phyddle 0.2.2__tar.gz → 0.3.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {phyddle-0.2.2 → phyddle-0.3.0}/.bumpversion.cfg +1 -1
- {phyddle-0.2.2 → phyddle-0.3.0}/.github/workflows/documentation.yml +1 -1
- {phyddle-0.2.2 → phyddle-0.3.0}/.github/workflows/tests.yml +1 -1
- {phyddle-0.2.2 → phyddle-0.3.0}/.gitignore +3 -0
- {phyddle-0.2.2 → phyddle-0.3.0}/LICENSE +1 -1
- {phyddle-0.2.2 → phyddle-0.3.0}/PKG-INFO +18 -19
- {phyddle-0.2.2 → phyddle-0.3.0}/README.md +1 -1
- phyddle-0.3.0/UPDATES.md +179 -0
- {phyddle-0.2.2 → phyddle-0.3.0}/pyproject.toml +16 -17
- {phyddle-0.2.2 → phyddle-0.3.0}/src/phyddle/__init__.py +4 -4
- {phyddle-0.2.2 → phyddle-0.3.0}/src/phyddle/command_line.py +3 -3
- {phyddle-0.2.2 → phyddle-0.3.0}/src/phyddle/estimate.py +76 -5
- {phyddle-0.2.2 → phyddle-0.3.0}/src/phyddle/format.py +215 -161
- {phyddle-0.2.2 → phyddle-0.3.0}/src/phyddle/network.py +26 -12
- {phyddle-0.2.2 → phyddle-0.3.0}/src/phyddle/plot.py +629 -514
- {phyddle-0.2.2 → phyddle-0.3.0}/src/phyddle/simulate.py +19 -9
- {phyddle-0.2.2 → phyddle-0.3.0}/src/phyddle/train.py +54 -19
- {phyddle-0.2.2 → phyddle-0.3.0}/src/phyddle/utilities.py +247 -37
- {phyddle-0.2.2 → phyddle-0.3.0}/CNAME +0 -0
- {phyddle-0.2.2 → phyddle-0.3.0}/DEVGUIDE.md +0 -0
- {phyddle-0.2.2 → phyddle-0.3.0}/src/phyddle/__main__.py +0 -0
|
@@ -10,7 +10,7 @@ jobs:
|
|
|
10
10
|
- uses: actions/setup-python@v3
|
|
11
11
|
- name: Install dependencies
|
|
12
12
|
run: |
|
|
13
|
-
pip install sphinx sphinx_rtd_theme sphinxemoji sphinxcontrib-googleanalytics
|
|
13
|
+
pip install sphinx sphinx_rtd_theme sphinxemoji sphinxcontrib-googleanalytics sphinx_subfigure
|
|
14
14
|
- name: Sphinx build
|
|
15
15
|
run: |
|
|
16
16
|
sphinx-build docs/source _build
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# Released under MIT License
|
|
2
2
|
|
|
3
|
-
Copyright (c)
|
|
3
|
+
Copyright (c) 2025 Michael Landis, Ammon Thompson
|
|
4
4
|
|
|
5
5
|
Permission is hereby granted, free of charge, to any person obtaining a copy of
|
|
6
6
|
this software and associated documentation files (phyddle; the “Software”), to deal in
|
|
@@ -1,7 +1,7 @@
|
|
|
1
|
-
Metadata-Version: 2.
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
2
|
Name: phyddle
|
|
3
|
-
Version: 0.
|
|
4
|
-
Summary: Software
|
|
3
|
+
Version: 0.3.0
|
|
4
|
+
Summary: Software for phylogenetic model exploration with deep learning
|
|
5
5
|
Project-URL: Homepage, https://github.com/mlandis/phyddle
|
|
6
6
|
Project-URL: Bug Reports, https://github.com/mlandis/phyddle/issues
|
|
7
7
|
Project-URL: Documentation, https://mlandis.github.io/phyddle
|
|
@@ -17,24 +17,23 @@ Classifier: Programming Language :: Python :: 3
|
|
|
17
17
|
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
18
18
|
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
|
|
19
19
|
Classifier: Topic :: Scientific/Engineering :: Mathematics
|
|
20
|
-
Requires-Python: >=3.
