ModelPerformance.py

import numpy as np
import  matplotlib.pyplot as plt
from sklearn.metrics import mean_squared_error
import math
def std_inverse(std,data):
    original_shape = data.shape
    try:
        data = data.copy()
    except Exception:
        pass
    inversed_data = std.inverse_transform(np.reshape(data,(-1,data.shape[-2]*data.shape[-1])))
    inversed_data = inversed_data.reshape(original_shape)
    return inversed_data
def compare_result(predict,real):
    assert(predict.shape == real.shape)
    original_shape = predict.shape
    predict_flatten = np.reshape(predict,(-1,original_shape[-2]*original_shape[-1]))
    real_flatten = np.reshape(real, (-1,original_shape[-2]*original_shape[-1]))

    
    # assert(np.array_equal(predict_flatten.reshape(original_shape), predict))
    
    print(mean_squared_error(predict_flatten,real_flatten))

    return (mean_squared_error(predict_flatten,real_flatten))
def plot_result(predict,real,batch =0,in_out = 0,figure_name = None,time_c = None):

    # vmin = min(predict[batch].min(), real[batch].min())
    vmin = 0
    vmax = max(predict[:,in_out].max(), real[:,in_out].max())

    cmap = 'viridis'
    fig, axs = plt.subplots(1, 3)
    if time_c !=None:
        month = round(float(time_c[0,0]*30))
        day = round(np.arcsin(time_c[1,0])/(2*np.pi)*30)
        hour = np.arcsin(time_c[2,0])
        minute = round(float(time_c[3,0])*30)

        fig.suptitle("2019-{:02}-{:02}".format(month,day))
    axs[0].set_title("predict")
    predict_fig = axs[0].imshow(predict[batch,in_out,:,:],cmap = cmap,vmin = vmin,vmax = vmax)
    axs[1].set_title("real")
    real_fig = axs[1].imshow(real[batch,in_out,:,:],cmap = cmap,vmin = vmin,vmax = vmax)
    axs[2].set_title("diff")
    diff_matrix  = np.abs(predict[batch,in_out,:,:] - real[batch,in_out,:,:])
    diff_fig = axs[2].imshow(diff_matrix, cmap = cmap,vmin = vmin,vmax = vmax)
    plt.colorbar(predict_fig,ax=axs)
    # plt.colorbar(real_fig,ax = axs)
    print(diff_matrix.mean(),diff_matrix.shape)
    if figure_name!=None:
        plt.savefig(f"./figure/{figure_name}.png")
    plt.show()