def PreprocessKernel(name):
img = DataHelper.ReadImage(name, gray=True)
grids = SVCClassifier.SVCPreprocess(img)
labels = np.array(
BoardHelper.FENtoOneHot(
DataHelper.GetCleanNameByPath(name))).argmax(axis=1)
return grids, labels
def make_json(self, coal_id, tech_id, json_file): # 读取数据库生成json文件(该文件是utf-8编码!!!) # 注意: 生成json的时候,所有字符串(包括key和value)都必须使用unicode,减少出错的概率!!!! DataHelper.generateJsonFileOfPoreReport(coal_id, tech_id, json_file) # json文件由utf-8转成gbk编码 # report.exe目前只能读取gbk编码的json文件才能正确的解析字符串里面的中文!!! EncodeHelper.UTF8_2_GBK(json_file, json_file)
def onCreatReport(self):
coal = SQLClientHelper.GetCoalById(self.coal_id)
if coal.id <= 0:
UiHelper.MessageBox(u'sorry,出了点问题,请联系技术人员(错误码:144)')
return
# 查找掘进面的抽采技术
ws_tech = SQLClientHelper.GetDesignWorkSurfTechnologyById(self.design_id)
if ws_tech.id <= 0:
UiHelper.MessageBox(u'sorry,出了点问题,请联系技术人员(错误码:145)')
return
# 向cad发送命令请求生成钻孔数据
ret = CbmClientHelper.SendCommandToCAD("JL.GeneratePore23 %d %d" % (coal.id, ws_tech.id), True)
if ret:
# 显示钻孔报表
DataHelper.show_report23(coal, ws_tech)
else:
UiHelper.MessageBox(u'启动AutoCAD失败!!!')
# json文件路径(使用绝对路径,避免出错!!!)
# json_file = os.path.abspath('.\\help\\json\\reportP21.json')
# 生成json文件
# self.make_json(coal.id, tws_tech.id, json_file)
# 生成word报单
# doc.CreatReport(json_file)
def make_json(self, coal_id, tech_id, json_file):
# 读取数据库生成json文件(该文件是utf-8编码!!!)
# 注意: 生成json的时候,所有字符串(包括key和value)都必须使用unicode,减少出错的概率!!!!
DataHelper.generateJsonFileOfPoreReport(coal_id, tech_id, json_file)
# json文件由utf-8转成gbk编码
# report.exe目前只能读取gbk编码的json文件才能正确的解析字符串里面的中文!!!
EncodeHelper.UTF8_2_GBK(json_file, json_file)
def main():
data = DataHelper("data/Twitter.csv")
# data.MinMaxScale()
rp = Representation(data.getdata())
# rp.cal_mean_by_class()
# rp.cal_cosdist_by_eigenvect()
_ = rp.cal_KLdivergence()
def append():
# display template for submitting CSV
if request.method == 'GET':
return render_template('index.html', acs_variables=DataHelper.ACS_VARIABLES)
# logic for manipulating submitted CSV and outputting
elif request.method == 'POST':
input_file = request.files['input_file']
acs_variable_codes = request.form.getlist('acs_variables')
# checks if inputs exist
assert input_file and acs_variable_codes and len(acs_variable_codes) > 0, 'INPUT ERROR'
# checks if input is a CSV
if DataHelper.allowed_file(input_file.filename):
output_csv_string = ''
try:
output_csv_string, error = DataHelper.append_variables(input_file, acs_variable_codes)
except:
print "Unable to append variables:", sys.exc_info()[0]
# sanitizes filename
output_filename = 'APPENDED-' + secure_filename(input_file.filename)
# prepares appended CSV file to be downloaded to user
output = Response(
output_csv_string,
mimetype='text/csv',
headers={ 'Content-disposition': 'attachment; filename=' + output_filename }
)
return output
else:
# NOT VALID FILE TYPE
# HANDLE EXCEPTION
raise
def __init__(self,
dataSet,
featureCount=None,
distanceCalculator=None,
isNormalizeFeatures=True):
if featureCount is not None and featureCount > dataSet.shape[1]:
raise ValueError()
if featureCount is None:
featureCount = dataSet.shape[1]
if distanceCalculator is None:
distanceCalculator = (
lambda X, v: DataHelper.calcMinkowskiDistance(X, v))
if isNormalizeFeatures:
if featureCount < dataSet.shape[1]:
self.__dataSet = dataSet[:, 0:featureCount]
self.__dataSet, self.__mu, self.__sigma = DataHelper.normalizeFeatures(
self.__dataSet)
self.__dataSet = np.hstack(
(self.__dataSet, dataSet[:, featureCount:]))
else:
self.__dataSet, self.__mu, self.__sigma = DataHelper.normalizeFeatures(
dataSet)
else:
self.__dataSet, self.__mu, self.__sigma = dataSet, 0, 1
self.__featureCount = featureCount
self.__distanceCalculator = distanceCalculator
self.__isNormalizeFeatures = isNormalizeFeatures
self.__tree = KDTree.KDTree(self.__dataSet, featureCount)
def onT0GetFocus(self):
# 提取界面数据
thick, ok = self.ui.thick.text().toDouble()
permeability_lambda, ok = self.ui.permeability_lambda.text().toDouble()
alpha, ok = self.ui.alpha.text().toDouble()
p0, ok = self.ui.p0.text().toDouble()
r0, ok = self.ui.r0.text().toInt()
t0, ok = self.ui.t0.text().toInt()
r1, ok = self.ui.r1.text().toInt()