|
|
21
|
-
Requires-Dist: dendropy
|
|
22
|
-
Requires-Dist: graphviz
|
|
23
|
-
Requires-Dist: h5py
|
|
24
|
-
Requires-Dist:
|
|
25
|
-
Requires-Dist:
|
|
26
|
-
Requires-Dist:
|
|
27
|
-
Requires-Dist:
|
|
28
|
-
Requires-Dist:
|
|
29
|
-
Requires-Dist:
|
|
30
|
-
Requires-Dist:
|
|
31
|
-
Requires-Dist:
|
|
32
|
-
Requires-Dist:
|
|
33
|
-
Requires-Dist:
|
|
34
|
-
Requires-Dist: tqdm
|
|
20
|
+
Requires-Python: >=3.12
|
|
21
|
+
Requires-Dist: dendropy>=4.6.0
|
|
22
|
+
Requires-Dist: graphviz>=0.20.0
|
|
23
|
+
Requires-Dist: h5py>=3.10.0
|
|
24
|
+
Requires-Dist: matplotlib>=3.8.2
|
|
25
|
+
Requires-Dist: numpy>=1.26.4
|
|
26
|
+
Requires-Dist: pandas>=2.2.0
|
|
27
|
+
Requires-Dist: pydot>=2.0.0
|
|
28
|
+
Requires-Dist: pypdf>=4.0.0
|
|
29
|
+
Requires-Dist: scikit-learn>=1.4.0
|
|
30
|
+
Requires-Dist: scipy>=1.14.0
|
|
31
|
+
Requires-Dist: torch>=2.2.0
|
|
32
|
+
Requires-Dist: torchview>=0.2.6
|
|
33
|
+
Requires-Dist: tqdm>=4.66.1
|
|
35
34
|
Description-Content-Type: text/markdown
|
|
36
35
|
|
|
37
|
-
# phyddle 0.
|
|
36
|
+
# phyddle 0.3.0
|
|
38
37
|
|
|
39
38
|
Phylogenetic model exploration with deep learning.
|
|
40
39
|
|
phyddle-0.3.0/UPDATES.md
ADDED
|
@@ -0,0 +1,179 @@
|
|
|
1
|
+
**phyddle v0.3.0** -- 25.02.xx
|
|
2
|
+
|
|
3
|
+
* Includes new safety features, settings, bug fixes, and documentation
|
|
4
|
+
* Estimate now warns user if empirical input/labels are out-of-distribution
|
|
5
|
+
* Estimate/Format no longer require labels file for empirical analyses unless param_data used
|
|
6
|
+
* Plot improved to make it easier to notice out-of-distribution empirical input/labels
|
|
7
|
+
* Plot now makes PCA of encoded trees to help with out-of-distribution detection
|
|
8
|
+
* Replace mean APE scores for training diagnostics with median APE scores
|
|
9
|
+
* Support to choose optimizer: adam, adamw, adagrad, adadelta, rmsprop, sgd
|
|
10
|
+
* Support to choose activation functions: relu, elu, leaky_relu, tanh, sigmoid
|
|
11
|
+
* Support to set learning rate
|
|
12
|
+
* Fix issue where Format reported divide-by-zero warning for summ. stat. with perfectly balanced trees
|
|
13
|
+
* Fix issue where large serial trees were not correctly converted to downsampled extant-only trees
|
|
14
|
+
* Add settings/warnings to prevent nearly-zero-aged tips in extant-only from being treated as extinct
|
|
15
|
+
* Add torchvision to dependency list
|
|
16
|
+
* Replace deprecated PdfMerger with PdfWriter
|
|
17
|
+
* Support to use 2+ GPUs
|
|
18
|
+
* Reorganize documentation
|
|
19
|
+
* Documentation now has Overview -> Safe Usage section
|
|
20
|
+
* Documentation tutorial now contains better explanations of figures
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
**phyddle v0.2.2** -- 24.07.19
|
|
24
|
+
|
|
25
|
+
* Reduce pypi package size from 100MB to 75kB.
|
|
26
|
+
* Fix bug that caused lower CPI bound to be slightly misestimated.
|
|
27
|
+
* Improve scatter/coverage and training history plots.
