def html_reset_password(token):
jwt_data = decode_jwt(token)
if jwt_data['role'] != 'password':
raise APIException('Access denied', 401)
if request.method == 'GET':
return render_template('reset_password.html',
data={
'host': os.environ.get('API_HOST'),
'token': token
})
# request.method == 'PUT'
body = request.get_json()
check_params(body, 'email', 'password')
user = Users.query.filter_by(id=jwt_data['sub'],
email=body['email']).first()
if not user:
raise APIException('User not found', 404)
user.password = sha256(body['password'])
db.session.commit()
return jsonify({'message': 'Your password has been updated'}), 200
def login():
req = request.get_json()
check_params(req, 'email', 'password', 'device_token')
user = Users.query.filter_by(email=req['email'],
password=sha256(req['password'])).first()
if user is None:
raise APIException('Sorry you entered the wrong email or password',
404)
if user.status._value_ == 'invalid':
raise APIException('Email not validated', 405)
if user.status._value_ == 'suspended':
raise APIException('Your account is suspended', 405)
is_token_registered = \
Devices.query.filter_by( token=req['device_token'] ).first() is not None
profile_exists = Profiles.query.get(user.id) is not None
if profile_exists and not is_token_registered:
db.session.add(Devices(user_id=user.id, token=req['device_token']))
db.session.commit()
return jsonify({
'jwt':
create_jwt({
'id': user.id,
'role': 'user',
'exp': req.get('exp', 15)
})
}), 200
def login():
if request.method == 'GET':
return render_template('login.html', host=os.environ.get('API_HOST'))
json = request.get_json()
utils.check_params(json, 'email', 'password')
user = Users.query.filter_by(email=json['email'],
password=utils.sha256(
json['password'])).first()
if user is None:
return jsonify({
'login': False,
'message': 'Email and password are incorrect',
})
return jsonify({
'login': True,
'jwt': create_jwt({
'id': user.id,
'role': 'admin'
})
})
def update_email(id):
if id == 'me':
id = str(get_jwt()['sub'])
if not id.isnumeric():
raise APIException('Invalid id: ' + id, 400)
body = request.get_json()
check_params(body, 'email', 'password', 'new_email')
user = Users.query.filter_by(id=int(id),
email=body['email'],
password=sha256(body['password'])).first()
if not user:
raise APIException('Invalid parameters', 400)
user.valid = False
user.email = body['new_email']
db.session.commit()
return jsonify({
'message': 'Please verify your new email',
'validation_link': validation_link(user.id)
}), 200
def create_buy_in():
body = request.get_json()
check_params(body, 'flight_id', 'chips', 'table', 'seat')
id = int(get_jwt()['sub'])
prof = Profiles.query.get(id)
if not prof:
raise APIException('User not found', 404)
buyin = Buy_ins(user_id=id,
flight_id=body['flight_id'],
chips=body['chips'],
table=body['table'],
seat=body['seat'])
db.session.add(buyin)
db.session.commit()
name = prof.nickname if prof.nickname else f'{prof.first_name} {prof.last_name}'
# Get the latest entry by checking the created_at
buyin = Buy_ins.query.filter_by(user_id=id,
flight_id=body['flight_id'],
chips=body['chips'],
table=body['table'],
seat=body['seat']).first()
return jsonify({**buyin.serialize(), "name": name}), 200
def register_user():
body = request.get_json()
check_params(body, 'email', 'password', 'device_token')
# If user exists and failed to validate his account
user = (Users.query.filter_by(email=body['email'],
password=sha256(
body['password'])).first())
if user and user.valid == False:
data = {'validation_link': validation_link(user.id)}
send_email(type='email_validation', to=user.email, data=data)
return jsonify({
'message':
'Another email has been sent for email validation'
})
elif user and user.valid:
raise APIException('User already exists', 405)
user = Users(email=body['email'], password=sha256(body['password']))
db.session.add(user)
db.session.add(Devices(token=body['device_token'], user=user))
db.session.commit()
user = Users.query.filter_by(email=body['email']).first()
send_email(type='email_validation',
to=user.email,
data={'validation_link': validation_link(user.id)})
return jsonify({'message': 'Please verify your email'}), 200
def login_admin():
if request.method == 'GET':
return render_template('login.html',
host=os.environ.get('API_HOST'))
json = request.get_json()
utils.check_params(json, 'email', 'password')
user = Users.query.filter_by(email=json['email'],
password=utils.sha256(
json['password'])).first()
if user is None:
return jsonify({
'login': False,
'message': 'Email and password are incorrect',
})
identity = {'id': user.id, 'role': 'admin', 'sub': user.id}
return jsonify({
'login':
True,
'jwt':
jwt.encode(identity,
os.environ['JWT_SECRET_KEY'],
algorithm='HS256')
})
def html_reset_password(token):
jwt_data = decode_jwt(token)
if request.method == 'GET':
user = Users.query.filter_by(id=jwt_data['sub'],
email=jwt_data['role']).first()
if user is None:
raise APIException('User not found', 404)
return render_template('reset_password.html',
host=os.environ.get('API_HOST'),
token=token,
email=jwt_data['role'])
# request.method == 'PUT'
req = request.get_json()
utils.check_params(req, 'email', 'password')
if len(req['password']) < 6:
raise APIException('Password must be at least 6 characters long')
user = Users.query.filter_by(id=jwt_data['sub'], email=req['email'])
if user is None:
raise APIException('User not found', 404)
user.password = utils.sha256(req['password'])
db.session.commit()
return jsonify({'message': 'Your password has been updated'}), 200
def create_buy_in(user_id):
body = request.get_json()
check_params(body, 'flight_id', 'chips', 'table', 'seat')
prof = Profiles.query.get(user_id)
buyin = Buy_ins(user_id=user_id,
flight_id=body['flight_id'],
chips=body['chips'],
table=body['table'],
seat=body['seat'])
db.session.add(buyin)
db.session.commit()
name = prof.nickname if prof.nickname else f'{prof.first_name} {prof.last_name}'
buyin = Buy_ins.query.filter_by(user_id=user_id,
flight_id=body['flight_id'],
chips=body['chips'],
table=body['table'],
seat=body['seat']).order_by(
Buy_ins.id.desc()).first()
return jsonify({**buyin.serialize(), "name": name}), 200
def update_email(user_id):
req = request.get_json()
utils.check_params(req, 'email', 'password', 'new_email')
if req['email'] == req['new_email']:
return jsonify(
{'message': 'Your email is already ' + req['new_email']})
user = Users.query.filter_by(id=user_id,
email=req['email'],
password=utils.sha256(
req['password'])).first()
if user is None:
raise APIException('User not found', 404)
user.status = 'invalid'
user.email = req['new_email']
db.session.commit()
send_email(template='email_validation',
emails=user.email,
data={
'validation_link':
utils.jwt_link(user.id, role='email_change')
})
return jsonify({'message': 'Please verify your new email'}), 200
def swapprofit_user():
json = request.get_json()
utils.check_params(json, 'api_token', 'email', 'password', 'first_name',
'last_name')
