def test(data): print 'data_range(data, data.get_headers())' print data_range(data, data.get_headers()) print 'mean(data, data.get_headers())' print mean(data, data.get_headers()) print 'stdev(data, data.get_headers())' print stdev(data, data.get_headers()) print 'normalize_columns_together(data, data.get_headers())' print normalize_columns_together(data, data.get_headers())
def __init__(self, parent, data):
Dialog.__init__(self,parent)
self.result=[]
self.size = ["6"]
self.color=["black"]
self.headers = data.get_headers()
self.dep_list = None
self.ind_list = None
def stdev(data, headers=[]):
list = []
if headers == []:
for header in data.get_headers():
headers.append(header)
for header in headers:
col_index = data.header2matrix[header]
list.append(data.matrix_data[:, col_index].std(ddof=1))
return list
def mean(data, headers=[]):
list = []
if headers == []:
for header in data.get_headers():
headers.append(header)
for header in headers:
col_index = data.header2matrix[header]
list.append(data.matrix_data[:, col_index].mean(0).tolist()[0][0])
return list
def __init__(self, parent, data): print "within dialog box" self.selectVal = 0 self.shapeVal = 0 self.numDataPoints = 10 self.datacols = [] self.headerXVal = 0 self.headerYVal = 0 self.headerZVal = 0 self.headers = data.get_headers() self.colorSelect = None Dialog.__init__(self, parent)
def normalize_columns_separately(data, headers=[]):
if headers == []:
headers = data.get_headers()
list = data_range(data, headers)
m = data.get_data(headers)
new = m.copy()
for i in range(m.shape[0]):
for j in range(m.shape[1]):
new[i, j] = (m[i, j] - list[j][0]) / (list[j][1] - list[j][0])
return new
def data_range(data, headers=[]):
list = []
if headers == []:
for header in data.get_headers():
headers.append(header)
for header in headers:
col_index = data.header2matrix[header]
list.append([
data.matrix_data[:, col_index].min(0).tolist()[0][0],
data.matrix_data[:, col_index].max(0).tolist()[0][0]
])
return list
def normalize_columns_together(data, headers=[]):
if headers == []:
headers = data.get_headers()
m = data.get_data(headers)
min = m.min()
max = m.max()
new = m.copy()
for i in range(m.shape[0]):
for j in range(m.shape[1]):
new[i, j] = (m[i, j] - min) / (max - min)
return new
def write(self, filename):
'''Writes the Bayes classifier to a file.'''
fp = open(filename, 'w')
for i in data.get_headers():
fp.write(i + ",")
fp.write("\n")
for i in range(len(self.headers)):
fp.write("numeric,")
fp.write("\n")
for k in range(data.self.headers.shape[0]):
for i in range(len(self.headers)):
fp.write(str(data[k, i]) + ",")
fp.write("\n")
return
def __init__(self, parent, data):
self.headers = data.get_headers()
self.name = tk.StringVar(parent, value='') #number of clusters
self.Cluster_box = None
Dialog.__init__(self, parent, 'K-Means Clustering')
def __init__(self, parent, data):
self.eheaders = data.get_headers()
self.PCA_box = None
Dialog.__init__(self, parent, 'PCA')
def __init__(self, parent, data):
self.evectors = data.get_eigenvectors()
self.evalues = data.get_eigenvalues() #convert from np array to python list
self.headers = data.get_headers()
self.eheaders = data.get_original_headers()
Dialog.__init__(self, parent, 'PCA')
def __init__(self, parent, data):
self.headers = data.get_headers()
self.check = tk.IntVar(parent, value=0) # whether data should be normalized
self.name = tk.StringVar(parent, value='')
self.PCA_box = None
Dialog.__init__(self, parent, 'PCA')
def __init__(self,parent,data):
self.headers = data.get_headers()
self.DV_list = None
self.IV_list = None
Dialog.__init__(self, parent, 'Choose variables for Regression')
def __init__(self,parent,data):
self.headers = data.get_headers()
Dialog.__init__(self,parent,'Choose Axes')
# CS 251 Project 6
#
# PCA test function
#
import numpy as np
import data
import analysis
import sys
if __name__ == "__main__":
if len(sys.argv) < 2:
print 'Usage: python %s <data file>' % (sys.argv[0])
exit()