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
**phyddle v0.2.1** -- 24.07.11
|
|
31
|
+
|
|
32
|
+
* New support to save, load, and clean projects. Nice for collaborations! |:handshake:|
|
|
33
|
+
* Improve detection of replicate indexing in Simulate/Format.
|
|
34
|
+
* Better warnings/errors for invalid settings.
|
|
35
|
+
* Remove logit transformation from summary statistics for state frequencies (caused crash in some cases).
|
|
36
|
+
|
|
37
|
+
|
|
38
|
+
**phyddle v0.2.0** -- 24.03.28
|
|
39
|
+
|
|
40
|
+
* New support for categorical labels (e.g. model testing).
|
|
41
|
+
* New plots for categorical results.
|
|
42
|
+
* Add support for GPU + CUDA + PyTorch to accelerate Train and Estimate.
|
|
43
|
+
* Support for early stopping rule with Train.
|
|
44
|
+
* Improved printed feedback for all steps.
|
|
45
|
+
* Better plots for PCA and scatter plot results.
|
|
46
|
+
* Simpler default directory structure. Default phyddle configs, scripts, and outputs now share a proj directory in ./workspace.
|
|
47
|
+
* Better support for multiple project names within a workspace directory.
|
|
48
|
+
* Rewrote how Format/Estimate/Plot interact so simulated-test/empirical datasets are treated similarly.
|
|
49
|
+
* Better error checking and helpful messages for Simulate-Format config mismatches.
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
**phyddle v0.1.1** -- 24.02.18
|
|
53
|
+
|
|
54
|
+
* Simpler directory settings for analyses
|
|
55
|
+
* Simpler settings application hierarchy
|
|
56
|
+
* Removed workspace and proj arguments
|
|
57
|
+
* Removed requirement for __config_default.py
|
|
58
|
+
* Repo directory restructuring, with clearer distinction between scripts and configs
|
|
59
|
+
* Added example simulation script for PhyloJunction
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
**phyddle v0.1.0** -- 24.02.08
|
|
63
|
+
|
|
64
|
+
* Update minor version from v0.0.10 to v0.1.0 |:partying_face:|
|
|
65
|
+
* Convert from Tensorflow to PyTorch on backend
|
|
66
|
+
* New support for scalable network architecture in Train
|
|
67
|
+
* New support for output precision for floating point output to files
|
|
68
|
+
* New summary csv report for Plot
|
|
69
|
+
* Better screen output for Train progress
|
|
70
|
+
* Better training history plot
|
|
71
|
+
* Better network architecture plot
|
|
72
|
+
* Better handling of cases where small tree size causes tree statistics to return 0/undefined/etc.
|
|
73
|
+
* Fix bug with non-sequential indices among simulated training examples
|
|
74
|
+
* Fix bug with Format for-loop to process summary statistics
|
|
75
|
+
* Switch summary statistics to log-scale
|
|
76
|
+
|
|
77
|
+
|
|
78
|
+
**phyddle v0.0.10** -- 23.11.10
|
|
79
|
+
|
|
80
|
+
* Basic GitHub Action tests working
|
|
81
|
+
* Format step faster (removed extraneous and costly deepcopy calls)
|
|
82
|
+
* Convert config_R.py to BiSSE example using R + castor
|
|
83
|
+
* Add external validation for phyddle vs. castor
|
|
84
|
+
* Improve config support
|
|
85
|
+
* Cleaning and commenting code
|
|
86
|
+
* Clean and finish sphinx documentation
|
|
87
|
+
|
|
88
|
+
|
|
89
|
+
**phyddle v0.0.9** -- 23.08.23
|
|
90
|
+
|
|
91
|
+
* Package now hosted through conda: https://anaconda.org/landismj/phyddle
|
|
92
|
+
* Better errors for missing files (configs, command, scripts, etc.)
|
|
93
|
+
* PyPI package installed through pip now autoinstalls dependencies
|
|
94
|
+
|
|
95
|
+
|
|
96
|
+
**phyddle v0.0.8** -- 23.08.16
|
|
97
|
+
|
|
98
|
+
* Minor fixes following 0.0.7 update
|
|
99
|
+
* Documentation visuals fixed
|
|
100
|
+
|
|
101
|
+
|
|
102
|
+
**phyddle v0.0.7** -- 23.08.16
|
|
103
|
+
|
|
104
|
+
* Format now splits training from test datasets.
