1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
|
%global _empty_manifest_terminate_build 0
Name: python-instancelib
Version: 0.4.9.1
Release: 1
Summary: A typed dataset abstraction toolkit for machine learning projects
License: GNU LGPL v3
URL: https://pypi.org/project/instancelib/
Source0: https://mirrors.nju.edu.cn/pypi/web/packages/6e/3d/7ee9dccc7fa94386539a2f528f8f2916f5061dbf82cc41a18497345578f7/instancelib-0.4.9.1.tar.gz
BuildArch: noarch
Requires: python3-numpy
Requires: python3-pandas
Requires: python3-h5py
Requires: python3-scikit-learn
Requires: python3-openpyxl
Requires: python3-xlrd
Requires: python3-tqdm
Requires: python3-more-itertools
Requires: python3-typing-extensions
Requires: python3-gensim
Requires: python3-tables
%description
`instancelib` provides a **generic architecture** for datasets.
© Michiel Bron, 2021
## Quick tour
**Load dataset**: Load the dataset in an environment
```python
import instancelib as il
text_env = il.read_excel_dataset("./datasets/testdataset.xlsx",
data_cols=["fulltext"],
label_cols=["label"])
ds = text_env.dataset # A `dict-like` interface for instances
labels = text_env.labels # An object that stores all labels
labelset = labels.labelset # All labels that can be given to instances
ins = ds[20] # Get instance with identifier key `20`
ins_data = ins.data # Get the raw data for instance 20
ins_vector = ins.vector # Get the vector representation for 20 if any
ins_labels = labels.get_labels(ins)
```
**Dataset manipulation**: Divide the dataset in a train and test set
```python
train, test = text_env.train_test_split(ds, train_size=0.70)
print(20 in train) # May be true or false, because of random sampling
```
**Train a model**:
```python
from sklearn.pipeline import Pipeline
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import TfidfTransformer, CountVectorizer
pipeline = Pipeline([
('vect', CountVectorizer()),
('tfidf', TfidfTransformer()),
('clf', MultinomialNB()),
])
model = il.SkLearnDataClassifier.build(pipeline, text_env)
model.fit_provider(train, labels)
predictions = model.predict(test)
```
## Installation
See [installation.md](docs/installation.md) for an extended installation guide.
| Method | Instructions |
|--------|--------------|
| `pip` | Install from [PyPI](https://pypi.org/project/instancelib/) via `pip install instancelib`. |
| Local | Clone this repository and install via `pip install -e .` or locally run `python setup.py install`.
## Documentation
Full documentation of the latest version is provided at [https://instancelib.readthedocs.org](https://instancelib.readthedocs.org).
## Example usage
See [usage.py](usage.py) to see an example of how the package can be used.
## Releases
`instancelib` is officially released through [PyPI](https://pypi.org/project/instancelib/).
See [CHANGELOG.md](CHANGELOG.md) for a full overview of the changes for each version.
## Citation
```bibtex
@misc{instancelib,
title = {Python package instancelib},
author = {Michiel Bron},
howpublished = {\url{https://github.com/mpbron/instancelib}},
year = {2021}
}
```
## Library usage
This library is used in the following projects:
- [python-allib](https://github.com/mpbron/allib). A typed Active Learning framework for Python for both Classification and Technology-Assisted Review systems.
- [text_explainability](https://marcelrobeer.github.io/text_explainability/). A generic explainability architecture for explaining text machine learning models
- [text_sensitivity](https://marcelrobeer.github.io/text_sensitivity/). Sensitivity testing (fairness & robustness) for text machine learning models.
## Maintenance
### Contributors
- [Michiel Bron](https://www.uu.nl/staff/MPBron) (`@mpbron`)
### Todo
Tasks yet to be done:
* Implement support for ONNX models
* Implement support for Python DataLoaders
* Make the external dataset interface more user friendly
* Redesign LabelProvider to support more attribute levels
* CI/CD tests
%package -n python3-instancelib
Summary: A typed dataset abstraction toolkit for machine learning projects
Provides: python-instancelib
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-instancelib
`instancelib` provides a **generic architecture** for datasets.
© Michiel Bron, 2021
## Quick tour
**Load dataset**: Load the dataset in an environment
```python
import instancelib as il
text_env = il.read_excel_dataset("./datasets/testdataset.xlsx",
data_cols=["fulltext"],
label_cols=["label"])
ds = text_env.dataset # A `dict-like` interface for instances
labels = text_env.labels # An object that stores all labels
labelset = labels.labelset # All labels that can be given to instances
ins = ds[20] # Get instance with identifier key `20`
ins_data = ins.data # Get the raw data for instance 20
ins_vector = ins.vector # Get the vector representation for 20 if any
ins_labels = labels.get_labels(ins)
```
**Dataset manipulation**: Divide the dataset in a train and test set
```python
train, test = text_env.train_test_split(ds, train_size=0.70)
print(20 in train) # May be true or false, because of random sampling
```
**Train a model**:
```python
from sklearn.pipeline import Pipeline
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import TfidfTransformer, CountVectorizer
pipeline = Pipeline([
('vect', CountVectorizer()),
('tfidf', TfidfTransformer()),
('clf', MultinomialNB()),
])
model = il.SkLearnDataClassifier.build(pipeline, text_env)
model.fit_provider(train, labels)
predictions = model.predict(test)
```
## Installation
See [installation.md](docs/installation.md) for an extended installation guide.
| Method | Instructions |
|--------|--------------|
| `pip` | Install from [PyPI](https://pypi.org/project/instancelib/) via `pip install instancelib`. |
| Local | Clone this repository and install via `pip install -e .` or locally run `python setup.py install`.
