#serialget.py
import serial;

# using datetime module
import datetime;

arduino_port = "/dev/ttyACM0" #serial port of Arduino
baud = 9600 #arduino uno runs at 9600 baud
ser = serial.Serial(arduino_port, baud)
print("Connected to Arduino port:" + arduino_port)

getData=str(ser.readline())
#data=getData
#print(data)

samples = 1500 #how many samples to collect
line = 0
file1 = "DATA/token.csv"
#file2 = "DATA/token2.csv"

open1 = open(file1, "a")
#open1.write("data" + ", " + "output" + "\n") 
# I initially timestamped each record may do it later.
while line <= samples:
    ct = datetime.datetime.now()
    #d = str(ct.strftime("%m/%d/%Y %H:%M:%S"))
    getData=ser.readline()
    data=getData.strip().decode()
    print(data)
    open1.write(data + "\n") 
    line = line+1
#line = 0
#open2 = open(file2, "a")
#open2.write("timestamp" + ", " + "data" + ", " + "output" + "\n") 
#while line <= samples:
#    ct = datetime.datetime.now()
#    d = ct.strftime("%m/%d/%Y, %H:%M:%S")
#    getData=ser.readline()
#    data=getData.strip().decode()
#    print(data) 
#    open2.write(str(ct) + ", " + data + ", " + "usb" +  "\n") 
#    line = line+1

#test.py
from pandas import read_csv
from pandas.plotting import scatter_matrix
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC

# Load dataset
names = ['moisture','floating', 'raw_pulse', 'pulse', 'class']
# dataset = read_csv(url, names=names)
dataset = read_csv("all.csv", names=names)

#print(dataset.shape)
#print(dataset.head(20))
print("The sensors used in test")
print(dataset.describe())
print("Two test people and ambient/no person")
print(dataset.groupby('class').size())

...
# box and whisker plots
dataset.plot(kind='box', subplots=True, layout=(2,2), sharex=False, sharey=False)
#pyplot.show()
# histograms
dataset.hist()
#pyplot.show()

# scatter plot matrix
scatter_matrix(dataset)
#pyplot.show()

# Split-out validation dataset
array = dataset.values
X = array[:,0:4]
y = array[:,4]
X_train, X_validation, Y_train, Y_validation = train_test_split(X, y, test_size=0.20, random_state=1)

# Spot Check Algorithms
models = []
models.append(('LogisticRegression', LogisticRegression(solver='liblinear', multi_class='ovr')))
models.append(('LinearDiscriminantAnalysis', LinearDiscriminantAnalysis()))
models.append(('KNeighborsClassifier', KNeighborsClassifier()))
models.append(('DecisionTreeClassifier', DecisionTreeClassifier()))
models.append(('GaussianNB', GaussianNB()))
models.append(('SVC', SVC(gamma='auto')))
# evaluate each model in turn
results = []
names = []
for name, model in models:
	kfold = StratifiedKFold(n_splits=20, random_state=1, shuffle=True)
	cv_results = cross_val_score(model, X_train, Y_train, cv=kfold, scoring='accuracy')
	results.append(cv_results)
	names.append(name)
	print('%s: %f (%f)' % (name, cv_results.mean(), cv_results.std()))

# Compare Algorithms
pyplot.boxplot(results, labels=names)
pyplot.title('Algorithm Comparison')
#pyplot.show()

# Make predictions on validation dataset
#model = SVC(gamma='auto')
#model = GaussianNB()
# choose a model for predicting
print("Using DecisionTreeClassifier()")
model = DecisionTreeClassifier()
#model = LogisticRegression(solver='liblinear', multi_class='ovr')

print("Fitting the training data...")
model.fit(X_train, Y_train)
predictions = model.predict(X_validation)

# Evaluate predictions
print(accuracy_score(Y_validation, predictions))
print(confusion_matrix(Y_validation, predictions))
print(classification_report(Y_validation, predictions))

#challenge test using live data stream or saved csv
#['peter' 'peter' 'peter' 'peter' 'peter' 'peter' 'peter' 'peter' 'peter'
# 'peter' 'peter' 'peter' 'peter' 'peter' 'peter' 'peter' 'peter' 'peter'
# 'peter' 'peter' 'peter' 'alex' 'alex' 'alex' 'alex' 'alex' 'alex' 'alex'
# 'alex']

print("External data challenge...")
challenge = read_csv("challenge.csv")
prediction = model.predict(challenge)
print(prediction)

#print(model.predict_proba(challenge))