if json['api_token'] != utils.sha256(os.environ['API_TOKEN']):
raise APIException('Invalid api token', 400)
# Find user in db
user = Users.query.filter_by(email=json['email']).first()
# If no user found, create one
if user is None:
print('user is None', end='\n')
user = Users(email=json['email'],
password=json['password'],
first_name=json['first_name'],
last_name=json['last_name'],
nickname=json.get('nickname'),
hendon_url=json.get('hendon_url'),
status='valid')
db.session.add(user)
db.session.commit()
return jsonify({'pokersociety_id': user.id})
def reset_password(id):
if id == 'me':
id = str(get_jwt())['sub']
if not id.isnumeric():
raise APIException('Invalid id: ' + id, 400)
if request.args.get('forgot') == 'true':
return jsonify({
'message':
'A link has been sent to your email to reset the password',
'link':
os.environ.get('API_HOST') + '/users/reset_password/' +
create_jwt({
'id': id,
'role': 'password'
})
}), 200
body = request.get_json()
check_params(body, 'email', 'password', 'new_password')
user = Users.query.filter_by(id=int(id),
email=body['email'],
password=sha256(body['password'])).first()
if not user:
raise APIException('Invalid parameters', 400)
user.password = sha256(body['new_password'])
db.session.commit()
return jsonify({'message': 'Your password has been changed'}), 200
def add_device(user_id):
req = request.get_json()
utils.check_params(req, 'device_token')
db.session.add(Devices(
user_id = user_id,
token = req['device_token'] ))
db.session.commit()
return jsonify({'message':'Device added successfully'})
def add_device(user_id):
body = request.get_json()
check_params(body, 'token')
db.session.add(Devices(user_id=user_id, token=body['token']))
db.session.commit()
return jsonify({'message': 'Device added successfully'})
def update_swap():
id = int(get_jwt()['sub'])
# get sender user
sender = Profiles.query.get(id)
if not sender:
raise APIException('User not found', 404)
body = request.get_json()
check_params(body, 'tournament_id', 'recipient_id')
# get recipient user
recipient = Profiles.query.get(body['recipient_id'])
if not recipient:
raise APIException('Recipient user not found', 404)
# get swap
swap = Swaps.query.get((id, recipient.id, body['tournament_id']))
counter_swap = Swaps.query.get((recipient.id, id, body['tournament_id']))
if not swap or not counter_swap:
raise APIException('Swap not found', 404)
if 'percentage' in body:
percentage = abs(body['percentage'])
counter = abs(body['counter_percentage']
) if 'counter_percentage' in body else percentage
sender_availability = sender.available_percentage(
body['tournament_id'])
if percentage > sender_availability:
raise APIException((
'Swap percentage too large. You can not exceed 50% per tournament. '
f'You have available: {sender_availability}%'), 400)
recipient_availability = recipient.available_percentage(
body['tournament_id'])
if counter > recipient_availability:
raise APIException(
('Swap percentage too large for recipient. '
f'He has available to swap: {recipient_availability}%'), 400)
# So it can be updated correctly with the update_table funcion
body['percentage'] = swap.percentage + percentage
update_table(counter_swap,
{'percentage': counter_swap.percentage + counter})
update_table(
swap,
body,
ignore=['tournament_id', 'recipient_id', 'paid', 'counter_percentage'])
db.session.commit()
return jsonify(swap.serialize())
def train_(self, x_0, x, a):
self.train()
self.optimizer.zero_grad()
loss, info = self(x_0, x, a, prior_sample=False)
loss.backward()