|
|
105
|
+
* Estimate now applies trained model against test dataset.
|
|
106
|
+
* Steps now initialize using settings look-up table.
|
|
107
|
+
* Add PCA contour plot.
|
|
108
|
+
* Simplify filenames within projects for many steps.
|
|
109
|
+
* Timestamp step start/end/duration.
|
|
110
|
+
* Docs now hosted online at http://mlandis.github.io/phyddle
|
|
111
|
+
* Python package now hosted through pip at https://pypi.org/project/phyddle/
|
|
112
|
+
* Add bump2version supports
|
|
113
|
+
|
|
114
|
+
|
|
115
|
+
**phyddle v0.0.6** -- 23.08.09
|
|
116
|
+
|
|
117
|
+
* Refreshed documentation, plus added setting tables and glossary.
|
|
118
|
+
* Centralize management of settings.
|
|
119
|
+
* Settings now automatically apply default config, then user config, then command line arguments.
|
|
120
|
+
* Format only enodes for a single tree width category now.
|
|
121
|
+
* Format now downsamples and stores raw num. taxa for each data point.
|
|
122
|
+
* Allow for "all-but-X" CPUs for multiprocessing.
|
|
123
|
+
* Simulate wth --sim_more option to add new replicates to training examples.
|
|
124
|
+
* Format encodes all detected datasets by default.
|
|
125
|
+
* Support to allow scripts to simulate batches (>1) of replicates.
|
|
126
|
+
* Major overhaul of help docs, but not done.
|
|
127
|
+
|
|
128
|
+
|
|
129
|
+
**phyddle v0.0.5** -- 23.07.30
|
|
130
|
+
|
|
131
|
+
* Pipeline steps renamed to: Simulate, Format, Train, Estimate, Plot
|
|
132
|
+
* Simulators now in scripts/sim/MASTER, scripts/sim/R, scripts/sim/Rev
|
|
133
|
+
* Streamlined handling of phyddle settings, internally
|
|
134
|
+
* Model configuration code moved outside phyddle
|
|
135
|
+
* MASTER simulator now outside phyddle, in scripts/sim/MASTER
|
|
136
|
+
* Complete source code reorg/rename
|
|
137
|
+
* Pipeline script now prints pipeline steps
|
|
138
|
+
* Support for granular management of flow of projects across pipeline steps
|
|
139
|
+
* Support asymmetric CPI calibration
|
|
140
|
+
* Better handling of FileNotFoundError related to Estimate step
|
|
141
|
+
* Much faster Formatting step (>100x speedup)
|
|
142
|
+
* Pipeline steps now generate logs in ``workspace/log/<project_name>`` to track phyddle is used during a project analysis
|
|
143
|
+
* Tested against Apple M1. Not an easy install, because unsupported by Tensorflow. Thanks Albert and Sean!
|
|
144
|
+
|
|
145
|
+
|
|
146
|
+
**phyddle v0.0.4** -- 23.07.09
|
|
147
|
+
|
|
148
|
+
* Simulating now supports command-line scripts
|
|
149
|
+
* Better backend support for alternative phylostate tensor encodings
|
|
150
|
+
* Simplified pipeline scripts and interface
|
|
151
|
+
* Docs improved to reflect current code design
|
|
152
|
+
* Tests now cover Simulating and Formatting
|
|
153
|
+
|
|
154
|
+
|
|
155
|
+
**phyddle v0.0.3** -- 23.07.02
|
|
156
|
+
|
|
157
|
+
* Sphinx configuration for documentation
|
|
158
|
+
* TestPyPI configuration for package deployment
|
|
159
|
+
* GitHub Actions configuration for unit testing
|
|
160
|
+
|
|
161
|
+
|
|
162
|
+
**phyddle v0.0.2** -- 23.06.25
|
|
163
|
+
|
|
164
|
+
* (first internal working version)
|
|
165
|
+
* trained network generates parameter estimates and coverage-calibrated prediction intervals (CPIs) for input datasets
|
|
166
|
+
* provides several state-dependent birth-death model types and variants (more to come)
|
|
167
|
+
* parallelized simulating, formatting, and learning
|
|
168
|
+
* encoding of phylogenetic-state tensor from serial and extant-only input with multiple states (CBLV+S and CDV+S extensions)
|
|
169
|
+
* encoding of auxiliary data tensor from automatically computed summary statistics and "known" parameter (e.g. sampling rate)
|
|
170
|
+
* HDF5 with gzip compression for tensor data
|
|
171
|
+
* shuffles and splits input tensors into training, test, validation, and calibration datasets for supervised learning
|
|
172
|
+
* builds network with convolution, pooling, and dense layers that match input tensors
|
|
173
|
+
* trains network and saves history
|
|
174
|
+
* automatic figure generation with Matplotlib
|
|
175
|
+
|
|
176
|
+
|
|
177
|
+
**phyddle v0.0.1** -- 23.03.16
|
|
178
|
+
|
|
179
|
+
* (initial development version)
|
|
@@ -4,31 +4,30 @@ build-backend = "hatchling.build"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "phyddle"
|
|
7
|
-
version = "0.
