def test_pandas_confusion_normalized():
y_true = [2, 0, 2, 2, 0, 1, 1, 2, 2, 0, 1, 2]
y_pred = [0, 0, 2, 1, 0, 2, 1, 0, 2, 0, 2, 2]
cm = ConfusionMatrix(y_true, y_pred)
df = cm.to_dataframe()
df_norm = cm.to_dataframe(normalized=True)
assert(df_norm.sum(axis=1).sum() == len(df))
def test_pandas_confusion_normalized_issue1():
# should insure issue 1 is fixed
# see http://stackoverflow.com/questions/19233771/sklearn-plot-confusion-matrix-with-labels/31720054#31720054
y_true = ['business', 'business', 'business', 'business', 'business',
'business', 'business', 'business', 'business', 'business',
'business', 'business', 'business', 'business', 'business',
'business', 'business', 'business', 'business', 'business']
y_pred = ['health', 'business', 'business', 'business', 'business',
'business', 'health', 'health', 'business', 'business', 'business',
'business', 'business', 'business', 'business', 'business',
'health', 'health', 'business', 'health']
cm = ConfusionMatrix(y_true, y_pred)
df = cm.to_dataframe()
df_norm = cm.to_dataframe(normalized=True)
assert(df_norm.sum(axis=1, skipna=False).fillna(1).sum() == len(df))
def train_test_and_evaluate(pipeline, X_train, y_train, X_test, y_test):
pipeline.fit(X_train, y_train)
y_pred_class = pipeline.predict(X_test)
unique_label = np.unique(y_test)
matrix = ConfusionMatrix(y_test,
y_pred_class,
labels=['True Value', 'Predicted Value'])
print('-' * 75 + '\nConfusion Matrix\n')
print(matrix)
print('f1_score', f1_score(y_test, y_pred_class, average="macro"))
print('precision', precision_score(y_test, y_pred_class, average="macro"))
print('recall', recall_score(y_test, y_pred_class, average="macro"))
return pipeline, matrix.to_dataframe(), y_pred_class
def get_confusion_matrix(_results_file):
df = pd.read_csv(results_file, sep='\t', header=None)
true_lbls = df[1]
pred_lbls = df[2]
confusion_matrix = ConfusionMatrix(true_lbls, pred_lbls)
confusion_matrix.plot()
cm_file = _results_file.replace('.txt', '_cm.jpg')
plt.savefig(cm_file)
print()
print(confusion_matrix)
print()
cm = confusion_matrix.to_dataframe()
correct = 0
for i in range(cm.shape[0]):
correct += cm.iloc[i][i]
recall = cm.iloc[i][i] * 100 / cm.sum(axis=0)[i]
prec = cm.iloc[i][i] * 100 / cm.sum(axis=1)[i]
print('Class %s recall = %.4f precision = %.4f' %
(cm.columns[i], recall, prec))
print('Overall accuracy = %.4f' %
float(correct * 100 / sum(cm.sum(axis=0))))
def main(save, show):
basepath = os.path.dirname(__file__)
# y_true = [2, 0, 2, 2, 0, 1, 1, 2, 2, 0, 1, 2]
# y_pred = [0, 0, 2, 1, 0, 2, 1, 0, 2, 0, 2, 2]
# cm = ConfusionMatrix(y_true, y_pred)
# cm = ConfusionMatrix(y_true, y_pred, labels=["ant", "bird", "cat"])
# y_true = [2, 0, 2, 2, 0, 1]
# y_pred = [0, 0, 2, 2, 0, 2]
# cm = ConfusionMatrix(y_true, y_pred)
# cm = ConfusionMatrix(y_true, y_pred, labels=["ant", "bird", "cat"])
y_true = ['rabbit', 'cat', 'rabbit', 'rabbit', 'cat', 'dog', 'dog', 'rabbit', 'rabbit', 'cat', 'dog', 'rabbit']
y_pred = ['cat', 'cat', 'rabbit', 'dog', 'cat', 'rabbit', 'dog', 'cat', 'rabbit', 'cat', 'rabbit', 'rabbit']
cm = ConfusionMatrix(y_true, y_pred)
# y_true = ["cat", "ant", "cat", "cat", "ant", "bird"]
# y_pred = ["ant", "ant", "cat", "cat", "ant", "cat"]
# >>> cm(y_true, y_pred, labels=["ant", "bird", "cat"])
# array([[2, 0, 0],
# [0, 0, 1],
# [1, 0, 2]])
# cm = ConfusionMatrix(y_true, y_pred)
print("Confusion matrix:\n%s" % cm)
