def bucket_sort(collection: Union, key=None):
if len(collection) == 0:
return collection
if key is None:
key = identity
collection = list(collection)
result = []
min_value, max_value, _, _ = min_max(collection, key)
bucket_count = np.floor(np.log(max_value - min_value)) + 1
step = get_step(min_value, max_value, bucket_count)
buckets = [[] for _ in range(int(bucket_count))]
for item in collection:
k = call(key, item)
bucket = _get_bucket(k, min_value, step, bucket_count)
buckets[int(bucket)].append(item)
for bucket in buckets:
part = sorted(bucket, key=key)
result.extend(part)
return result
def main(input_file):
PREAMBLE_LENGTH = 25
numbers = []
invalid_number = None
with open(input_file) as f:
while True:
line = f.readline().strip()
if not line:
break
number_under_test = int(line)
if invalid_number is None and len(numbers) >= PREAMBLE_LENGTH:
# We have enough numbers to start testing
window = numbers[(-1 * PREAMBLE_LENGTH):].copy()
logging.debug(
"Number under test: {}".format(number_under_test))
logging.debug(window)
if not sum_of_two(number_under_test, window):
invalid_number = number_under_test
logging.debug(
"Invalid number {} found.".format(invalid_number))
break # We don't have to consider any numbers past this point, nor this number
# TODO: Confirm this is valid. It worked but i'm not sure if this is true
# Confirmed invalid assumption. Consider the malicious example 1,2,3,13,8,... with preamble 3
numbers.append(number_under_test)
logging.debug(numbers)
found_range = None
for i in range(len(numbers)):
range_sum = 0
end = i + 2 # At least 2 numbers in the contiguous range
while range_sum < invalid_number and end < len(numbers):
checking = numbers[i:end]
range_sum = sum(checking)
logging.debug("Checking {} Sum: {}".format(checking, range_sum))
if range_sum == invalid_number:
found_range = checking
logging.debug("Weakness range found: {}".format(found_range))
break
end += 1
if found_range is not None:
break
smallest, largest = util.min_max(found_range)
logging.debug("Smallest: {} Largest: {}".format(smallest, largest))
answer = smallest + largest
logging.info("Answer: {}".format(answer))
def main(input_file):
PREAMBLE_LENGTH = 25
numbers = []
invalid_number = None
with open(input_file) as f:
while True:
line = f.readline().strip()
if not line:
break
number_under_test = int(line)
if invalid_number is None and len(numbers) >= PREAMBLE_LENGTH:
# We have enough numbers to start testing
window = numbers[(-1*PREAMBLE_LENGTH):].copy()
logging.debug("Number under test: {}".format(number_under_test))
logging.debug(window)
if not sum_of_two(number_under_test, window):
invalid_number = number_under_test
logging.debug("Invalid number {} found.".format(invalid_number))
numbers.append(number_under_test)
logging.debug(numbers)
found_range = None
for i in range(len(numbers)):
range_sum = 0
end = i + 2
while range_sum < invalid_number and end < len(numbers):
checking = numbers[i:end]
range_sum = sum(checking)
logging.debug("Checking {} Sum: {}".format(checking, range_sum))
if range_sum == invalid_number:
found_range = checking
logging.debug("Weakness range found: {}".format(found_range))
break
end += 1
if found_range is not None:
break
smallest, largest = util.min_max(found_range)
logging.debug("Smallest: {} Largest: {}".format(smallest, largest))
answer = smallest + largest
logging.info("Answer: {}".format(answer))
def browse_ms(company):
print("Morning star")
driver.get(url.morningstar)
time.sleep(3)
driver.find_element_by_xpath(
'//*[@id="ctl00_ucHeader_txtQuote_txtAutoComplete"]').click()
company_search = driver.find_element_by_xpath(
'//*[@id="ctl00_ucHeader_txtQuote_txtAutoComplete"]')
company_search.send_keys(company)
time.sleep(3)
driver.find_element_by_xpath('//*[@id="ui-id-1"]/li[1]').click()
time.sleep(4)
driver.find_element_by_xpath(
