def train_2_hidden_layer_anns(lwr=10,
upr=50,
eta=0.25,
mini_batch_size=10,
num_epochs=10):
assert 100 >= upr > lwr >= 10
assert lwr % 10 == 0 and upr % 10 == 0 # divisible by 10
hl1 = 10
eta_vals = (2, 1.5, 1.0, 0.5, 0.25)
results = np.zeros([6, 6], dtype=float)
results[0, 0] = -1
results[1:, 0] = np.array(list(eta_vals))
for y in range(len(results) - 1):
results[0, y + 1] = 10 * (y + 1)
for i in range(len(eta_vals)):
eta = eta_vals[i]
hl2 = lwr
while hl2 <= upr:
print(
f"==== Training {input_layer}x{hl1}x{hl2}x{output_layer} - eta:{eta} ANN ======"
)
net = ann([input_layer, hl1, hl2, output_layer])
net.mini_batch_sgd(train_d, num_epochs, mini_batch_size, eta,
test_d)
result = net.evaluate(test_d)
results[i + 1, hl2 // 10] = result
print(
f"==== Training {input_layer}x{hl1}x{hl2}x{output_layer} ANN - DONE - eta:{eta} ======"
)
hl2 += 10
print(f"Training DONE {input_layer}x{hl1}x10-50x{output_layer}")
print(results)
def __init__(self, suffix, name, main, num_episodes):
self.total_steps = 0
self.batch_size = 64
self.gamma = 0.99
self.gradient_update_step = 1
self.main_update_step = 2
self.grads = {}
self.env = gym.make(name)
oshape = self.env.observation_space.shape
assert main.output_size == self.env.action_space.n
assert oshape[0] == main.input_shape
self.steps = history.history(self.batch_size)
self.main = main
self.num_episodes = num_episodes
self.current_state = state.state(oshape[0], main.state_size)
self.network = ann.ann('thread_' + suffix, main.input_size,
main.output_size, main.swriter)
self.network.import_params(main.network.export_params())
self.thread = threading.Thread(target=self.run)
def __init__(self, name, state_size, output_path):
self.name = name
self.state_size = state_size
self.input_shape = 2
self.output_size = 3
self.input_size = self.state_size * self.input_shape
output_path += '/run.%d' % (time.time())
self.swriter = tf.summary.FileWriter(output_path)
self.network = ann.ann("main", self.input_size, self.output_size,
self.swriter)
def train_1_hidden_layer_anns(lwr=10,
upr=50,
eta=0.25,
mini_batch_size=10,
num_epochs=10):
assert 100 >= upr > lwr >= 10
assert lwr % 10 == 0 and upr % 10 == 0 # divisible by 10
while lwr <= upr:
print(f"==== Training {input_layer}x{lwr}x{output_layer} ANN ======")
net = ann([input_layer, lwr, output_layer])
net.mini_batch_sgd(train_d, num_epochs, mini_batch_size, eta, test_d)
print(
f"==== Training {input_layer}x{lwr}x{output_layer} ANN - DONE - eta:{eta} ======"
)
lwr += 10
import pathlib as path
from ann import ann
from pickle import dump
from mnist_loader import load_data_wrapper
train_d, valid_d, test_d = load_data_wrapper()
dir_name = "pck_nets"
p = path.Path(dir_name)
assert p.is_dir()
nets = []
dummy_sizes = [10, 10]
for json in p.iterdir():
if json.is_file() and json.name.endswith(".json"):
net = ann(dummy_sizes)
net.load(json)
# nets.append(net)
name = json.name.replace(".json", ".pkl")
with open(path.Path.joinpath(p, name), "wb") as my_path:
dump(net, my_path)
# print(nets)
# best_3 = ""
# best_3_score = 0
# best_4 = ""
# best_4_score = 0
# best_5 = ""
# best_5_score = 0
# for net in nets:
# accuracy = net.accuracy(valid_d)
def main():
myann = ann.ann()
myann.request()
def load_csq(self, pos_subset=None):
#pos_subset = ["1","2","3"]
obj_ann = ann.ann(self.params["annfile"], self.params["tabix"])
results = {"loci": [], "variants": []}
for l in open(self.params["dr_vcffile"]):
if l[0] == "#": continue
arr = l.rstrip().split()
if pos_subset and arr[1] not in pos_subset: continue
dp4 = [int(x) for x in re_dp4.search(l).group(1).split(",")]
dp4r = (dp4[2] + dp4[3]) / (dp4[0] + dp4[1] + dp4[2] + dp4[3])
var = {}
var["pos"] = arr[1]
var["chr"] = arr[0]
var["ref"] = arr[3]
var["alt"] = arr[4]
var["dp4r"] = dp4r
if "BCSQ" not in l:
var["bcsq"] = "intergenic"
results["variants"].append(var)
results["loci"].append((arr[0], arr[1]))
continue
csq = re.search("BCSQ=(.*)", arr[7]).group(1).split("|")
