File size: 3,146 Bytes
6977ea8 |
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 66 67 68 69 70 71 72 73 74 75 76 77 78 |
import numpy as np
import pandas as pd
np.random.seed(42)
epsilon = 1e-8
class Dataset:
def __init__(self, mat_name='FRP'):
filename = './Data/240_simulations_DS.xlsx'
self.df = pd.read_excel(filename, sheet_name=mat_name, header=1)
# normalize data
self.input_columns = [
'Gate Location',
'Matrix',
'Fiber Type',
'Fiber wt%(Volume Fractions)',
# 'Fiber-Matrix Combination',
'Packing Pressure (MPa)',
'Packing Time (s)',
'Mold Temperature (°C)',
'Injection Speed (cm^3/s)'
]
self.output_columns = ['Alpha_angle_deg(ABS)', 'Beta_angle_deg(ABS)', 'Gamma_angle_deg(ABS)']
self.material_map = {'PA6': 0, 'PP': 1}
self.fiber_map = {'CF': 0, 'GF': 1}
self.combination_map = {'PA6-CF-10': 0, 'PA6-CF-15': 1, 'PA6-CF-30': 2, 'PA6-CF-40': 3,
'PA6-GF-15': 4, 'PA6-GF-30': 5, 'PA6-GF-40': 6, 'PA6-GF-50': 7,
'PP-CF-10': 8, 'PP-CF-15': 9, 'PP-CF-30': 10, 'PP-CF-40': 11,
'PP-GF-15': 12, 'PP-GF-30': 13, 'PP-GF-40': 14, 'PP-GF-50': 15}
self.df['Matrix'] = self.df['Matrix'].map(self.material_map)
self.df['Fiber Type'] = self.df['Fiber Type'].map(self.fiber_map)
self.df['Fiber-Matrix Combination'] = self.df['Fiber-Matrix Combination'].map(self.combination_map)
self.df['Fiber wt%(Volume Fractions)'] = self.df['Fiber wt%(Volume Fractions)'] / 100.0
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=False)
output_data = dataset.get_output(normalize=False)
print("Input shape:", input_data.shape)
print("Output shape:", output_data.shape) |