|
|
7
|
+
version = "0.3.0"
|
|
8
8
|
authors = [
|
|
9
9
|
{ name="Michael Landis", email="michael.landis@wustl.edu" },
|
|
10
10
|
{ name="Ammon Thompson", email="ammonthompson@gmail.com" },
|
|
11
11
|
]
|
|
12
|
-
description = "Software
|
|
12
|
+
description = "Software for phylogenetic model exploration with deep learning"
|
|
13
13
|
readme = "README.md"
|
|
14
14
|
|
|
15
|
-
requires-python = ">=3.
|
|
15
|
+
requires-python = ">=3.12"
|
|
16
16
|
|
|
17
17
|
dependencies = [
|
|
18
|
-
"dendropy",
|
|
19
|
-
"graphviz",
|
|
20
|
-
"h5py",
|
|
21
|
-
"
|
|
22
|
-
"
|
|
23
|
-
"
|
|
24
|
-
"
|
|
25
|
-
"
|
|
26
|
-
"
|
|
27
|
-
"
|
|
28
|
-
"
|
|
29
|
-
"
|
|
30
|
-
"
|
|
31
|
-
"tqdm"
|
|
18
|
+
"dendropy>=4.6.0",
|
|
19
|
+
"graphviz>=0.20.0",
|
|
20
|
+
"h5py>=3.10.0",
|
|
21
|
+
"matplotlib>=3.8.2",
|
|
22
|
+
"numpy>=1.26.4",
|
|
23
|
+
"pandas>=2.2.0",
|
|
24
|
+
"pydot>=2.0.0",
|
|
25
|
+
"pypdf>=4.0.0",
|
|
26
|
+
"scikit-learn>=1.4.0",
|
|
27
|
+
"scipy>=1.14.0",
|
|
28
|
+
"torch>=2.2.0",
|
|
29
|
+
"torchview>=0.2.6",
|
|
30
|
+
"tqdm>=4.66.1"
|
|
32
31
|
]
|
|
33
32
|
|
|
34
33
|
classifiers = [
|
|
@@ -5,7 +5,7 @@ __init__
|
|
|
5
5
|
Initializes phyddle package and discovers all modules.
|
|
6
6
|
|
|
7
7
|
Authors: Michael Landis, Ammon Thompson
|
|
8
|
-
Copyright: (c) 2022-
|
|
8
|
+
Copyright: (c) 2022-2025, Michael Landis and Ammon Thompson
|
|
9
9
|
License: MIT
|
|
10
10
|
"""
|
|
11
11
|
|
|
@@ -14,10 +14,10 @@ License: MIT
|
|
|
14
14
|
from multiprocessing import set_start_method
|
|
15
15
|
|
|
16
16
|
__project__ = 'phyddle'
|
|
17
|
-
__version__ = '0.
|
|
17
|
+
__version__ = '0.3.0'
|
|
18
18
|
__author__ = 'Michael Landis and Ammon Thompson'
|
|
19
|
-
__copyright__ = '(c) 2022-
|
|
20
|
-
__citation__ = '
|
|
19
|
+
__copyright__ = '(c) 2022-2025, Michael Landis and Ammon Thompson'
|
|
20
|
+
__citation__ = 'MJ Landis, A Thompson. 2024. phyddle: software for phylogenetic model exploration with deep learning. bioRxiv 2024.08.06.606717.'