if csq[0][0] == "@": continue
var["bcsq"] = csq[0]
if csq[0] == "non_coding":
var["csq"] = {
"locus_tag": csq[1],
"nt_change": "-",
"aa_change": "-"
}
elif csq[0] == "stop_lost&inframe_deletion":
var["csq"] = {
"locus_tag": csq[1],
"nt_change": "-",
"aa_change": "-"
}
elif csq[0] == "inframe_deletion&start_lost":
var["csq"] = {
"locus_tag": csq[1],
"nt_change": "-",
"aa_change": "-"
}
elif csq[0] == "frameshift":
var["csq"] = {
"locus_tag": csq[1],
"nt_change": "-",
"aa_change": "-"
}
else:
if len(csq) == 7:
var["csq"] = {
"locus_tag": csq[1],
"aa_change": csq[5],
"nt_change": csq[6]
}
else:
var["csq"] = {
"locus_tag": csq[1],
"nt_change": "-",
"aa_change": "-"
}
results["variants"].append(var)
results["loci"].append((arr[0], arr[1]))
if len(results["loci"]) == 0:
print("Warning! No Variants")
pos_tup = [("Chromosome", x["pos"]) for x in results["variants"]]
dict_ann = obj_ann.pos2ann(pos_tup)
for var in results["variants"]:
tann = dict_ann["Chromosome"][var["pos"]]
if var["bcsq"] == "intergenic" or var["bcsq"] == "non_coding" or var[
"bcsq"] == "frameshift":
locus_type = "intergenic" if tann["ncr"] == "inter" else "ncRNA"
change = "%s%s>%s" % (tann["gene_nt"], var["ref"], var["alt"])
var["csq"] = {
"var_type": locus_type,
"locus_tag": tann["rv"],
"nt_change": change,
"aa_change": "-"
}
var["csq"]["gene"] = tann["gene"]
return results
import game as myGame
from board import Board
import random
import os
import ann as annie
import numpy
from load import normalize, append_snake
from ai2048demo import welch
import scipy
moves = [Board.LEFT, Board.UP, Board.RIGHT, Board.DOWN]
ann = annie.ann([1000])
def setup_ai(silent=False):
ann.main(silent)
def get_ai_move(game):
board = get_board_weird(game)
board = numpy.asarray(board)
prob = ann.predict_move(board)
#print("prob", prob)
return moves[prob]
def get_ai_moves(game):
board = get_board_weird(game)
board = numpy.asarray(board)
board = normalize(board)
#board = append_snake(board)
return ann.predict_move(board)
import pandas as p
import sys
from ann import ann
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
#from data_plotter import data_plotter
data = p.read_csv("data_cancer.txt", header=None, index_col=0)
data = data.replace("M", 1)
data = data.replace("B", 0)
x = data.values #returns a numpy array
min_max_scaler = preprocessing.MinMaxScaler()
x_scaled = min_max_scaler.fit_transform(x)
data = p.DataFrame(x_scaled)
train, test = train_test_split(data, test_size=0.5)
machine = ann()
machine.create_ann(input_nodes=30,
hidden_layer_lenght=30,
number_hidden_layers=4,
output_nodes=1)
machine.train(train[list(range(1, 31))], train[[0]])
machine.test(test[list(range(1, 31))], test[[0]])
#meta = computeMeta(ds) qds = quantifyData(learning, dum, False) #testing = ds[:200000] print "Quantifying testing data with dum" tds = quantifyData(testing, dum, False) td = quantifyData(ts, dum, True) #print len(qds[0]) #tds = quantifyData(testing, dum) # s, i, g = learn(10) print "Doing gradient descent..." #s = gdescent(0.1, 20, 6) print "ANN" # s = ann.ann(qds, 0.005, 8000) # s = ann.ann(qds, 0.008, 12000) s = ann.ann(qds, 0.01, 10000) #print "Resulting weights of the gradient descent" #print s # s = loadWeights() print "Before doing prediction" prediction = ann.predict(tds, False) #prediction = predict(s,tds, False) #prediction = loadPrediction() print accuracy(prediction, testing, 0.5) print "Printing ROC" x,y = plotROC(prediction, testing) print "AUC" print AUC(x, y) prediction = ann.predict(td, True)
net = ann([input_layer, hl1, hl2, output_layer])
net.mini_batch_sgd(train_d, num_epochs, mini_batch_size, eta,
test_d)
result = net.evaluate(test_d)
results[i + 1, hl2 // 10] = result
print(
f"==== Training {input_layer}x{hl1}x{hl2}x{output_layer} ANN - DONE - eta:{eta} ======"
)
hl2 += 10
print(f"Training DONE {input_layer}x{hl1}x10-50x{output_layer}")
print(results)
