urban/data_mining_algorithms
1
0
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity

General Bugfixes

Browse Source 
- Rewrote certain numGen functions
- Removed ++ functions
This commit is contained in:
Conrad
2018-06-05 16:58:05 +02:00
parent 667e7881cc
commit 54f81b2291
4 changed files with 26 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
src/algorithms/dmlib.py
View File

@@ -1,27 +1,26 @@
# Calculate the difference between two points giving the indexes of these xdata entries
import math
def calcdiff(point1, point2, data):
# Calculate the difference between two points giving the indexes of these xdata entries
def calcdiff(point1, point2):
if int(point2) > int(point1):
difference = int(point2) - int(point1)
else:
difference = int(point1) - int(point2)
# print("Datapoint: " + str(xdata[point1]) + " | Cluster: " + str(xdata[point2]) + " | Difference: " + str(difference))
return betrag(difference)
return difference
# Calculate the difference between two points in 2D space
def calcdiff2d(point1, point2):
point1 = [int(i) for i in point1]
point2 = [int(i) for i in point2]
difference = math.sqrt(((point2[0])-(point1[0]))**2+((point2[0])-(point1[0]))**2)
difference = math.sqrt(((point2[0]) - (point1[0])) ** 2 + ((point2[1]) - (point1[1])) ** 2)
return betrag(difference)
# Get the absolute value of a number and returns it as int
def betrag(number):
if number < 0:
number = int((-2 * number) / 2)
return number
# Determine the highest int value in an array and returns is as an int
def findHighest(data):
maximum = 0
@@ -29,21 +28,3 @@ def findHighest(data):
if int(data[i]) > maximum:
maximum = int(data[i])
return maximum
def pp_calcdiff(data, clusterpoint):
max_diff = 0
new_cluster = 0
for item in range(0,len(data)):
if calcdiff(data[item], clusterpoint) > max_diff:
max_diff = calcdiff(data[item], clusterpoint)
new_cluster = data[item]
return new_cluster
def pp_calcdiff_2(data, clusterpoint, clusterpoint_2):
max_diff = 0
new_cluster = 0
for item in range(0,len(data)):
if calcdiff(data[item], clusterpoint) + calcdiff(data[item], clusterpoint_2) > max_diff:
max_diff = calcdiff(data[item], clusterpoint)
new_cluster = data[item]
return new_cluster

55
src/algorithms/dmtest.py
View File

@@ -1,21 +1,21 @@
# For random generation of numbers import randint
from random import randint, shuffle
# Simple generator for test plzs (40-40-20 biased), returns 1D array of plzs
def plzGen(entries):
# Simple generator for test nums (40-40-20 biased), returns 1D array of nums
def numGenLight(entries, shuffle, num_lenght):
dataArray = []
plz_lenght = 5
for i in range(0, int(entries)):
if i < round(entries * 0.4):
plz = generateNumber(plz_lenght, 2)
num = generateNumber(num_lenght, 2)
elif i >= round(entries * 0.4) and i < round(entries * 0.6):
plz = generateNumber(plz_lenght, 9)
num = generateNumber(num_lenght, 9)
elif i >= round(entries * 0.6) and i < round(entries * 0.9):
plz = generateNumber(plz_lenght, 4)
num = generateNumber(num_lenght, 4)
else:
plz = generateNumber(plz_lenght, randint(0,9))
dataArray.append(plz)
shuffle(dataArray)
num = generateNumber(num_lenght, randint(0,9))
dataArray.append(num)
if shuffle:
shuffle(dataArray)
return dataArray
# Function for generating the content of one single row randomly
@@ -34,7 +34,7 @@ def writeFile(content, nameChunkStart, namePartStart):
file.write(content[w] + "\n")
# Function for generating 'entries'x int_lenght'-long numbers in 'clusters' clusters
def numGen(entries, cluster, int_lenght):
def numGen(entries, cluster, int_lenght, suffle_value):
dataArray = []
clusterArray = []
@@ -48,35 +48,8 @@ def numGen(entries, cluster, int_lenght):
else:
cluster_decider = randint(0, cluster - 1)
dataArray.append(generateNumber(int_lenght - 1, clusterArray[cluster_decider]))
shuffle(dataArray)
if suffle_value:
shuffle(dataArray)
return dataArray
# Simple generator for test plzs (40-40-20 biased), returns 1D array of plzs
def plzGenNS(entries):
dataArray = []
plz_lenght = 5
for i in range(0, int(entries)):
if i < round(entries * 0.4):
plz = generateNumber(plz_lenght, 2)
elif i >= round(entries * 0.4) and i < round(entries * 0.8):
plz = generateNumber(plz_lenght, 6)
else:
plz = generateNumber(plz_lenght, randint(0, 9))
dataArray.append(plz)
#i had to remove shuffle for the connectrion (age ==> plz) to work, else we would have 4 clusters
# shuffle(dataArray)
return dataArray #
def ageGenNS(entries):
dataArray = []
age_lenght = 2
for i in range(0, int(entries)):
if i < round(entries * 0.4):
age = generateNumber(age_lenght, 2)
elif i >= round(entries * 0.4) and i < round(entries * 0.8):
age = generateNumber(age_lenght, 5)
else:
age = generateNumber(age_lenght, randint(0, 9))
dataArray.append(age)
# shuffle(dataArray)
return dataArray

