def run_analysis(img: ImageData) -> dict:
"""
Analyzes and returns information on the given image.
:param img:
:return:
"""
tags = []
a_start = timer()
results = run_predict(img.data)
a_end = timer()
b_start = timer()
tags += analyze_results(results)
# tags += analyze_colors(img.data)
b_end = timer()
width, height, orientation = get_image_info(img.data)
print('----- Analysis Results -----')
print(f'width: {width} | height: {height} | orientation: {orientation}')
for tag in tags:
print(tag)
print('----------------------------')
print(f'Inference took {a_end - a_start} seconds')
print(f'Analysis took {b_end - b_start} seconds')
print('')
return {
'width': width,
'height': height,
'orientation': orientation,
'tags': tags
}
def character_classification():
"""run character classifiation prediction
---
parameters:
- name: body
in: body
schema:
id: text
required:
- text
properties:
text:
type: string
description: the required text for POST method
required: true
definitions:
SentimentResponse:
Project:
properties:
status:
type: string
ml-result:
type: object
responses:
40x:
description: Client error
200:
description: Character Classification Response
examples:
[
{
"status": "success",
"sentiment": "1"
},
{
"status": "error",
"message": "Exception caught"
},
]
"""
json_request = request.get_json()
if not json_request:
return Response("No json provided.", status=400)
text = json_request['text']
if text is None:
return Response("No text provided.", status=400)
else:
label = run_predict(text)
return flask.jsonify({"status": "success", "label": label})
def predicting(load_path):
model = joblib.load(load_path + 'model.pkl')
S_test = joblib.load(load_path + 'S_test.pkl')
y_test = joblib.load(load_path + 'y_test.pkl')
run_predict((model, S_test, y_test))
if test_bool == True:
gridsearch = True
print('Running star binary')
conf = ConfigVars(test = test_bool, kind = 'star', gridsearch = gridsearch)
lib = HelperFunctions(conf)
run_binary(conf, lib)
print('Running galaxy binary')
conf = ConfigVars(test = test_bool, kind = 'galaxy', gridsearch = gridsearch)
lib = HelperFunctions(conf)
run_binary(conf, lib)
print('Running qso binary')
conf = ConfigVars(test = test_bool, kind = 'qso', gridsearch = gridsearch)
lib = HelperFunctions(conf)
run_binary(conf, lib)
print('Running consolidation')
conf = ConfigVars(test = test_bool)
lib = HelperFunctions(conf)
run_consolidation(conf, lib)
print('Running prediction')
after_opt_str = run_predict(conf, lib)
if test_bool == True:
assert after_opt_str == 'optimal consolidation method: star: 21135, gal: 24111, qso: 1173, outlier: 3581.\n' , 'Test run failed'
if after_opt_str == 'optimal consolidation method: star: 21135, gal: 24111, qso: 1173, outlier: 3581.\n':
print('Test run passed.')
ohlc['ts'] = ohlc[0]
data = pd.merge(ohlc, token_data, on='ts')
data.drop(['ts'], axis='columns', inplace=True)
data.reset_index(drop=True, inplace=True)
if not first_start:
data = data[-2:]
update_markets_data(data)
def exchange_data(first_start):
# TODO futures
trades = get_trades()
bids, asks = get_orderbook()
bids['pr'] = bids[0] * bids[1]
bids_avg = bids['pr'].sum() / bids[1].sum()
asks['pr'] = asks[0] * asks[1]
asks_avg = asks['pr'].sum() / asks[1].sum()
if __name__ == "__main__":
first_start = True
while True:
try:
market_data(first_start)
exchange_data(first_start)
run_predict()
first_start = False
time.sleep(360)
except:
print(datetime.datetime.now(), traceback.format_exc())
def main():
get_number()
guess = predict.run_predict()
show_predict(guess)