data = data.Data(sys.argv[1])
analysisObj = analysis.Analysis()
pcadata = analysisObj.pca(data, data.get_headers(), False)
print "\nOriginal Data Headers"
print pcadata.get_data_headers()
print "\nOriginal Data",
print data.get_data(data.get_headers(), data.get_num_rows())
print "\nOriginal Data Means"
print pcadata.get_data_means()
print "\nEigenvalues"
print pcadata.get_eigenvalues()
print "\nEigenvectors"
print pcadata.get_eigenvectors()
print "\nProjected Data"
print pcadata.get_data(pcadata.get_headers(), data.get_num_rows())
# Spring 2015
# CS 251 Project 6
#
# PCA test function
#
import numpy as np
import data
import analysis
import sys
if __name__ == "__main__":
if len(sys.argv) < 2:
print 'Usage: python %s <data file>' % (sys.argv[0])
exit()
data = data.Data(sys.argv[1])
pcadata = analysis.pca(data, data.get_headers(), False)
print "\nOriginal Data Headers"
print pcadata.get_data_headers()
print "\nOriginal Data",
print data.get_data(data.get_headers())
print "\nOriginal Data Means"
print pcadata.get_data_means()
print "\nEigenvalues"
print pcadata.get_eigenvalues()
print "\nEigenvectors"
print pcadata.get_eigenvectors()
print "\nProjected Data"
print pcadata.get_data(pcadata.get_headers())
# Updated for python3
# CS 251 Project 6
#
# PCA test function
#
import numpy as np
import data
import analysis
import sys
if __name__ == "__main__":
if len(sys.argv) < 2:
print('Usage: python %s <data file>' % (sys.argv[0]))
exit()
data = data.Data(sys.argv[1])
pcadata = analysis.pca(data, data.get_headers(), False)
print("\nOriginal Data Headers")
print(pcadata.get_original_headers())
print("\nOriginal Data")
print(data.get_matrix(data.get_headers()))
print("\nOriginal Data Means")
print(pcadata.get_original_means())
print("\nEigenvalues")
print(pcadata.get_eigenvalues())
print("\nEigenvectors")
print(pcadata.get_eigenvectors())
print("\nProjected Data")
print(pcadata.get_matrix(pcadata.get_headers()))
from data import TRAINING_DATA_1, get_headers
from matplotlib import pyplot
#Get all headers and removes the datetime column.
columns = get_headers()
columns = columns[1:]
#Creates a plot for all column for the first 300 values
for column in columns:
column_data = TRAINING_DATA_1[column]
values = column_data.values
plot_values = [x for x in values[:300]]
pyplot.plot(plot_values)
pyplot.ylabel(column)
pyplot.xlabel("index")
pyplot.savefig("cyclic/%s" % column)
pyplot.cla()
def __init__(self, parent, data):
self.cheaders = data.get_headers()
self.Cluster_box = None
Dialog.__init__(self, parent, 'Clustering')
# Spring 2015
# CS 251 Project 6
#
# PCA test function
#
import numpy as np
import data
import analysis
import sys
if __name__ == "__main__":
if len(sys.argv) < 2:
print('Usage: python %s <data file>' % (sys.argv[0]))
exit()
data = data.Data( sys.argv[1] )
pcadata = analysis.pca( data, data.get_headers(), False )
print("\nOriginal Data Headers")
print(pcadata.get_data_headers())
print("\nOriginal Data")
print(data.get_data( data.get_headers() ))
print("\nOriginal Data Means")
print(pcadata.get_data_means())
print("\nEigenvalues")
print(pcadata.get_eigenvalues())
print("\nEigenvectors")
print(pcadata.get_eigenvectors())
print("\nProjected Data")
print(pcadata.get_data(pcadata.get_headers()))
# CS 251 Project 6
#
# PCA test function
#
import numpy as np
import data
import analysis
import sys
# import pcadata
if __name__ == "__main__":
if len(sys.argv) < 2:
print('Usage: python %s <data file>' % (sys.argv[0]))
exit()
data = data.Data(sys.argv[1])
pcadata = analysis.pca(data, data.get_headers(), False)
print("\nOriginal Data Headers")
print(pcadata.get_original_headers())
print("\nOriginal Data")
print(data.limit_columns(data.get_headers()))
print("\nOriginal Data Means")
print(pcadata.get_original_means())
print("\nEigenvalues")
print(pcadata.get_eigenvalues())
print("\nEigenvectors")
print(pcadata.get_eigenvectors())
print("\nProjected Data")
print(pcadata.limit_columns(pcadata.get_headers()))
