def fscore(y_test, y_score):
"""
:param y_test: output vector - predictions on the test set
:param y_score: output vector which contains probabilities for each contained estimator
:return: plot object
"""
# binarize output vector
y_test = binarize(y_test)
print('y_test binarized shape = ', np.shape(y_test))
n_classes = np.shape(y_test)[1]
# Compute Precision-Recall and plot curve
precision = dict()
recall = dict()
average_precision = dict()
for i in range(n_classes):
precision[i], recall[i], _ = precision_recall_curve(y_test[:, i],
y_score[:, i])
average_precision[i] = average_precision_score(y_test[:, i], y_score[:, i])
# Compute micro-average ROC curve and ROC area
precision["micro"], recall["micro"], _ = precision_recall_curve(y_test.ravel(),
y_score.ravel())
average_precision["micro"] = average_precision_score(y_test, y_score,
average="micro")
# Plot Precision-Recall curve
plt.clf()
plt.plot(recall[0], precision[0], label='Precision-Recall curve')
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.ylim([0.0, 1.05])
plt.xlim([0.0, 1.0])
plt.title('Precision-Recall example: AUC={0:0.2f}'.format(average_precision[0]))
plt.legend(loc="lower left")
plt.show()
# Plot Precision-Recall curve for each class
plt.clf()
plt.plot(recall["micro"], precision["micro"],
label='micro-average Precision-recall curve (area = {0:0.2f})'
''.format(average_precision["micro"]))
for i in range(n_classes):
plt.plot(recall[i], precision[i],
label='Precision-recall curve of class {0} (area = {1:0.2f})'
''.format(i, average_precision[i]))
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Recall')
plt.ylabel('Precision')
plt.title('Extension of Precision-Recall curve to multi-class')
plt.legend(loc="lower right")
plt.show()
return plt
# output vector
y = df['KONCENTRACIJA'].as_matrix()
del df['KONCENTRACIJA']
# output the column names
print(df.columns.values.tolist())
# binarize id columns
id_cols = ["vrstaBiljke", "ID_VRSTE", "ID_LOKACIJE"]
id_columns = df[id_cols].as_matrix()
for col in id_cols:
del df[col]
id_columns_binarized = binarize(id_columns[:, 0])
for i in range(1, np.size(id_cols)):
id_columns_binarized = np.column_stack((id_columns_binarized, binarize(id_columns[:, i])))
# transform to suitable representation
X = df.as_matrix()
# testing the shapes before and after the binarization
print('before binarization X = ', X.shape)
print('id_columns_binazried = ', id_columns_binarized.shape)
X = np.column_stack((X, id_columns_binarized))
print('after binarization X = ', X.shape)
# clear from n/a's
clear_rows = ~np.isnan(X).any(axis=1)
# output vector
y = df['KONCENTRACIJA'].as_matrix()
del df['KONCENTRACIJA']
# output the column names
print(df.columns.values.tolist())
# binarize id columns
id_cols = ["vrstaBiljke", "ID_VRSTE", "ID_LOKACIJE"]
id_columns = df[id_cols].as_matrix()
for col in id_cols:
del df[col]
id_columns_binarized = binarize(id_columns[:, 0])
for i in range(1, np.size(id_cols)):
id_columns_binarized = np.column_stack(
(id_columns_binarized, binarize(id_columns[:, i])))
# transform to suitable representation
X = df.as_matrix()
# testing the shapes before and after the binarization
print('before binarization X = ', X.shape)
print('id_columns_binazried = ', id_columns_binarized.shape)
X = np.column_stack((X, id_columns_binarized))
print('after binarization X = ', X.shape)
# clear from n/a's
