rmitsch

import numpy
import scipy
import scipy.io.arff
import sklearn.feature_selection as skfs
from sklearn.cluster import KMeans
from sklearn.metrics.cluster import normalized_mutual_info_score


def arff_to_ndarray(path_to_arff_file):
    """

rmitsch

"""
Exercise 3-1 for course Data Mining at University of Vienna, winter semester 2017.
Note that this code implementing some definitions for PreDeCon serves demonstration purposes and is not optimized for
performance.
"""

import numpy
import math

rmitsch

import sys
import numpy as np
import matplotlib.pyplot as plt
from numpy.linalg import eigh
import math

# reading csv Data into a File
def read_data(file):
    f = open( file, 'r')
    data = []

rmitsch

import sys
import numpy
import matplotlib.pyplot as plt


def apply_hough_transformation(data, num_dims, alpha_values):
    """
    Maps data points to parameter functions.
    :param data:
    :param num_dims:

rmitsch

rmitsch

rmitsch

from pyspark import SparkConf
from pyspark import SparkContext
import numpy.random as rnd
import numpy as np
import os

# os.environ["SPARK_HOME"] = "/usr/local/Cellar/apache-spark/1.5.1/"
os.environ["PYSPARK_PYTHON"] = "/home/raphael/Development/datamining/py3env/bin/python3"

rmitsch

high_dim_data = [
  [ 0.          3.49753522  3.02660794  2.84250465  3.56685389  2.52528988
   2.55323161  2.40778388  2.96434891  2.54889821  2.77240632  3.4098677
   3.37132917  3.88512522  3.4479446   3.07118824  2.72022264  3.0514949
   3.55990871  2.49992525  1.28789316  3.64068884  2.43015883  3.49005344
   3.28969545  4.90884015  3.35593523  3.94372099  2.94004997  2.60276568
   3.61007435  3.02692458  3.00512055  3.41895422  3.0188693   2.81568659
   3.37344153  3.79362238  3.87271647  2.6809203   1.8798772   4.29976882
   2.70462412  3.88317653  2.75354735  3.38018601  2.72213461  2.5788172
   2.61540864  2.62093943  3.97909614  2.92664878  2.69721918  2.71499576

rmitsch

apt-get install mysql-server