def evaluate(self,
prefix,
X1,
X2,
Y,
record_details=False,
names_1=None,
names_2=None):
ret = self.model.test((X1, X2), Y)
logs.new_line(True)
for indicator, score in ret.items():
logs.add(self.M.name, f'{prefix}_evaluation',
f'{indicator}: {score}', logs.LEVEL_RET, True)
if record_details:
predict_y = self.model.predict_label(
(self.__test_X1, self.__test_X2))
logs.new_line(True)
for i, v in enumerate(predict_y):
logs.add(
self.M.name, 'test_samples',
json.dumps({
'ret': "success" if v == Y[i] else "fail",
'predict': int(v),
'ground_truth': int(Y[i]),
'name_1': names_1[i],
'name_2': names_2[i],
}), logs.LEVEL_DETAIL, True)
def __init__(self):
train_loader = Loader(self.M.data_params['neg_rate_train'],
0,
self.M.data_params['train_ratio'],
use_cache=False)
val_loader = Loader(self.M.data_params['neg_rate_val'],
self.M.data_params['train_ratio'],
self.M.data_params['train_ratio'] +
self.M.data_params['val_ratio'],
use_cache=False)
test_loader = Loader(self.M.data_params['neg_rate_test'],
self.M.data_params['train_ratio'] +
self.M.data_params['val_ratio'],
1.0,
use_cache=False)
self.__train_X1, self.__train_X2, self.__train_Y, self.__train_names_1, self.__train_names_2 = train_loader.all(
)
self.__val_X1, self.__val_X2, self.__val_Y, self.__val_names_1, self.__val_names_2 = val_loader.all(
)
self.__test_X1, self.__test_X2, self.__test_Y, self.__test_names_1, self.__test_names_2 = test_loader.all(
)
logs.new_paragraph(True)
logs.add(
self.M.name, 'data_shape',
json.dumps({
'train_x': self.__train_X1.shape,
'train_y': self.__train_Y.shape,
'val_x': self.__val_X1.shape,
'val_y': self.__val_Y.shape,
'test_x': self.__test_X1.shape,
'test_y': self.__test_Y.shape,
}), logs.LEVEL_DATA, True)
def statistic():
print(f'\nstatistic the shared competitors for competitors ... ')
# record statistics
shared_competitor_counts = []
# to remove duplicate statistic
d_min_name_max_name_2_has_statistic = {}
length = len(d_name_2_competitors)
_i = 0
for _name_1, competitors in d_name_2_competitors.items():
if _i % 2 == 0:
progress = float(_i + 1) / length * 100.
print('\rprogress: %.2f%% ' % progress, end='')
_i += 1
for _j, _name_2 in enumerate(list(competitors)):
# remove duplicate statistic
key = f'{min(_name_1, _name_2)}____{max(_name_1, _name_2)}'
if key in d_min_name_max_name_2_has_statistic:
continue
d_min_name_max_name_2_has_statistic[key] = True
if _name_2 not in d_name_2_competitors:
shared_competitor_counts.append(0)
continue
shared_num = len(competitors.intersection(d_name_2_competitors[_name_2]))
shared_competitor_counts.append(shared_num)
logs.new_line()
logs.add('statistics', 'total count of competitors companies', f'{len(d_name_2_competitors)}', output=True)
logs.add('statistics', 'mean of shared competitors', f'among competitors: {np.mean(shared_competitor_counts)}',
output=True)
logs.add('statistics', 'std of shared competitors', f'among competitors: {np.std(shared_competitor_counts)}',
output=True)
logs.add('statistics', 'max of shared competitors', f'among competitors: {np.max(shared_competitor_counts)}',
output=True)
logs.add('statistics', 'min of shared competitors', f'among competitors: {np.min(shared_competitor_counts)}',
output=True)
bins = list(range(0, 53, 1))
plt.figure(figsize=(18, 8))
plt.hist(shared_competitor_counts, bins=bins, edgecolor='white')
plt.title(
f'histogram for count of shared competitors among competitors',
fontsize=22)
plt.xlabel('count of shared competitors for each similar company pair', fontsize=16)
plt.ylabel('count of company pairs', fontsize=16)
plt.xticks(bins)
plt.savefig(path_lib.get_relative_file_path(
'runtime', 'analysis', 'figures', f'hist_for_shared_competitor_among_competitors.png'),
dpi=300)
plt.show()
plt.close()
def train(self, use_cache=True):
print('\nBuilding model ({}) ...'.format(self.M.TIME))
self.model = self.M()
print('\nTraining model ...')
start_time = time.time()
self.model.train(self.__X, self.__names, use_cache)
train_time = time.time() - start_time
print('\nFinish training')
logs.add(self.M.name, 'training_time', f'{train_time}')
def train(self):
print('\nBuilding model ({}) ...'.format(self.M.TIME))
self.model = self.M()
print('\nTraining model ...')
