def sameNum(fst,sec):
"""
calculate same and different nums
"""
length = min(len(fst),len(sec))
x = 0
for index in range(length):
if fst[index] == sec[index]:
x += 1
z = sum((Counter(fst) & Counter(sec)).values())
return ("{}A{}B".format(x,(z-x)))
def findAnagrams(self, s: str, p: str) -> List[int]:
answer = []
m, n = len(s), len(p)
if m < n:
return answer
sc = Counter(s[:n - 1])
pc = Counter(p)
for index in range(n - 1, m):
sc[s[index]] += 1
if sc == pc:
answer.append(index + 1 - n)
sc[s[index + 1 - n]] -= 1
if sc[s[index + 1 - n]] == 0:
del sc[s[index + 1 - n]]
return answer
def sortColors(self, nums: List[int]) -> None:
from collection import Counter
count = Counter(nums)
for i in range(len(nums)):
if i < count[0]:
nums[i] = 0
elif i < count[1] + count[0]:
nums[i] = 1
else:
nums[i] = 2
def calculate_popular(base_dir, lines):
pn = r'\[IMAGE_VIEW\] image view (.+) at (\d+)'
pn = re.compile(pn)
counter = Counter()
for line in lines:
match = pn.search(line)
if match.group(1).find(base_dir) != -1:
path = os.path.relpath(match.group(1), base_dir)
else:
path = match.group(1)
counter[path.replace('\\', '/')] += 1
return dict(counter.most_common(50))
def make_dictionary(train_dir, number): emails = [os.path.join(train_dir, f) for f in os.listdir(train_dir)] all_words = [] for mail in emails: with open(mail) as m: for line in m: words = line.split() all_words += words dictionary = Counter(all_words) list_to_remove = dictionary.keys() for item in list_to_remove: if item.isalpha() == False and item.isnumeric()==False and item[0:2] != "__": del dictionary[item] elif len(item) <= 1 and item!= "i": del dictionary[item] dictionary = dictionary.most_common(number) return dictionary
counts = get_count(time_zones)
###### 对字典进行排序
# 转化为list再排序
def top_counts(countDict, n=10):
countList = [(value, key) for key, value in countDict.items()]
countList.sort()
return countList[-n:]
top_counts(counts)
###### 利用库函数直接实现对字典的 统计+排序
from collection import Counter
counts = Counter(time_zones)
counts.most_common(10)
###### 利用pandas和numpy进行分析
from pandas import DataFrame, Series
import pandas as pd
import numpy as np
frame = DataFrame(records) # records 是一个List，其中每一个元素是一个字典
frame['tz'][:10] # 直接查看tz列的前10个数据，frame['tz']是一个Series对象
tz_counts = frame['tz'].value_counts() # Series对象有一个value_counts方法用于统计出现的次数
clean_tz = frame['tz'].fillna('Missing') # 填补的是 Nan
clean_tz[clean_tz == ''] = 'Unknown' # 填补的是 空
tz_counts = clean_tz.value_counts()
tz_counts[:10].plot(kind='barh', rot=0)
def fit(self, data):
result = Counter()
result.update([item for item in self.data])
return result
from collection import Counter a = "aaaaaabbbbccc" my_counter = Counter(a) print(my_counter)
# number of speeches
len(speeches)
# list the presidents
[speech['president'] for speech in speeches]
# list the dates
[speech['date'] for speech in speeches]
# get text from first speech and make list of words
text = speeches[0]['text']
words = [w for w in re.split('\W', text) if w]
vocab = sorted(set(words))
from collection import Counter
word_counts = Counter(words)
# function to extract president and word count
def summarize(speech):
text = speech['text']
words = [w for w in re.split('\W', text) if w]
return (speech['president'], len(words), speech['date'])
summary = [summarize(speech) for speech in speeches]
# https://wiki.python.org/moin/HowTo/Sorting
from operator import itemgetter
[speech[2] for speech in sorted(summary, key=itemgetter(1))]
from collection import Counter 2 in Counter(["one", "one", "two"]).values() 2 in Counter(["one", "two", "three"]).values()
#ordenar
num_friends.sort()
#media
num_friends.mean()
#mediana
np.median(num_friend)
#moda
np.bincount(num_friends).argmax()
#or
from collection import Counter
b = Counter(num_friends)
b.most_common(1)
#dispersão ou amplitude
num_friends.max() - num_friends.mix()
#variancia
variace = np.sum(
np.square([x_list - myfriends.mean() for x_list in num_friends]))
#or
np.var(num_friends)
#standart deviantion
np.sqrt(
np.sum(np.square([x_list - myfriends.mean() for x_list in num_friends])))
def getRaceCount():
races = char_df['Race'].tolist()
race_count = Counter(races)
return (race_count)
def evaluate(_):
win_name = 'Detector'
cv2.namedWindow(win_name)
video = FLAGS.video
if is_url(video):
videoPafy = pafy.new(video)
video = videoPafy.getbest(preftype="mp4").url
cam = cv2.VideoCapture(video)
if not cam.isOpened():
raise IOError('Can\'t open "{}"'.format(FLAGS.video))
source_h = cam.get(cv2.CAP_PROP_FRAME_HEIGHT)
source_w = cam.get(cv2.CAP_PROP_FRAME_WIDTH)
model_cls = find_class_by_name(FLAGS.model_name, [yolo])
model = model_cls(input_shape=(source_h, source_w, 3))
model.init()
frame_num = 0
start_time = time.time()
fps = 0
try:
while True:
ret, frame = cam.read()
if not ret:
logger.info('Can\'t read video data. Potential end of stream')
return
object_count_dict = Counter()
predictions = model.evaluate(frame)
for o in predictions:
x1 = o['box']['left']
x2 = o['box']['right']
y1 = o['box']['top']
y2 = o['box']['bottom']
color = o['color']
class_name = o['class_name']
object_count_dict[str(class_name)] += 1
# Draw box
cv2.rectangle(frame, (x1, y1), (x2, y2), color, 2)
# Draw label
(test_width, text_height), baseline = cv2.getTextSize(
class_name, cv2.FONT_HERSHEY_SIMPLEX, 0.75, 1)
cv2.rectangle(frame, (x1, y1),
(x1 + test_width, y1 - text_height - baseline),
color,
thickness=cv2.FILLED)
cv2.putText(frame, class_name, (x1, y1 - baseline),
cv2.FONT_HERSHEY_SIMPLEX, 0.75, (0, 0, 0), 1)
logger.info(object_count_dict)
end_time = time.time()
fps = fps * 0.9 + 1 / (end_time - start_time) * 0.1
start_time = end_time
# Draw additional info
frame_info = 'Frame: {0}, FPS: {1:.2f}'.format(frame_num, fps)
cv2.putText(frame, frame_info, (10, frame.shape[0] - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1)
logger.info(frame_info)
cv2.imshow(win_name, frame)
if predictions:
logger.info('Predictions: {}'.format(
format_predictions(predictions)))
key = cv2.waitKey(1) & 0xFF
# Exit
if key == ord('q'):
break
# Take screenshot
if key == ord('s'):
cv2.imwrite('frame_{}.jpg'.format(time.time()), frame)
frame_num += 1
finally:
cv2.destroyAllWindows()
cam.release()
model.close()