def transformer(inputs):
"""applies yeo-johnson power transform to first two indices of array (n_files, total_mb) using lambdas, mean and standard deviation calculated for each variable prior to model training.
Returns: X inputs as 2D-array for generating predictions
"""
X = inputs
n_files = X[0]
total_mb = X[1]
# apply power transformer normalization to continuous vars
x = np.array([[n_files], [total_mb]]).reshape(1, -1)
pt = PowerTransformer(standardize=False)
pt.lambdas_ = np.array([-1.51, -0.12])
xt = pt.transform(x)
# normalization (zero mean, unit variance)
f_mean, f_sigma = 0.5682815234265285, 0.04222565843608133
s_mean, s_sigma = 1.6250374589283951, 1.0396138451086632
x_files = np.round(((xt[0, 0] - f_mean) / f_sigma), 5)
x_size = np.round(((xt[0, 1] - s_mean) / s_sigma), 5)
# print(f"Power Transformed variables: {x_files}, {x_size}")
X_values = {
"x_files": x_files,
"x_size": x_size,
"drizcorr": X[2],
"pctecorr": X[3],
"crsplit": X[4],
"subarray": X[5],
"detector": X[6],
"dtype": X[7],
"instr": X[8],
}
# X = np.array([x_files, x_size, X[2], X[3], X[4], X[5], X[6], X[7], X[8]])
return X_values
def transformer(self, pt_data):
"""applies yeo-johnson power transform to first two indices of array (n_files, total_mb) using lambdas, mean and standard deviation calculated for each variable prior to model training.
Returns: X inputs as 2D-array for generating predictions
"""
X = self.inputs
n_files = X[0]
total_mb = X[1]
# apply power transformer normalization to continuous vars
x = np.array([[n_files], [total_mb]]).reshape(1, -1)
pt = PowerTransformer(standardize=False)
pt.lambdas_ = np.array([pt_data["f_lambda"], pt_data["s_lambda"]])
# pt.lambdas_ = np.array([-1.05989146, 0.1691683])
xt = pt.transform(x)
# normalization (zero mean, unit variance)
f_mean, f_sigma = pt_data["f_mean"], pt_data["f_sigma"]
s_mean, s_sigma = pt_data["s_mean"], pt_data["s_sigma"]
# f_mean, f_sigma = 0.7313458816815209, 0.09209684806404451
# s_mean, s_sigma = 4.18491577280472, 2.4467903663338366
x_files = np.round(((xt[0, 0] - f_mean) / f_sigma), 5)
x_size = np.round(((xt[0, 1] - s_mean) / s_sigma), 5)
X = np.array([x_files, x_size, X[2], X[3], X[4], X[5], X[6], X[7], X[8]]).reshape(1, -1)
return X
