import pandas as pd
import numpy as np
import scipy.sparse as sparse
import matplotlib.pyplot as plt
plt.close('all')
""" Load Data """
loadall=True #set to true to load from csv
#load from pre-saved sparse matrix (fast and sexier)
if not loadall:
import sparse_manip
sparsefile = 'data/data.npz' #default location
try:
data = sparse_manip.load(sparsefile)
except IOError:
loadall = True
#load from csv (slow)
if loadall:
#load data
filename='data/dataset.txt'
X = pd.read_csv(filename, ';')
#'real world' data (no indication regarding origin)
labels = X['category'] #let's be fair, but not too fair :P
X = X.drop('category', axis=1)
X = X.drop('project', axis=1)
def SparseData(filename = 'data/drop_presence.npz'):
import sparse_manip
data = sparse_manip.load(filename)
return data
