def main(args):
"""
Main running script
"""
# Get the config file
config = util.get_config(args.config)
root_dir = config['ROOT_DIR']
# fill out initial folders
if not os.path.isdir('{}/metadata'.format(root_dir)):
os.mkdir('{}/metadata'.format(root_dir))
print('created metadata dir')
if not os.path.isdir('{}'.format(config['OBS_ROOT'])):
os.mkdir('{}'.format(config['OBS_ROOT']))
print('created OBS dir')
if not os.path.isdir('{}'.format(config['ESTIMATORS_ROOT'])):
os.mkdir('{}'.format(config['ESTIMATORS_ROOT']))
print('created ESTIMATORS dir')
if not os.path.isdir('{}'.format(config['PREDICTIONS_ROOT'])):
os.mkdir('{}'.format(config['PREDICTIONS_ROOT']))
print('created PREDICTIONS dir')
if not os.path.isdir('{}'.format(config['QAQC_ROOT'])):
os.mkdir('{}'.format(config['QAQC_ROOT']))
print('created QAQC dir')
if not os.path.isdir('{}'.format(config['PLOT_ROOT'])):
os.mkdir('{}'.format(config['PLOT_ROOT']))
print('created PLOT dir')
# --- download data ---
if args.clean:
clean.main(config)
else:
print('skipping database cleaning')
# --- download data ---
if args.download:
download.main(config)
else:
print('skipping download of new data')
# --- train models
if args.train:
train.main(config)
else:
print('skip training')
# --- make predictions ---
if args.predict:
predict.main(config)
else:
print('skipping download of new data')
# --- run qaqc checks ---
if args.qaqc:
qaqc.main(config)
else:
print('skipping qaqc')
# --- plot ---
if args.plot:
plot.main(config)
else:
print('skipping plots')
def main():
logger.info("Running main ...")
train.main()
predict.main()
logger.info("Run complete ...")
return
def main():
print 'TRAINING'
train.main()
print 'PREDICTING'
predict.main()
print 'EVAlUATING'
evaluate.main()
def main():
print "TRAINING"
train.main()
print "PREDICTING"
predict.main()
print "EVAlUATING"
evaluate.main()
def main1():
trainimgpath='/home/zhaojin/data/TacomaBridge/segdata/train/img/'
checkpointsavepath='/home/zhaojin/data/TacomaBridge/segdata/train/checkpoint/'
checkpointreadpath='/home/zhaojin/data/TacomaBridge/segdata/train/checkpoint/weight_logloss_softmax/CP30.pth'
predictimgname='/home/zhaojin/data/TacomaBridge/segdata/train/img/00034.png'
predictimgpath='/home/zhaojin/data/TacomaBridge/capture/high-reso-clip2_rename/'
predictlblpath='/home/zhaojin/data/TacomaBridge/segdata/predict/'
predictlblvizpath=predictlblpath.rstrip('/') + "_viz"
predict.main(['--model',checkpointreadpath, '--input',predictimgname, '--viz'])
def main(): sqlite.main() createtable.main() myObj.main() rough.main() ratinggen.main() predict.main() #jsut.main() piechart.main() tocsv.main() predweek.main()
def test_house(self):
# svr
result = predict.main(f'{TEST_PATH}/house/test_config.json')
"""
assert_frame_equal(
result['Y_pred_df'].round(0),
pd.read_csv(f'{TEST_PATH}/house/output.csv').round(0))
"""
# keras
result = predict.main(f'{TEST_PATH}/house/test_config2.json')
# ensemble(vote)
result = predict.main(f'{TEST_PATH}/house/test_config3.json')
# tabnet
result = predict.main(f'{TEST_PATH}/house/test_config4.json')
def main():
feature.main()
'''
利用网格搜索选择参数，时间较长，可以不运行
'''
# params.main()
'''
利用最后一星期的数据来测试模型的效果
'''
test.main()
'''
预测结果
'''
predict.main()
def main():
tstart = dt.now()
print('\nStarting with program\n')
model_training.main()
print('Finished training model in:\n', dt.now()-tstart)
print('predicting outcome of test set:\n')
bool_ = input('start predicting? Y/N?\n')
if bool_=='Y':