start_time = time.time()
self.model.train((self.__train_X1, self.__train_X2), self.__train_Y,
(self.__val_X1, self.__val_X2), self.__val_Y)
train_time = time.time() - start_time
print('\nFinish training')
logs.add(self.M.name, 'training_time', f'{train_time}')
def __init__(self):
o_loader = Loader(negative_rate=self.M.data_params['neg_rate'],
use_cache=True)
(self.__train_X1, self.__train_X2, self.__train_Y, self.__train_names_1, self.__train_names_2), \
(self.__val_X1, self.__val_X2, self.__val_Y, self.__val_names_1, self.__val_names_2), \
(self.__test_X1, self.__test_X2, self.__test_Y, self.__test_names_1, self.__test_names_2) = \
o_loader.train_val_test(self.M.data_params['train_ratio'], self.M.data_params['val_ratio'])
logs.new_paragraph(True)
logs.add(
self.M.name, 'data_shape',
json.dumps({
'train_x': self.__train_X1.shape,
'train_y': self.__train_Y.shape,
'val_x': self.__val_X1.shape,
'val_y': self.__val_Y.shape,
'test_x': self.__test_X1.shape,
'test_y': self.__test_Y.shape,
}), logs.LEVEL_DATA, True)
def __log(self):
logs.new_line()
logs.add(self.name, 'data_params', json.dumps(self.data_params),
logs.LEVEL_PARAM, True)
logs.add(self.name, 'train_params', json.dumps(self.train_params),
logs.LEVEL_PARAM, True)
logs.add(self.name, 'model_params', json.dumps(self.model_params),
logs.LEVEL_PARAM, True)
logs.add(self.name, 'monitor_params', json.dumps(self.monitor_params),
logs.LEVEL_PARAM, True)
logs.add(self.name, 'model_dir', self.model_dir, logs.LEVEL_PATH, True)
logs.add(self.name, 'tensorboard_dir', self.tb_dir, logs.LEVEL_PATH,
True)
def statistic(_top_k_similar):
_top_k_idx = top_k_idx[:, -_top_k_similar:]
_top_k_idx = _top_k_idx[::-1]
print(f'\nstatistic the shared competitors for top {_top_k_similar} similar companies of all Linkedin companies ... ')
# record statistics
shared_competitor_counts = []
# to remove duplicate statistic
d_min_name_max_name_2_has_statistic = {}
length = len(names)
for _i, _name_1 in enumerate(names):
if _i % 2 == 0:
progress = float(_i + 1) / length * 100.
print('\rprogress: %.2f%% ' % progress, end='')
similar_names = names[_top_k_idx[_i]]
for _j, _name_2 in enumerate(similar_names):
# remove duplicate statistic
key = f'{min(_name_1, _name_2)}____{max(_name_1, _name_2)}'
if key in d_min_name_max_name_2_has_statistic:
continue
d_min_name_max_name_2_has_statistic[key] = True
if _name_1 not in d_name_2_competitors or _name_2 not in d_name_2_competitors:
shared_competitor_counts.append(0)
continue
competitor_set_1 = d_name_2_competitors[_name_1]
competitor_set_2 = d_name_2_competitors[_name_2]
shared_num = len(competitor_set_1.intersection(competitor_set_2))
shared_competitor_counts.append(shared_num)
logs.new_line()
logs.add('statistics', 'total count of companies', f'{len(names)}', output=True)
logs.add('statistics', 'mean of shared competitors', f'among top {_top_k_similar} similar companies: {np.mean(shared_competitor_counts)}', output=True)
logs.add('statistics', 'std of shared competitors', f'among top {_top_k_similar} similar companies: {np.std(shared_competitor_counts)}', output=True)
logs.add('statistics', 'max of shared competitors', f'among top {_top_k_similar} similar companies: {np.max(shared_competitor_counts)}', output=True)
logs.add('statistics', 'min of shared competitors', f'among top {_top_k_similar} similar companies: {np.min(shared_competitor_counts)}', output=True)
num_0 = len(list(filter(lambda x: x == 0, shared_competitor_counts)))
shared_competitor_counts = list(filter(lambda x: x > 0, shared_competitor_counts))
plt.figure(figsize=(14, 8))
plt.hist(shared_competitor_counts, bins=[0.1, 1, 2, 3, 4, 5, 10, 20, 40], edgecolor='white')
plt.title(
f'histogram for count of shared competitors among top {_top_k_similar} similar companies of all Linkedin companies\n(spike for ({num_0} zero shared competitors) is removed)',
fontsize=22)
plt.xlabel('count of shared competitors for each similar company pair', fontsize=16)
plt.ylabel('count of company pairs', fontsize=16)
plt.xticks([0, 1, 2, 3, 4, 5, 10, 20, 40])
plt.savefig(
path_lib.get_relative_file_path('runtime', 'analysis', 'figures',
f'hist_for_shared_competitor_among_top_{_top_k_similar}_similar_companies.png'),
dpi=300)
plt.show()
plt.close()