eta, ok = self.ui.eta.text().toDouble()
if r0 <= 0 or thick <= 0: return
# 孔径单位换算
r0, r1 = r0 * 0.001, r1 * 1
# psai计算
k = DataHelper.gas_psai(permeability_lambda, p0, alpha, r0)
print 'k= %.2f' % log10(k)
# 提取x. y, z
x = t0 # t0
y = DataHelper.R0_func(r1, thick) / r0 # R0/r0
z = eta # η
# 插值计算
gdo = DataHelper.GasDrillingOpt()
x = gdo.xValue(y, z, k)
x = int(round(x))
# 更新计算结果
if abs(x - t0) > 1:
self.ui.t0.setText(u'%d' % x)
def onAnalyse(self):
# 提取界面数据
thick, ok = self.ui.thick.text().toDouble()
permeability_lambda, ok = self.ui.permeability_lambda.text().toDouble()
alpha, ok = self.ui.alpha.text().toDouble()
p0, ok = self.ui.p0.text().toDouble()
r0, ok = self.ui.r0.text().toInt()
t0, ok = self.ui.t0.text().toInt()
r1, ok = self.ui.r1.text().toInt()
eta, ok = self.ui.eta.text().toDouble()
if r0 <= 0 or thick <= 0: return
# 孔径单位换算
r0, r1 = r0 * 0.001, r1 * 1
# psai计算
k = DataHelper.gas_psai(permeability_lambda, p0, alpha, r0)
print 'k= %.2f' % log10(k)
# 提取x. y, z
x = t0 # t0
y = DataHelper.R0_func(r1, thick) / r0 # R0/r0
z = eta # η
DataHelper.DrawXYZ(x, y, k)
def onCreatReport(self):
coal = SQLClientHelper.GetCoalById(self.coal_id)
if coal.id <= 0:
UiHelper.MessageBox(u'sorry,出了点问题,请联系技术人员(错误码:144)')
return
# 查找掘进面的抽采技术
ws_tech = SQLClientHelper.GetDesignWorkSurfTechnologyById(
self.design_id)
if ws_tech.id <= 0:
UiHelper.MessageBox(u'sorry,出了点问题,请联系技术人员(错误码:145)')
return
# 向cad发送命令请求生成钻孔数据
ret = CbmClientHelper.SendCommandToCAD(
"JL.GeneratePore23 %d %d" % (coal.id, ws_tech.id), True)
if ret:
# 显示钻孔报表
DataHelper.show_report23(coal, ws_tech)
else:
UiHelper.MessageBox(u'启动AutoCAD失败!!!')
# json文件路径(使用绝对路径,避免出错!!!)
# json_file = os.path.abspath('.\\help\\json\\reportP21.json')
# 生成json文件
# self.make_json(coal.id, tws_tech.id, json_file)
# 生成word报单
# doc.CreatReport(json_file)
def demo_update(i, graphHolder, rotations):
if i < len(rotations):
data, theta = DataHelper.get_points(rotations[i])
graphHolder.set_data(theta, data)
else:
data, theta = DataHelper.get_points(rotations[len(rotations) - 1])
graphHolder.set_data(theta, data)
def func_generator(train_file_names):
for image_file_name in train_file_names:
img = DataHelper.ReadImage(image_file_name)
x = CNNClassifier.PreprocessImage(img)
y = np.array(
BoardHelper.FENtoOneHot(
DataHelper.GetCleanNameByPath(image_file_name)))
yield x, y
def onDrawCurve(self):
# 从界面中读取数据
q0, ok = self.ui.q0.text().toDouble()
alpha, ok = self.ui.alpha.text().toDouble()
# 关闭对话框并返回1
self.accept()
# 绘制曲线
DataHelper.draw_curve(q0, alpha)
def onDrawCurve(self): # 从界面中读取数据 q0, ok = self.ui.q0.text().toDouble() alpha, ok = self.ui.alpha.text().toDouble() # 关闭对话框并返回1 self.accept() # 绘制曲线 DataHelper.draw_curve(q0, alpha)
def onReg(self):
uname = unicode(self.ui.username.text()).encode('utf-8')
pwd = unicode(self.ui.password.text()).encode('utf-8')
# 检查用户名是否已注册
if DataHelper.sql_check_user(uname, pwd):
UiHelper.MessageBox('用户名已经被注册了,换一个吧!')
else:
# 注册新用户
account_id = DataHelper.sql_create_user(uname, pwd)
if account_id <= 0:
UiHelper.MessageBox('抱歉，注册失败\n请联系技术人员(错误码:A1)!')
return
# 从界面中读取数据
mine_name = unicode(self.ui.name.text()).encode('utf-8')
mine_province = unicode(self.ui.province.text()).encode('utf-8')
mine_city = unicode(self.ui.city.text()).encode('utf-8')
mine_region = unicode(self.ui.region.currentText()).encode('utf-8')
# 注册新矿井
mine_id = DataHelper.sql_create_mine(mine_name, mine_province,
mine_city, mine_region,
account_id)
# 注册新矿井失败
if mine_id <= 0:
# 删除新注册用户
SQLClientHelper.DeleteAccount(account_id)
UiHelper.MessageBox('抱歉，注册失败\n请联系技术人员(错误码:A2)!')
return
# 分解煤层编号(空格分隔)
mine_coal_names = unicode(self.ui.coal_nums.text()).encode('utf-8')
# 分解成字符串列表
mine_coal_names = mine_coal_names.strip().split()
# 去除重复编号名称
mine_coal_names = list(set(mine_coal_names))
# 新建煤层(逐个添加到数据)
coal_ids = []
for name in mine_coal_names:
coal_ids.append(DataHelper.sql_create_coal(name, mine_id))
# 增加煤层失败,删除添加的所有煤层
if -1 in coal_ids:
# 删除已增加的所有煤层
SQLClientHelper.DeleteMoreCoal(coal_ids)
# 删除已注册的矿井
SQLClientHelper.DeleteMine(mine_id)
# 删除已注册的用户
SQLClientHelper.DeleteAccount(account_id)
UiHelper.MessageBox('抱歉，注册失败\n请联系技术人员(错误码:A3)!')
else:
UiHelper.MessageBox('恭喜您，注册成功啦!')