'//*[@id="tabs"]/div/mds-button-group/div/slot/div/mds-button[2]/label/input'
).click()
time.sleep(4)
debt_equity = "Debt/Equity = " + str(
driver.find_element_by_xpath(
'//*[@id="siteContent"]/div[2]/div/div/div[1]/div/div/div[2]/div/div[2]/div/div[2]/div[2]/div/div[2]/ul/li[8]/div/div[2]'
).text)
driver.find_element_by_xpath(
'//*[@id="siteContent"]/div[2]/div/div/div[1]/div/div/div[2]/div/div[2]/div/div[2]/div[2]/div/div[2]/div[1]/a'
).click()
time.sleep(4)
driver.switch_to_window(driver.window_handles[1])
fcf = util.find_fcf(driver) + "\n"
operating_margin_str = util.operating_margin(driver) + "\n"
range_opm = util.min_max(operating_margin_str) + "\n"
gross_margin_str = util.gross_margin(driver) + "\n"
range_gpm = util.min_max(gross_margin_str) + "\n"
final_str = debt_equity + "\n" + operating_margin_str + range_opm + gross_margin_str + range_gpm + fcf
print(final_str)
print(final_str, file=f)
def plot_feature_importance(feature_importances):
feature = [
'lattice type', 'space group', 'nspecies', 'natoms', 'volume/atom',
'volume/cell', r'$\rho$', 'atomic number', 'mendeleev number',
'period', 'group', 'mass', 'density', 'valence', 'radii', '$r_{cov}$',
'$r_{vdw}$', 'electron affinity', 'electron negativity',
'ionization energy', '$T_b$', '$T_m$', 'molar volume',
'thermal conductivity', 'orbital exponent', 'polarizability',
'global hardness', 'electrophilicity', r'$\Delta H_{atomic}$',
'fusion enthalpy', 'vaporization enthalpy', 'binding energy'
]
pos = range(len(feature_importances))
sorted_index = np.argsort(feature_importances)
fig, ax1 = plt.subplots(figsize=(7, 8))
ax1.xaxis.grid(True, linestyle='-.', which='major', color='grey')
ax1.tick_params(labelsize=12)
# plt.grid(True, axis='x',which='major', ls='-.')
sorted_feature = feature_importances[sorted_index]
min_max_color = min_max(sorted_feature)
min_max_color = np.power(min_max_color, 1 / 2)
print(min_max_color)
bar_color = [
tuple([0.1803921568627451, 0.3411764705882353, 0.5019607843137255, i])
for i in min_max_color
]
# bar_color = [tuple([0.49019607843137253, 0.6745098039215687, 0.8, i]) for i in min_max_color]
ax1.barh(pos, sorted_feature, align='center', color=bar_color)
FP = FontProperties(family='Times New Roman', size=14)
plt.yticks(pos, np.array(feature)[sorted_index], fontproperties=FP)
plt.xticks(fontproperties=FP)
plt.xlabel('Importance', size=18, fontdict={'family': 'Times New Roman'})
SAVE = False
if SAVE:
plt.savefig('./fig/feature_importance.png',
dpi=600,
bbox_inches='tight')
plt.show()
for i in range(1, 4995):
if os.path.exists(f'data/hot_entry/masuda_{i}.json'):
hot_df = pd.read_json(f'data/hot_entry/masuda_{i}.json')
hot_concat.append(hot_df)
hot_concat_df = pd.concat(hot_concat)
not_hot_concat = []
for i in range(2, 5001):
if os.path.exists(f'data/entry/masuda_{i}.json'):
not_hot_df = pd.read_json(f'data/entry/masuda_{i}.json')
not_hot_concat.append(not_hot_df)
not_hot_concat_df = pd.concat(not_hot_concat)
all_concat_df = pd.concat([hot_concat_df, not_hot_concat_df])
all_concat_df.bookmark_count = util.min_max(
all_concat_df.bookmark_count.tolist())
all_concat_df.num_of_sentences = util.min_max(
all_concat_df.num_of_sentences.tolist())
all_concat_df.num_of_comma = util.min_max(all_concat_df.num_of_comma.tolist())
all_concat_df.num_of_period = util.min_max(
all_concat_df.num_of_period.tolist())
all_concat_df.num_of_exclamation_mark = util.min_max(
all_concat_df.num_of_exclamation_mark.tolist())
all_concat_df.num_of_question_mark = util.min_max(
all_concat_df.num_of_question_mark.tolist())
all_concat_df.length_of_text = util.min_max(
all_concat_df.length_of_text.tolist())
all_concat_df.distance_btw_commas = util.min_max(
all_concat_df.distance_btw_commas.tolist())
all_concat_df.kanji_content_rate = util.min_max(
all_concat_df.kanji_content_rate.tolist())