y = pd.concat([y_gal.replace(di_gal), y_exgal.replace(di_exgal)],
ignore_index=True)
y_pred_gal = pd.DataFrame(y_pred_gal)
y_pred_gal.columns = [f'class_{di_gal[x]}' for x in range(len(di_gal))]
y_pred_exgal = pd.DataFrame(y_pred_exgal)
y_pred_exgal.columns = [f'class_{di_exgal[x]}' for x in range(len(di_exgal))]
y_pred = pd.concat([y_pred_gal, y_pred_exgal],
ignore_index=True).fillna(0)
y_pred = y_pred[[f'class_{c}' for c in utils_metric.classes]]
loss = utils_metric.multi_weighted_logloss(y.values, y_pred.values)
# =============================================================================
# weight
# =============================================================================
import utils_post
y_true = pd.get_dummies(y)
weight = utils_post.get_weight(y_true, y_pred.values, eta=0.1, nround=9999)
weight = np.append(weight, 1)
print(list(weight))
# =============================================================================
sub_tr = pd.concat([sub_tr, oof], axis=1)
sub_tr.columns = ['object_id'] + [
f'class_{i}' for i in sorted(classes_gal + classes_exgal)
]
sub_tr.loc[sub_tr.object_id.isin(oid_gal),
[f'class_{i}' for i in classes_exgal]] = 0
sub_tr.loc[sub_tr.object_id.isin(oid_exgal),
[f'class_{i}' for i in classes_gal]] = 0
weight = np.array([1, 2, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1])
weight = weight / sub_tr.iloc[:, 1:].sum()
weight = weight.values
y_pred = sub_tr.iloc[:, 1:].values.astype(float)
print('before:', utils_metric.multi_weighted_logloss(y.values, y_pred))
print('after:', utils_metric.multi_weighted_logloss(y.values, y_pred * weight))
utils.plot_confusion_matrix(__file__, y_pred * weight)
# =============================================================================
# weight
# =============================================================================
import utils_post
y_pred *= weight
y_true = pd.get_dummies(y)
weight = utils_post.get_weight(y_true, y_pred, eta=0.1, nround=9999)
print(f'weight: np.array({list(weight)})')
wloss_list.append(ret['wloss-mean'][-1])
for i, y_pred in enumerate(y_preds):
y_pred = utils_metric.softmax(y_pred.astype(float).values)
if i == 0:
y_preds_ = y_pred
else:
y_preds_ += y_pred
y_preds_ /= len(y_preds)
# =============================================================================
#
# =============================================================================
utils_metric.multi_weighted_logloss(y, y_preds_)
def multi_weighted_logloss(y_true: np.array, y_preds: np.array):
"""
@author olivier https://www.kaggle.com/ogrellier
multi logloss for PLAsTiCC challenge
"""
# class_weights taken from Giba's topic : https://www.kaggle.com/titericz
# https://www.kaggle.com/c/PLAsTiCC-2018/discussion/67194
# with Kyle Boone's post https://www.kaggle.com/kyleboone
classes = [6, 15, 16, 42, 52, 53, 62, 64, 65, 67, 88, 90, 92, 95]
class_weight = {
6: 1,
15: 2,
16: 1,
1.1768777584208459, 0.9498970981272328, 0.6113702626667485,
0.48242068928933035, 1.2894930889416614, 1.423971561601788,
0.6535155757119984, 1.6161049089839221, 0.5743188118409728,
1.1906849086994178, 0.6527050232072442, 0.42181435682919677,
0.9394690895273552, 1.061672745432284
])
classes_gal = [6, 16, 53, 65, 92]
classes_exgal = [15, 42, 52, 62, 64, 67, 88, 90, 95]
sub_tr = utils.load_train(['object_id'])
sub_tr = pd.concat([sub_tr, oof2], axis=1)
sub_tr.columns = ['object_id'] + [
f'class_{i}' for i in sorted(classes_gal + classes_exgal)
]
sub_tr.loc[sub_tr.object_id.isin(oid_gal),
[f'class_{i}' for i in classes_exgal]] = 0
sub_tr.loc[sub_tr.object_id.isin(oid_exgal),
[f'class_{i}' for i in classes_gal]] = 0
oof2 = sub_tr.iloc[:, 1:].values.astype(float) * weight
oof = (oof1 + oof2) / 2
y = utils.load_target().target
print('oof1:', utils_metric.multi_weighted_logloss(y.values, oof1))
print('oof2:', utils_metric.multi_weighted_logloss(y.values, oof2))
print('ave:', utils_metric.multi_weighted_logloss(y.values, oof))
def plot_confusion_matrix(__file__, y_pred, normalize=True,
title='Confusion Matrix'):
import matplotlib as mpl
mpl.use('Agg')
from matplotlib import pyplot as plt
from sklearn.metrics import confusion_matrix
import itertools
import utils_metric
classes = ['class_6',
'class_15',
'class_16',
'class_42',
'class_52',
'class_53',
'class_62',
'class_64',
'class_65',
'class_67',
'class_88',
'class_90',
'class_92',
'class_95']
y = load_target().target
target_dict = {}
target_dict_r = {}
for i,e in enumerate(y.sort_values().unique()):
target_dict[e] = i
target_dict_r[i] = e
y = y.replace(target_dict).values
score = utils_metric.multi_weighted_logloss(y, y_pred)
cnf_matrix = confusion_matrix(y, np.argmax(y_pred, axis=-1))
np.set_printoptions(precision=2)
if normalize:
cnf_matrix = cnf_matrix.astype('float') / cnf_matrix.sum(axis=1)[:, np.newaxis]
print("Normalized confusion matrix")
else:
print('Confusion matrix, without normalization')
print(cnf_matrix)
plt.figure(figsize=(12,12))
plt.imshow(cnf_matrix, interpolation='nearest', cmap=plt.cm.Blues)
plt.title(f'{title}: {round(score, 5)}')
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=45)
plt.yticks(tick_marks, classes)
fmt = '.2f' if normalize else 'd'
thresh = cnf_matrix.max() / 2.
for i, j in itertools.product(range(cnf_matrix.shape[0]), range(cnf_matrix.shape[1])):
plt.text(j, i, format(cnf_matrix[i, j], fmt),
horizontalalignment="center",
color="white" if cnf_matrix[i, j] > thresh else "black")
plt.ylabel('True label')
plt.xlabel('Predicted label')
plt.tight_layout()
plt.savefig(f'LOG/CM_{__file__}.png')
send_line(f'Confusion Matrix wmlogloss: {score}', png=f'LOG/CM_{__file__}.png')
return
imp = ex.getImp(model_all)
imp['split'] /= imp['split'].max()
imp['gain'] /= imp['gain'].max()
imp['total'] = imp['split'] + imp['gain']
imp.sort_values('total', ascending=False, inplace=True)
imp.reset_index(drop=True, inplace=True)
imp.to_csv(f'LOG/imp_{__file__}.csv', index=False)
# =============================================================================
# eval
# =============================================================================
for i, y_pred in enumerate(y_preds):
y_pred = pd.DataFrame(utils_metric.softmax(y_pred.astype(float).values))
if i == 0:
tmp = y_pred
else:
tmp += y_pred
tmp /= len(y_preds)
y_preds = tmp.copy().values.astype(float)
w_score = utils_metric.multi_weighted_logloss(y.values, y_preds)
a_score = utils_metric.akiyama_metric(y.values, y_preds)
print(f'{w_score} {a_score}')
#==============================================================================
utils.end(__file__)
utils.stop_instance()
