class EventDataFrame(DummyModule):
# In the constructor, provide whatever arguments
# you intend to play with
def __init__(self, name):
DummyModule.__init__(self, name)
self.df = object
def beginRun(self, runNumber, runRecord):
self.df = DataFrame(runNumber)
def printSpecificData(self, item, eventNumber, eventRecord):
print(eventNumber,
"Key : {} , Value : {}".format(item, eventRecord[item]))
def printRawDataOutput(self, eventNumber, eventRecord):
for item in eventRecord:
print(eventNumber,
"Key : {} , Value : {}".format(item, eventRecord[item]))
def processEvent(self, runNumber, eventNumber, eventRecord):
self.df.updateDataFrame(eventRecord, eventNumber)
# print("Processing the DF....")
# self.df.showDataFrame()
def endRun(self, runNumber, runRecord):
self.df.saveDataFrame()
def test_mean_add(self):
x = scipy.random.randint(0, 10, 100)
twox = x * 2
df = DataFrame(x=x, tx=2 * x)
glob = df.scope
s = df.group_by('tx').summarize(txo=mean(glob['x'] + glob['x']))
self.assertAllClose(s.txo, s.tx)
def setUp(self):
self.data_frame = DataFrame(labels=test_data[0], data=test_data[1:])
self.labels = [
'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'type'
]
self.data = test_data[1:]
pass
def on_load_csv(self, event):
'''loads data from csv file into pandas dataFrame object'''
dlg = wx.FileDialog(self, 'Select File to Open', '', '', '*.csv', wx.OPEN)
if dlg.ShowModal() == wx.ID_OK:
csv_file_path = dlg.GetPath()
new_dataFrame = DataFrame()
new_dataFrame.from_csv(csv_file_path)
if self.parent.project.add_dataFrame(new_dataFrame):
self.parent.history.log_new_dataFrame(new_dataFrame.source)
else:
self.parent.history.log_already_exists(new_dataFrame.source)
def on_load_csv(self, event):
'''loads data from csv file into pandas dataFrame object'''
dlg = wx.FileDialog(self, 'Select File to Open', '', '', '*.csv',
wx.OPEN)
if dlg.ShowModal() == wx.ID_OK:
csv_file_path = dlg.GetPath()
new_dataFrame = DataFrame()
new_dataFrame.from_csv(csv_file_path)
if self.parent.project.add_dataFrame(new_dataFrame):
self.parent.history.log_new_dataFrame(new_dataFrame.source)
else:
self.parent.history.log_already_exists(new_dataFrame.source)
def processArrivalDataFrame(self, event_time: float, receiver: "Host", _type: str, df = None, origin = None):
"""
create one of the following arrival event and put it to the GEL event list
internal DF: df created in this host
success => schedule sense event to see if the channel is idle to process the df
failure => put into the buffer
external DF: df from external host to this host
success => schedule receive event and then return an ACK latter
failure => no failure
ACK DF: ACK from external host
success => take the next df from the buffer and process it
failure => no failure
"""
sender = self
success = None
failure = None
arrival = None
if _type == "internal DF":
"""
Schedule next event
To create a sense channel event, or put it into the buffer
"""
if self.status == "idle" and len(self.buffer.array)==0 and self.blocking==False:
self.createSenseChannelEvent(event_time, df, "df, stage 0", df.origin)
else:
self.addToBuffer(df)
elif _type == "external DF":
"""
create an ack packet, and then create a SenseChannel Event for this ack packet
"""
ack_time = event_time
ack = DataFrame("ack", ack_time, df.sender, df.receiver, df.id, df.origin)
ack.global_Id = df.global_Id
ack.size = 64
self.createSenseChannelEvent(event_time, ack, "ack, stage 0", df.origin)
elif _type == "ack": # if received is ack
success_time = event_time
success_event = SuccessTransferEvent(success_time, df, failure, df.origin)
self.GEL.addEvent(success_event)
def load_data():
"""
This is a custom file parser
Used this because pd.read_csv() was very, very slow
:return:
"""
# open file and set type of data under `dtype`
with open(r"statistics/state_fips_master.csv") as states:
state_list = pd.read_csv(states,
sep=',',
header=0,
dtype={
'state_name': str,
'state_abbr': str,
'long_name': str,
'fips': str,
'sumlev': str,
'region': str,
'division': str,
'state': str,
'region_name': str,
'division_name': str
})
# add state name to DataFrame
for line in state_list['state_name']:
DataFrame.state_list.append(line)
# open the data file BYAREA.txt in read mode
with open(DataFrame.data_file, mode='r') as readcsv:
index = 0
# for each line in the file
for line in readcsv:
# skip the first line (contains headers)
if index == 0:
index = index + 1
else:
# split the line by pipe `|` symbol into list
class_instance = line.rstrip("\n").split("|")
