import csv
import pandas as pd # Import datafiles
# Personal libraries
from ML_treatment import componentAnalysis, normalizeData, componentAnalysisLast
print('Libaries loaded')
# Close all open windows
plt.close()
dataset = np.loadtxt("Datasets/winequality-white.csv",delimiter=';',skiprows=1) #"Users/groenera/Desktop/file.csv"
dataName = 'wineQuality_'
# Crop for easy calcualtion
analysisDim = -1
componentAnalysisLast(dataset[1:10000,:], 'energyData_raw', analysisDim) #plot preprocessing
normalizeData(dataset)
#dataset = dataset[0:1000,:] # crop for ease of calculation
print('Data set loaded with shape: {}'.format(dataset.shape))
plt.show()
# Define Parameters
tt_ratios = np.linspace(0.1,0.9, num=2)
gammaVals = np.logspace(0.001,100,num=2)
# Inititialize lists
rvr_errs = []
# Personal libraries
from ML_treatment import componentAnalysis, normalizeData, componentAnalysisLast
print('libaries loaded')
# Close all open windows
plt.close()
#dataset = np.loadtxt("Datasets/housing.data") #"Users/groenera/Desktop/file.csv"
print('data set loaded')
# Preprocessing
shape = dataset.shape
print("Dataset shape is {}x{}".format(shape[0], shape[1]))
normalizeData(dataset)
componentAnalysisLast(dataset)
dataset = np.delete(dataset, 3, axis=1) # 4th dimesion = 3rd element
dataset = dataset[:, :] # reduce dataset, remove for large calculations
shape = dataset.shape
print("Dataset shape is {}x{}".format(shape[0], shape[1]))
# Wine dataset
dataset = np.loadtxt("Datasets/winequality-white.csv",
delimiter=';',
skiprows=1) #"Users/groenera/Desktop/file.csv"
normalizeData(dataset)
print('Data set loaded with shape: {}'.format(dataset.shape))
# Define Parameters
tt_ratios = np.linspace(0.1, 0.9, num=2)