Closed ulf1 closed 1 year ago
mkdir myproject
cd myproject
# setup virtualenv or conda ...
# install software
pip install TSInterpret
# download demo examples
git clone git@github.com:fzi-forschungszentrum-informatik/TSInterpret.git
python3
then
import pickle
import numpy as np
import matplotlib.pyplot as plt
import seaborn as snst
from tslearn.datasets import UCR_UEA_datasets
import tensorflow as tf
# the path are different.
# i don't know why the original example refers to '../../'
dataset='BasicMotions'
train_x,train_y, test_x, test_y=UCR_UEA_datasets().load_dataset(dataset)
enc1=pickle.load(open(f'TSInterpret/ClassificationModels/models/{dataset}/OneHotEncoder.pkl','rb'))
train_y=enc1.transform(train_y.reshape(-1,1))
test_y=enc1.transform(test_y.reshape(-1,1))
model_to_explain = tf.keras.models.load_model(f'TSInterpret/ClassificationModels/models/{dataset}/cnn/{dataset}best_model.hdf5')
Is there also a function to save a PNG file to disk instead of using Jupyter?
%matplotlib inline
int_mod.plot(np.array([test_x[0,:,:]]),exp)
Hi ,
I added clarifications to the ReadMe.md. Usually the classification models are not provided by our package. The intention is to provide insights into the models customized by the users of this package. Therefore, classification models are not included in the PyPi installation and only available by cloning this repo. I hope the current version is now clearer. @ulf1 If you have ideas on how to make this more elegant, feel free to share those.
Yes the plot function has a parameter called save where you can specify the path to save the images (.png/.jpg/.svg).
Best, Jacqueline
https://github.com/fzi-forschungszentrum-informatik/TSInterpret/blob/345942838dbe3fa6526c0bd0659a405271ea5117/README.md?plain=1#L50
the code examples in the README.md only works if the user downloaded the git repo but not via the pypi package. You should also give the instruction to download the git repo to run the examples.