# take each index in list and load it into a DataFrame
# append this DataFrame into class_array
DataFrame.class_instances.append(
DataFrame(
class_instance[0], # AREA
class_instance[1], # AGE_ADJUSTED_CI_LOWER
class_instance[2], # AGE_ADJUSTED_CI_UPPER
class_instance[3], # AGE_ADJUSTED_RATE
class_instance[4], # COUNT
class_instance[5], # EVENT_TYPE
float(class_instance[6]), # POPULATION
class_instance[7], # RACE
class_instance[8], # SEX
class_instance[9], # SITE
class_instance[10], # YEAR
class_instance[11], # CRUDE_CI_LOWER
class_instance[12], # CRUDE_CI_UPPER
class_instance[13])) # CRUDE_RATE
def data_indication(destination_address, source_address, l_sdu):
for segment in l_sdu:
print('MENSAGEM A SER ENVIADA: ', segment)
# Delimitador já é inserido no quadro
# comprimento do payload
length = Conversion.decimal_to_binary(len(segment))
# campo de sequencia TODO
# SEQ----ACK
sequence = '00000000'
# destino do quadro
destination_address_frame = Conversion.ip_to_binary(
destination_address)
# origem do quadro
source_address_frame = Conversion.ip_to_binary(source_address)
# dados convertidos
payload = Conversion.string_to_binary(segment)
# cria o frame
frame = DataFrame(length, sequence, destination_address_frame,
source_address_frame, payload)
# Calcula o crc
MyCRC = CRC.crc(frame.return_data_frame_to_crc())
frame.set__crc(MyCRC)
# cria a string para enviar
frame_str = frame.return_data_frame()
socket_envio = MySocketTCP(destination_address)
if segment == 'FIM':
socket_envio.send('#')
else:
# Adicionar ruido ao quadro
# corrompe = random.randrange(0, 2)
# if corrompe == 1:
# print('---houve ruido----')
# frame_str = Fisica.add_noise(frame_str)
# ENVIA!!!
print('FRAME: ', frame_str)
socket_envio.send(frame_str)
print('FRAME ENVIADO')
receive_ack_socket = MySocketTCP()
got_it = receive_ack_socket.receive()
OK = ConfirmationFrame.string_to_ConfirmationFrame(got_it)
ACK = OK.last_bit_sequence()
print('ACK RECEBIDO: ', ACK)
def train_split_data(dataframe, column, test_size):
types_of_data = dataframe.get_types_of_data(column)
data_divided_by_give_column = {}
for key in types_of_data:
data_divided_by_give_column[key] = dataframe.get_values_equal_to(column, key)
number_of_sumples = {}
for key in data_divided_by_give_column:
number_of_sumples[key] = __get_number_of_samples(test_size, len(data_divided_by_give_column[key]))
to_learn_dataframe = {}
for key in data_divided_by_give_column:
to_learn_dataframe[key] = copy(data_divided_by_give_column[key])
test_datafram = DataFrame()
for key in to_learn_dataframe:
for i in range(number_of_sumples[key]):
index_to_test = random.randrange(0, len(to_learn_dataframe[key]))
temp = to_learn_dataframe[key].pop_on_poss(index_to_test)
test_datafram.data.append(temp)
test_datafram.labels = dataframe.labels
return test_datafram, to_learn_dataframe
def data_request():
mensagem = ''
while True:
socket_receber = MySocketTCP('127.0.0.1')
resposta = socket_receber.receive()
if resposta == '#':
print('CLIENTE DESCONECTOU')
break
r2 = DataFrame.string_to_DataFrame(resposta)
r2_payload_bin = r2.get_payload()
r2_crc_recebido = r2.get_crc()
crc_novo = CRC.crc(r2.return_data_frame_to_crc())
source_bin = r2.get_destination_address()
destination_bin = r2.get_source_address()
destination = Conversion.binary_to_ip(destination_bin)
n_ack = 0
sequence = r2.first_bit_sequence()
if crc_novo != r2_crc_recebido:
sequence += '0000000'
n_ack = 0
# manda quadro de confirmação com ack = 0
else:
sequence += '0000001'
n_ack = 1
mensagem += Conversion.binary_to_string(r2_payload_bin)
print('MENSAGEM RECEBIDA:',
Conversion.binary_to_string(r2_payload_bin))
print('FRAME OK')
ack_frame = ConfirmationFrame(sequence, destination_bin,
source_bin)
print('ENVIANDO CONFIRMATION FRAME: ',
ack_frame.return_confirmation_frame())
ack_socket = MySocketTCP(destination)
ack_socket.send(ack_frame.return_confirmation_frame())
print('CONFIRMATION FRAME ENVIADO COM ACK = ', n_ack)
return (mensagem)
def get_sample(self):
self.dataframe = DataFrame()
# get inputs and decision class
self.inputs = self.dataframe.inputs
self.decision = self.dataframe.decision_class
try:
for column, decision in zip(self.inputs[:5], self.decision[:5]):
print(f'\n{column} => {decision}')
except IndexError as e:
print(e)
answer = input(
'\nPaste the sample with ";" delimitier among the values: ')
if ';' not in answer:
raise ValueError("The input does not contain delimiter.")
