Spaces:
Sleeping
Sleeping
File size: 2,407 Bytes
a106a7b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
import numpy as np
import pandas as pd
np.random.seed(42)
epsilon = 1e-8
class Dataset:
def __init__(self, inverse=False):
filename = './Data/DataForThermoforming.xlsx'
self.df = pd.read_excel(filename, sheet_name='Data')
# remove rows by index
self.df = self.df.drop([20, 48], axis=0)
# normalize data
if inverse:
self.input_columns = ['Ply_Number', 'A1(abs)', 'B1(abs)', 'C1(abs)', 'Stress(Max) MPa']
self.output_columns = ['Initial_Temp (degree celsius)', 'Punch_Velocity (mm/s)', 'Cooling_Time (s)']
else:
self.input_columns = ['Ply_Number', 'Initial_Temp (degree celsius)', 'Punch_Velocity (mm/s)', 'Cooling_Time (s)']
self.output_columns = ['A1(abs)', 'B1(abs)', 'C1(abs)', 'Stress(Max) MPa']
self.input_mean = self.df[self.input_columns].mean().to_numpy(dtype=np.float32)
self.input_std = self.df[self.input_columns].std().to_numpy(dtype=np.float32) + epsilon
self.output_mean = self.df[self.output_columns].mean().to_numpy(dtype=np.float32)
self.output_std = self.df[self.output_columns].std().to_numpy(dtype=np.float32) + epsilon
def get_input(self, normalize=False):
data = self.df[self.input_columns].to_numpy(dtype=np.float32)
if normalize:
data = self.normalize_input(data)
return data
def get_output(self, normalize=False):
data = self.df[self.output_columns].to_numpy(dtype=np.float32)
if normalize:
data = self.normalize_output(data)
return data
def __str__(self):
return str(self.df.head())
def normalize_input(self, input_data):
return (input_data - self.input_mean) / self.input_std
def normalize_output(self, output_data):
return (output_data - self.output_mean) / self.output_std
def denormalize_input(self, normalized_input):
return normalized_input * self.input_std + self.input_mean
def denormalize_output(self, normalized_output):
return normalized_output * self.output_std + self.output_mean
if __name__ == "__main__":
dataset = Dataset()
# Example usage
input_data = dataset.get_input(normalize=True)
output_data = dataset.get_output(normalize=True)
print("Input shape:", input_data.shape)
print("Output shape:", output_data.shape)
|