# clip_grad_norm_(self.distributions.parameters(), 1000)
self.optimizer.step()
if self.debug:
check_params(self)
return loss, info
def delete_device(user_id):
req = request.get_json()
utils.check_params(req, 'device_token')
devices = Devices.query.filter_by(token=req['device_token'])
for device in devices:
db.session.delete(device)
db.session.commit()
return jsonify({'message': 'Device deleted successfully'})
def update_profile(user_id):
prof = Profiles.query.get(user_id)
req = request.get_json()
utils.check_params(req)
utils.update_table(prof, req, ignore=['profile_pic_url'])
db.session.commit()
return jsonify(prof.serialize())
def invite_users(user_id):
req = request.get_json()
utils.check_params(req, 'email')
user = Users.query.get(user_id)
send_email('invitation_email',
emails=req['email'],
data={'user_name': f'{user.first_name} {user.last_name}'})
return jsonify({'message': 'Invitation sent successfully'})
def update_profile(user_id):
prof = Profiles.query.get(user_id)
body = request.get_json()
check_params(body)
update_table(prof, body, ignore=['profile_pic_url'])
db.session.commit()
return jsonify(prof.serialize())
def svm_pred(argv):
"""A top level script to parse input parameters and train and predict"""
assert(argv[1]=='pred')
if len(argv)<6:sys.stderr.write("usage: %s pred C kernelname kernelparameters [arff|fasta] inputfiles outputfile [dna|protein] non(nucleotide|amino)converter\n" % argv[0]);sys.exit(-1)
# parse input parameters
C = float(argv[2])
(kernelname,kparam,argv_rest) = parse.parse_kernel_param(argv[3:],False)
(trainex, trainlab, testex, argv_rest) = parse.parse_input_file_train_test(kernelname, argv_rest)
(seq_source, nuc_con) = ('', '')
if kernelname == 'spec' or kernelname == 'wd':
if len(argv_rest)<1:sys.stderr.write("outputfile [dna|protein] non(nucleotide|amino)converter are missing\n");sys.exit(-1)
if len(argv_rest)<2:sys.stderr.write("[dna|protein] non(nucleotide|amino)converter are missing\n");sys.exit(-1)
if len(argv_rest)<3:
if argv_rest[-1] == 'dna':
sys.stderr.write("non-nucleotide converter like [A|T|C|G|R|Y|N] is missing. Cannot continue.\n")
sys.exit(-1)
elif argv_rest[-1] == 'protein':
sys.stderr.write("non-amino acid converter like [G|P|A|V|L|I|M|C|F|Y|W|H|K|R|Q|N|E|D|S|T|random] is missing. Cannot continue.\n")
sys.exit(-1)
else:
sys.stderr.write("Here expect FASTA sequence type as [dna|protein] instead of -"+ argv_rest[-1] +"- Cannot continue.\n")
sys.exit(-1)
if len(argv_rest)>3:sys.stderr.write("Too many arguments\n");sys.exit(-1)
seq_source = argv_rest[1]
nuc_con = argv_rest[2]
if kernelname == 'linear' or kernelname== 'poly' or kernelname == 'gauss':
if len(argv_rest)<1:sys.stderr.write("outputfile missing\n");sys.exit(-1)
if len(argv_rest)>1:sys.stderr.write("Too many arguments\n");sys.exit(-1)
outfilename = argv_rest[0]
utils.check_params(kparam, C, len(trainex[0]))
# run training and testing
svmout = train_and_test(trainex, trainlab, testex, C, kernelname, kparam, seq_source, nuc_con)
# write output file
try:
f = open(outfilename,'w')
except:
sys.stderr.write('Fails to open the outputfile at ' + outfilename + ' Cannot continue.\n')
sys.exit(-1)
res_str = '#example\toutput\n'
f.write(res_str)
for ix in xrange(len(svmout)):
res_str = str(ix)+'\t'+str(svmout[ix])+'\n'
f.write(res_str)
f.close()
def swapprofit_email_update(id):
json = request.get_json()
utils.check_params(json, 'api_token', 'email')
if json['api_token'] != utils.sha256(os.environ['API_TOKEN']):
raise APIException('Invalid api token', 400)