values = answer.lstrip('-+').split(';')
# validate if the values are numeric
for value in values:
testing = value.replace('.', '', 1)
if not testing.isdigit():
raise ValueError("The given value is not a digit.")
filtered = list(filter(lambda x: x, values))
# map the float convert
values = list(map(lambda x: float(x), filtered))
print(
f'Your sample:\n\tinputs: {values[1:]}\n\tdecision_class: {values[0]}'
)
self.sample = values
return self
def makeWindows(self):
# if self.mixfr:
for w in self.windows:
try:
w.destroy()
except:
pass
fr = [MixtureFrame, ThermoFrame, TransportFrame]
self.mixfr = MixtureFrame(self.cwin, self)
self.thermo = ThermoFrame(self.cwin, self)
# self.transport = TransportFrame(self.cwin, self)
self.kinetics = SpeciesKineticsFrame(self.cwin, self)
self.addWindow('rxndata',ReactionKineticsFrame(self.vrxn, self))
self.addWindow('rxnpaths',ReactionPathFrame(self))
self.addWindow('dataset',DataFrame(None, self))
#self.edit = EditFrame(t, self)
self.windows = [self.mixfr,
self.thermo, self.transport,
self.kinetics]
self.showthermo()
self.showcomp()
#self.showtransport()
self.showkinetics()
#self.showrxns()
#self.showrpaths()
#self.showdata()
if self.mech:
self.mechframe.grid(row=1,column=0)
else:
self.mechframe.grid_forget()
def test_sum_n(self):
a = DataFrame(globals(),
x=scipy.random.randint(0, 10, 100),
y=scipy.random.randint(0, 10, 100))
s = a.group_by(x, y).summarize(n=n())
self.assertEqual(s.n.sum(), 100)
def __init__(self,
_type,
event_time,
sender,
receiver,
gel,
origin=None,
df=None):
self.type = _type
self.event_time = event_time
self.sender = sender
self.receiver = receiver
if origin == None:
self.origin = sender
else:
self.origin = origin
self.GEL = gel
self.dataframe = df
if self.type == "internal DF":
"""
The origin of an internal DF is the sender
The origin of an external DF is the origin of the df
The origin of an ack is the origin of the df
"""
arrival_time = event_time + negative_exponential_distribution(
ARRIVE_RATE)
df = DataFrame("data",
arrival_time,
self.sender,
self.receiver,
self.sender.ackId,
origin=self.origin)
df.global_Id = self.GEL.packet_counter
self.arrival_time = arrival_time
self.dataframe = df
self.GEL.packet_counter += 1
self.sender.ackId += 1
def success():
self.sender.processArrivalDataFrame(arrival_time,
self.receiver,
"internal DF", df,
df.origin)
arrival_Event = ProcessDataFrameArrivalEvent(
self.type, arrival_time, self.sender, self.receiver, df)
arrival_Event.success = success
self.GEL.addEvent(arrival_Event)
elif self.type == "external DF":
arrival_time = event_time
self.arrival_time = arrival_time
self.dataframe = df
def success():
self.sender.processArrivalDataFrame(arrival_time,
self.receiver,
"external DF", df,
df.origin)
arrival_Event = ProcessDataFrameArrivalEvent(
self.type, arrival_time, self.sender, self.receiver, df)
arrival_Event.success = success
self.GEL.addEvent(arrival_Event)
elif self.type == "ack":
arrival_time = event_time
self.arrival_time = arrival_time
self.dataframe = df
def success():
self.sender.processArrivalDataFrame(arrival_time,
self.receiver, "ack", df,
df.origin)
arrival_Event = ProcessDataFrameArrivalEvent(
self.type, arrival_time, self.sender, self.receiver, df)
arrival_Event.success = success
self.GEL.addEvent(arrival_Event)
import sys
import numpy as np
sys.path.append('../src')
from DataFrame import DataFrame
from kNN import kNearestNeighbors
# Initialize the dataframe object
df = DataFrame()
# split data to inputs and decision classess
X_set, y_set = df.inputs, df.decision_class
# print decision class and input columns
#print(df.print_inputs())
#print(df.print_decision_class())
#print(df)
# first version of knn
print(
f'First version of k-nearest neighbors classificator (Euclidean Metric):')
knn = kNearestNeighbors(k=5, metric='euclidean')
knn.OneVsRest(df.inputs, df.decision_class, version='first')
print(
f'First version of k-nearest neighbors classificator (Manhattan Metric):')
knn = kNearestNeighbors(k=5, metric='manhattan')
