Lime-for-Time for multi feature of time series data

[edmundarmin]

Hellow, i have data time series of multiple sensor, and i dont know how to use it in your code, can you give me an example ?

[Th3Fr0g]

I have got the same Problem. I followed the demo version and I am getting: Found input variables with inconsistent numbers of samples: [100, 1900]  in the explain_instance method. Any ideas?

`def lime(): df_new = pd.DataFrame(df.iloc[:40000]) signal_names = df_new.columns.names X = dfnew.values y = np.array([np.random.randint(0,2) for in range(760000)])

steps = [
    ("concatenate", ColumnConcatenator()),
    ("classify", HistGradientBoostingClassifier())
]

clf = Pipeline(steps)
clf.fit(X, y)

class_names=[y[0]]
num_slices=20
num_features=17

explainer = lime_ts.LimeTimeSeriesExplainer(
    class_names=class_names,
    signal_names=signal_names)

labelid = 0

exp = explainer.explain_instance(
    X[0], clf.predict_proba,
    num_features=num_features,
    num_samples=100,
    num_slices=num_slices,
    labels=[labelid],
    replacement_method='total_mean')

exp.as_pyplot_figure(labelid)

plt.savefig("lime.png")`