tstart2 = dt.now()
predict.main()
print('\nFinished predicting in:\n',dt.now()-tstart2)
print('\nFinished whole program in:\n',dt.now()-tstart)
print('Predictions can be found in:', Data_importer.location_lookup()["submission_path"])
def main(test_user, max_reco):
ind = retrieve_pickle('review_index.txt')
idf = calc_idf(ind, test_user)
similarity_score = find_similarity(ind, test_user)
#sim_score = take_max(similarity_score)
sim_score = take_avg(similarity_score)
sim_score = sorted(sim_score.iteritems(), key=operator.itemgetter(1), reverse=True)
best_users = select_no_of_users(sim_score, 100)
predict.main(ind, best_users, test_user, max_reco)
def getData(roadName):
global tempData
road = roadName[:-2]
url = ""
if '1000_E' in roadName:
url = up_1000
elif '1000_S' in roadName:
url = down_1000
elif '1200_E' in roadName:
url = up_1200
elif '1200_S' in roadName:
url = down_1200
elif '0150_E' in roadName:
url = up_0150
elif '0150_S' in roadName:
url = down_0150
elif '0600_E' in roadName:
url = up_0600
elif '0600_S' in roadName:
url = up_0600
else:
print('\t[+] ERROR in roadName request - {}'.format(roadName))
return
parsedList = parseURL(url)
data = formatData(roadName[-1], parsedList, road)
data = predict.main(data)
return json.dumps(data)
def eval():
#sys.argv[1:]=[e2.get()]
sys.argv[1:] = [e2.get(), e3.get()]
print(e2.get())
print(e3.get())
dic, time1 = predict.main(predict.parse_arguments(sys.argv[1:]))
var7.set(dic)
var8.set(time1)
def uploaded_file(filename):
predict.FilePaths.fnInfer = os.path.join(app.config['UPLOAD_FOLDER'],
filename)
result = predict.main()
return render_template('second.html',
text=result['Recognized'],
prob=result['Probability'],
accu=result['Accuracy'])
def textres(request):
if request.method == "POST":
x = request.POST.get('content')
temp = get_template('textres.html')
new_x = str(x)
val = predict.main(new_x)
cont = RequestContext(request,{'string':x,'sentiment':val})
return HttpResponse(temp.render(cont))
def get_caption(filename):
os.chdir('../ImageCaptionGenerator')
src = os.path.join('../image_autocaption/static/images', filename)
dst = os.path.join('image/pred', filename)
shutil.copyfile(src, dst)
caption = predict.main()
os.chdir(os.path.dirname(os.path.realpath(__file__)))
return caption
def main():
import json
import requests
from bs4 import BeautifulSoup
import predict
title = input('Search by title: ')
year = input('Year of title (Optional): ')
omdbapi_url = 'http://www.omdbapi.com/?t=' + title + '&y=' + year + '&apikey=1fb69a60'
s = requests.session()
r = s.get(omdbapi_url)
omdbapi_reponse = json.loads(r.text)
reviews = []
if (omdbapi_reponse['Response'] == 'True'):
imdbID = omdbapi_reponse['imdbID']
title = omdbapi_reponse['Title']
year = omdbapi_reponse['Year']
elif (omdbapi_reponse['Response'] == 'False'):
print(omdbapi_reponse['Error'])
input('No movie is found.\nPress Enter to continue...')
return reviews
imdb_url = 'https://www.imdb.com/title/' + imdbID + '/reviews/_ajax?'
processed = 0
while True:
r = s.get(imdb_url)
soup = BeautifulSoup(r.text, 'html.parser')
for div in soup.findAll('div', 'text show-more__control'):
reviews.append(div.text)
processed += 1
print(processed, ' reviews retrieved.', end='\r')
load_more_data = soup.findAll('div', 'load-more-data')
if load_more_data == []:
break
else:
imdb_url = 'http://www.imdb.com/title/' + imdbID + '/reviews/_ajax?paginationKey=' + load_more_data[
0]['data-key']
print('\nAll reviews retrieved.')