knn.OneVsRest(df.inputs, df.decision_class, version='first')
print(
f'First version of k-nearest neighbors classificator (Minkowski Metric):')
def beginRun(self, runNumber, runRecord):
self.df = DataFrame(runNumber)
def test_mean(self):
df = DataFrame(x=scipy.random.randint(0, 10, 100))
s = df.group_by('x').summarize(mu=mean('x'))
self.assertAllClose(s.x, s.mu)
def create_from_csv(csv_path, sep=";"):
data_read = CsvReader.__read_from_file(csv_path)
unprocessed_data = CsvReader.__create_data_frame_from_read_data(
data_read, sep=sep)
return DataFrame(labels=CsvReader.create_labels(unprocessed_data),
data=CsvReader.create_data(unprocessed_data))
def processArrivalDataFrame(self, event_time: float, receiver: "Host", _type: str, df = None, origin = None):
"""
create one of the following arrival event and put it to the GEL event list
internal DF: df created in this host
success => schedule sense event to see if the channel is idle to process the df
failure => put into the buffer
external DF: df from external host to this host
success => schedule receive event and then return an ACK latter
failure => no failure
ACK DF: ACK from external host
success => take the next df from the buffer and process it
failure => no failure
"""
sender = self
success = None
failure = None
arrival = None
if _type == "internal DF":
"""
Schedule next event
To create a sense channel event, or put it into the buffer
"""
if self.GEL.packet_counter < self.GEL.TOTAL_PACKET:
new_arrival_event = ScheduleDataFrameEvent(_type, event_time, sender, receiver, self.GEL, sender)
self.GEL.addEvent(new_arrival_event)
if self.status == "idle":
sense_event_time = event_time + self.senseTime
self.createSenseChannelEvent(sense_event_time, df, "df, stage 0", df.origin)
else:
self.buffer.insert_dataframe(df)
elif _type == "external DF":
"""
create an ack packet, and then create a SenseChannel Event for this ack packet
"""
ack_time = event_time
sense_event_time = event_time + self.senseTime
# print("ack", ack_time, df.sender, df.receiver, df.id, df.origin)
ack = DataFrame("ack", ack_time, df.sender, df.receiver, df.id, df.origin)
ack.global_Id = df.global_Id
ack.size = 64
self.createSenseChannelEvent(sense_event_time, ack, "ack, stage 0", df.origin)
elif _type == "ack":
success_time = event_time + 0
def success():
"to get the unacked event from the notAckedDict and then acknowledge the packet"
unacked = self.notACKedDict[df.id]
unacked.ACKed = True
if len(self.buffer.array) != 0:
next_df = self.origin.buffer.popleft()
self.createSenseChannelEvent(event_time, next_df, "df, stage 0", df.origin)
success_event = SuccessTransferEvent(success_time, df, success, failure, df.origin)
self.GEL.addEvent(success_event)
def initData(self):
self.dataFrame = DataFrame()
class MainWindow(QWidget):
def __init__(self):
super().__init__()
self.initData()
self.initUI()
self.createSelectGroupBox()
self.createViewGroupBox()
mainLayout = QVBoxLayout()
mainLayout.addWidget(self.selectGroupBox)
mainLayout.addWidget(self.viewGroupBox)
# mainLayout.addWidget(self.messageGroupBox)
self.setLayout(mainLayout)
def initData(self):
self.dataFrame = DataFrame()
def initUI(self):
QToolTip.setFont(QFont('SansSerif', 10))
self.setToolTip('This is a <b>QWidget</b> widget')
# btn = QPushButton('Button', self)
# btn.setToolTip('This is a <b>QPushButton</b> widget')
# btn.resize(btn.sizeHint())
# btn.move(50, 50)
self.setGeometry(300, 300, 640, 480)
self.setWindowTitle('NumpyViewer')
self.show()
def createSelectGroupBox(self):
'''
用于文件加载模块的控制面板。
'''
# create groupbox
self.selectGroupBox = QGroupBox("Select File")
self.selectGroupBox.setFixedHeight(80)
# create widgets
self.selectButton = QPushButton('Select a file')
# widgets connect
self.selectButton.clicked.connect(self.selectButtonClicked)
# layout
selectLayout = QHBoxLayout()
selectLayout.addWidget(self.selectButton)
self.selectGroupBox.setLayout(selectLayout)
def createViewGroupBox(self):
'''
用于创建查看区，由图像和查看按钮组成。
'''
# create groupbox
self.viewGroupBox = QGroupBox("View")