df = cm.to_dataframe()
print(df)
print(df.dtypes)
cm.plot()
filename = 'cm.png'
if save:
plt.savefig(os.path.join(basepath, '..', 'screenshots', filename))
if show:
plt.show()
cm.plot(normalized=True)
filename = 'cm_norm.png'
if save:
plt.savefig(os.path.join(basepath, '..', 'screenshots', filename))
if show:
plt.show()
cm.print_stats()
print(cm.classification_report)
print("sklearn confusion_matrix:\n%s" % confusion_matrix(y_true, y_pred))
print(classification_report(y_true, y_pred))
# stat = 'precision'
# print(cm._avg_stat(stat))
# print(cm.ACC)
# import seaborn as sns
# cm.plot(normalized=True, backend=Backend.Seaborn)
# sns.plt.show()
print("Binarize a confusion matrix")
y_true = ["cat", "ant", "cat", "cat", "ant", "bird"]
y_pred = ["ant", "ant", "cat", "cat", "ant", "cat"]
cm = ConfusionMatrix(y_true, y_pred)
print(cm)
binary_cm = cm.binarize(['ant', 'cat'])
# A bird is not a "land_animal"
print(binary_cm)
def main(save, show):
basepath = os.path.dirname(__file__)
# y_true = [2, 0, 2, 2, 0, 1, 1, 2, 2, 0, 1, 2]
# y_pred = [0, 0, 2, 1, 0, 2, 1, 0, 2, 0, 2, 2]
# cm = ConfusionMatrix(y_true, y_pred)
# cm = ConfusionMatrix(y_true, y_pred, labels=["ant", "bird", "cat"])
# y_true = [2, 0, 2, 2, 0, 1]
# y_pred = [0, 0, 2, 2, 0, 2]
# cm = ConfusionMatrix(y_true, y_pred)
# cm = ConfusionMatrix(y_true, y_pred, labels=["ant", "bird", "cat"])
y_true = [
'rabbit', 'cat', 'rabbit', 'rabbit', 'cat', 'dog', 'dog', 'rabbit',
'rabbit', 'cat', 'dog', 'rabbit'
]
y_pred = [
'cat', 'cat', 'rabbit', 'dog', 'cat', 'rabbit', 'dog', 'cat', 'rabbit',
'cat', 'rabbit', 'rabbit'
]
cm = ConfusionMatrix(y_true, y_pred)
# y_true = ["cat", "ant", "cat", "cat", "ant", "bird"]
# y_pred = ["ant", "ant", "cat", "cat", "ant", "cat"]
# >>> cm(y_true, y_pred, labels=["ant", "bird", "cat"])
# array([[2, 0, 0],
# [0, 0, 1],
# [1, 0, 2]])
# cm = ConfusionMatrix(y_true, y_pred)
print("Confusion matrix:\n%s" % cm)
df = cm.to_dataframe()
print(df)
print(df.dtypes)
cm.plot()
filename = 'cm.png'
if save:
plt.savefig(os.path.join(basepath, '..', 'screenshots', filename))
if show:
plt.show()
cm.plot(normalized=True)
filename = 'cm_norm.png'
if save:
plt.savefig(os.path.join(basepath, '..', 'screenshots', filename))
if show:
plt.show()
cm.print_stats()
print(cm.classification_report)
print("sklearn confusion_matrix:\n%s" % confusion_matrix(y_true, y_pred))
print(classification_report(y_true, y_pred))
# stat = 'precision'
# print(cm._avg_stat(stat))
# print(cm.ACC)
# import seaborn as sns
# cm.plot(normalized=True, backend=Backend.Seaborn)
# sns.plt.show()
print("Binarize a confusion matrix")
y_true = ["cat", "ant", "cat", "cat", "ant", "bird"]
y_pred = ["ant", "ant", "cat", "cat", "ant", "cat"]
cm = ConfusionMatrix(y_true, y_pred)
print(cm)
binary_cm = cm.binarize(['ant', 'cat'])
# A bird is not a "land_animal"
print(binary_cm)
plt.plot(c, cv_scores, '-o')
plt.xscale('log')
# In[ ]:
predicted = clf.predict(X_test)
expected = y_test
print(accuracy_score(expected, predicted))
# In[ ]:
predicted_probs = clf.predict_proba(X_test)
print(log_loss(y_test, predicted_probs))
# In[ ]:
cm = ConfusionMatrix(expected, predicted)
cm_stats = cm.to_dataframe().apply(lambda x: x/sum(x), axis=1)
cm_stats.to_csv('data/confusion_matrix_stats.csv')
# In[ ]:
mpl.rcParams['figure.figsize'] = (10.0, 5.0)
cm.plot(normalized=True)