## Documentation
Full documentation of the latest version is provided at [https://instancelib.readthedocs.org](https://instancelib.readthedocs.org).
## Example usage
See [usage.py](usage.py) to see an example of how the package can be used.
## Releases
`instancelib` is officially released through [PyPI](https://pypi.org/project/instancelib/).
See [CHANGELOG.md](CHANGELOG.md) for a full overview of the changes for each version.
## Citation
```bibtex
@misc{instancelib,
title = {Python package instancelib},
author = {Michiel Bron},
howpublished = {\url{https://github.com/mpbron/instancelib}},
year = {2021}
}
```
## Library usage
This library is used in the following projects:
- [python-allib](https://github.com/mpbron/allib). A typed Active Learning framework for Python for both Classification and Technology-Assisted Review systems.
- [text_explainability](https://marcelrobeer.github.io/text_explainability/). A generic explainability architecture for explaining text machine learning models
- [text_sensitivity](https://marcelrobeer.github.io/text_sensitivity/). Sensitivity testing (fairness & robustness) for text machine learning models.
## Maintenance
### Contributors
- [Michiel Bron](https://www.uu.nl/staff/MPBron) (`@mpbron`)
### Todo
Tasks yet to be done:
* Implement support for ONNX models
* Implement support for Python DataLoaders
* Make the external dataset interface more user friendly
* Redesign LabelProvider to support more attribute levels
* CI/CD tests
%package help
Summary: Development documents and examples for instancelib
Provides: python3-instancelib-doc
%description help
`instancelib` provides a **generic architecture** for datasets.
© Michiel Bron, 2021
## Quick tour
**Load dataset**: Load the dataset in an environment
```python
import instancelib as il
text_env = il.read_excel_dataset("./datasets/testdataset.xlsx",
data_cols=["fulltext"],
label_cols=["label"])
ds = text_env.dataset # A `dict-like` interface for instances
labels = text_env.labels # An object that stores all labels
labelset = labels.labelset # All labels that can be given to instances
ins = ds[20] # Get instance with identifier key `20`
ins_data = ins.data # Get the raw data for instance 20
ins_vector = ins.vector # Get the vector representation for 20 if any
ins_labels = labels.get_labels(ins)
```
**Dataset manipulation**: Divide the dataset in a train and test set
```python
train, test = text_env.train_test_split(ds, train_size=0.70)
print(20 in train) # May be true or false, because of random sampling
```
**Train a model**:
```python
from sklearn.pipeline import Pipeline
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import TfidfTransformer, CountVectorizer
pipeline = Pipeline([
('vect', CountVectorizer()),
('tfidf', TfidfTransformer()),
('clf', MultinomialNB()),
])
model = il.SkLearnDataClassifier.build(pipeline, text_env)
model.fit_provider(train, labels)
predictions = model.predict(test)
```
## Installation
See [installation.md](docs/installation.md) for an extended installation guide.
| Method | Instructions |
|--------|--------------|
| `pip` | Install from [PyPI](https://pypi.org/project/instancelib/) via `pip install instancelib`. |
| Local | Clone this repository and install via `pip install -e .` or locally run `python setup.py install`.
## Documentation
Full documentation of the latest version is provided at [https://instancelib.readthedocs.org](https://instancelib.readthedocs.org).
## Example usage
See [usage.py](usage.py) to see an example of how the package can be used.
## Releases
`instancelib` is officially released through [PyPI](https://pypi.org/project/instancelib/).
See [CHANGELOG.md](CHANGELOG.md) for a full overview of the changes for each version.
## Citation
```bibtex
@misc{instancelib,
title = {Python package instancelib},
author = {Michiel Bron},
howpublished = {\url{https://github.com/mpbron/instancelib}},
year = {2021}
}
```
## Library usage
This library is used in the following projects:
- [python-allib](https://github.com/mpbron/allib). A typed Active Learning framework for Python for both Classification and Technology-Assisted Review systems.
- [text_explainability](https://marcelrobeer.github.io/text_explainability/). A generic explainability architecture for explaining text machine learning models
- [text_sensitivity](https://marcelrobeer.github.io/text_sensitivity/). Sensitivity testing (fairness & robustness) for text machine learning models.
## Maintenance
### Contributors
- [Michiel Bron](https://www.uu.nl/staff/MPBron) (`@mpbron`)
### Todo
Tasks yet to be done:
* Implement support for ONNX models
* Implement support for Python DataLoaders
* Make the external dataset interface more user friendly
* Redesign LabelProvider to support more attribute levels
* CI/CD tests
%prep
%autosetup -n instancelib-0.4.9.1
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-instancelib -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Fri May 05 2023 Python_Bot <Python_Bot@openeuler.org> - 0.4.9.1-1
- Package Spec generated
|