# 记录注册成功的用户(用于外部调用)
self.reg_user_name = uname
# 关闭对话框,并返回1
self.accept()
def _getX(self, x):
if self._K > 0:
Y = np.hstack(
tuple([
DataHelper.truncatedPower(x, self._knots[k], self.__d)
for k in range(0, self._K)
]))
return np.hstack(
(DataHelper.vectorPoly(x, self.__d), Y)) if self.__d > 0 else Y
else:
return DataHelper.vectorPoly(x, self.__d) if self.__d > 0 else None
def onReg(self):
uname = unicode(self.ui.username.text()).encode('utf-8')
pwd = unicode(self.ui.password.text()).encode('utf-8')
# 检查用户名是否已注册
if DataHelper.sql_check_user(uname, pwd):
UiHelper.MessageBox('用户名已经被注册了,换一个吧!')
else:
# 注册新用户
account_id = DataHelper.sql_create_user(uname, pwd)
if account_id <= 0:
UiHelper.MessageBox('抱歉，注册失败\n请联系技术人员(错误码:A1)!')
return
# 从界面中读取数据
mine_name = unicode(self.ui.name.text()).encode('utf-8')
mine_province = unicode(self.ui.province.text()).encode('utf-8')
mine_city = unicode(self.ui.city.text()).encode('utf-8')
mine_region = unicode(self.ui.region.currentText()).encode('utf-8')
# 注册新矿井
mine_id = DataHelper.sql_create_mine(mine_name, mine_province, mine_city, mine_region, account_id)
# 注册新矿井失败
if mine_id <= 0:
# 删除新注册用户
SQLClientHelper.DeleteAccount(account_id)
UiHelper.MessageBox('抱歉，注册失败\n请联系技术人员(错误码:A2)!')
return
# 分解煤层编号(空格分隔)
mine_coal_names = unicode(self.ui.coal_nums.text()).encode('utf-8')
# 分解成字符串列表
mine_coal_names = mine_coal_names.strip().split()
# 去除重复编号名称
mine_coal_names = list(set(mine_coal_names))
# 新建煤层(逐个添加到数据)
coal_ids = []
for name in mine_coal_names:
coal_ids.append(DataHelper.sql_create_coal(name, mine_id))
# 增加煤层失败,删除添加的所有煤层
if -1 in coal_ids:
# 删除已增加的所有煤层
SQLClientHelper.DeleteMoreCoal(coal_ids)
# 删除已注册的矿井
SQLClientHelper.DeleteMine(mine_id)
# 删除已注册的用户
SQLClientHelper.DeleteAccount(account_id)
UiHelper.MessageBox('抱歉，注册失败\n请联系技术人员(错误码:A3)!')
else:
UiHelper.MessageBox('恭喜您，注册成功啦!')
# 记录注册成功的用户(用于外部调用)
self.reg_user_name = uname
# 关闭对话框,并返回1
self.accept()
def onT0GetFocus(self):
# 提取界面数据
thick, ok = self.ui.thick.text().toDouble()
permeability_lambda, ok = self.ui.permeability_lambda.text().toDouble()
alpha, ok = self.ui.alpha.text().toDouble()
p0, ok = self.ui.p0.text().toDouble()
r0, ok = self.ui.r0.text().toInt()
t0, ok = self.ui.t0.text().toInt()
r1, ok = self.ui.r1.text().toInt()
eta, ok = self.ui.eta.text().toDouble()
if r0 <= 0 or thick <= 0:
return
# 孔径单位换算
r0, r1 = r0 * 0.001, r1 * 1
# psai计算
k = DataHelper.gas_psai(permeability_lambda, p0, alpha, r0)
print "k= %.2f" % log10(k)
# 提取x. y, z
x = t0 # t0
y = DataHelper.R0_func(r1, thick) / r0 # R0/r0
z = eta # η
# 插值计算
gdo = DataHelper.GasDrillingOpt()
x = gdo.xValue(y, z, k)
x = int(round(x))
# 更新计算结果
if abs(x - t0) > 1:
self.ui.t0.setText(u"%d" % x)
def main():
data = DataHelper.Data()
x_train, y_train, x_test, y_test, attr_list = data.loadData(
"hw2_data_2.txt", 20, 700)
# print(x_train.shape, y_train.shape, x_test.shape, y_test.shape, attr_list.shape)
gb = GradientBoosting(x_train, y_train, x_test, y_test, attr_list)
gb.fit()
def main():
data = DataHelper.Data()
x_train, y_train, x_test, y_test, _ = data.loadData("hw2_data_1.txt", 2, 70)
epoch = 3
weights = np.ones(len(x_train)) / len(x_train)
adaboost = Adaboost(weights, epoch, DecisionRule())
adaboost.train(x_train, y_train)
prediction = adaboost.predict(x_test)
print("Error rate for %d iterations is %.2f%%" % (epoch, adaboost.evaluate(prediction, y_test)))
epoch = 5
weights = np.ones(len(x_train)) / len(x_train)
adaboost = Adaboost(weights, epoch, DecisionRule())
adaboost.train(x_train, y_train)
prediction = adaboost.predict(x_test)
print("Error rate for %d iterations is %.2f%%" % (epoch, adaboost.evaluate(prediction, y_test)))
epoch = 10
weights = np.ones(len(x_train)) / len(x_train)
adaboost = Adaboost(weights, epoch, DecisionRule())
adaboost.train(x_train, y_train)
prediction = adaboost.predict(x_test)
print("Error rate for %d iterations is %.2f%%" % (epoch, adaboost.evaluate(prediction, y_test)))
epoch = 20
weights = np.ones(len(x_train)) / len(x_train)
adaboost = Adaboost(weights, epoch, DecisionRule())
adaboost.train(x_train, y_train)
prediction = adaboost.predict(x_test)
print("Error rate for %d iterations is %.2f%%" % (epoch, adaboost.evaluate(prediction, y_test)))
def setUp(self):
maker = DataHelper.get_data_maker()