# create widgets
# self.viewBox = QLabel('Show Image') # QLabel is widget, but QPixmap is not.
# self.viewBox.setPixmap(QPixmap('./64.png'))
self.static_canvas = FigureCanvas(Figure(figsize=(10, 10)))
self.viewPlot = self.static_canvas.figure.subplots()
self.lastButton = QPushButton('Last')
self.nextButton = QPushButton('Next')
self.levelLabel = QLabel('level：') # Show level
# connect buttons
self.nextButton.clicked.connect(self.nextButtonClicked)
self.lastButton.clicked.connect(self.lastButtonClicked)
# layout
viewLayout = QHBoxLayout()
# viewLayout.addWidget(self.viewBox)
viewLayout.addWidget(self.static_canvas)
## sub layout
viewButtonsLayout = QVBoxLayout()
viewButtonsLayout.addWidget(self.lastButton)
viewButtonsLayout.addWidget(self.nextButton)
viewButtonsLayout.addWidget(self.levelLabel)
viewLayout.addLayout(viewButtonsLayout)
self.viewGroupBox.setLayout(viewLayout)
# self.viewLabel = QLabel("View:o")
# self.iconComboBox = QComboBox()
# self.iconComboBox.addItem(QIcon(':/images/bad.png'), "Bad")
# self.iconComboBox.addItem(QIcon(':/images/heart.png'), "Heart")
# self.iconComboBox.addItem(QIcon(':/images/trash.png'), "Trash")
# self.showIconCheckBox = QCheckBox("Show icon")
# self.showIconCheckBox.setChecked(True)
# iconLayout = QHBoxLayout()
# iconLayout.addWidget(self.iconLabel)
# iconLayout.addWidget(self.iconComboBox)
# iconLayout.addStretch()
# iconLayout.addWidget(self.showIconCheckBox)
# self.iconGroupBox.setLayout(iconLayout)
def update_level_label(self):
self.levelLabel.setText('level:' + str(self.dataFrame.index))
def selectButtonClicked(self):
fileName1, filetype = QFileDialog.getOpenFileName(
self, "选取Numpy矩阵文件", "./",
"Numpy Files (*.npy)") #设置文件扩展名过滤,注意用双分号间隔
if fileName1 is not None and fileName1 != '':
self.dataFrame.path = fileName1
self.dataFrame.ReadFile()
self.dataFrame.index = 0
self.dataFrame.ShowInPlot(self.viewPlot)
self.update_level_label()
# draw something
# self.viewPlot = self.static_canvas.figure.subplots()
# height, width= self.dataFrame.dataArray[0].shape
# self.viewBox.setPixmap(QPixmap())
# print(fileName1)
# print(filetype)
def nextButtonClicked(self):
if (self.dataFrame.index + 1 >= self.dataFrame.dataArray.shape[0]):
pass
else:
self.dataFrame.index = self.dataFrame.index + 1
self.dataFrame.ShowInPlot(self.viewPlot)
self.update_level_label()
def lastButtonClicked(self):
if (self.dataFrame.index - 1 < 0):
pass
else:
self.dataFrame.index = self.dataFrame.index - 1
self.dataFrame.ShowInPlot(self.viewPlot)
self.update_level_label()
from DataFrame import DataFrame
from itertools import product
if __name__ == "__main__":
df = DataFrame.read_csv(csv_path='test.csv')
raw = df.copy()
raw.select.where("description").prefix("PAU")().print(10)
df["value"] = list(map(float, df["value"]))
df["sp_value"] = list(map(float, df["sp_value"]))
df.select.where("description").prefix("PAU").where("sp_value").equal(70).where("value").Not.between(69.8, 70.2)().sort("value").print(10)
print(df.select.where("description").contain("R").count())
# raw.append_csv("test.csv")
print(df[[3, 5]])
df[["time", "value"]].print(10, highlight_rows=[1, 2, 3, 4])
lst = list(range(10))
mat = [[i, j, k] for i, j, k in product(lst, lst, lst)]
df = DataFrame.read_matrix(matrix=mat)
print(df.variance("col_1"))
a = DataFrame.read_matrix(matrix=[[1, 1, 1], [2, 2, 2], [3, 3, 3]])
b = a.copy()
a[2] = [123, 234, 345]
c = a + b
d = c - a
a.print()
b.print()
c.print()
d.print()
d = {"date": "2019-01-01", "person": "Mark", "value": 20}
def __init__(self,
_type,
event_time,
sender,
receiver,
gel,
origin=None,
df=None):
self.type = _type
self.event_time = event_time
self.sender = sender
self.receiver = receiver
if origin == None:
self.origin = sender
else:
self.origin = origin
self.GEL = gel
self.dataframe = df
self.result_description = ""
if self.type == "internal DF":
"""
The origin of an internal DF is the sender