predict.main(reviews, title=title, year=year)
def main():
with open('pi', 'rb') as f:
data = pi.load(f)
lt, count = [], 0
print('Select any one of the following to visualize graph')
for i in data:
lt.append(i)
print(count, i)
count += 1
print('Press any other key to visualize all graphs')
try:
r = int(input('Enter number:-'))
except:
print('Only integers are allowed.')
exit()
if r >= 0 and r < count:
predict.main(True, lt[r])
else:
predict.main(False, 'No')
def test(name=None):
if request.method == 'POST':
result = request.form
result = pd.Series(result)
query_input = str(result[0])
predictions = predict.main(query_input)
predictions = json.dumps(predictions[0])
return render_template('test.html', userinput=predictions)
else:
return render_template('test.html')
def textres(request):
if request.method == "POST":
x = request.POST.get('content')
temp = get_template('textres.html')
new_x = str(x)
val = predict.main(new_x)
cont = RequestContext(request,{'string':x,'sentiment':val})
return HttpResponse(temp.render(cont))
def startLoad(self):
self.startLoading.setEnabled(False)
self.statusLabel.setText("Scaning Images.")
scanner.main(MainWindow.form_id)
self.statusLabel.setText("Images Scanned. Cropping Images.")
cropper.main(MainWindow.form_id)
self.statusLabel.setText("Images Cropped. Finding Tags.")
PatternLocator.main(MainWindow.form_id)
self.statusLabel.setText("Tags located. Extraacting Data.")
predict.main(MainWindow.form_id)
self.statusLabel.setText("Done.")
self.startVerifying.setEnabled(True)
temp = list(np.load("results.npy"))
for each in temp:
MainWindow.result.append(list(each))
MainWindow.x, MainWindow.y = len(MainWindow.result), len(
MainWindow.result[1])
def result():
file = request.files['dataset']
interval = request.form['interval']
actualValue, lPredictedValue, sPredictedValue = main(file, interval)
return render_template('result.html',
a=actualValue,
lp=lPredictedValue,
sp=sPredictedValue,
len=len(actualValue))
def index_get():
if request.method == 'GET':
return render_template('index.html')
elif request.method == 'POST':
img = request.files['file']
img = img.stream.read()
bin_data = io.BytesIO(img)
file_bytes = np.asarray(bytearray(bin_data.read()), dtype=np.uint8)
img = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
result = main(img)
print(result)
return render_template('result.html', result=result)
def result():
global x, y, z
file = request.files['dataset']
interval = request.form['interval']
destination = 'static/dataset.csv'
file.save(destination)
linear, rbf, date, a1, a2, coef, const = main(str(interval),destination)
x = date
y = linear
z = rbf
return render_template('result.html', valv = [linear, rbf, date, a1, a2, coef, const, len(linear)])
def main():
commands = ['train', 'predict', 'evaluate']
help_msg = \
'''
Usage: cliner [OPTIONS] COMMAND [ARGS]...
Options:
--help Show this message and exit.
Commands:
%s
''' % '\n '.join(commands)
# Is argument correct?
if len(sys.argv
) < 2 or sys.argv[1] not in commands or sys.argv[1] == '--help':
sys.stderr.write('%s\n\n' % (help_msg))
exit(1)
# select appropriate sub-command
subcmd = sys.argv[1]
del sys.argv[1]
# Where to import code from
homedir = os.path.dirname(os.path.abspath(__file__))
codedir = os.path.join(homedir, 'code')
if codedir not in sys.path:
sys.path.append(codedir)
# Call appropriate sub-command
if subcmd == 'train':
import train
train.main()
elif subcmd == 'predict':
import predict
predict.main()
elif subcmd == 'evaluate':
import evaluate
evaluate.main()
def run_dir(in_path, out_path):
f = open('error.txt', 'w')
cwd = os.getcwd()
for item in os.listdir(in_path):
os.chdir(cwd)
e = True
if item.endswith('.wav'):
out_file_path = out_path + item.replace('.wav', '.TextGrid')
if not os.path.exists(out_file_path):
e = main(in_path + item, out_file_path)
if not e:
f.write(item + '\n')
print('ERROR with file: ' + item)
f.close()
def model_predict(img):
"""
Returns Severity of diagnosis
:returns : prediction
"""
print('Loading Model...')