|
|
21
21
|
|
|
22
22
|
# DEFAULT
|
|
23
23
|
CONFIG_DEFAULT_FN = 'config_default.py'
|
|
@@ -39,9 +39,9 @@ def run():
|
|
|
39
39
|
if 'E' in step:
|
|
40
40
|
import phyddle.format as fmt
|
|
41
41
|
import phyddle.estimate as est
|
|
42
|
-
est_prefix = f"{my_args['est_dir']}/{my_args['est_prefix']}"
|
|
43
|
-
my_fmt = fmt.load(my_args)
|
|
44
|
-
my_fmt.encode_one(tmp_fn=est_prefix, idx=-1, save_phyenc_csv=True)
|
|
42
|
+
# est_prefix = f"{my_args['est_dir']}/{my_args['est_prefix']}"
|
|
43
|
+
# my_fmt = fmt.load(my_args)
|
|
44
|
+
# my_fmt.encode_one(tmp_fn=est_prefix, idx=-1, mode='emp', save_phyenc_csv=True)
|
|
45
45
|
my_est = est.load(my_args)
|
|
46
46
|
my_est.run()
|
|
47
47
|
|
|
@@ -7,7 +7,7 @@ network and uses it to generate new estimates, e.g. estimate model parameters
|
|
|
7
7
|
for a new empirical dataset.
|
|
8
8
|
|
|
9
9
|
Authors: Michael Landis and Ammon Thompson
|
|
10
|
-
Copyright: (c) 2022-
|
|
10
|
+
Copyright: (c) 2022-2025, Michael Landis and Ammon Thompson
|
|
11
11
|
License: MIT
|
|
12
12
|
"""
|
|
13
13
|
|
|
@@ -16,6 +16,7 @@ import os
|
|
|
16
16
|
|
|
17
17
|
# external imports
|
|
18
18
|
import numpy as np
|
|
19
|
+
import scipy as sp
|
|
19
20
|
import pandas as pd
|
|
20
21
|
import h5py
|
|
21
22
|
import torch
|
|
@@ -88,6 +89,12 @@ class Estimator:
|
|
|
88
89
|
self.log_offset = float(args['log_offset'])
|
|
89
90
|
self.use_cuda = bool(args['use_cuda'])
|
|
90
91
|
|
|
92
|
+
# error checking
|
|
93
|
+
self.warn_aux_outlier = float(args['warn_aux_outlier'])
|
|
94
|
+
self.warn_lbl_outlier = float(args['warn_lbl_outlier'])
|
|
95
|
+
self.est_aux_data_raw = None
|
|
96
|
+
self.est_labels_num_raw = None
|
|
97
|
+
|
|
91
98
|
# get size of CPV+S tensors
|
|
92
99
|
self.num_tree_col = util.get_num_tree_col(self.tree_encode,
|
|
93
100
|
self.brlen_encode)
|
|
@@ -122,8 +129,10 @@ class Estimator:
|
|
|
122
129
|
self.phy_data = None # init in load_format_input()
|
|
123
130
|
self.aux_data = None # init in load_format_input()
|
|
124
131
|
self.idx_data = None # init in load_format_input()
|
|
125
|
-
self.