clustering_year = 2020
self.model = Models.get_model('classic', clustering_year=clustering_year)
self.model.load_raw_data(maker)
self.model.fit()
def __calcDiscreteProbability(self, dataSet, featureValueNumbers):
if dataSet is None:
return np.log(
np.mat(
np.ones(
(featureValueNumbers.max(),
featureValueNumbers.shape[1]))) / featureValueNumbers)
frequency = None
count = dataSet.shape[0]
result = np.mat(np.zeros(
(featureValueNumbers.max(), dataSet.shape[1])))
for i in range(0, result.shape[1]):
frequency = DataHelper.statisticFrequency(dataSet[:, i])
result[:, i] = np.mat([
np.log(((frequency[key] if key in frequency else 0) +
self.__smoothingFactor) /
(count +
featureValueNumbers[0, i] * self.__smoothingFactor))
if key < featureValueNumbers[0, i] else np.nan
for key in range(0, result.shape[0])
]).T
return result
def testOptimalSubset():
names, X, y = __loadData()
p = X.shape[1]
models = []
for i in range(0, p):
layerModels = []
for j in DataHelper.combinations(p, i + 1):
model = MultipleLinearRegression()
model.fit(X[:, j], y)
layerModels.append((j, model))
models.append(layerModels[np.argmin(
[item[1].rss for item in layerModels])])
for indices, model in models:
print(
"variables: {0}, rss: {1}, r^2: {2}, aic: {3}, bic: {4}, adjusted-r^2: {5}"
.format(", ".join(names[indices]), model.rss, model.r2, model.aic,
model.bic, model.adjustedR2))
print("")
print("selected model: {0}\r\n".format(
np.argmin([item[1].bic for item in models])))
print("\r\n\r\n".join([item[1].__str__() for item in models]))
def main():
data = DataHelper.Data()
x_train, y_train, x_test, y_test, _ = data.loadData(
"hw2_data_2.txt", 20, 700)
# radial kernel
svm_radial = SVM(x_train,
y_train,
x_test,
y_test,
kernel="RADIAL",
gamma_range=np.logspace(-3, 2, 6))
svm_radial.run()
# sigmoid kernel
svm_sigmoid = SVM(x_train,
y_train,
x_test,
y_test,
kernel="SIGMOID",
gamma_range=np.logspace(-3, 2, 6))
svm_sigmoid.run()
# polynomial kernel
svm_poly = SVM(x_train,
y_train,
x_test,
y_test,
kernel="POLYNOMIAL",
degree_range=range(1, 11))
svm_poly.run()
plt.show()
def onAnalyse(self):
# 提取界面数据
thick, ok = self.ui.thick.text().toDouble()
permeability_lambda, ok = self.ui.permeability_lambda.text().toDouble()
alpha, ok = self.ui.alpha.text().toDouble()
p0, ok = self.ui.p0.text().toDouble()
r0, ok = self.ui.r0.text().toInt()
t0, ok = self.ui.t0.text().toInt()
r1, ok = self.ui.r1.text().toInt()
eta, ok = self.ui.eta.text().toDouble()
if r0 <= 0 or thick <= 0:
return
# 孔径单位换算
r0, r1 = r0 * 0.001, r1 * 1
# psai计算
k = DataHelper.gas_psai(permeability_lambda, p0, alpha, r0)
print "k= %.2f" % log10(k)
# 提取x. y, z
x = t0 # t0
y = DataHelper.R0_func(r1, thick) / r0 # R0/r0
z = eta # η
DataHelper.DrawXYZ(x, y, k)
def main():
data = DataHelper('data/Twitter.csv')
data.MinMaxScale()
data = data.getdata()
traindata = data[:4]
# traindata = oversamplingSMOTE(traindata,read=True)
traindata = np.concatenate(traindata)
testdata = data[4:]
# method = 'KNN' # run abour 40s acc 96.75% f-measure 0.65
# method = 'SVM' # run about 30s acc 95% f-measure overfit(nan)
# method = 'Random Forest' # run about 0.44s acc 98.28% f-measure 0.79
method = 'XGBoost'
start = time.time()
clf = train(method, traindata)
acc = []
imbalanced = []
MDDT = [[5, 9], [11, 14], [16, 18], [25, 29], [31, 37]]
CUSUM = [[13, 16], [23, 24], [25, 26], [28, 30], [35, 38]]
PH = [[7, 8], [13, 14], [25, 26]]
for i in range(len(testdata) // 4):
print(i)
last_i = 0
testbatch = np.concatenate(testdata[i * 4:(i + 1) * 4])
try:
acc.append(test(clf, testbatch, criteria='acc'))
imbalanced.append(test(clf, testbatch,
criteria='confusion matrix'))
except:
acc.append(0)
imbalanced.append([0, 0, 0])
testbatch = np.concatenate(testdata[i * 4:(i + 1) * 4])
clf.fit(testbatch[:, :-1], testbatch[:, -1])
for t in MDDT:
start = np.floor(t[0] / 4.0) - 1
end = np.ceil(t[1] / 4.0) - 1
if start == i:
try:
testbatch = np.concatenate(testdata[t[0] - 4:t[1] - 4])
clf.fit(testbatch[:, :-1], testbatch[:, -1])
except:
continue
break
df = pd.DataFrame(acc)
# df.to_csv("MDDT_ACC_XGB.csv",header=None,index=None)
df = pd.DataFrame(imbalanced)
# df.to_csv("MDDT_CONFUSION_XGB.csv",header=None,index=None)
print("time:", time.time() - start)
def run_blstm(
dim_proj=256, # LSTM number of hidden units.
