You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
| matching |matching|macOS, Ubuntu, Windows | 3.10 |
73
+
| nncontrastive |nncontrastive |macOS, Ubuntu, Windows | 3.10 |
74
+
| profwt |profwt |macOS, Ubuntu, Windows | 3.6 |
75
+
| protodash |protodash |macOS, Ubuntu, Windows | 3.10 |
76
+
| rbm |brcg, glrm |macOS, Ubuntu, Windows | 3.10 |
77
+
| rule_induction |ripper |macOS, Ubuntu, Windows | 3.10 |
78
+
| shap |shap |macOS, Ubuntu, Windows | 3.6 |
79
+
| ted |ted |macOS, Ubuntu, Windows | 3.10 |
80
+
| tsice |tsice |macOS, Ubuntu, Windows | 3.10 |
81
+
| tslime |tslime |macOS, Ubuntu, Windows | 3.10 |
82
+
| tssaliency |tssaliency |macOS, Ubuntu, Windows | 3.10 |
83
83
84
84
85
85
### (Optional) Create a virtual environment
@@ -130,11 +130,11 @@ their respective folders as described in
130
130
Then, navigate to the root directory of the project which contains `setup.py` file and run:
131
131
132
132
```bash
133
-
(aix360)$ pip install -e .[<algo1>,<algo2>, ...]
133
+
(aix360)$ pip install -e .[<algo1>,<algo2>, ...]
134
134
```
135
-
The above command installs packages required by specific algorithms. Here `<algo>`keyword refers to one or more explainability algorithms. For instance to install packages needed by BRCG, DIPVAE, and TSICE algorithms, one could use
135
+
The above command installs packages required by specific algorithms. Here `<algo>` refers to the installation keyword in [table](https://github.com/Trusted-AI/AIX360/edit/master/README.md#supported-configurations) above. For instance to install packages needed by BRCG, DIPVAE, and TSICE algorithms, one could use
136
136
```bash
137
-
(aix360)$ pip install -e .[rbm,dipvae,tsice]
137
+
(aix360)$ pip install -e .[rbm,dipvae,tsice]
138
138
```
139
139
The default command `pip install .` installs [default dependencies](https://github.com/Trusted-AI/AIX360/blob/462c4d575bfc71c5cbfd32ceacdb3df96a8dc2d1/setup.py#L9) alone.
140
140
@@ -149,13 +149,27 @@ If you face any issues, please try upgrading pip and setuptools and uninstall an
149
149
150
150
## PIP Installation of AI Explainability 360
151
151
152
-
If you would like to quickly start using the AI explainability 360 toolkit without cloning this repository, then you can install the [aix360 pypi package](https://pypi.org/project/aix360/) as follows.
152
+
If you would like to quickly start using the AI explainability 360 toolkit without explicitly cloning this repository, you can use one of these options:
For example, use `pip install -e git+https://github.com/Trusted-AI/AIX360.git#egg=aix360[rbm,dipvae,tsice]` to install BRCG, DIPVAE, and TSICE. You may need to install `cmake` if its not already installed in your environment using `conda install cmake`.
159
+
160
+
* Install previous version v0.2.1 via [pypi](https://pypi.org/project/aix360/)
154
161
```bash
155
162
(your environment)$ pip install aix360
156
163
```
164
+
v0.2.1 includes fewer explainability algorithms. The pip installable package of v0.3.0 will be made available on [pypi](https://pypi.org/project/aix360/) soon.
165
+
166
+
If you follow either of these two options, you will need to download the notebooks available in the [examples](./examples) folder separately.
167
+
168
+
## Dealing with installation errors
169
+
170
+
AI Explainability 360 toolkit is tested on Windows, MacOS, and Linux [here](https://github.com/Trusted-AI/AIX360/blob/master/.github/workflows/Build.yml). However, if you still face installation issues due to package dependencies, please try installing the corresponding package via conda (e.g. conda install package-name) and then install the toolkit by following the usual steps. For example, if you face issues related to pygraphviz during installation, use `conda install pygraphviz` and then install the toolkit.
157
171
158
-
This will install v0.2.1 which includes a subset of algorithms. This will be updated soon. If you follow this approach, you will need to download the notebooks available in the [examples](./examples) folder separately.
172
+
Please use the right python environment based on the [table](https://github.com/Trusted-AI/AIX360/edit/master/README.md#supported-configurations) above.
0 commit comments