Hirokazu Takaya

Interface could be as follows. ```Python import covsirphy as cs snr = cs.ODEScenario.auto_build(geo="Japan", model=cs.SIRFModel) # Prediction of ODE parameters WITHOUT indocators snr.build_with_template(name="Predicted", template="Baseline") snr.predict(days=30, name="Predicted", verbose=1) # Prediction of ODE...

For ducumentation, new notebook will be added to example.

With #1157, - #477: user can specify the seed via `MLEngineer(seed)` and `ODEScenario().predict(seed)`

This will be required to improve efficiency of prediction with regressor. PCA is a method to reduce the number of variables.

Because PCA assumes data is normal distributed, standardization (or Z-score normalization) should be perfomed as explained in the documentatin of `pca`. https://erdogant.github.io/pca/pages/html/Algorithm.html#standardization

To check the amount of information, cumulative explained variance should be displayed as default.

Trial https://gist.github.com/lisphilar/a044704f0382e010f257e950c787aee5

Installation error was raised with scatterd version 1.1.2 (a dependency of `pca`), but this error was fixed at scatterd version 1.1.3. https://github.com/erdogant/scatterd/issues/2

#1140: - new; `MLEngineer().pca(X, n_components)`: perform PCA on a data ```Python import covsirphy as cs data_eng = DataEngineer() data_eng.download() data_eng.clean() data_eng.transform() subset_df, *_ = data_eng.subset(geo="Japan") subset_df = subset_df.drop(["Population", "Susceptible", "Confirmed",...

On documentation, the URL of pca package and the following usage should be recorded. https://github.com/erdogant/pca ```Python from matplotlib import pyplot as plt import numpy as np # Explained variance pca_dict["model"].plot()...