user = Users.query.get(id)
user.email = json['email']
db.session.commit()
return jsonify({'message': 'ok'}), 200
def add_coins(user_id):
req = request.get_json()
utils.check_params(req, 'coins')
db.session.add(
Transactions(user_id=user_id,
coins=req['coins'],
dollars=req.get('dollars', 0)))
db.session.commit()
user = Profiles.query.get(user_id)
return jsonify({'total_coins': user.get_coins()})
def svm_cv(argv):
"""A top level script to parse input parameters and run cross validation"""
assert(argv[1]=='cv')
if len(argv)<5:sys.stderr.write("usage: %s cv repeat C kernelname [kernelparameters] [arff|fasta] inputfiles outputfile [dna|protein] non(nucleotide|amino)converter \n" % argv[0]);sys.exit(-1)
# parse input parameters
cv = int(argv[2])
C = float(argv[3])
(kernelname,kparam,argv_rest) = parse.parse_kernel_param(argv[4:],False)
(examples,labels,argv_rest) = parse.parse_input_file_train(kernelname, argv_rest)
(seq_source, nuc_con) = ('', '')
if kernelname == 'spec' or kernelname == 'wd':
if len(argv_rest)<1:sys.stderr.write("outputfile [dna|protein] non(nucleotide|amino)converter are missing\n");sys.exit(-1)
if len(argv_rest)<2:sys.stderr.write("[dna|protein] non(nucleotide|amino)converter are missing\n");sys.exit(-1)
if len(argv_rest)<3:
if argv_rest[-1] == 'dna':
sys.stderr.write("non-nucleotide converter like [A|T|C|G|R|Y|N] is missing. Cannot continue.\n")
sys.exit(-1)
elif argv_rest[-1] == 'protein':
sys.stderr.write("non-amino acid converter like [G|P|A|V|L|I|M|C|F|Y|W|H|K|R|Q|N|E|D|S|T|random] is missing. Cannot continue.\n")
sys.exit(-1)
else:
sys.stderr.write("Here expect FASTA sequence type as [dna|protein] instead of -"+ argv_rest[-1] +"- Cannot continue.\n")
sys.exit(-1)
if len(argv_rest)>3:sys.stderr.write("Too many arguments\n");sys.exit(-1)
seq_source = argv_rest[1]
nuc_con = argv_rest[2]
if kernelname == 'linear' or kernelname == 'gauss' or kernelname == 'poly':
if len(argv_rest)<1:sys.stderr.write("outputfile misssing\n");sys.exit(-1)
if len(argv_rest)>1:sys.stderr.write("Too many arguments\n");sys.exit(-1)
outfilename = argv_rest[0]
utils.check_params(kparam, C, len(examples[0]))
# run cross-validation
(all_outputs, all_split) = crossvalidation(cv, kernelname, kparam, C, examples, labels, seq_source, nuc_con)
try:
f = open(outfilename, 'w+')
except:
sys.stderr.write('Fails to open the outputfile at ' + outfilename + ' Cannot continue.\n')
sys.exit(-1)
res_str = '#example\toutput\tsplit\n'
f.write(res_str)
for ix in xrange(len(all_outputs)):
res_str = '%d\t%2.7f\t%d\n' % (ix,all_outputs[ix],all_split[ix])
f.write(res_str)
f.close()
def main(config_file,mode,distributed):
config = check_params(config_file)
if mode in ["Train","train"]:
train_dataset = Dataset(config["train_params"]["input_path"],config["train_params"]["imsize"])
if distributed:
import horovod as hvd
hvd.init()
if hvd.rank()==0:
writer = setup_tensorboard(get_params(config["train_params"],"tensorboard_location","./summary/"))
train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset, num_replicas=hvd.size(),
rank=hvd.rank())
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=config["train_params"]["batch_size"],
sampler=train_sampler, shuffle=True)
model = ConvLSTM(**config["model_params"])
optimizer = hvd.DistributedOptimizer(model.optimizer, named_parameters=model.named_parameters())
hvd.broadcast_parameters(model.state_dict(), root_rank=0)
train_distributed(model,train_loader,optimizer,config,writer)
else:
writer = setup_tensorboard(get_params(config["train_params"], "tensorboard_location", "./summary/"))
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=config["train_params"]["batch_size"],
shuffle = True)
model = ConvLSTM(**config["model_params"])
train(model,train_loader,model.optimizer,config,writer)
elif mode in ["infer","Infer"]:
model = ConvLSTM(**config["model_params"])
model.load_state_dict(config["infer_params"]["model_save_path"])
output_file = open(config["infer_params"]["output_path"])
def set_swap_paid(user_id):
# get sender user
sender = Profiles.query.get(user_id)
body = request.get_json()
check_params(body, 'tournament_id', 'recipient_id')
swap = Swaps.query.get(user_id, body['recipient_id'],
body['tournament_id'])
swap.paid = True
db.session.commit()
return jsonify({'message': 'Swap has been paid'})
def update_buy_in(id):
body = request.get_json()
check_params(body)
user_id = int(get_jwt()['sub'])
buyin = Buy_ins.query.get(id)
update_table(buyin,
body,
ignore=['user_id', 'flight_id', 'receipt_img_url'])
db.session.commit()
return jsonify(Buy_ins.query.get(id).serialize())
def update_buy_in(user_id, id):
req = request.get_json()
utils.check_params(req)
buyin = Buy_ins.query.get(id)
if buyin is None:
raise APIException('Buy_in not found', 404)
if buyin.status._value_ == 'busted':
raise APIException('This buyin has a status of "busted"')
if request.args.get('validate') == 'true':
if buyin.status._value_ == 'pending':
utils.check_params(req, 'chips', 'table', 'seat')
buyin.status = 'active'
# send_email(template='buyin_receipt', emails=buyin.user.user.email,
# data={
# 'receipt_url': buyin.receipt_img_url,
# 'tournament_date': buyin.flight.tournament.start_at,
# 'tournament_name': buyin.flight.tournament.name
# })
elif buyin.status._value_ == 'active':
raise APIException('Buy in already validated')
elif buyin.status._value_ == 'pending':
raise APIException('This buyin has not been validated', 406)
# Update status
if req.get('status') == 'busted':
buyin.status = 'busted'
# Update chips, table and seat
if req.get('chips') is not None:
if req['chips'] > 999999999:
raise APIException('Too many characters for chips')
buyin.chips = req['chips']
if req.get('table') is not None:
if len(req['table']) > 20:
raise APIException('Too many characters for table')
buyin.table = req['table']
if req.get('seat') is not None:
buyin.seat = req['seat']
db.session.commit()
return jsonify({'buy_in': buyin.serialize()})
def create_chat(user_id):
req = request.get_json()
utils.check_params(req, 'user2_id', 'tournament_id')
chat = Chats.get(user_id, req['user2_id'], req['tournament_id'])
if chat is not None:
raise APIException('Chat already exists with id ' + str(chat.id),
400)
chat = Chats(user1_id=user_id,
user2_id=req['user2_id'],
tournament_id=req['tournament_id'])
db.session.add(chat)
db.session.commit()
return jsonify(chat.serialize())
def create_swap():
id = int(get_jwt()['sub'])
# get sender user
sender = Profiles.query.get(id)
if not sender:
raise APIException('User not found', 404)
body = request.get_json()
check_params(body, 'tournament_id', 'recipient_id', 'percentage')
# get recipient user
recipient = Profiles.query.get(body['recipient_id'])
if not recipient:
raise APIException('Recipient user not found', 404)
if Swaps.query.get((id, body['recipient_id'], body['tournament_id'])):
raise APIException('Swap already exists, can not duplicate', 400)
sender_availability = sender.available_percentage(body['tournament_id'])
