EpsilonDiagnosis - Diff between normal_data and abnormal_data

[igorestevanjasinski]

I would like a help to understand how to using EpsilonDiagnosis, in the case to train a model with historical data for example 90 days and in the moment of an incident use the function find_root_causes with an abnormal_data dataframe to find the root cause, but when testing I got this error.

`---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[33], line 1
----> 1 results = model.find_root_causes(anomaly_df)
2 print(results.to_dict())

File ~/.local/lib/python3.10/site-packages/pyrca/analyzers/epsilon_diagnosis.py:88, in EpsilonDiagnosis.find_root_causes(self, abnormal_df, **kwargs)
85 self.correlations[colname] = 0
86 else:
87 self.correlations[colname] = np.square(
---> 88 np.cov(self.normal_df[colname].values, abnormal_df[colname].values)[0, 1]
89 ) / (np.var(self.normal_df[colname].values) * np.var(abnormal_df[colname].values))
90 if self.correlations[colname] > self.statistics[colname]:
91 root_cause_nodes.append((colname, self.correlations[colname]))

File <array_function internals>:180, in cov(*args, **kwargs)

File ~/.local/lib/python3.10/site-packages/numpy/lib/function_base.py:2639, in cov(m, y, rowvar, bias, ddof, fweights, aweights, dtype)
2637 if not rowvar and y.shape[0] != 1:
2638 y = y.T
-> 2639 X = np.concatenate((X, y), axis=0)
2641 if ddof is None:
2642 if bias == 0:

File <array_function internals>:180, in concatenate(*args, **kwargs)

ValueError: all the input array dimensions for the concatenation axis must match exactly, but along dimension 1, the array at index 0 has size 2881 and the array at index 1 has size 73`

It seems the two dataframes need to have the same amount of lines, but I think this is not achievable.