dim_frame=4096, # feature dimension of image frame in the video
output_dim=4096,
v_length=24, # video length or number of frames
max_iter=100, # The maximum number of epoch to run
l2_decay=0.0001, # Weight decay for model params.
lrate=0.0001, # Learning rate for SGD, Adam
lamb=0.2,
optimizer='SGD', # SGD, Adam available
saveto='pairwise-blstm_model.npz', # The best model will be saved there
dispFreq=2, # Display to stdout the training progress every N updates
validFreq=20, # Compute the validation error after this number of update.
saveFreq=2, # Save the parameters after every saveFreq updates
batch_size=256, # The batch size during training.
valid_batch_size=20, # The batch size used for validation/test set.
test_batch_size=1024,
weights=[
1. / 3., 1. / 3., 1. / 3.
], # The Weights for forwoad and backward reconstruction and mean value reconstruction
pairwise_weight=0.999,
reload_model=False, # If reload model from saveto.
is_train=False,
test_step=1,
hiera_step=2,
train_data_file_path='/mnt/data2/lixiangpeng/dataset/features/FCV/fcv/',
test_data_file_path='/mnt/data2/lixiangpeng/dataset/features/FCV/fcv/',
#train_data_file_path = './',
#test_data_file_path = './',
train_splits_num=1,
test_splits_num=1,
record_path='./records.txt',
SS_path='/mnt/data2/lixiangpeng/dataset/features/FCV/SimilarityInfo/Sim_K1_10_K2_5_fcv.pkl'
):
model_options = locals().copy()
if reload_model:
print "Reloading model options"
with open('%s.pkl' % saveto, 'rb') as f:
model_options = pkl.load(f)
print "model options", model_options
test_data = DataHelper.DataHelper(model_options['v_length'],
model_options['valid_batch_size'],
model_options['dim_frame'],
data_file='./data/fcv_test_demo.h5',
train=False)
model = build_model(model_options)
if reload_model:
model.reload_params(saveto)
model.compile(model_options)
if is_train:
model.train(model_options['train_data_file_path'], test_data,
model_options)
else:
model.test(test_data, model_options)
def convertToTrainData(self, data):
helper = DataHelper.Helper()
data = helper.convertToAIFormat(data)
unit_to_multiplier = {
"smaller_to_smaller": self.smallerToSmaller(data),
"smaller_to_larger": self.smallerToLarger(data),
}
return unit_to_multiplier[self.mode]
def main():
data = DataHelper.Data()
x_train, y_train, x_test, y_test, _ = data.loadData(
"hw2_data_2.txt", 20, 700)
mars = MARS(x_train, y_train, x_test, y_test)
mars.fit()
print("The testing error rate for MARS classifier is: %.4f" %
mars.evaluate())
def optimalSubsets(X, y, m=None):
if X is None or y is None:
raise ValueError("matrix X or vector y is None")
result = []
p = X.shape[1]
if m is not None and (m < 1 or m > p):
raise ValueError("m must be between 1 and column numbers of X")
# number of models when m is null: 2^p
if p <= 14 or m is not None:
result.extend([
min([
LinearRegression._optimalSubsetsCore(X, y, indices)
for indices in DataHelper.combinations(p, k)
],
key=lambda item: item[1].rss)
for k in (range(1, p + 1) if m is None else range(m, m + 1))
])
else:
data, models = [], None
for k in range(1, p + 1):
data.extend([(X, y, indices)
for indices in DataHelper.combinations(p, k)])
data = list(
map(
tuple,
np.array(data, np.object)[
DataHelper.randomArrangement(len(data)), :].tolist()))
with multiprocessing.Pool(max(1,
psutil.cpu_count(False) -
2)) as pool:
models = pool.starmap(LinearRegression._optimalSubsetsCore,
data)
for k in range(1, p + 1):
result.append(
min([item for item in models if len(item[0]) == k],
key=lambda item: item[1].rss))
# result item format: (indices, model)
return result
def isConstant(y, periods, alpha):
if y.var() == 0:
return True;
p1 = [DataHelper.testWhiteNoise(y - y.mean(), m) for m in periods];
if np.any(np.mat(p1) <= alpha):
return False;
p2 = LinearRegression.LinearRegression().fit(np.mat(range(0, y.shape[0])).T, y).betaP;
if p2[1, 0] <= alpha:
return False;
p3 = DataHelper.testRunsLeft((y > np.quantile(y, 0.5)) - 0);
if p3 <= alpha:
return False;
print("{0}, {1}, {2}".format(p1, p2.T, p3));
return True;
def onCreatReport(self):
coal = SQLClientHelper.GetCoalById(self.coal_id)
if coal.id <= 0:
UiHelper.MessageBox(u'sorry,出了点问题,请联系技术人员(错误码:124)')
return
# 查找掘进面的抽采技术
tws_tech = SQLClientHelper.GetDesignDrillingSurfTechnologyById(self.design_id)
if tws_tech.id <= 0:
UiHelper.MessageBox(u'sorry,出了点问题,请联系技术人员(错误码:125)')
return
# 向cad发送命令请求生成钻孔数据
ret = CbmClientHelper.SendCommandToCAD("JL.GeneratePore12 %d %d" % (coal.id, tws_tech.id), True)
if ret:
# 显示钻孔报表
DataHelper.show_report12(coal, tws_tech)
else:
UiHelper.MessageBox(u'启动AutoCAD失败!!!')
