From e94c61e224f8cd4b66a870a9d9d03c0ed810d656 Mon Sep 17 00:00:00 2001
From: David Luevano Alvarado <55825613+luevano@users.noreply.github.com>
Date: Wed, 11 Mar 2020 10:52:02 -0700
Subject: Refactor db reading
---
ml_exp/__init__.py | 3 +-
ml_exp/krr.py | 2 +-
ml_exp/qm7db.py | 76 -------------------------------------
ml_exp/qm9db.py | 62 -------------------------------
ml_exp/readdb.py | 107 +++++++++++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 110 insertions(+), 140 deletions(-)
delete mode 100644 ml_exp/qm7db.py
delete mode 100644 ml_exp/qm9db.py
create mode 100644 ml_exp/readdb.py
diff --git a/ml_exp/__init__.py b/ml_exp/__init__.py
index 02819d6a1..b40957baf 100644
--- a/ml_exp/__init__.py
+++ b/ml_exp/__init__.py
@@ -23,7 +23,7 @@ SOFTWARE.
from ml_exp.compound import Compound
from ml_exp.representations import coulomb_matrix, lennard_jones_matrix,\
get_helping_data, adjacency_matrix, epsilon_index, check_bond, bag_of_bonds
-from ml_exp.qm7db import qm7db
+from ml_exp.readdb import qm7db, qm9db
from ml_exp.data import NUCLEAR_CHARGE, POSSIBLE_BONDS
from ml_exp.kernels import laplauss_kernel
from ml_exp.krr import krr, multi_krr
@@ -37,6 +37,7 @@ __all__ = ['Compound',
'check_bond',
'bag_of_bonds',
'qm7db',
+ 'qm9db',
'laplauss_kernel',
'krr',
'multi_krr',
diff --git a/ml_exp/krr.py b/ml_exp/krr.py
index dca1e14e6..a77bfdaf8 100644
--- a/ml_exp/krr.py
+++ b/ml_exp/krr.py
@@ -31,7 +31,7 @@ except ImportError:
TF_AV = False
from ml_exp.misc import printc
from ml_exp.kernels import laplauss_kernel
-from ml_exp.qm7db import qm7db
+from ml_exp.readdb import qm7db
def krr(descriptors,
diff --git a/ml_exp/qm7db.py b/ml_exp/qm7db.py
deleted file mode 100644
index 1e78b8d56..000000000
--- a/ml_exp/qm7db.py
+++ /dev/null
@@ -1,76 +0,0 @@
-"""MIT License
-
-Copyright (c) 2019 David Luevano Alvarado
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
-"""
-from ml_exp.compound import Compound
-import numpy as np
-try:
- import tensorflow as tf
- TF_AV = True
-except ImportError:
- print('Tensorflow couldn\'t be imported. Maybe it is not installed.')
- TF_AV = False
-import random
-
-
-def qm7db(db_path='data',
- is_shuffled=True,
- r_seed=111,
- use_tf=True):
- """
- Creates a list of compounds with the qm7 database.
- db_path: path to the database directory.
- is_shuffled: if the resulting list of compounds should be shuffled.
- r_seed: random seed to use for the shuffling.
- use_tf: if tensorflow should be used.
- """
- # If tf is to be used but couldn't be imported, don't try to use it.
- if use_tf and not TF_AV:
- use_tf = False
-
- fname = f'{db_path}/hof_qm7.txt'
- with open(fname, 'r') as f:
- lines = f.readlines()
-
- compounds = []
- for i, line in enumerate(lines):
- line = line.split()
- compounds.append(Compound(f'{db_path}/{line[0]}', db='qm7'))
- compounds[i].qm7pbe0 = np.float64(line[1])
- compounds[i].qm7delta = np.float64(line[1]) - np.float64(line[2])
-
- if is_shuffled:
- random.seed(r_seed)
- random.shuffle(compounds)
-
- e_pbe0 = np.array([comp.qm7pbe0 for comp in compounds], dtype=np.float64)
- e_delta = np.array([comp.qm7delta for comp in compounds], dtype=np.float64)
-
- if use_tf:
- # Check if there's a gpu available and use the first one.
- if tf.config.experimental.list_physical_devices('GPU'):
- with tf.device('GPU:0'):
- e_pbe0 = tf.convert_to_tensor(e_pbe0)
- e_delta = tf.convert_to_tensor(e_delta)
- else:
- raise TypeError('No GPU found, could not create Tensor objects.')