# Getting the score of diagnosis
score = predict.main()
print('Model loaded. Check http://127.0.0.1:5000/')
sev_diag = severity(score)
return sev_diag
def get_video_stream():
"""
Here is where we receive streamed images from the Kafka Server and convert
them to a Flask-readable format.
"""
for msg in consumer:
# print(type(msg.value)) # class <bytes>
imageStream = io.BytesIO(
msg.value
) # kafka msg.value will be in bytes format. This is to read binary img object which is msg.value
imageFile = Image.open(
imageStream
) #imageStream will have img binary data in object format or array format
b = io.BytesIO()
filename = "test.jpeg"
imageFile.save(filename, format="jpeg")
# test=imageFile.save(imageStream, format="jpeg")
# print(type(test))
predict.main()
yield (b'--frame\r\n'
b'Content-Type: image/jpg\r\n\r\n' + msg.value + b'\r\n\r\n')
def result():
global x, y, z
file = request.files['dataset']
interval = request.form['interval']
destination = 'static/dataset.csv'
file.save(destination)
linear, rbf, date, a1, a2, coef, const = main(str(interval), destination)
x = date
y = linear
z = rbf
return render_template(
'result.html',
valv=[linear, rbf, date, a1, a2, coef, const,
len(linear)])
def stacked_dataset(members):
stackX = None
for i in members:
yhat = main(i)
print(yhat.size())
# stack predictions into [rows, members, probabilities]
if stackX is None:
stackX = yhat
else:
stackX = dstack((stackX, yhat))
# flatten predictions to [rows, members x probabilities]
print(type(stackX))
stackX = stackX.reshape(
(stackX.shape[0], stackX.shape[1] * stackX.shape[2]))
return stackX
def lips_to_text():
# try:
start = time.time()
video = request.files.get("video")
if video == None:
return Response("No video received", status=400)
vname = "video." + video.filename.split(".")[-1]
start0 = time.time()
video.save(vname)
print("video saving ", time.time() - start0)
result = predict.main(vname)
print("request time ", time.time() - start)
return Response(result)
def setPredictWindow(conn):
print('predictwindow!!!!')
#title, id, url, channel, duration, viewcount
#predict 후 운동이름, 영상리스트 순서대로 보냄.
exercise_name = Predict.main()
conn.sendall(
pack('i', len(exercise_name.encode('utf-8'))) +
exercise_name.encode('utf-8'))
setSelectWindow(exercise_name, conn)
os.system(
'cd C:\\Users\\MBM\\Desktop\\TRAIN\\video_classification\\data\\predict'
)
os.system('del *.jpg')
def getAnswers(self):
res = []
#import predict
#TODO put input img path and question.
#predict.main(img,question)
# get answers from model eval forward
##### ASK QUESTION HERE
# for i in range(len(self.answers)):
# self.answers[i].set(res[i])
ans_map, answer_probab_tuples = predict.main(self.filename, self.getQuestion())
for i in range(5):
res.append(ans_map[answer_probab_tuples[i][1]] +"," + "%0.2f" % (-100*answer_probab_tuples[i][0]) + "%")
self.answers[i].set(res[i])
def detection():
if request.method == 'POST':
image_b64 = request.values['image'] #vyžádání obrázku z html form jako base64 data
image_b64 = re.sub('^data:image/.+;base64,', '', image_b64) #odříznutí metadat
image_data = BytesIO(base64.b64decode(image_b64)) #dekódovaní base64 dat
image = Image.open(image_data)
predictions = main(image_data) #předání snímku customvision modelu
image = draw_boxes(image, predictions) #vykreslí boxy
#pokud nenajde dost nebo žádný objekt vrátí uživatele zpět
if image == None: return render_template('camera.html', message="Nenalezeno dost objektů, zkuste to prosím znovu.")