def onCreatReport(self):
coal = SQLClientHelper.GetCoalById(self.coal_id)
if coal.id <= 0:
UiHelper.MessageBox(u"sorry,出了点问题,请联系技术人员(错误码:134)")
return
# 查找掘进面的抽采技术
ws_tech = SQLClientHelper.GetDesignWorkSurfTechnologyById(self.design_id)
if ws_tech.id <= 0:
UiHelper.MessageBox(u"sorry,出了点问题,请联系技术人员(错误码:135)")
return
# 向cad发送命令请求生成钻孔数据
ret = CbmClientHelper.SendCommandToCAD("JL.GeneratePore21 %d %d" % (coal.id, ws_tech.id), True)
if ret:
# 显示钻孔报表
DataHelper.show_report21(coal, ws_tech)
else:
UiHelper.MessageBox(u"启动AutoCAD失败!!!")
def login_or_switch(self, uname, pwd):
account_id = SQLClientHelper.GetAccountIdByField2('username', uname, 'password', pwd)
# 查找已登录用户
pre_account_id = CbmClientHelper.GetOnlineAccountId()
# 当前没有用户登录
if pre_account_id <= 0:
# 用户登陆(记录在sys_info表中)
DataHelper.sql_login_user(account_id)
# UiHelper.MessageBox('恭喜您,登录成功!')
# 当前已有用户登录
elif pre_account_id == account_id:
# UiHelper.MessageBox('您已经登录过了!')
pass
else:
reply = UiHelper.MessageBox('是否注销并切换到用户%s?' % uname, True)
if reply == True:
# 切换用户
DataHelper.sql_switch_user(account_id)
def __findCluster(self, dataSet, center):
result = None
for i in range(0, center.shape[0]):
distance = DataHelper.calcManhattanDistance(dataSet, center[i, :])
result = distance if result is None else np.hstack(
(result, distance))
return result.argmin(1), result.min(1)
def login_or_switch(self, uname, pwd):
account_id = SQLClientHelper.GetAccountIdByField2(
'username', uname, 'password', pwd)
# 查找已登录用户
pre_account_id = CbmClientHelper.GetOnlineAccountId()
# 当前没有用户登录
if pre_account_id <= 0:
# 用户登陆(记录在sys_info表中)
DataHelper.sql_login_user(account_id)
# UiHelper.MessageBox('恭喜您,登录成功!')
# 当前已有用户登录
elif pre_account_id == account_id:
# UiHelper.MessageBox('您已经登录过了!')
pass
else:
reply = UiHelper.MessageBox('是否注销并切换到用户%s?' % uname, True)
if reply == True:
# 切换用户
DataHelper.sql_switch_user(account_id)
def onCreatReport(self):
coal = SQLClientHelper.GetCoalById(self.coal_id)
if coal.id <= 0:
UiHelper.MessageBox(u'sorry,出了点问题,请联系技术人员(错误码:144)')
return
# 查找掘进面的抽采技术
goaf_tech = SQLClientHelper.GetDesignGoafTechnologyById(self.design_id)
if goaf_tech.id <= 0:
UiHelper.MessageBox(u'sorry,出了点问题,请联系技术人员(错误码:145)')
return
# 向cad发送命令请求生成钻孔数据
ret = CbmClientHelper.SendCommandToCAD(
"JL.GeneratePore32 %d %d" % (coal.id, goaf_tech.id), True)
if ret:
# 显示钻孔报表
DataHelper.show_report32(coal, goaf_tech)
else:
UiHelper.MessageBox(u'启动AutoCAD失败!!!')
def main():
data = DataHelper.Data()
x_train, y_train, x_test, y_test, _ = data.loadData(
"hw2_data_1.txt", 2, 70) # load data
weights = np.ones(x_train.shape[1] + 1)
epochs = 50
model = perceptron(weights, learningRate=1, epoch=epochs)
model.train(x_train, y_train)
print("The error rate for perceptron after %i epochs is %.2f %%" %
(epochs, model.evaluate(x_test, y_test)))
def onCacl(self):
DataHelper.drilling_ratio(40, 10, 1)
return
# 从界面中提取数据
r, ok = self.ui.r.text().toDouble()
l, ok = self.ui.l.text().toDouble()
k1, ok = self.ui.k1.text().toDouble()
rho, ok = self.ui.rho.text().toDouble()
q0, ok = self.ui.q0.text().toDouble()
a, ok = self.ui.a.text().toDouble()
t, ok = self.ui.t.text().toDouble()
h, ok = self.ui.hw.text().toDouble()
w, ok = self.ui.gas_w0.text().toDouble()
qm, ok = self.ui.qm.text().toDouble()
q, ok = self.ui.qsum.text().toDouble()
eta, ok = self.ui.eta.text().toDouble()
# 计算
if r == 0 or h == 0 or w == 0 or l == 0:
UiHelper.MessageBox(u'所有数据都必须大于0!!!')
return
# 计算Qm
if 2 * r < h or abs(2 * r - h) < 1e-3:
s = pi * r * r # 面积
qm = 1440 * k1 * q0 * (1 - exp(-1 * a * t)) / (rho * a * s *
(r + l))
else:
s = 2 * r * r * asin(0.5 * h / r) + h * sqrt(r * r - 0.25 * h * h)
qm = 1440 * k1 * q0 * (1 - exp(-1 * a * t)) / (rho * a * s *
(r + l))
# 计算eta和wc
eta = qm / w
wc = w - q
# 更新到界面
self.ui.qm.setText(u'%.1f' % qm)
self.ui.eta.setText(u'%.1f' % eta)
self.ui.gas_wc3.setText(u'%.1f' % wc)
UiHelper.MessageBox(u'更新计算结果成功!')