if body['percentage'] > sender_availability:
raise APIException((
'Swap percentage too large. You can not exceed 50% per tournament. '
f'You have available: {sender_availability}%'), 400)
recipient_availability = recipient.available_percentage(
body['tournament_id'])
if body['percentage'] > recipient_availability:
raise APIException(
('Swap percentage too large for recipient. '
f'He has available to swap: {recipient_availability}%'), 400)
db.session.add(
Swaps(sender_id=id,
tournament_id=body['tournament_id'],
recipient_id=body['recipient_id'],
percentage=body['percentage']))
db.session.add(
Swaps(sender_id=body['recipient_id'],
tournament_id=body['tournament_id'],
recipient_id=id,
percentage=body['percentage']))
db.session.commit()
return jsonify({'message': 'ok'}), 200
def svm_poim(argv):
"""A top level script to parse input parameters and plot poims"""
assert(argv[1]=='poim')
if len(argv)<7:sys.stderr.write("usage: %s poim C poimdegree wd [kernelparameters] [arff|fasta] inputfiles poim.png [dna|protein] non(nucleotide|amino)converter\n" % argv[0]);sys.exit(-1)
# parse input parameters
C = float(argv[2])
poimdegree = int(argv[3])
(kernelname,kparam,argv_rest) = parse.parse_kernel_param(argv[4:], False)
(examples,labels,argv_rest) = parse.parse_input_file_train(kernelname, argv_rest)
if len(argv_rest)<1:sys.stderr.write("poim.png [dna|protein] non(nucleotide|amino)converter are missing\n");sys.exit(-1)
if len(argv_rest)<2:sys.stderr.write("[dna|protein] non(nucleotide|amino)converter are missing\n");sys.exit(-1)
if len(argv_rest)<3:
if argv_rest[-1] == 'dna':
sys.stderr.write("non-nucleotide converter like [A|T|C|G|R|Y|N] is missing. Cannot continue.\n")
sys.exit(-1)
elif argv_rest[-1] == 'protein':
sys.stderr.write("non-amino acid converter like [G|P|A|V|L|I|M|C|F|Y|W|H|K|R|Q|N|E|D|S|T|random] is missing. Cannot continue.\n")
sys.exit(-1)
else:
sys.stderr.write("Here expect FASTA sequence type as [dna|protein] instead of -"+ argv_rest[-1] +"- Cannot continue.\n")
sys.exit(-1)
if len(argv_rest)>3:sys.stderr.write("Too many arguments\n");sys.exit(-1)
poimfilename = argv_rest[0]
seq_source = argv_rest[1]
nuc_con = argv_rest[2]
utils.check_params(kparam, C, len(examples[0]))
# train svm and compute POIMs
(svm, kernel, feats_train, preproc) = train(examples,labels,C,kernelname,kparam,seq_source,nuc_con)
print "done with training "
(poim, max_poim, diff_poim, poim_totalmass) = compute_poims(svm, kernel, poimdegree, len(examples[0]))
# plot poims
plots.plot_poims(poimfilename, poim, max_poim, diff_poim, poim_totalmass, poimdegree, len(examples[0]))
def svm_modelsel(argv):
"""A top level script to parse input parameters and run model selection"""
assert(argv[1]=='modelsel')
if len(argv)<5:sys.stderr.write("usage: %s modelsel repeat Cs kernelname [kernelparameters] [arff|fasta] inputfiles outputfile [dna|protein] non(nucleotide|amino)converter\n" % argv[0]);sys.exit(-1)
# parse input parameters
cv = int(argv[2])
Cs = parse.parse_float_list(argv[3])
(kernelname,kparam,argv_rest) = parse.parse_kernel_param(argv[4:], True)
(examples,labels,argv_rest) = parse.parse_input_file_train(kernelname, argv_rest)
(seq_source, nuc_con) = ('', '')
if kernelname == 'spec' or kernelname == 'wd':
if len(argv_rest)<1:sys.stderr.write("outputfile [dna|protein] non(nucleotide|amino)converter are missing\n");sys.exit(-1)
if len(argv_rest)<2:sys.stderr.write("[dna|protein] non(nucleotide|amino)converter are missing\n");sys.exit(-1)
if len(argv_rest)<3:
