) -> str:
"""Converts a label (integer) or one-hot encoded list into
a SELFIES string.
If the input is label encoded, then a list of size ``(N,)`` is
expected; and if the input is one-hot encoded, then a 2D list of
size ``(N, len(vocab_itos))`` is expected.
:param encoded: a label or one-hot encoded list.
:param vocab_itos: a dictionary that maps non-negative indices (the keys)
to SELFIES symbols. The indices of the dictionary
must be contiguous, starting from 0.
:param enc_type: the type of encoding of the output:
``label`` or ``one_hot``.
:return: the SELFIES string represented by the encoded input.
:Example:
>>> import selfies as sf
>>> one_hot = [[0, 1, 0], [0, 0, 1], [1, 0, 0]]
>>> vocab_itos = {0: '[nop]', 1: '[C]', 2: '[F]'}
>>> sf.encoding_to_selfies(one_hot, vocab_itos, enc_type='one_hot')
'[C][F][nop]'
"""
if enc_type not in ('label', 'one_hot'):
raise ValueError("enc_type must be in ('label', 'one_hot')")
if enc_type == 'one_hot': # Get integer encoding
integer_encoded = []
for row in encoded:
integer_encoded.append(row.index(1))
else:
integer_encoded = encoded
# Integer encoding -> SELFIES
char_list = [vocab_itos[i] for i in integer_encoded]
selfies = "".join(char_list)
return selfies
def batch_selfies_to_flat_hot(
selfies_batch: List[str],
vocab_stoi: Dict[str, int],
pad_to_len: int = -1,
) -> List[List[int]]:
"""Converts a list of SELFIES into a list of
flattened one-hot encodings.
Returned is a list of size ``(batch_size, N * len(vocab_stoi))``;
where ``N`` is the symbol length of the (potentially padded) SELFIES.
Note that SELFIES uses the special padding symbol ``[nop]``.
:param selfies_batch: a list of SELFIES to be converted.
:param vocab_stoi: a dictionary that maps SELFIES symbols (the keys)
to a non-negative index. The indices of the dictionary
must contiguous, starting from 0.
:param pad_to_len: the length that each SELFIES is be padded to.
If ``pad_to_len`` is less than or equal to the symbol
length of the SELFIES, then no padding is added. Defaults to ``-1``.
:return: the flattened one-hot encoded representations of the SELFIES
from the batch. This is a 2D list of size
``(batch_size, N * len(vocab_stoi))``.
:Example:
>>> import selfies as sf
>>> batch = ["[C]", "[C][C]"]
>>> vocab_stoi = {'[nop]': 0, '[C]': 1}
>>> sf.batch_selfies_to_flat_hot(batch, vocab_stoi, 2)
[[0, 1, 1, 0], [0, 1, 0, 1]]
"""
hot_list = list()
for selfies in selfies_batch:
one_hot = selfies_to_encoding(selfies, vocab_stoi, pad_to_len,
enc_type='one_hot')
flattened = [elem for vec in one_hot for elem in vec]
hot_list.append(flattened)
return hot_list
def batch_flat_hot_to_selfies(
one_hot_batch: List[List[int]],
vocab_itos: Dict[int, str],
) -> List[str]:
"""Convert a batch of flattened one-hot encodings into
a list of SELFIES.
We expect ``one_hot_batch`` to be a list of size ``(batch_size, S)``,
where ``S`` is divisible by the length of the vocabulary.
:param one_hot_batch: a list of flattened one-hot encoded representations.
:param vocab_itos: a dictionary that maps non-negative indices (the keys)
to SELFIES symbols. We expect the indices of the dictionary
to be contiguous and starting from 0.
:return: a list of SELFIES strings.
:Example:
>>> import selfies as sf
>>> batch = [[0, 1, 1, 0], [0, 1, 0, 1]]
>>> vocab_itos = {0: '[nop]', 1: '[C]'}
>>> sf.batch_flat_hot_to_selfies(batch, vocab_itos)
['[C][nop]', '[C][C]']
"""
selfies_list = []
for flat_one_hot in one_hot_batch:
# Reshape to an N x M array where each column represents an alphabet
# entry and each row is a position in the selfies
one_hot = []
M = len(vocab_itos)
if len(flat_one_hot) % M != 0:
raise ValueError("size of vector in one_hot_batch not divisible "
"by the length of the vocabulary.")
N = len(flat_one_hot) // M
for i in range(N):
one_hot.append(flat_one_hot[M * i: M * (i + 1)])
selfies = encoding_to_selfies(one_hot, vocab_itos, enc_type='one_hot')
selfies_list.append(selfies)
return selfies_list
+0
-0
setup.cfg

@@ -0,0 +0,0 @@ [egg_info]

+1
-1
setup.py

@@ -10,3 +10,3 @@ #!/usr/bin/env python

name="selfies",
version="1.0.1",
version="1.0.2",
author="Mario Krenn",

@@ -13,0 +13,0 @@ author_email="mario.krenn@utoronto.ca, alan@aspuru.com",