def getPCAProjections(input_filename):
""" Run PCA on the Kushmerick ad data
Stop when there are sufficient PCA components to explain threshold_variance
Project input data onto the top PCA components that explain threshold_variance
Normalize this data
Sort attributes by their correlation with output
- input_filename : prepocessed data
- Output 'pca': data projected onto PCA components
'norm': pca data normalized to std deviation 1
'corr': normalized data sorted by correlation with output
'index':
"""
print 'getPCAProjections:', input_filename
explained_variance = 0.99
root_name = 'pca%03d' % round(explained_variance * 100.0)
pca_filename = csv.makeCsvPath(root_name)
pca_norm_filename = csv.makeCsvPath(root_name + '.norm')
pca_norm_corr_filename = csv.makeCsvPath(root_name + '.norm.corr')
corr_index_filename = csv.makeCsvPath(root_name + '.corr.idx')
pca.pcaAdData(explained_variance, input_filename, pca_filename)
pca.normalizeData(pca_filename, pca_norm_filename)
sort_order, corr_index = pca.rankByCorrelationWithOutcomes(pca_norm_filename)
def reorder(in_cells):
return pca.reorderMatrix(in_cells, sort_order)
csv.modifyCsvRaw(pca_norm_filename, pca_norm_corr_filename, reorder)
csv.writeCsv(corr_index_filename, corr_index)
return {'pca': pca_filename, 'norm':pca_norm_filename, 'corr':pca_norm_corr_filename, 'index':corr_index_filename}
def selectAttibutesGA():
matrix = csv.readCsvRaw(csv.headered_name_pca_corr)
num_attributes = len(matrix[0])-1
if False:
num_subset = 5
num_trials = max(100, num_attributes*2)
results = findBestOfSize(matrix, num_subset, num_trials)
order = orderByResults(results,num_attributes)
if True:
sort_order = [i for i in range(num_attributes)]
for num_subset in range(5, num_attributes, 5):
num_trials = max(100, num_attributes*2)
csv_matrix_name = csv.makeCsvPath('subset.matrix' +('%03d'%num_subset))
csv_results_name = csv.makePath('subset.results'+('%03d'%num_subset))
csv_best_name = csv.makeCsvPath('subset.best' +('%03d'%num_subset))
csv_summary_name = csv.makeCsvPath('subset.summary'+('%03d'%num_subset))
ordered_matrix = pca.reorderMatrix(matrix, sort_order)
csv.writeCsv(csv_matrix_name, ordered_matrix)
results = findBestOfSize(ordered_matrix, num_subset, num_trials, csv_summary_name)
sort_order = orderByResults(results,num_attributes)
#c_x = results[0].columns + [-1] # include outcome
#sub_matrix = [[row[i] for i in c_x] for row in ordered_matrix]
#csv.writeCsv(csv_best_name,sub_matrix, )
if not is_testing:
shutil.copyfile(results[0]['csv'],csv_best_name)
shutil.copyfile(results[0]['results'],csv_results_name)
def testBySize(incrementing_hidden):
"Test MLP results on matrix by number of left side columns"
start_num_columns = 30
delta_num_columns = 10
opts = '-M 0.5 -L 0.3 -x 4 -H '
num_hidden = 13
csv_matrix_name = csv.makeCsvPath('subset.matrix035')
base_name = 'number.attributes'
if incrementing_hidden:
base_name = base_name + '.inc'
csv_results_name = csv.makePath(base_name + '.results')
csv_summary_name = csv.makeCsvPath(base_name + '.summary')
csv_best_name = csv.makeCsvPath(base_name + '.best')
matrix = csv.readCsvRaw(csv_matrix_name)
num_attribs = len(matrix[0])-1 # last column is category
print 'testBySize', len(matrix), start_num_columns, delta_num_columns, len(matrix[0])
best_accuracy = 0.0
summary = []
csv_summary = file(csv_summary_name, 'w')
for num_columns in range(start_num_columns, len(matrix[0]), delta_num_columns):
columns = [i for i in range(num_columns)]
if incrementing_hidden:
num_hidden = int(float(num_columns)*13.0/30.0)
accuracy, temp_csv, temp_results, duration = testMatrixMLP(matrix, columns, opts + str(num_hidden))
r = {'num':num_columns, 'accuracy':accuracy, 'csv':temp_csv, 'results':temp_results, 'duration':duration}
summary.append(r)
summary.sort(key = lambda r: -r['accuracy'])
if True:
print num_columns, ':', accuracy, len(results), int(duration), 'seconds'
for i in range(min(3,len(results))):
rr = results[i]
print ' ',i, ':', rr['accuracy'], rr['num'], int(rr['duration'])
summary_row = [num_columns, accuracy, duration, temp_csv, temp_results]
csv_line = ','.join([str(e) for e in summary_row])
csv_summary.write(csv_line + '\n')
csv_summary.flush()
if accuracy > best_accuracy:
best_accuracy = accuracy
shutil.copyfile(temp_csv, csv_best_name)
shutil.copyfile(temp_results, csv_results_name)
return results
def testByNumberHidden(csv_matrix_name, output_basename, num_columns, num_cv = 4):
"""Test MLP results on matrix by number of neurons in hidden layer
num_columns is number of leftmost columns of matrix to test
num_cv is the number of cross-validation rounds
"""
start_num_hidden = min(10, num_columns-1)
delta_num_hidden = 10
results_name = csv.makePath(output_basename + '.results')
model_name = csv.makePath(output_basename + '.model')