# 关闭对话框并返回1
# self.accept()
def run(): import sys app = QtGui.QApplication(sys.argv) # 设置utf-8编码 SetUTF8Code(app) # 设置样式 SetStyle(app, 'blue') # 设置qt中文界面(消息框、菜单之类的默认使用中文) SetChinese(app) # 首先启动登录窗口 if loginFirst(): #启动CAD # doc.RunCAD() # 登录成功后启动主界面 mw = MainWindow() mw.show() # 进入消息循环 app.exec_() # 注销(清空sys_info表) DataHelper.sql_logout()
def run():
import sys
app = QtGui.QApplication(sys.argv)
# 设置utf-8编码
SetUTF8Code(app)
# 设置样式
SetStyle(app, 'blue')
# 设置qt中文界面(消息框、菜单之类的默认使用中文)
SetChinese(app)
# 首先启动登录窗口
if loginFirst():
#启动CAD
# doc.RunCAD()
# 登录成功后启动主界面
mw = MainWindow()
mw.show()
# 进入消息循环
app.exec_()
# 注销(清空sys_info表)
DataHelper.sql_logout()
def onCacl(self): DataHelper.drilling_ratio(40,10,1) return # 从界面中提取数据 r, ok = self.ui.r.text().toDouble() l, ok = self.ui.l.text().toDouble() k1, ok = self.ui.k1.text().toDouble() rho, ok = self.ui.rho.text().toDouble() q0, ok = self.ui.q0.text().toDouble() a, ok = self.ui.a.text().toDouble() t, ok = self.ui.t.text().toDouble() h, ok = self.ui.hw.text().toDouble() w, ok = self.ui.gas_w0.text().toDouble() qm, ok = self.ui.qm.text().toDouble() q, ok = self.ui.qsum.text().toDouble() eta, ok = self.ui.eta.text().toDouble() # 计算 if r == 0 or h == 0 or w == 0 or l == 0: UiHelper.MessageBox(u'所有数据都必须大于0!!!') return # 计算Qm if 2*r < h or abs(2*r - h) < 1e-3: s = pi * r * r # 面积 qm = 1440*k1*q0*(1-exp(-1*a*t)) / (rho * a * s *(r+l)) else: s = 2 * r * r * asin(0.5*h/r) + h*sqrt(r*r -0.25*h*h) qm = 1440*k1*q0*(1-exp(-1*a*t)) / (rho * a * s *(r+l)) # 计算eta和wc eta = qm / w wc = w - q # 更新到界面 self.ui.qm.setText(u'%.1f' % qm) self.ui.eta.setText(u'%.1f' % eta) self.ui.gas_wc3.setText(u'%.1f' % wc) UiHelper.MessageBox(u'更新计算结果成功!') # 关闭对话框并返回1 # self.accept()
def try_run(self, DialogClass, authority): can_run = True while can_run: # 检查用户登录状态 ret = DataHelper.sql_login_status() # 内部错误 if ret == 0 or ret == -1: UiHelper.MessageBox(u"系统技术性故障(错误码:M1),请联系技术人员!",error = True) can_run = False break # 用户未登录 elif ret == 2: if UiHelper.MessageBox(u"您需要登录才能使用本功能!", error = True): can_run = self.login() # 登录 else: can_run = False break # 管理员已登录 elif ret == 3 and authority == Authority.USER: if UiHelper.MessageBox(u"管理员禁止使用该功能,请重新登录!", error = True): can_run = self.login() # 登录 else: can_run = False break # 普通用户已登录 elif ret == 1 and authority == Authority.ADMIN: if UiHelper.MessageBox(u"您的权限不够,请重新登录!", error = True): can_run = self.login() # 登录 else: can_run = False break if can_run and DataHelper.sql_login_authority(authority): break # 启动对话框 if can_run: # 启动对话框(传入当前登录用户的) self.run_dialog(DialogClass)
def onPartition(self):
index = self.ui.work_surf.currentIndex()
if index < 0:
UiHelper.MessageBox(u'请指定一个工作面进行设计!')