|
|
132
|
+
self.aux_data_names = None # init in load_format_input()
|
|
133
|
+
self.true_labels_num = None # init in load_format_input()
|
|
126
134
|
self.true_labels_cat = None # init in load_format_input()
|
|
135
|
+
self.est_labels_num = None # init in make_results()
|
|
127
136
|
self.mymodel = None # init in make_results()
|
|
128
137
|
|
|
129
138
|
# done
|
|
@@ -208,6 +217,9 @@ class Estimator:
|
|
|
208
217
|
# make estimates
|
|
209
218
|
util.print_str('▪ Making empirical estimates', verbose)
|
|
210
219
|
self.make_results(mode='emp')
|
|
220
|
+
|
|
221
|
+
# check inputs/outputs
|
|
222
|
+
self.check_empirical_results()
|
|
211
223
|
|
|
212
224
|
# done
|
|
213
225
|
found_emp = True
|
|
@@ -348,6 +360,7 @@ class Estimator:
|
|
|
348
360
|
label_names = labels[0,:]
|
|
349
361
|
labels = labels[1:,:].astype('float64')
|
|
350
362
|
aux_data = aux_data[1:,:].astype('float64')
|
|
363
|
+
aux_data_names = aux_data[0,:]
|
|
351
364
|
|
|
352
365
|
elif self.tensor_format == 'hdf5':
|
|
353
366
|
hdf5_file = h5py.File(hdf5_fn, 'r')
|
|
@@ -358,6 +371,7 @@ class Estimator:
|
|
|
358
371
|
if mode == 'sim':
|
|
359
372
|
labels = pd.DataFrame(hdf5_file['labels']).to_numpy()
|
|
360
373
|
label_names = [ s.decode() for s in hdf5_file['label_names'][0,:] ]
|
|
374
|
+
aux_data_names = [ s.decode() for s in hdf5_file['aux_data_names'][0,:] ]
|
|
361
375
|
hdf5_file.close()
|
|
362
376
|
|
|
363
377
|
# get number of samples
|
|
@@ -371,7 +385,8 @@ class Estimator:
|
|
|
371
385
|
# test dataset normalization
|
|
372
386
|
assert aux_data.shape[0] == num_sample
|
|
373
387
|
self.aux_data = util.normalize(aux_data, self.train_aux_data_mean_sd)
|
|
374
|
-
|
|
388
|
+
self.aux_data_names = aux_data_names
|
|
389
|
+
|
|
375
390
|
# dataset index
|
|
376
391
|
self.idx_data = idx_data
|
|
377
392
|
|
|
@@ -394,7 +409,10 @@ class Estimator:
|
|
|
394
409
|
for idx in range(self.true_labels_cat.shape[1]):
|
|
395
410
|
unique_cats, encoded_cats = np.unique(self.true_labels_cat[:,idx],
|
|
396
411
|
return_inverse=True)
|
|
397
|
-
self.true_labels_cat[:,idx] = encoded_cats
|
|
412
|
+
self.true_labels_cat[:,idx] = encoded_cats
|
|
413
|
+
# num_outliers = np.sum(np.abs(self.aux_data[:, i]) > bound)
|
|
414
|
+
# if num_outliers > num_expected:
|
|
415
|
+
# util.print_warn(f'Outlier detected in column {i} of aux_data')
|
|
398
416
|
|
|
399
417
|
# done
|
|
400
418
|
return
|
|
@@ -425,7 +443,7 @@ class Estimator:
|
|
|
425
443
|
out_true_labels_cat_fn = f'{path_prefix}_true.labels_cat.csv'
|
|
426
444
|
|
|
427
445
|
# load model
|
|
428
|
-
self.mymodel = torch.load(model_arch_fn, map_location=self.TORCH_DEVICE)
|
|
446
|
+
self.mymodel = torch.load(model_arch_fn, map_location=self.TORCH_DEVICE, weights_only=False)
|
|
429
447
|
self.mymodel.to(self.TORCH_DEVICE)
|
|
430
448
|
|
|
431
449
|
# get estimates
|
|
@@ -480,6 +498,15 @@ class Estimator:
|
|
|
480
498
|
df_true_labels_cat = pd.concat( [self.idx_data, df_true_labels_cat], axis=1)
|
|
481
499
|
df_true_labels_cat.to_csv(out_true_labels_cat_fn, index=False, sep=',')
|
|
482
500
|
|
|
501
|
+
if mode == 'emp':
|
|
502
|
+
# self.est_labels_num_raw = denorm_est_labels_num
|
|
503
|
+
self.est_aux_data_raw = util.denormalize(self.aux_data,