if argv_rest[-1] == 'dna':
sys.stderr.write("non-nucleotide converter like [A|T|C|G|R|Y|N] is missing. Cannot continue.\n")
sys.exit(-1)
elif argv_rest[-1] == 'protein':
sys.stderr.write("non-amino acid converter like [G|P|A|V|L|I|M|C|F|Y|W|H|K|R|Q|N|E|D|S|T|random] is missing. Cannot continue.\n")
sys.exit(-1)
else:
sys.stderr.write("Here expect FASTA sequence type as [dna|protein] instead of -"+ argv_rest[-1] +"- Cannot continue.\n")
sys.exit(-1)
if len(argv_rest)>3:sys.stderr.write("Too many arguments\n");sys.exit(-1)
seq_source = argv_rest[1]
nuc_con = argv_rest[2]
if kernelname == 'linear' or kernelname == 'gauss' or kernelname== 'poly':
if len(argv_rest)<1:sys.stderr.write("outputfile missing\n");sys.exit(-1)
if len(argv_rest)>1:sys.stderr.write("Too many arguments\n");sys.exit(-1)
outfilename = argv_rest[0]
# run cross-validation
mean_rocs=[] ;
mean_prcs=[] ;
mean_accs=[] ;
all_Cs = [] ;
all_kparam=[] ;
if kparam["modelsel_name"]==None:
for C in Cs:
utils.check_params(kparam, C, len(examples[0]))
(all_outputs, all_split) = crossvalidation(cv, kernelname, kparam, C, examples, labels, seq_source, nuc_con)
(res_str, mean_roc, mean_prc, mean_acc) = evaluate(all_outputs, all_split, labels)
mean_rocs.append(mean_roc)
mean_prcs.append(mean_prc)
mean_accs.append(mean_acc)
all_Cs.append(C)
all_kparam.append(None)
else: # also optimize one kernel parameter
for C in Cs:
for kp in kparam["modelsel_params"]:
kparam[kparam["modelsel_name"]] = kp
utils.check_params(kparam, C, len(examples[0]))
(all_outputs, all_split) = crossvalidation(cv, kernelname, kparam, C, examples, labels, seq_source, nuc_con)
(res_str, mean_roc, mean_prc, mean_acc) = evaluate(all_outputs, all_split, labels)
mean_rocs.append(mean_roc)
mean_prcs.append(mean_prc)
mean_accs.append(mean_acc)
all_Cs.append(C)
all_kparam.append(kp)
max_roc=numpy.max(numpy.array(mean_rocs))
max_prc=numpy.max(numpy.array(mean_prcs))
max_acc=numpy.max(numpy.array(mean_accs))
try:
f = open(outfilename, 'w+')
except:
sys.stderr.write('Fails to open the outputfile at ' + outfilename + ' Cannot continue.\n')
sys.exit(-1)
if kparam["modelsel_name"]==None or len(kparam["modelsel_params"])==1:
detail_str = "\tC\tROC\tPRC\tAccuracy (at threshold 0)\n"
else:
detail_str = "\tC\t%s\tROC\tPRC\tAccuracy (at threshold 0)\n" % kparam["modelsel_name"]
best_roc_str=''
best_prc_str=''
best_acc_str=''
for i in xrange(len(all_Cs)):
# determine the best parameter combinations
if mean_rocs[i]==max_roc:
rocsym='+'
best_roc_str+=model2str(kparam, all_Cs[i], all_kparam[i])+'\n'
else:
rocsym=' '
if mean_prcs[i]==max_prc:
prcsym='+'
best_prc_str+=model2str(kparam, all_Cs[i], all_kparam[i])+'\n'
else:
prcsym=' '
if mean_accs[i]==max_acc:
accsym='+'
best_acc_str+=model2str(kparam, all_Cs[i], all_kparam[i])+'\n'
else:
accsym=' '
detail_str+=model2str(kparam, all_Cs[i], all_kparam[i], False)+'\t'
if kparam["modelsel_name"]==None or len(kparam["modelsel_params"])==1:
detail_str += '%c%2.1f%%\t%c%2.1f%%\t%c%2.1f%%\n' % (rocsym, 100*mean_rocs[i], prcsym, 100*mean_prcs[i], accsym, 100*mean_accs[i])
else:
detail_str += '%c%2.1f%%\t%c%2.1f%%\t%c%2.1f%%\n' % (rocsym, 100*mean_rocs[i], prcsym, 100*mean_prcs[i], accsym, 100*mean_accs[i])
f.write('Best model(s) according to ROC measure:\n%s' % best_roc_str)
f.write('\nBest model(s) according to PRC measure:\n%s' % best_prc_str)
f.write('\nBest model(s) according to accuracy measure:\n%s' % best_acc_str)
f.write('\nDetailed results:\n')
f.write(detail_str)
f.close()