5
src/algorithms/kmeansMkI.py
View File

@@ -135,8 +135,5 @@ def startup(data):
print(str(seconds) + " seconds for execution")
# Start the algorithm and generate test data
# data = dmtest.plzGen(10000)
# data = dmtest.numGen(10000, 3, 5)
data = dmtest.numGen(10000, 8, 7)
data = dmtest.numGen(10000, 2, 5, True)
startup(data)

15
src/algorithms/kmeansMkI_2d.py
View File

@@ -31,8 +31,6 @@ import matplotlib.pyplot as plt
import dmlib
import dmtest
# CODE
# Main function of the algorithm
def kmeansmk1(xdata, ydata, clusters):
@@ -63,6 +61,7 @@ def kmeansmk1(xdata, ydata, clusters):
plt.plot(globals()["cpoint_" + str(i)][0], globals()["cpoint_" + str(i)][1], 'ro')
plt.scatter([int(x) for x in xdata], [int(y) for y in ydata], marker='x', s=7, color='k')
plt.show()
# Calculates middle values for each cluster, takes 2D array (item, assigned_cluster)
def calcClusters(xdata, ydata, assigned_points, clusters):
for cluster in range(0, clusters):
@@ -86,7 +85,6 @@ def calcClusters(xdata, ydata, assigned_points, clusters):
return cpointunchanged
def assignCluster(xdata, ydata, clusters, highpointx, highpointy):
data_assigned = []
assigned_cluster = 0
@@ -103,15 +101,13 @@ def assignCluster(xdata, ydata, clusters, highpointx, highpointy):
# print('cluster number ' + str(cluster) + ' assigned')
data_assigned.append(assigned_cluster)
# Add the assigned values list to the new_data array
#new_data.append(data_assigned)
# new_data.append(data_assigned)
return data_assigned
# Startup function for collecting necesarry xdata
def startup(xdata, ydata):
# Using two clusters for testing
clusters = int(input("How many clusters are known? (hint: 2) "))
clusters = int(input("How many clusters are known? "))
# cores = input("How many cores should be used? ")
# path = input("Where is the xdata? ") or in this case xdata
@@ -125,9 +121,8 @@ def startup(xdata, ydata):
seconds = time.time() - start_time
print(str(seconds) + " seconds for execution")
# Start the algorithm and generate test xdata
xdata = dmtest.plzGenNS(1000)
ydata = dmtest.ageGenNS(1000)
xdata = dmtest.numGenLight(10000, False, 5)
ydata = dmtest.numGenLight(10000, False, 2)
startup(xdata, ydata)