def updateWindow(self, win, cm, cvscores, Y, title):
f = win.gcf()
f.clear()
ax = f.add_subplot(111)
DataGuru.plot_confusion_matrix(cm, np.unique(Y), ax, title="confusion matrix")
ax.set_title(title)
win.show()
def evaluate(self, data_frame, classifier_model):
"""
Run a trained classifier on multiple arrays
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
# Get the data frame
sns.set(color_codes=True)
#command_status, df, kl1, _ = DataGuru.transformArray_to_dataFrame(array_datas)
df = data_frame.data
# if command_status == CommandStatus.Error:
# return ResultObject(None, None, None, CommandStatus.Error)
if StatContainer.ground_truth is None:
Printer.Print("Please set a feature vector to ground truth by",
"typing set ground truth to",
"to get the prediction accuracy")
result_object = ResultObject(None, None, None, CommandStatus.Error)
return result_object
else:
df = DataGuru.removeGT(df, StatContainer.ground_truth)
Y = StatContainer.ground_truth.data
# Remove nans:
df, Y = DataGuru.removenan(df, Y)
X = df.values
# Get the classifier model
trained_model = classifier_model.data
model = trained_model['Model']
scaler = trained_model['Scaler']
# Scale the values based on the training standardizer
X = scaler.transform(X)
# Code to run the classifier
# Plot the classification result
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
Printer.Print('Running the trained classifier...')
predictions = model.predict(X)
accuracy = metrics.accuracy_score(predictions, Y)
Printer.Print("Accuracy : %s" % "{0:.3%}".format(accuracy))
cm = metrics.confusion_matrix(Y, predictions)
DataGuru.plot_confusion_matrix(cm,
np.unique(Y),
ax,
title="confusion matrix")
win.show()
# TODO Need to save the result
result_object = ResultObject(None, None, None, CommandStatus.Success)
return result_object
def evaluate(self, data_frame, classifier_algos):
"""
Train a classifier on multiple arrays
"""
result_object = ResultObject(None, None, None, CommandStatus.Error)
# Get the data frame
sns.set(color_codes=True)
df = data_frame.data
#command_status, df, kl1, _ = DataGuru.transformArray_to_dataFrame(array_datas)
# if command_status == CommandStatus.Error:
# return ResultObject(None, None, None, CommandStatus.Error)
# Get the ground truth array
if StatContainer.ground_truth is None:
Printer.Print("Please set a feature vector to ground truth by",
"typing set ground truth before using this command")
result_object = ResultObject(None, None, None, CommandStatus.Error)
return result_object
else:
df = DataGuru.removeGT(df, StatContainer.ground_truth)
Y = StatContainer.ground_truth.data
# Remove nans:
df, Y = DataGuru.removenan(df, Y)
Printer.Print("Training classifier using the following features:")
Printer.Print(df.columns)
# Get all the classifier models to test against each other
modelList = []
Printer.Print("Testing the following classifiers: ")
for classifier_algo in classifier_algos:
model = (classifier_algo.data[0])
Printer.Print(classifier_algo.name)
modelList.append({'Name': classifier_algo.name, 'Model': model})
# Code to run the classifier
X = df.values
# Get a standard scaler for the extracted data X
scaler = preprocessing.StandardScaler().fit(X)
X = scaler.transform(X)
Printer.Print('Finding the best classifier using',
'k fold cross validation...')
all_cv_scores, all_mean_cv_scores, all_confusion_matrices = DataGuru.FindBestClassifier(X, Y, modelList, 10)
Printer.Print('\n\nPlotting the confusion matrices...\n')
for iter in range(len(modelList)):
win = Window.window()
f = win.gcf()
ax = f.add_subplot(111)
DataGuru.plot_confusion_matrix(all_confusion_matrices[iter], np.unique(Y), ax, title=modelList[iter]['Name'])
win.show()
Printer.Print("\n\nBest classifier is " + modelList[np.argmax(all_mean_cv_scores)]['Name'] + " with an accuracy of - %.2f%% " % max(all_mean_cv_scores))
# TODO Need to save the model
# Ask user for a name for the model
result_object = ResultObject(None, None, None, CommandStatus.Success)
return result_object