|
|
504
|
+
self.train_aux_data_mean_sd,
|
|
505
|
+
exp=False)
|
|
506
|
+
self.est_labels_num_raw = util.denormalize(labels_est_num,
|
|
507
|
+
self.train_labels_num_mean_sd,
|
|
508
|
+
exp=False)[0,:,:]
|
|
509
|
+
|
|
483
510
|
# done
|
|
484
511
|
return
|
|
485
512
|
|
|
@@ -499,4 +526,48 @@ class Estimator:
|
|
|
499
526
|
|
|
500
527
|
return pd.concat(df_list, axis=1)
|
|
501
528
|
|
|
529
|
+
|
|
530
|
+
def check_empirical_results(self):
|
|
531
|
+
|
|
532
|
+
# check for outliers in aux_data
|
|
533
|
+
aux_data = util.normalize(self.est_aux_data_raw, self.train_aux_data_mean_sd)
|
|
534
|
+
aux_std_bound = np.round(sp.stats.norm.ppf(1.0 - self.warn_aux_outlier/2, loc=0, scale=1), 2)
|
|
535
|
+
for i in range(aux_data.shape[1]):
|
|
536
|
+
outlier_fail = np.abs(aux_data[:, i]) > aux_std_bound
|
|
537
|
+
mu = self.train_aux_data_mean_sd[0][i]
|
|
538
|
+
sd = self.train_aux_data_mean_sd[1][i]
|
|
539
|
+
raw_lower = "{:.2e}".format(mu - aux_std_bound * sd)
|
|
540
|
+
raw_upper = "{:.2e}".format(mu + aux_std_bound * sd)
|
|
541
|
+
percent = 100*(1.0 - self.warn_aux_outlier)
|
|
542
|
+
outlier_idx = np.where(outlier_fail)[0]
|
|
543
|
+
outliers = self.est_aux_data_raw[outlier_fail, i]
|
|
544
|
+
if outliers.shape[0] > 0:
|
|
545
|
+
util.print_warn(f'Outlier(s) detected in empirical aux. data: {self.aux_data_names[i]}')
|
|
546
|
+
# util.print_str(f' Values outside {(1.0 - self.warn_aux_outlier)*100}% interval of [{raw_lower}, {raw_upper}]')
|
|
547
|
+
util.print_str(f' - Values outside ± {aux_std_bound}sd ({percent}%) interval of [{raw_lower}, {raw_upper}]')
|
|
548
|
+
util.print_str(f' - Detected outlier(s):')
|
|
549
|
+
for j in range(outliers.shape[0]):
|
|
550
|
+
util.print_str(f' index {outlier_idx[j]} : value {outliers[j]}')
|
|
551
|
+
|
|
552
|
+
# check for outliers in labels
|
|
553
|
+
if self.has_label_num:
|
|
554
|
+
est_labels_num = util.normalize(self.est_labels_num_raw, self.train_labels_num_mean_sd)
|
|
555
|
+
lbl_std_bound = np.round(sp.stats.norm.ppf(1.0 - self.warn_lbl_outlier/2, loc=0, scale=1), 2)
|
|
556
|
+
for i in range(est_labels_num.shape[1]):
|
|
557
|
+
outlier_fail = np.abs(est_labels_num[:, i]) > lbl_std_bound
|
|
558
|
+
mu = self.train_labels_num_mean_sd[0][i]
|
|
559
|
+
sd = self.train_labels_num_mean_sd[1][i]
|
|
560
|
+
raw_lower = "{:.2e}".format(mu - lbl_std_bound * sd)
|
|
561
|
+
raw_upper = "{:.2e}".format(mu + lbl_std_bound * sd)
|
|
562
|
+
percent = 100*(1.0 - self.warn_lbl_outlier)
|
|
563
|
+
outlier_idx = np.where(outlier_fail)[0]
|
|
564
|
+
outliers = self.est_labels_num_raw[outlier_fail, i]
|
|
565
|
+
if outliers.shape[0] > 0:
|
|
566
|
+
util.print_warn(f'Outlier(s) detected in empirical labels: {self.label_num_names[i]}')
|
|
567
|
+
# util.print_str(f' Values outside {(1.0 - self.warn_lbl_outlier*100)}% interval of [{raw_lower}, {raw_upper}]')
|
|
568
|
+
util.print_str(f' - Values outside ± {lbl_std_bound}sd ({percent}%) interval of [{raw_lower}, {raw_upper}]')
|
|
569
|
+
util.print_str(f' - Detected outlier(s):')
|
|
570
|
+
for j in range(outliers.shape[0]):
|
|
571
|
+
util.print_str(f' index {outlier_idx[j]} : value {outliers[j]}')
|
|
572
|
+
|
|
502
573
|
##################################################
|