The origin of an external DF is the origin of the df
The origin of an ack is the origin of the df
"""
config = configparser.ConfigParser()
config.read("configuration_file.ini")
ARRIVE_RATE = float(config["DEFAULT"]["ARRIVE_RATE"])
arrival_time = event_time + negative_exponential_distribution(
ARRIVE_RATE)
df = DataFrame("data",
arrival_time,
self.sender,
self.receiver,
self.sender.ackId,
origin=self.origin)
df.global_Id = self.GEL.packet_counter
df.ACKed = False
self.arrival_time = arrival_time
self.dataframe = df
self.GEL.packet_counter += 1
self.GEL.packet_array.append(df)
self.sender.ackId += 1
def success():
self.sender.processArrivalDataFrame(arrival_time,
self.receiver,
"internal DF", df,
df.origin)
arrival_Event = ProcessDataFrameArrivalEvent(
self.type, arrival_time, self.sender, self.receiver, df)
arrival_Event.success = success
self.arrival_time += 0.00000001
self.GEL.addEvent(arrival_Event)
elif self.type == "external DF":
arrival_time = event_time + 0.00000001
self.arrival_time = arrival_time
self.dataframe = df
def success():
self.sender.processArrivalDataFrame(arrival_time,
self.receiver,
"external DF", df,
df.origin)
arrival_Event = ProcessDataFrameArrivalEvent(
self.type, arrival_time, self.sender, self.receiver, df)
arrival_Event.success = success
self.GEL.addEvent(arrival_Event)
elif self.type == "ack":
arrival_time = event_time + 0.00000001
original_sender = self.sender
original_receiver = self.receiver
self.sender = original_receiver
self.receiver = original_sender
self.arrival_time = arrival_time
self.dataframe = df
def success():
"""
The sender process the arrived ack, and then
"""
self.sender.processArrivalDataFrame(arrival_time,
self.receiver, "ack", df,
df.origin)
arrival_Event = ProcessDataFrameArrivalEvent(
self.type, arrival_time, self.sender, self.receiver, df)
arrival_Event.success = success
self.GEL.addEvent(arrival_Event)
class TestDataFrame(TestCase):
def setUp(self):
self.data_frame = DataFrame(labels=test_data[0], data=test_data[1:])
self.labels = [
'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'type'
]
self.data = test_data[1:]
pass
def test_indexing(self):
self.data_frame.reindex()
for index, item in enumerate(self.data_frame):
self.assertEqual(index, item.index)
def test_createDataFrame_labels(self):
self.assertEqual(len(self.data_frame.labels), len(test_data[0]))
def test_createDataFrame_data(self):
self.assertEqual(len(self.data_frame.data), len(test_data) - 1)
def test_label_correct(self):
for item_loc, item_to_test in zip(self.labels, self.data_frame.labels):
self.assertEqual(item_loc, item_to_test)
def test_data_correct(self):
for line_loc, line_to_test in zip(test_data[1:], self.data_frame.data):
for item_loc, item_to_test in zip(line_loc, line_to_test):
self.assertEqual(item_loc, item_to_test)
def test_get_types_from_data_frame_by_index_last_column(self):
types = self.data_frame.get_types_of_data(-1)
a = {'SML', "MID", "BIG"}
for key in types:
a.remove(key)
self.assertEqual(0, len(a))
def test_get_types_from_data_frame_by_label_name(self):
types = self.data_frame.get_types_of_data('type')
a = {'SML', "MID", "BIG"}
for key in types:
a.remove(key)
self.assertEqual(0, len(a))
def test_get_types_from_data_frame_by_label_a_column(self):
types = self.data_frame.get_types_of_data('a')
a = {1, 2, 3, 4, 5, 6, 7, 8, 9, 0}
for key in types:
a.remove(key)
self.assertEqual(0, len(a))
def test_indexing_check_labels_01(self):
data = self.data_frame[1, 2]
for item_loc, item_to_check in zip(self.labels[1], data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in indexing')
def test_indexing_check_labels_02(self):
data = self.data_frame[0, 2]
for item_loc, item_to_check in zip(self.labels[0], data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in indexing')
def test_indexing_check_labels_03(self):
data = self.data_frame[-1, 2]