return
work_surf_id, ok = self.ui.work_surf.itemData(index).toInt()
work_surf = SQLClientHelper.GetWorkSurfById(work_surf_id)
if work_surf.id <= 0:
UiHelper.MessageBox(u'sorry,出了点问题,请联系技术人员(错误码:Z9)')
return
deup = SQLClientHelper.GetDesignEvalUnitPartitionByForeignKey('work_surf_id', work_surf_id)
if deup.id <= 0:
UiHelper.MessageBox(u'sorry,出了点问题,请联系技术人员(错误码:Z12)')
return
# 设计评价单元
DataHelper.design_eval_unit(deup.id)
# 给cad发送命令请求绘制评价单元示意图
ret = CbmClientHelper.SendCommandToCAD("JL.DrawEvalUnitGraph %d" % deup.id, True)
if not ret:
UiHelper.MessageBox(u'启动AutoCAD失败')
def onAddCoal(self):
# 弹出名称对话框,获取名称
coal_name = unicode(UiHelper.GetNameFromDlg(u"新增煤层"))
if coal_name == u'null' or coal_name == u'':
UiHelper.MessageBox(u"请输入有效的名称！")
else:
# 新建煤层,并提交到数据库
coal_id = DataHelper.sql_create_coal(coal_name.encode('utf-8'), self.mine_id)
if coal_id <= 0:
UiHelper.MessageBox(u"新增煤层失败")
else:
# 添加到下拉列表
index = UiHelper.AddItemToCombobox(self.ui.coal, coal_name, coal_id)
# 切换到新增item
self.ui.coal.setCurrentIndex(index)
def onHelp(self): angle, ok = self.ui.dip_angle.text().toDouble() if angle < 0: UiHelper.MessageBox(u'煤层倾角不能小于0!!!') return # 煤层按倾角划分的类型 left,right, top, bottom = 15, 15, 15, 15 # 按瓦斯突出规定,调整上下左右帮距 if DataHelper.dip_angle_type(angle) > 2: # 倾斜、急倾斜煤层 top, bottom = 20, 10 # 更新界面 self.ui.left.setText(u'%.1f' % left) self.ui.right.setText(u'%.1f' % right) self.ui.top.setText(u'%.1f' % top) self.ui.bottom.setText(u'%.1f' % bottom)
def onAddDrillingSurf(self):
# 获取当前煤层id
index = self.ui.work_area.currentIndex()
if index < 0:return
work_area_id, ok = self.ui.work_area.itemData(index).toInt()
# 弹出名称对话框,获取名称
drilling_surf_name = unicode(UiHelper.GetNameFromDlg(u"新增掘进工作面"))
if drilling_surf_name == u'null' or drilling_surf_name == u'':
UiHelper.MessageBox(u"请输入有效的名称！")
else:
# 新建煤层,并提交到数据库
drilling_surf_id = DataHelper.sql_create_drilling_surf(drilling_surf_name.encode('utf-8'), work_area_id)
if drilling_surf_id <= 0:
UiHelper.MessageBox(u"新增掘进工作面失败")
else:
# 添加到下拉列表
index = UiHelper.AddItemToCombobox(self.ui.drilling_surf, drilling_surf_name, drilling_surf_id)
# 切换到新增item
self.ui.drilling_surf.setCurrentIndex(index)
def onAddWorkArea(self):
# 获取当前煤层id
index = self.ui.coal.currentIndex()
if index < 0:return
coal_id, ok = self.ui.coal.itemData(index).toInt()
# 弹出名称对话框,获取名称
work_area_name = unicode(UiHelper.GetNameFromDlg(u"新增采区"))
if work_area_name == u'null' or work_area_name == u'':
UiHelper.MessageBox(u"请输入有效的名称！")
else:
# 新建煤层,并提交到数据库
work_area_id = DataHelper.sql_create_work_area(work_area_name.encode('utf-8'), coal_id)
if work_area_id <= 0:
UiHelper.MessageBox(u"新增采区失败")
else:
# 添加到下拉列表
index = UiHelper.AddItemToCombobox(self.ui.work_area, work_area_name, work_area_id)
# 切换到新增item
self.ui.work_area.setCurrentIndex(index)
updateVarNames.py
Creates new csv of variable code and name pairs with parent variable names added to variable names
'''
import csv
import sys
sys.path.insert(0, '..')
import DataHelper
file_name = sys.argv[1]
with open(file_name, 'rb') as f: # open list of variable code and name pairs
labels_csv = csv.reader(f)
with open('codes_names_new.csv', 'wb') as nf: # open new file for updated list of variable code and name pairs
labels_csv_new = csv.writer(nf)
parent_codes_names = DataHelper.create_labelcode_dict('parent_codes_names.csv')
# update each line in original csv and add to new csv
for row in labels_csv:
var_code = row[1].split('_')[0]
if var_code in parent_codes_names:
var_name = parent_codes_names[var_code]
extended_varname = var_name + ':!!' + row[2]
newline = [row[1], extended_varname]
if row[1] == 'B01001H_002E':
print extended_varname
print newline
labels_csv_new.writerow(newline)
def onPermeabilityLambdaGetFocus(self): # 根据"透气性系数"计算"渗透率" p_k, ok = self.ui.permeability_k.text().toDouble() p_lambda = DataHelper.permeability_k_to_lambda(p_k) # 更新计算结果 self.ui.permeability_lambda.setText(u'%.2f' % p_lambda)
'''
updateVarNames.py
creates new csv of variable code and name pairs with parent variable names added to variable names
'''
import csv
import sys
sys.path.insert(0, '..')
import DataHelper
with open('codes_names.csv', 'rb') as f: # open list of variable code and name pairs
labels_csv = csv.reader(f)
with open('codes_names_new.csv', 'wb') as nf: # open new file for updated list of variable code and name pairs
labels_csv_new = csv.writer(nf)
parent_codes_names = DataHelper.labels_to_codes('parent_codes_names.csv') #TODO: gotta update parent_codes csv to only contain important parents
# update each line in original csv and add to new csv
for row in labels_csv:
var_code = row[0][:6]
print var_code
if var_code in parent_codes_names:
var_name = parent_codes_names[var_code]
newline = [row[0], var_name + ':!!' + row[1]]
labels_csv_new.writerow(newline)
def onPermeabilityKGetFocus(self): # 根据"渗透率"计算"透气性系数" p_lambda, ok = self.ui.permeability_lambda.text().toDouble() p_k = DataHelper.permeability_lambda_to_k(p_lambda) # 更新计算结果 self.ui.permeability_k.setText(u'%.2f' % p_k)
def real_logout(self): # 注销(清空sys_info表) DataHelper.sql_logout() # 设置菜单激活状态 self.loginAction.setEnabled(True) self.logoutAction.setEnabled(False)