csv_summary_name = csv.makeCsvPath(output_basename + '.summary')
csv_best_name = csv.makeCsvPath(output_basename + '.best')
matrix = csv.readCsvRaw(csv_matrix_name)
num_attribs = len(matrix[0])-1 # last column is category
print 'testByNumberHidden', len(matrix), start_num_hidden, delta_num_hidden, num_columns
best_accuracy = 0.0
results = []
csv_summary = file(csv_summary_name, 'w')
for num_hidden in range(start_num_hidden, num_columns, delta_num_hidden):
columns = [i for i in range(num_columns)]
accuracy, temp_csv, temp_results, duration = testMatrixMLP(matrix, columns, makeWekaOptions(0.3, 0.5, num_hidden, num_cv))
r = {'num':num_hidden, 'accuracy':accuracy, 'csv':temp_csv, 'results':temp_results, 'duration':duration}
results.append(r)
results.sort(key = lambda r: -r['accuracy'])
if True:
print num_hidden, ':', accuracy, len(results), int(duration), 'seconds'
for i in range(min(5,len(results))):
rr = results[i]
print ' ',i, ':', rr['accuracy'], rr['num'], int(rr['duration'])
summary = [num_hidden, accuracy, duration, temp_csv, temp_results]
csv_line = ','.join([str(e) for e in summary])
csv_summary.write(csv_line + '\n')
csv_summary.flush()
if accuracy > best_accuracy:
best_accuracy = accuracy
shutil.copyfile(temp_csv, csv_best_name)
shutil.copyfile(temp_results, results_name)
shutil.copyfile(outnameToModelname(temp_results), model_name)
return {'summary':csv_summary_name, 'best':csv_best_name, 'results':results_name, 'model':model_name}
def testCostMatrix(num_columns, num_cv = 4):
"""Test MLP results with a range of false positive costs
"""
num_hidden = 5
csv_matrix_name = csv.makeCsvPath('subset.matrix035')
base_name = 'cost.col' + str(num_columns) + '.x' + str(num_cv)
csv_results_name = csv.makePath(base_name + '.results')
csv_summary_name = csv.makeCsvPath(base_name + '.summary')
csv_best_name = csv.makeCsvPath(base_name + '.best')
matrix = csv.readCsvRaw(csv_matrix_name)
num_attribs = len(matrix[0])-1 # last column is category
print 'testCostMatrix', len(matrix), num_hidden, num_columns
best_accuracy = 0.0
results = []
csv_results = file(csv_summary_name, 'w')
for false_positive_cost in range(1, 11, 2):
columns = [i for i in range(num_columns)]
costs_map = {'True':1.0, 'False':float(false_positive_cost)}
accuracy, temp_csv, temp_results, duration = testMatrixMLP(matrix, columns, makeWekaOptions(0.3, 0.5, num_hidden, num_cv, costs_map))
r = {'cost':false_positive_cost, 'accuracy':accuracy, 'csv':temp_csv, 'results':temp_results, 'duration':duration}
results.append(r)
results.sort(key = lambda r: -r['accuracy'])
if True:
print false_positive_cost, ':', accuracy, len(results), int(duration), 'seconds'
for i in range(min(5,len(results))):
rr = results[i]
print ' ',i, ':', rr['accuracy'], rr['cost'], int(rr['duration'])
summary = [num_hidden, accuracy, duration, temp_csv, temp_results]
csv_line = ','.join([str(e) for e in summary])
csv_results.write(csv_line + '\n')
csv_results.flush()
if accuracy > best_accuracy:
best_accuracy = accuracy
shutil.copyfile(temp_csv, csv_best_name)
shutil.copyfile(temp_results, csv_results_name)
return results
csv_line = ','.join([str(e) for e in summary])
csv_results.write(csv_line + '\n')
csv_results.flush()
if accuracy > best_accuracy:
best_accuracy = accuracy
shutil.copyfile(temp_csv, csv_best_name)
shutil.copyfile(temp_results, csv_results_name)
return results
#
#
# Data files used in this test
# Input data - Don't touch this
raw_name = csv.makeCsvPath('ad1')
# Input data with header. Needs to be generated once
headered_name = csv.makeCsvPath('header')
#Input data with header and pre-processing
headered_name_pp = csv.makeCsvPath('header.pp')
# PCA on headered_name_pp
#headered_name_pca = csv.makePath('header.pp.pca')
# PCA data normalized to stdev == 1
#headered_name_pca_norm = csv.makePath('header.pp.pca.norm')
# PCA data normalized to stdev == 1 by correlation with outcome
#headered_name_pca_corr = csv.makePath('header.pp.pca.norm.corr_order')
if __name__ == '__main__':
if False:
dumpEnv()
if __name__=='__main__':
describe(numpy)
describe(scipy)
describe(mdp)
describe(bimdp)
if False:
covTest()
#doTests()
explained_variance = 0.99
ev = str(int(explained_variance*100.0))
# pca_filename = csv.headered_name_pca
pca_filename = csv.makeCsvPath('pca' + ev)
#pca_norm_filename = csv.headered_name_pca_norm
pca_norm_filename = csv.makeCsvPath('pca' + ev + '.norm')
#pca_norm_corr_filename = csv.headered_name_pca_corr
pca_norm_corr_filename = csv.makeCsvPath('pca' + ev + '.norm.corr')
if True:
pcaAdData(explained_variance, csv.headered_name_pp, pca_filename)
if True:
normalizeData(pca_filename, pca_norm_filename)
if True:
sort_order = rankByCorrelationWithOutcomes(pca_norm_filename)
def reorder(in_cells):
return reorderMatrix(in_cells, sort_order)