for item_loc, item_to_check in zip(self.labels[-1], data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in indexing')
def test_indexing_check_labels_04(self):
data = self.data_frame[-5, 2]
for item_loc, item_to_check in zip(self.labels[-5], data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in indexing')
def test_indexing_check_data_01(self):
data = self.data_frame[:, 1]
for item_loc, item_to_check in zip(self.data[1], data.data[0]):
self.assertEqual(item_loc, item_to_check, 'wrong data in indexing')
def test_indexing_check_data_02(self):
data = self.data_frame[:, -1]
for item_loc, item_to_check in zip(self.data[-1], data.data[0]):
self.assertEqual(item_loc, item_to_check, 'wrong data in indexing')
def test_indexing_check_data_03(self):
data = self.data_frame[:, 100]
for item_loc, item_to_check in zip(self.data[100], data.data[0]):
self.assertEqual(item_loc, item_to_check, 'wrong data in indexing')
def test_slicing_only_col_check_labels_01(self):
data = self.data_frame[1:]
for item_loc, item_to_check in zip(self.labels[1:], data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in slicing')
def test_slicing_only_col_check_labels_02(self):
data = self.data_frame[:-1]
for item_loc, item_to_check in zip(self.labels[:-1], data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in slicing')
def test_slicing_only_col_check_labels_03(self):
data = self.data_frame[1:-1]
for item_loc, item_to_check in zip(self.labels[1:-1], data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in slicing')
def test_slicing_only_col_check_labels_04(self):
data = self.data_frame[2:5]
for item_loc, item_to_check in zip(self.labels[2:5], data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in slicing')
def test_slicing_check_labels_01(self):
data = self.data_frame[2:5, 2]
for item_loc, item_to_check in zip(self.labels[2:5], data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in slicing')
def test_slicing_check_labels_02(self):
data = self.data_frame[:, 2]
for item_loc, item_to_check in zip(self.labels, data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in slicing')
def test_slicing_check_labels_03(self):
data = self.data_frame[3:, 2]
for item_loc, item_to_check in zip(self.labels[3:], data.labels):
self.assertEqual(item_loc, item_to_check,
'wrong labels in slicing')
def test_slicing_check_data_01(self):
data = self.data_frame[:, 1:10]
for line_loc, line_to_check in zip(self.data[1:10], data.data):
for item_loc, item_to_check in zip(line_loc, line_to_check):
self.assertEqual(item_loc, item_to_check,
'wrong data in slicing')
def test_slicing_check_data_02(self):
data = self.data_frame[:, 12:120]
for line_loc, line_to_check in zip(self.data[12:120], data.data):
for item_loc, item_to_check in zip(line_loc, line_to_check):
self.assertEqual(item_loc, item_to_check,
'wrong data in slicing')
def test_slicing_check_data_03(self):
data = self.data_frame[:, 19:-5]
for line_loc, line_to_check in zip(self.data[19:-5], data.data):
for item_loc, item_to_check in zip(line_loc, line_to_check):
self.assertEqual(item_loc, item_to_check,
'wrong data in slicing')
def test_slicing_check_data_04(self):
data = self.data_frame[:4, 19:-5]
for line_loc, line_to_check in zip(self.data[19:-5], data.data):
for item_loc, item_to_check in zip(line_loc[:4], line_to_check):
self.assertEqual(item_loc, item_to_check,
'wrong data in slicing')
def test_slicing_check_data_05(self):
data = self.data_frame[1:6, 54:120]
for line_loc, line_to_check in zip(self.data[54:120], data.data):
for item_loc, item_to_check in zip(line_loc[1:6], line_to_check):
self.assertEqual(item_loc, item_to_check,
'wrong data in slicing')
def test_swap_values_one(self):
self.data_frame.swap_values('type', {"MID": "@MID@"})
types = self.data_frame.get_types_of_data('type')
self.assertTrue("@MID@" in types)
def test_swap_values_all(self):
