def main(datafile):
print("\nFile: " + datafile)
data = read_data_file(datafile, separator=',')
# data is now a python listlist of strings
# remove headers and convert to numpy
data = np.array(data[1:])
# read headers
column_map = parse_headers_in_file(datafile)
#Now report on missing data
print("{:20s} : {:5s} percentage".format("Covariate", "num"))
for var, col in column_map.iteritems():
missing = len(data[:, col][data[:, col] == ''])
print("{:20s} : {:5s} {:.2f}%".format(var, str(missing), 100*missing/len(data[:, col])))
def main(datafile):
print("\nFile: " + datafile)
data = read_data_file(datafile, separator=',')
# data is now a python listlist of strings
# remove headers and convert to numpy
data = np.array(data[1:])
# read headers
column_map = parse_headers_in_file(datafile)
#Now report on missing data
print("{:20s} : {:5s} percentage".format("Covariate", "num"))
for var, col in column_map.iteritems():
missing = len(data[:, col][data[:, col] == ''])
print("{:20s} : {:5s} {:.2f}%".format(
var, str(missing), 100 * missing / len(data[:, col])))
def scatterplot_files(targetfile, targetcol, eventcol, modelfile,
modeloutputcol, **kwargs):
'''
scatterplot_files(targetfile, targetcol, eventcol, modelfile, modeloutputcol)
Takes two files because the target data and model data is allowed to be in different files.
Events are ONLY taken from target data.
Writes two files:
scatter_cens_targetfile_modelfile.eps
scatter_nocens_targetfile_modelfile.eps
'''
#Calculate suitable size for the figure for use in LaTEX
fig_width_pt = 396.0 # Get this from LaTeX using \showthe\columnwidth
inches_per_pt = 1.0 / 72.27 # Convert pt to inch
golden_mean = (sqrt(5) - 1.0) / 2.0 # Aesthetic ratio
fig_width = fig_width_pt * inches_per_pt # width in inches
fig_height = fig_width * golden_mean # height in inches
fig_size = [fig_width, fig_height]
#Update settings
plt.rcParams['figure.figsize'] = fig_size
#params = {'axes.labelsize': 10,
# 'text.fontsize': 10,
# 'legend.fontsize': 10,
# 'xtick.labelsize': 8,
# 'ytick.labelsize': 8,
#'text.usetex': True,
# 'figure.figsize': fig_size}
#plt.rcParams.update(params)
# with open(targetfile, 'r') as f:
# X_in = [line.split() for line in f.readlines()]
# X_in = numpy.array(X_in)
# X = X_in[1:, first_col]
# X = numpy.array(X, dtype = 'float')
data = np.array(read_data_file(targetfile, ","))
T, t = parse_data(data,
inputcols=(targetcol, eventcol),
ignorerows=[0],
normalize=False)
X = T[:, 0]
events = T[:, 1]
# with open(modeloutputcol, 'r') as f:
# Y_in = [line.split() for line in f.readlines()]
#
# Y_in = numpy.array(Y_in)
# Y = Y_in[1:, second_col]
# Y = numpy.array(Y, dtype = 'float')
data = np.array(read_data_file(modelfile, ","))
D, t = parse_data(data,
inputcols=[modeloutputcol],
ignorerows=[0],
normalize=False)
Y = D[:, 0]
# if event_col is not None:
# events = X_in[1:, event_col]
# events = numpy.array(events, dtype = 'float')
# print 'Using events'
# else:
# events = None
# T = numpy.empty((len(X), 2), dtype='float')
# T[:, 0] = X
# T[:, 1] = events
outputs = np.empty((len(X), 2), dtype='float')
outputs[:, 0] = Y
outputs[:, 1] = events
c_index = get_C_index(T, outputs)
print("C-Index between these files is: {0}".format(c_index))
scatter(X,
Y,
events=events,
x_label='Targets',
y_label='Model output',
gridsize=30,
mincnt=0,
show_plot=False)
#plt.xlabel(os.path.basename(sys.argv[1]) + "\nC-Index between these files is: {0}".format(c_index))
#plt.ylabel('Correlation of ' + os.path.basename(sys.argv[2]))
plt.savefig('scatter_cens_cind_{cindex}_{0}_{1}.eps'.format(
os.path.splitext(os.path.basename(modelfile))[0],
os.path.splitext(os.path.basename(targetfile))[0],
cindex=c_index))
scatter(X,
Y,
x_label='Targets',
y_label='Model output',
gridsize=30,
mincnt=0,
show_plot=False)
#plt.xlabel(os.path.basename(sys.argv[1]) + "\nC-Index between these files is: {0}".format(c_index))
#plt.ylabel('Correlation of ' + os.path.basename(sys.argv[2]))
plt.savefig('scatter_nocens_{cindex}_{0}_{1}.eps'.format(
os.path.splitext(os.path.basename(modelfile))[0],
os.path.splitext(os.path.basename(targetfile))[0],
cindex=c_index))
def scatterplot_files(targetfile, targetcol, eventcol, modelfile, modeloutputcol, **kwargs):
'''
scatterplot_files(targetfile, targetcol, eventcol, modelfile, modeloutputcol)
Takes two files because the target data and model data is allowed to be in different files.
