from keras.layers import Dense, Dropout, Activation, Flatten, Convolution2D, MaxPooling2D
from sklearn.metrics import classification_report, confusion_matrix
from keras.callbacks import EarlyStopping, TensorBoard
from keras.models import Sequential, load_model
from keras import optimizers, regularizers
from keras.utils import np_utils
import data_processing as data
import numpy as np
from time import time
import os
np.random.seed(123) # for reproducibility
# load data
dataset = data.getData() #instance
dataset.get()
(X_train, Y_train), (X_test, Y_test) = (dataset.X_train,
dataset.Y_train), (dataset.X_test,
dataset.Y_test)
# preprocess data
X_train = X_train.reshape(X_train.shape[0], 1, 430, 1)
X_test = X_test.reshape(X_test.shape[0], 1, 430, 1)
print X_train.shape
print X_test.shape
# normalize data values to range [0, 1]
X_train /= 255
X_test /= 255
def createLayout():
global cases, casesText, casesNew, deaths, deathsText, deathsNew, \
recovered, recoveredText, recoveredNew, active, activeText, activeNew, population
cases, casesText, casesNew, deaths, deathsText, deathsNew, \
recovered, recoveredText, recoveredNew, active, activeText, activeNew, population = data_processing.getData()
return html.Div(
id="mainContainer",
className="mainContainer",
children=[
html.Div(id="header_accumulator_cases", style={"display": "none"}),
html.Div(id="header_accumulator_active", style={"display":
"none"}),
html.Div(id="header_accumulator_recovered",
style={"display": "none"}),
html.Div(id="header_accumulator_deaths", style={"display":
"none"}),
# empty Div to trigger javascript file for autocomplete off
html.Div(id="output-clientside"),
html.Div(
className="flex-display",
children=[
html.H3(id="header",
style={
"flex": "1",
"marginTop": "0",
"textAlign": "center"
}),
],
),
dcc.Tabs(
id='tab_selector',
value='cases',
className="tab_container",
# Style needs to be here not in style.css or it doesn't work
style={
"display": "flex",
"flexFlow": "row nowrap"
},
children=[
dcc.Tab(label='Total cases',
value='cases',
className="tab",
selected_className="tab--selected"),
dcc.Tab(label='Active cases',
value='active',
className="tab",
selected_className="tab--selected"),
dcc.Tab(label='Recovered',
value='recovered',
className="tab",
selected_className="tab--selected"),
dcc.Tab(label='Deaths',
value='deaths',
className="tab",
selected_className="tab--selected"),
dcc.Tab(label='New cases vs total cases',
value='newVsTotal',
className="tab",
selected_className="tab--selected"),
]),
html.Div(
id="main_row",
className="main_row pretty_container",
style={"marginTop": "0"},
# Tab content goes here
),
html.Div(className="flex-display",
children=[
dcc.Markdown(children=dataSourceText,
style={
"textAlign": "center",
"margin": "2rem",
"flex": "1"
}),
]),
])
import pandas as pd
import data_processing as d_p
import pickle
import scipy.stats as stats
import numpy as np
import matplotlib.pyplot as plt
fname = "processed_data.pkl"
data = pickle.load(open(fname, "rb"))
latitude = d_p.getData('latitude')
assessment_r = d_p.getData('assessment_result')
ar_type = []
group_data = []
for i in range(len(assessment_r)):
if assessment_r[i] not in ar_type:
ar_type.append(assessment_r[i])
group_data.append([])
var_index = ar_type.index(assessment_r[i])
group_data[var_index].append(latitude[i])
print(ar_type)
fv, pv = stats.f_oneway(group_data[0],group_data[1],group_data[2],group_data[3],group_data[4])
print(fv,pv)
temp_data = []
for i in range(len(ar_type)):
temp_data.append( np.array(group_data[i]).astype(np.float))
group_data = temp_data
from statistics import *
import pandas as pd
import data_processing as d_p
import pickle
import scipy.stats as stats
import numpy as np
import matplotlib.pyplot as plt
fname = "processed_data.pkl"
data = pickle.load(open(fname, "rb"))
latitude = d_p.getData('latitude')
latitude = np.array(latitude).astype(np.float)
cat = True
plot_cat = True
num = False
plot_num = False
# seperate latitude to 3 lists [L,M,H]
latitude_list = [[],[],[]]
L_M = 53.9047
M_H = 59.0688
for i in range(len(latitude)):
if latitude[i] < L_M:
latitude_list[0].append(i)
elif latitude[i] >= M_H:
latitude_list[2].append(i)
else:
latitude_list[1].append(i)