def test():
## Main functions to be used
def sim_prediction_bin(n, real, noise):
noise = noise*(np.random.random(n)-.5)*2
pred = real_cat+noise
pred = (pred-pred.min())/(pred.max()-pred.min())
return pred
def sim_prediction_cont(n, real, noise):
noise = noise*np.random.random(n)
pred = real_cat+noise
return pred
## Parameters
n, m_preds, noise = 1000, 10, .6
real_cat = np.random.randint(0, 2, n)
real_cont = np.random.random(n)
pred_cat = sim_prediction_bin(n, real_cat, noise)
preds_cat = [sim_prediction_bin(n, real_cat, noise)
for i in range(m_preds)]
pred_cont = sim_prediction_cont(n, real_cont, noise)
preds_cont = [sim_prediction_cont(n, real_cont, noise)
for i in range(m_preds)]
tags = ['prediction '+str(i) for i in range(m_preds)]
x, y = np.random.random(100), np.random.random(100)
G_x = nx.from_numpy_matrix(x.reshape((10, 10)))
G_y = nx.from_numpy_matrix(x.reshape((10, 10)) > 0.5)
Gs_x = [G_x for i in range(10)]
## Testing sorting measures
###########################
fpr, tpr, _ = roc_comparison(real_cat, pred_cat)
rocs = [roc_comparison(real_cat, preds_cat[i])
for i in range(m_preds)]
fprs = [rocs[i][0] for i in range(m_preds)]
tprs = [rocs[i][1] for i in range(m_preds)]
measures = np.random.random(len(rocs))
compute_lift_curve(real_cat, pred_cat, 10)
lift = compute_lift_curve(real_cont, pred_cont, 10)[1]
lifts = [compute_lift_curve(real_cat, preds_cat[i], 10)[1]
for i in range(m_preds)]
## Testing plotting
###################
fig = plot_roc_curves(fprs, tprs, measures, tags)
fig = plot_roc_curve(fpr, tpr, measures[0])
fig = plot_lift_curves(lifts, tags)
fig = plot_lift_curve(lift)
## Testing main computing funcitons
###################################
measures, fig = compute_measure(real_cat, pred_cat, metric="roc_curve",
create_plot=True, tags=['0'])
measures = compute_measure(real_cat, pred_cat, metric="roc_curve",
create_plot=False, tags=['0'])
measures, fig = compute_measure(real_cat, preds_cat, metric="roc_curve",
create_plot=True, tags=tags)
measures = compute_measure(real_cat, preds_cat, metric="roc_curve",
create_plot=False, tags=tags)
measures, fig = compute_measure(real_cat, pred_cat, metric="lift10",
create_plot=True, tags=['0'])
measures = compute_measure(real_cat, pred_cat, metric="lift10",
create_plot=False, tags=['0'])
measures, fig = compute_measure(real_cat, preds_cat, metric="lift10",
create_plot=True, tags=tags)
measures = compute_measure(real_cat, preds_cat, metric="lift10",
create_plot=True, tags=tags)
########
names = ['network inferred '+str(i) for i in range(10)]
measure, fig = network_roc_comparison(G_x, G_y)
measure, fig = network_roc_comparison(G_x, G_y, names)
measure, fig = network_roc_comparison(Gs_x, G_y, ['network inferred 0'])
def compute_measure(real, pred, metric="roc_curve", create_plot=True,
tags=None):
"""This function compute some given measures of fit of the given real
labels (real) and the predicted labels (pred).
Parameters
----------
real: array_like, shape (N,)
labels of correct real values.
pred: array_like, shape (N,), list of arrays.
predicted labels.
metric: str, optional
metric used to check how good is the prediction.
There are available roc_curve, and lift10.
tags: list
the tags assigned for the possible predictions we are going to test.
Returns
-------
measures: float
the measure of divergence between both
fig : matplotlib figure
the plot of related to the measure.
Examples
--------
>>> real = np.random.randint(0,2,50)
>>> pred = np.random.rand(50)
>>> measure, fig = compute_measure(real, pred, "roc_curve")
>>> measure
[0.6]
>>> measure, fig = compute_measure(real, pred, "lift10")
>>> measure
[1.7]
>>> measure = compute_measure(real, pred, "lift10", False)
See also
--------
sklearn.metrics.roc_curve, compute_lift_curve,
pythonUtils.TesterResults.plotting_testerresults.plot_roc_curve ,
pythonUtils.TesterResults.plotting_testerresults.plot_lift_curve
"""
multiple = type(pred) == list
# ROC measure
if metric == 'roc_curve':
if not multiple:
# Compute the measure of ROC curve
# fpr, tpr, thresholds = roc_curve(real, pred)
# # numerical measure
# measure = auc(fpr, tpr)
fpr, tpr, measure = roc_comparison(real, pred)
fprs, tprs, measures = [fpr], [tpr], [measure]
else:
assert(len(pred) == len(tags))
fprs, tprs, measures = [], [], []
for i in range(len(pred)):
# # Compute the measure of ROC curve
# fpr, tpr, thresholds = roc_curve(real, pred[i])
# # numerical measure
# measure = auc(fpr, tpr)
fpr, tpr, measure = roc_comparison(real, pred[i])
# Appending
fprs.append(fpr)
tprs.append(tpr)
measures.append(measure)
assert(len(measures) == len(pred))
# Plot: Handle this plot.
if create_plot:
# Call for the plot
fig = plot_roc_curves(fprs, tprs, measures, tags)
else:
return measures
# LIFT 10 MEASURE
elif metric == 'lift10':
if not multiple:
# Compute lift10 curve
_, lift10, _ = compute_lift_curve(real, pred, 10)
# numerical measure
lift10 = [lift10]
measure = [lift10[0]/lift10[-1]]
else:
assert(len(pred) == len(tags))
lift10, measures = [], []
for i in range(len(pred)):
# Compute lift10 curve
_, lift10i, _ = compute_lift_curve(real, pred[i], 10)
# numerical measure
measure = lift10i[0]/lift10i[-1]
# appending
lift10.append(lift10i)
measures.append(measure)
# Plot
if create_plot:
fig = plot_lift_curves(lift10, tags)
else:
return measure
return measure, fig