-
- return compounds, e_pbe0, e_delta
diff --git a/ml_exp/qm9db.py b/ml_exp/qm9db.py
deleted file mode 100644
index 8354075bc..000000000
--- a/ml_exp/qm9db.py
+++ /dev/null
@@ -1,62 +0,0 @@
-"""MIT License
-
-Copyright (c) 2019 David Luevano Alvarado
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
-"""
-from ml_exp.compound import Compound
-import numpy as np
-try:
- import tensorflow as tf
- TF_AV = True
-except ImportError:
- print('Tensorflow couldn\'t be imported. Maybe it is not installed.')
- TF_AV = False
-import random
-
-
-def qm9db(db_path='data',
- is_shuffled=True,
- r_seed=111,
- use_tf=True):
- """
- Creates a list of compounds with the qm9 database.
- db_path: path to the database directory.
- is_shuffled: if the resulting list of compounds should be shuffled.
- r_seed: random seed to use for the shuffling.
- use_tf: if tensorflow should be used.
- """
- # If tf is to be used but couldn't be imported, don't try to use it.
- if use_tf and not TF_AV:
- use_tf = False
-
- fname = f'{db_path}/xyz_qm9.txt'
- with open(fname, 'r') as f:
- lines = f.readlines()
-
- compounds = []
- for i, line in enumerate(lines):
- line = line.strip()
- compounds.append(Compound(f'{db_path}/{line}', db='qm9'))
-
- if is_shuffled:
- random.seed(r_seed)
- random.shuffle(compounds)
-
- return compounds
diff --git a/ml_exp/readdb.py b/ml_exp/readdb.py
new file mode 100644
index 000000000..e6fbc7224
--- /dev/null
+++ b/ml_exp/readdb.py
@@ -0,0 +1,107 @@
+"""MIT License
+
+Copyright (c) 2019 David Luevano Alvarado
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+"""
+from ml_exp.compound import Compound
+import numpy as np
+try:
+ import tensorflow as tf
+ TF_AV = True
+except ImportError:
+ print('Tensorflow couldn\'t be imported. Maybe it is not installed.')
+ TF_AV = False
+import random
+
+
+def qm7db(db_path='data',
+ is_shuffled=True,
+ r_seed=111,
+ use_tf=True):
+ """
+ Creates a list of compounds with the qm7 database.
+ db_path: path to the database directory.
+ is_shuffled: if the resulting list of compounds should be shuffled.
+ r_seed: random seed to use for the shuffling.
+ use_tf: if tensorflow should be used.
+ """
+ # If tf is to be used but couldn't be imported, don't try to use it.
+ if use_tf and not TF_AV:
+ use_tf = False
+
+ fname = f'{db_path}/hof_qm7.txt'
+ with open(fname, 'r') as f:
+ lines = f.readlines()
+
+ compounds = []
+ for i, line in enumerate(lines):
+ line = line.split()
+ compounds.append(Compound(f'{db_path}/{line[0]}', db='qm7'))
+ compounds[i].qm7pbe0 = np.float64(line[1])
+ compounds[i].qm7delta = np.float64(line[1]) - np.float64(line[2])
+
+ if is_shuffled:
+ random.seed(r_seed)
+ random.shuffle(compounds)
+
+ e_pbe0 = np.array([comp.qm7pbe0 for comp in compounds], dtype=np.float64)
+ e_delta = np.array([comp.qm7delta for comp in compounds], dtype=np.float64)
+
+ if use_tf:
+ # Check if there's a gpu available and use the first one.
+ if tf.config.experimental.list_physical_devices('GPU'):
+ with tf.device('GPU:0'):
+ e_pbe0 = tf.convert_to_tensor(e_pbe0)
+ e_delta = tf.convert_to_tensor(e_delta)
+ else:
+ raise TypeError('No GPU found, could not create Tensor objects.')
+
+ return compounds, e_pbe0, e_delta
+
+
+def qm9db(db_path='data',
+ is_shuffled=True,
+ r_seed=111,
+ use_tf=True):
+ """
+ Creates a list of compounds with the qm9 database.
+ db_path: path to the database directory.
+ is_shuffled: if the resulting list of compounds should be shuffled.
+ r_seed: random seed to use for the shuffling.
+ use_tf: if tensorflow should be used.
+ """
+ # If tf is to be used but couldn't be imported, don't try to use it.
+ if use_tf and not TF_AV:
+ use_tf = False
+
+ fname = f'{db_path}/xyz_qm9.txt'
+ with open(fname, 'r') as f:
+ lines = f.readlines()
+
+ compounds = []
+ for i, line in enumerate(lines):
+ line = line.strip()
+ compounds.append(Compound(f'{db_path}/{line}', db='qm9'))
+
+ if is_shuffled:
+ random.seed(r_seed)
+ random.shuffle(compounds)
+
+ return compounds
--
cgit v1.2.3-70-g09d2