def test_duration():
assert Duration.set_time('2:5:0').to_str() == '2:5:0'
assert Duration.set_time('2:5:0').to_duration() == 7500
assert Duration.set_duration(7500).to_duration() == 7500
assert Duration.set_duration(7500).to_str() == '2:5:0'
assert (Duration.set_duration(7500) - duration_delta(m=5)).to_str() == '2:0:0'
assert (Duration.set_duration(7500) - duration_delta(s=5)).to_str() == '2:4:55'
def _trans_set2result(self, vod_set: dict) -> typing.Dict:
result = {}
for station_num, vod_range in vod_set.items():
result[station_num] = []
for start, s_range in vod_range.items():
s = start.split('_')[-1]
for min_r, max_r in s_range:
min_r_str = (Duration.set_time(s) + duration_delta(
s=min_r *
config.THUMBNAIL_SIZE.DURATION_SEC)).to_str()
max_r_str = (Duration.set_time(s) + duration_delta(
s=max_r *
config.THUMBNAIL_SIZE.DURATION_SEC)).to_str()
result[station_num].append((min_r_str, max_r_str))
return result
def sub_path(path: str, num, label: int = 0) -> str:
p = Path(path)
station_str, raw_duration = p.stem.split('_')
duration = (Duration.set_time(raw_duration) +
duration_delta(s=num)).to_str()
file_name = f'{station_str}_{duration}_{label}{p.suffix}'
file_dir = 'img'
sub_img_path = Path(file_dir, file_name)
return str(sub_img_path)
def _find_top(self, raw_data: typing.List,
time_duration: int) -> typing.Optional[typing.List]:
if not raw_data or not time_duration:
return
cnt = pd.DataFrame(raw_data, columns=['index', 'value'])
perfect_duration = (
Duration.set_duration(time_duration) -
duration_delta(m=self.perfect_start_min)).to_duration()
per_index = time_duration // len(cnt)
diff_duration = time_duration - perfect_duration
perfect_start = diff_duration // per_index
y = pd.DataFrame(raw_data[perfect_start:], columns=['index', 'value'])
sma_period = perfect_start * self.smooth_factor
Y = ta.SMA(y['value'].values.astype('float64'),
timeperiod=sma_period).tolist()
top = []
for i, d in enumerate(Y):
if d > 0 and i < len(Y) - 1:
if (Y[i - 1] <= d and d >= Y[i + 1]) or (i == 0
and d >= Y[i + 1]):
top.append((i + perfect_start, d))
def row_sma(row):
cond = (row['start_index'] <= cnt['index']) & (cnt['index'] <=
row['index'])
max_id = cnt.where(cond).dropna()['value'].idxmax()
result = cnt.loc[max_id]
row['ori_index'] = result['index']
row['ori_value'] = result['value']
ori_duration = result['index'] * per_index
start_duration = Duration.set_duration(ori_duration - MIN_SEC *
self.range_factor).to_str()
end_duration = Duration.set_duration(ori_duration + MIN_SEC *
self.range_factor).to_str()
row['ori_range_duration'] = (start_duration, end_duration)
return row
top_df = pd.DataFrame(top, columns=['index', 'value'])
top_df['value'].where(top_df['value'] > top_df['value'].mean(),
inplace=True)
top_df = top_df.where(top_df['value'] > 0).dropna()
top_df['start_index'] = top_df['index'] - sma_period + 1
top_df['index'] = top_df['index']
target = top_df.apply(row_sma, axis=1)
return target['ori_range_duration'].drop_duplicates().to_list()
def sub_path(
self,
path,
file_dir: str,
num,
label: int = 0,
) -> str:
p = Path(path)
station_str, raw_duration = p.stem.split('_')
duration = (Duration.set_time(raw_duration) +
duration_delta(s=num)).to_str()
file_name = f'{duration}_{label}{p.suffix}'
# self.log.info(f'[{self.user_id}:{station_str}] {file_name}')
file_dir = file_dir
# sub_img_path = Path(file_dir, station_str, file_name)
sub_img_path = Path(file_dir, f'{station_str}_{file_name}')
if not sub_img_path.parent.exists():
sub_img_path.parent.mkdir(parents=True)
return str(sub_img_path)
def pl(raw_data, time_duration, station_num):
if raw_data and time_duration:
cnt = pd.DataFrame(raw_data, columns=['index', 'value'])
x = list(range(0, len(cnt)))
perfect_duration = (Duration.set_duration(time_duration) -
duration_delta(m=5)).to_duration()
per_index = time_duration // len(cnt)
diff_duration = time_duration - perfect_duration
perfect_start = diff_duration // per_index
y = pd.DataFrame(raw_data[perfect_start:], columns=['index', 'value'])
sma_period = perfect_start * 2
Y = ta.SMA(y['value'].values.astype('float64'),
timeperiod=sma_period).tolist()
top = []
for i, d in enumerate(Y):
if d > 0 and i < len(Y) - 1:
if (Y[i - 1] <= d and d >= Y[i + 1]) or (i == 0
and d >= Y[i + 1]):
top.append((i + perfect_start, d))
# elif Y[i - 1] >= d and d <= Y[i + 1]:
# bottom.append((i, d))
def row_sma(row):
cond = (row['start_index'] <= cnt['index']) & (cnt['index'] <=
row['index'])
max_id = cnt.where(cond).dropna()['value'].idxmax()
result = cnt.loc[max_id]
row['ori_index'] = result['index']
row['ori_value'] = result['value']
row['ori_duration'] = result['index'] * per_index
row['ori_range_duration'] = (row['ori_duration'] - MIN_SEC * 3,
row['ori_duration'] + MIN_SEC * 3)
return row
top_df = pd.DataFrame(top, columns=['index', 'value'])
top_df['value'].where(top_df['value'] > top_df['value'].mean(),
inplace=True)
top_df = top_df.where(top_df['value'] > 0).dropna()
top_df['start_index'] = top_df['index'] - sma_period + 1
top_df['index'] = top_df['index']
a = top_df.apply(row_sma, axis=1)
plt.plot(x, cnt['value'].values, 'r', linewidth=1, label='ori')
plt.plot(x[5:], Y, 'b', linewidth=1, label=f'sma-{sma_period}')
plt.scatter(top_df['index'],
top_df['value'],
100,
marker='^',
label='max')
plt.scatter(a['ori_index'],
a['ori_value'],
100,
marker='v',
label='ori_max')
plt.title(station_num)
plt.legend()
plt.show()