self.data_frame.swap_values('type', {
"SML": "TINY",
"MID": "@MID@",
"BIG": "HUGE"
})
types = self.data_frame.get_types_of_data('type')
self.assertTrue("@MID@" in types)
self.assertTrue("TINY" in types)
self.assertTrue("HUGE" in types)
self.assertTrue("SML" not in types)
self.assertTrue("MID" not in types)
self.assertTrue("BIG" not in types)
def test_check_if_correct_values_are_teken(self):
data = self.data_frame.get_values_equal_to('type', "SML")
self.assertEqual(len(data.data), 50)
data_sliced = data[-1, :]
for item in data_sliced.data:
self.assertEqual(item[0], 'SML')
def test_pop_item_int_index_0(self):
data_raw = self.data_frame.pop_item(0)
expected_values = [0] * 10 + ['SML']
for exp_item, test_item in zip(expected_values, data_raw):
self.assertEqual(exp_item, test_item)
def test_pop_item_int_index_50(self):
data_raw = self.data_frame.pop_item(50)
expected_values = [0] * 10 + ['MID']
for exp_item, test_item in zip(expected_values, data_raw):
self.assertEqual(exp_item, test_item)
def test_pop_item_int_index_100(self):
data_raw = self.data_frame.pop_item(100)
expected_values = [0] * 10 + ['BIG']
for exp_item, test_item in zip(expected_values, data_raw):
self.assertEqual(exp_item, test_item)
def test_len_of_data_for_poping(self):
items_in_frame = len(self.data_frame)
for item in range(items_in_frame):
self.assertEqual(len(self.data_frame), items_in_frame - (item))
self.data_frame.pop_item(item)
self.assertEqual(len(self.data_frame), 0)
def test_copy_dataframe_if_is_correct_instance(self):
copied_dataframe = copy(self.data_frame)
self.assertTrue(isinstance(copied_dataframe, DataFrame))
def test_copy_correct_values(self):
copied_dataframe = copy(self.data_frame)
for rawdata_base, rawdata_copied in zip(self.data_frame,
copied_dataframe):
self.assertEquals(rawdata_base.index, rawdata_copied.index)
for item_base, item_copied in zip(rawdata_base, rawdata_copied):
self.assertEquals(item_base, item_copied)
def test_if_inner_objects_are_diffrent_data(self):
copied_dataframe = copy(self.data_frame)
copied_dataframe.data[0][0] = "Mu point"
self.assertEquals(copied_dataframe.data[0].index,
self.data_frame.data[0].index)
self.assertNotEquals(copied_dataframe.data[0][0],
self.data_frame.data[0][0])
def test_if_inner_objects_are_diffrent_lables(self):
copied_dataframe = copy(self.data_frame)
copied_dataframe.labels[0] = "Mu point"
self.assertNotEquals(copied_dataframe.labels[0],
self.data_frame.labels[0])
def test_check_pop_by_position(self):
self.data_frame.pop_on_poss(50)
self.assertEqual(self.data_frame.data[50].index, 51)
from DataFrame import DataFrame
from PlotGeneration import PlotGeneration
from LoadData import load_data
from StatisticalTest import StatisticalTest
if __name__ == "__main__":
print("Loading data frames. . .")
load_data() # load data
print("Loading statistics. . .")
DataFrame.FemaleIncidenceRate() # generate female incidence rates
DataFrame.FemaleMortalityRate() # generate female mortality rates
DataFrame.MaleIncidenceRate() # generate male incidence rates
DataFrame.MaleMortalityRate() # generate male morality rates
print("Generating CSV file. . .")
PlotGeneration.create_csv() # generate the CSV file to create the map
print("Generating map. . .")
PlotGeneration.generate_choropleth() # map creation
PlotGeneration.generate_sankey() # sankey plot generation
PlotGeneration.generate_boxplot()
print("Calculating statistics. . .\n"
) # T-Test generation, calculating averages
StatisticalTest()
StatisticalTest.box_plot_statistics(
PlotGeneration.map_data['total_incidence'],
PlotGeneration.map_data['state_name'], 'incidence_rate')
print("")
def __init__(self, master=None):
self.master = master
DataFrame.__init__(self, sp.load_fields, sp.load_field_types)
def test_sd(self):
df = DataFrame(x=scipy.random.randint(0, 10, 100))
s = df.group_by('x').summarize(sd=sd('x'))
self.assertAllClose(0, s.sd)