# define your networks
net1 = ann([input_layer, 50, 60, output_layer]) # 4 layers
net2 = ann([input_layer, 50, 60, 30, output_layer]) # 5 layers
net3 = ann([input_layer, 10, 30, output_layer]) # 3 layers
net4 = ann([input_layer, 60, 30, 20, 40, 20, output_layer]) # 7 layers
net5 = ann([input_layer, 10, 50, 60, 30, output_layer]) # 6 layers
# define an ensemble of 5 nets
networks = (net1, net2, net3, net4, net5)
eta_vals = (0.1, 0.25, 0.3, 0.4, 0.5)
mini_batch_sizes = (5, 10, 15, 20)
# train networks
def train_nets(networks, eta_vals, mini_batch_sizes, num_epochs, path):
assert pathlib.Path(path).is_dir()
x_train2=train_X[e+1:len(train_X):,]
y_train2=train_Y[e+1:len(train_X):,]
x_test=train_X[s:e:,]
y_test=train_Y[s:e:,]
x_train=np.vstack((x_train1,x_train2))
y_train=np.vstack((y_train1,y_train2))
#print len(x_train1),len(x_train2),len(x_train),len(x_test)
#print len(y_train1),len(y_train2),len(y_train),len(y_test)
#x_train=pd.DataFrame(x_train)
train['x']=x_train
train['y']=y_train
val['x']=x_test
val['y']=y_test
print ('------------------------k=',i,'--------------------')
model=ann.ann()
#model=logistic_regression.LRegression()
model.learning_rate=0.0007
model.model_restore =False
model.batch_size=100000
epoch=2000
model.epochs=epoch
model.no_of_features=X.shape[1]
model.no_of_classes=no_of_classes
model.working_dir=str(i)
#model.hidden_layer_list=[100,100,100]
model.hidden_layer_list=lay
model.activation_list=['relu','relu','tanh']
model.loss_type=l
model.optimizer_type=opt
model.setup()
from ann import ann
import mnist_basics as mnist
EPOCHS_PER_GAME = 3
BATCH = 100
NEURONS_IN_HIDDEN_LAYERS = [784, 500, 500, 10]
LIST_OF_FUNCTIONS = ["rectify", "rectify", "softmax"]
LEARNING_RATE = 0.001
MOMENTUM_RATE = 0.9
a = ann(neuronsInHiddenLayers=NEURONS_IN_HIDDEN_LAYERS,
listOfFunctions=LIST_OF_FUNCTIONS,
learningRate=LEARNING_RATE,
momentumRate=MOMENTUM_RATE,
errorFunc="RMSprop")
a.run(BATCH, EPOCHS_PER_GAME)
mnist.minor_demo(a)
from ann import ann import mnist_basics as mnist EPOCHS_PER_GAME = 3 BATCH = 100 NEURONS_IN_HIDDEN_LAYERS = [784,500,500,10] LIST_OF_FUNCTIONS = ["rectify","rectify","softmax"] LEARNING_RATE = 0.001 MOMENTUM_RATE = 0.9 a = ann(neuronsInHiddenLayers=NEURONS_IN_HIDDEN_LAYERS, listOfFunctions=LIST_OF_FUNCTIONS, learningRate=LEARNING_RATE, momentumRate=MOMENTUM_RATE, errorFunc="RMSprop") a.run(BATCH,EPOCHS_PER_GAME) mnist.minor_demo(a)
# files.saveData(eann, 'eann-all.db')
# files.saveData(eann.w, 'eann-w-all.db')
#init ann
eann = files.loadData('eann-all.db')
eann_w = files.loadData('eann-w-all.db')
opt = {
'architecture' : eann.architecture,
'learningRate' : 9,
'error' : 0.001,
'epochs' : 50,
'batch' : 100
}
nn = ann.ann(opt)
eann_w = np.asarray(eann_w)
for i in range(len(eann_w)):
eann_w[i] = eann_w[i].astype(float)
nn.w = eann_w
nn.train(train_data, train_result)
# files.saveData(nn, 'eann-bp.db')
_results = nn.sim(test_data)
_results = _results.transpose()
accuracy = 0
for i in range(len(test_result)):
if i < 20:
print _results[i].argmax(), " : ", test_result[i].argmax()
"Stop": "*"
}
re_mut = re.compile("([A-Za-z]+)([\s-]*[0-9]+)([A-Za-z]+)")
infile = sys.argv[1]
outfile = sys.argv[2]
drdb = defaultdict(lambda: defaultdict(list))
positions = set()
for l in open(infile):
arr = l.rstrip().split()
for p in arr[1].split("/"):
if p == "-": continue
positions.add(int(p))
obj_ann = ann.ann(
"/Users/jody/github/TBProfiler/ref/MTB-h37rv_asm19595v2-eg18.tab.ann.gz",
"/Users/jody/github/TBProfiler/bin/tabix")
annot = obj_ann.pos2ann([("Chromosome", str(x)) for x in sorted(positions)])
for l in open(infile):
# print l.rstrip()
#AMINOGLYCOSIDES 1473247 C A rrs C1402A
arr = l.rstrip().split()
re_obj = re_mut.match(arr[5])
ref = re_obj.group(1)
gene_pos = re_obj.group(2)
alt = re_obj.group(3)
if arr[1] == "-": continue
# print "%s\t%s\t%s" % (ref,gene_pos,alt)
tmp = annot["Chromosome"][arr[1].split("/")[0]]
def main():
myann = ann.ann()
myann.test()
