def pull_new_data(crossval_rate, pca, path=None):
from csxdata.frames import RData
from csxdata.utilities.parsers import parse_csv
if path is None:
from csxdata import roots
path = roots["csvs"] + "sum_ntab.csv"
X, _, header = parse_csv(path, headers=1, indeps=4, sep="\t", end="\n")
return RData((X[..., 2:], X[..., :2]), crossval_rate, indeps_n=0, header=0, pca=pca)
def pull_xy_data():
X, Y, header = parse_csv(roots["csvs"] + "sum_ntab2.csv", headers=1, indeps=7)
data = RData((X, Y[:, -2:].astype("float32")), cross_val=0.0, indeps_n=2, header=header)
data.transformation = PRETREAT
cities = Y[:, -3]
return data.table("learning"), cities
def get_data(path=None):
if path is None:
from tkinter import Tk
import tkinter.filedialog as tkfd
tk = Tk()
tk.withdraw()
path = tkfd.askopenfilename(title="Please open the csv containing the data!",
initialdir=csvroot)
tk.destroy()
return parse_csv(path, headers=1, indeps=1, sep="\t", end="\n")
def test_ica_on_etalon(self):
self.data.reset_data(shuff=False)
calcme = parse_csv(etalonroot + "ica.csv", dtype="float64")[0]
calcme = np.round(np.sort(np.abs(calcme.ravel())), 1)
self.data.transformation = "ica"
X = self.data.learning.astype("float64")
X = np.round(np.sort(np.abs(X.ravel())), 1)
self.assertEqual(self.data.transformation, "ica",
"The transformation property is faulty!")
self.assertTrue(np.allclose(X, calcme, rtol=1.e-4, atol=1.e-7),
"ICA is faulty!")
def test_lda_on_etalon(self):
self.data.reset_data(shuff=False)
calcme = parse_csv(etalonroot + "lda.csv", dtype="float64")[0]
calcme = np.round(np.sort(np.abs(calcme.ravel())), 1)
self.data.transformation = "lda"
X = self.data.learning.astype("float64")
X = np.round(np.sort(np.abs(X.ravel())), 1)
eq = np.isclose(X, calcme)
self.assertEqual(self.data.transformation, "lda",
"The transformation property is faulty!")
self.assertTrue(np.all(eq), "LDA is faulty!")
def test_standardization_on_etalon(self):
self.data.reset_data(shuff=False)
calcme = parse_csv(etalonroot + "std.csv", dtype="float64")[0]
calcme = np.sort(calcme.ravel())
self.data.transformation = "std"
X = np.round(self.data.learning.astype("float64"), 3)
X = np.sort(X.ravel())
self.assertEqual(self.data.transformation, "std",
"The transformation property is faulty!")
self.assertTrue(np.all(np.equal(X, calcme)),
"Standardization is faulty!")
def setUp(self):
self.X_, self.y_, headers = parse_csv(etalonroot + "/input.csv")
self.data = CData((self.X_, self.y_), cross_val=0)