Events are ONLY taken from target data.
Writes two files:
scatter_cens_targetfile_modelfile.eps
scatter_nocens_targetfile_modelfile.eps
'''
#Calculate suitable size for the figure for use in LaTEX
fig_width_pt = 396.0 # Get this from LaTeX using \showthe\columnwidth
inches_per_pt = 1.0/72.27 # Convert pt to inch
golden_mean = (sqrt(5)-1.0)/2.0 # Aesthetic ratio
fig_width = fig_width_pt*inches_per_pt # width in inches
fig_height = fig_width*golden_mean # height in inches
fig_size = [fig_width,fig_height]
#Update settings
plt.rcParams['figure.figsize'] = fig_size
#params = {'axes.labelsize': 10,
# 'text.fontsize': 10,
# 'legend.fontsize': 10,
# 'xtick.labelsize': 8,
# 'ytick.labelsize': 8,
#'text.usetex': True,
# 'figure.figsize': fig_size}
#plt.rcParams.update(params)
# with open(targetfile, 'r') as f:
# X_in = [line.split() for line in f.readlines()]
# X_in = numpy.array(X_in)
# X = X_in[1:, first_col]
# X = numpy.array(X, dtype = 'float')
data = np.array(read_data_file(targetfile, ","))
T, t = parse_data(data, inputcols = (targetcol, eventcol), ignorerows = [0], normalize = False)
X = T[:, 0]
events = T[:, 1]
# with open(modeloutputcol, 'r') as f:
# Y_in = [line.split() for line in f.readlines()]
#
# Y_in = numpy.array(Y_in)
# Y = Y_in[1:, second_col]
# Y = numpy.array(Y, dtype = 'float')
data = np.array(read_data_file(modelfile, ","))
D, t = parse_data(data, inputcols = [modeloutputcol], ignorerows = [0], normalize = False)
Y = D[:, 0]
# if event_col is not None:
# events = X_in[1:, event_col]
# events = numpy.array(events, dtype = 'float')
# print 'Using events'
# else:
# events = None
# T = numpy.empty((len(X), 2), dtype='float')
# T[:, 0] = X
# T[:, 1] = events
outputs = np.empty((len(X), 2), dtype='float')
outputs[:, 0 ] = Y
outputs[:, 1] = events
c_index = get_C_index(T, outputs)
print("C-Index between these files is: {0}".format(c_index))
scatter(X, Y, events = events,
x_label = 'Targets',
y_label = 'Model output',
gridsize = 30, mincnt = 0, show_plot = False)
#plt.xlabel(os.path.basename(sys.argv[1]) + "\nC-Index between these files is: {0}".format(c_index))
#plt.ylabel('Correlation of ' + os.path.basename(sys.argv[2]))
plt.savefig('scatter_cens_cind_{cindex}_{0}_{1}.eps'.format(os.path.splitext(os.path.basename(modelfile))[0],
os.path.splitext(os.path.basename(targetfile))[0],
cindex=c_index))
scatter(X, Y,
x_label = 'Targets',
y_label = 'Model output',
gridsize = 30, mincnt = 0, show_plot = False)
#plt.xlabel(os.path.basename(sys.argv[1]) + "\nC-Index between these files is: {0}".format(c_index))
#plt.ylabel('Correlation of ' + os.path.basename(sys.argv[2]))
plt.savefig('scatter_nocens_{cindex}_{0}_{1}.eps'.format(os.path.splitext(os.path.basename(modelfile))[0],
os.path.splitext(os.path.basename(targetfile))[0],
cindex=c_index))
cb.set_label('log10(N)')
if plotSlope:
ax.plot(sorted_x_y[:, 0], slope*sorted_x_y[:, 0] + cut, 'r-') #Print slope
#ax.scatter(sorted_x_y[:, 0], sorted_x_y[:, 1], c='g')
ax.set_xlabel(x_label)
ax.set_ylabel(y_label)
ax.set_title(title)
if axWasNone and show_plot:
show()
if __name__ == '__main__':
import sys
if len(sys.argv) < 2:
#filename = "/home/gibson/jonask/Projects/Kaplan-Meier/genetic.csv"
#filename = "/home/gibson/jonask/Projects/Kaplan-Meier/censored_3node.csv"
#filename = "/home/gibson/jonask/Projects/Experiments/src/cox_com_3tanh_output"
filename = "/home/gibson/jonask/Dropbox/Ann-Survival-Phd/publication_data/ann/" + \
".test_.15_tanh_1323233958_Two_thirds_of_the_n4369_dataset_with_logs_lymf_5YEAR.cvs"
else:
filename = sys.argv[1]
data = np.array(read_data_file(filename, "\t"))
D, t = parse_data(data, inputcols = (0, 1, 2), ignorerows = [0], normalize = False)
kaplanmeier(D, 0, 2, 1, show_plot = False)
scatter(D[:, 0], D[:, 1], D[:, 2], x_label = 'Target Data', y_label = 'Model Correlation', show_plot = False)
scatter(D[:, 0], D[:, 1], x_label = 'Target Data', y_label = 'Model Output')
