File size: 1,931 Bytes
c176aea |
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 |
import numpy as np
import _pickle
import pandas as pd
# import tensorflow as tf
# from keras.layers import Input,Dense
# from keras.models import Model
# from sklearn.model_selection import train_test_split
from utils.ndgan import DCGAN
np.random.seed(4269)
class dataset():
""" Creates dataset from input source
"""
def __init__(self,number_samples:int, name:str,source:str,boundary_conditions:list=None):
""" Init
Args:
number_samples (int): number of samples to be genarated
name (str): name of dataset
source (str): source file
boundary_conditions (list): y1,y2,x1,x2
"""
self.sample_size = number_samples
self.name = name
self.samples = []
self.encoding_dim = 8
self.latent_dim = 16
self.source = source
self.boundary_conditions = boundary_conditions
def generate(self):
with open(f"./data/{self.source}", "rb") as input_file:
local = pd.read_csv(input_file)
dfs = local.drop("Name",axis=1)
dfs = (dfs-dfs.min())/(dfs.max()-dfs.min())
dfs = pd.concat([local.Name,dfs],1)
self.vae = DCGAN(self.latent_dim,dfs)
self.vae.start_training()
self.samples = self.vae.predict(self.sample_size)
if self.boundary_conditions:
self.samples=self.samples[((self.samples[:,0]>self.boundary_conditions[2]) & (self.samples[:,0] < self.boundary_conditions[-1]))&((self.samples[:,0]>self.boundary_conditions[0]) & (self.samples[:,0] < self.boundary_conditions[1]))]
print("Samples:",self.samples)
dataframe = pd.concat([dfs,pd.DataFrame(self.samples,columns=dfs.columns[1:])])
dataframe.to_pickle(f'./data/{self.name}')
print(dataframe)
return dataframe
|