#uloží snímek s vykreslenými boxy
image = image.save(os.path.join(app.config['IMAGE_UPLOADS'], '{}.png'.format(predictions[0]['probability'])))
return render_template('choice.html', user_image=os.path.join(app.config['IMAGE_UPLOADS'], '{}.png'.format(predictions[0]['probability']))
,port1=predictions[0]['tagName'], port2=predictions[1]['tagName'])
def index():
# This is a dummy list, 2 nested arrays containing some
# params and values
content = request.get_json(silent=True)
print (content)
n = json.dumps(content)
j = json.loads(n)
print (j['question'])
question = j['question']
answer = "placeholder"
answer = predict.main(question)
#os.system('predict.py')
list = [
{'param': 'answer', 'val': answer},
]
# jsonify will do for us all the work, returning the
# previous data structure in JSON
return jsonify(results=list)
print "Creating a development set for cross-validation"
dev = defaultdict(list)
for i in range(DEV_SIZE/2):
dev['pos'].append(data.train['pos'].pop())
dev['neg'].append(data.train['neg'].pop())
pos = data.train['pos'][:]
neg = data.train['neg'][:]
print "Batch loop - running train and predict"
for i in range(BATCHES):
print "****** Batch #%d ******" % (i+1)
# Build training set
t = defaultdict(list)
for j in range(BATCH_SIZE/2):
t['pos'].append(pos.pop())
t['neg'].append(neg.pop())
# train
main(t)
with open(os.path.join(TMP_DIR, 'batch_%d.txt' % (i)), 'w') as f:
# predict
predict.main(dev, f)
def run_dir(in_path, out_path):
for item in os.listdir(in_path):
if item.endswith('.wav'):
out_file_path = out_path + item.replace('.wav', '.TextGrid')
main(in_path + item, out_file_path)
def main():
parser = argparse.ArgumentParser(description="CliRel (Clinical Relation) \
extractor- trains a classifier able to \
determine the type of relation between \
two medical concepts in a sentence.")
# Add arguments here
parser.add_argument("--train", nargs=3,
metavar=("train_dir", "model_file", "model_type"), type=str,
help="Directory should contain three subdirs (txt, \
concept, rel) containing .txt, .con, .rel files. \
Will train a classifier on this data. \
Trained model will be written to specified model file.\n \
Current model types:[svm-spt, svm-insert, svm-suffix]",
default=None)
parser.add_argument("--predict", nargs=3,
metavar=("test_dir", "model_file", "results_dir"), type=str,
help="Directory contains concept and text files \
that the specified (or default) model will predict. \
Resulting relation files will be written to \
the specified results directory.",
default=None)
parser.add_argument("--evaluate", nargs=3,
metavar=("test_dir", "gold_dir", "eval_file"), type=str,
help="Evaluate the relation files in the test directory \
in comparison with those in the gold directory. The \
results will be written to the evaluation file.",
default=None)
parser.add_argument("--verbose", action="store_true",
default=False, help="Show debugging info.")
args = parser.parse_args()
if not args.predict and not args.train and not args.evaluate:
sys.stderr.write("ERROR: No valid flag specified.\n")
parser.print_help()
sys.exit(1)
if args.train:
checkDir(args.train[0])
checkDir(os.path.dirname(args.train[1]))
if (os.path.isdir(args.train[1])):
sys.stderr.write("ERROR: Model expected to be a file, %s is a directory\n"
% args.train[1])
sys.exit(1)
train.main(args.train[0], args.train[1], args.train[2], args.verbose)
if args.predict:
checkDir(args.predict[0])
checkFile(args.predict[1])
checkDir(args.predict[2])
predict.main(args.predict[0], args.predict[1], args.predict[2], args.verbose)
if args.evaluate:
checkDir(args.evaluate[0])
checkDir(args.evaluate[1])
checkDir(os.path.dirname(args.evaluate[2]))
if (os.path.isdir(args.evaluate[2])):
sys.stderr.write("ERROR: eval_file expected to be a file, %s is a \
directory\n" % args.evaluate[2])
sys.exit(1)
evaluate.main(args.evaluate[0], args.evaluate[1], args.evaluate[2], args.verbose)