def correlation_experiment(file, lan, embf, name):
data, cencoder, tencoder, embchars = readdata(file, lan)
cdecoder = {v: k for k, v in cencoder.items()}
tdecoder = {v: k for k, v in tencoder.items()}
features = getphonfeatures()
lanfeatures = [
np.array(features[cdecoder[f]]) if cdecoder[f] in features else None
for f in range(len(cencoder))
]
featsim = getsimmatrix(lanfeatures, len(cencoder), embchars)
embeddings = embf(data, cencoder, embchars, tencoder, cdecoder, tdecoder,
lan)
sims = [getsimmatrix(m, len(cencoder), embchars) for m in embeddings]
rs = [correlation(featsim, sims[i])[0] for i in [0, 1, 2]]
print("%s %s:" % (lan, name))
print(" PEARSON R FOR EMBEDDING AND FEATURE REPR. SIMILARITIES:")
print(" %s,DIM=5" % lan, rs[0])
print(" %s,DIM=15" % lan, rs[1])
print(" %s,DIM=30" % lan, rs[2])
randrs = [[], [], []]
for i in range(N):
ranembeddings = [matshuf(m) for m in embeddings]
ransims = [
getsimmatrix(m, len(cencoder), embchars) for m in ranembeddings
]
randrs[0].append(correlation(featsim, ransims[0])[0])
randrs[1].append(correlation(featsim, ransims[1])[0])
randrs[2].append(correlation(featsim, ransims[2])[0])
print((" P=%.2f CONF. INTERVALS FOR PEARSON R OF RANDOM ASSIGNMENT OF\n" %
P) + " EMBEDDINGS TO PHONEMES AND PHONETIC FEATURE DESCRIPTIONS:")
civals = [confidenceival(randrs[i]) for i in [0, 1, 2]]
print(" %s,DIM=5" % lan, confidenceival(randrs[0]),
checkr(civals[0], rs[0]), rs[0])
print(" %s,DIM=15" % lan, confidenceival(randrs[1]),
checkr(civals[1], rs[1]), rs[1])
print(" %s,DIM=30" % lan, confidenceival(randrs[2]),
checkr(civals[2], rs[2]), rs[2])
print()
# print()
# print(mod.status,"\t",mod.objVal,"\t",ct)
return mod
# %%
# Number of instances
Is = 10
# Number of models, where model 0 is the non altered basic order model
M = 1
# Combinations
Combs = order_pot(poten(list(range(1, M))))
parN,parP,parC,parD=readdata()
Ic = 0
h=0
# For instance ii in set of instances Is
for ii in range(Is):
# For model set mn in set of models:
for mn in Combs:
Ic = Ic + 1
h = h + 1
MathModel(parC[ii], parD[ii], parN[ii], parP[ii], mn, ii, Ic)
print(h,"\t",ii,"\t",mn)
print("")
#closeddf = data.collect("Close")
#highdf = data.collect("High")
#lowdf = data.collect("Low")
#pre-saved data in pickle, open it for quicker run.
pickle_in = open("Close.pickle", "rb")
closeddf = pickle.load(pickle_in)
pickle_in = open("Low.pickle", "rb")
lowdf = pickle.load(pickle_in)
pickle_in = open("High.pickle", "rb")
highdf = pickle.load(pickle_in)
#different indicators is calculated by calling back to data.py and save it as the particular
#pandas database
#normalizing the closeddf by using the first day closing price
normalizedCloseddf = data.normalizeData(closeddf)
volumeDF = data.readdata("Volume")
SMAdf = data.SMA(closeddf, 20)
EMAdf = data.EMA(closeddf, 5)
RSIdf = data.RSI(closeddf, 14)
KSTdf = data.KST(closeddf, 10, 15, 20, 30, 10, 10, 10, 15)
TRIXdf = data.TRIX(closeddf, 15)
IXIC = pd.DataFrame(index=normalizedCloseddf.index)
IXIC = normalizedCloseddf[['IXIC Close']]
highbbdf, lowbbdf = data.BollingerBand(closeddf)
MassIdf = data.MassI(highdf, lowdf)
MOMdf = data.MOM(closeddf, 10)
ROCdf = data.ROC(closeddf, 10)
dailyReturnDF = data.dailyReturn(normalizedCloseddf)
MACDdf, MACDsigndf, MACDDiffdf = data.MACD(closeddf)
STOKdf = data.STOK(closeddf, lowdf, highdf)
STOdf = data.STO(closeddf, lowdf, highdf, 14)
checkr(civals[0], rs[0]), rs[0])
print(" %s,DIM=15" % lan, confidenceival(randrs[1]),
checkr(civals[1], rs[1]), rs[1])
print(" %s,DIM=30" % lan, confidenceival(randrs[2]),
checkr(civals[2], rs[2]), rs[2])
print()
if __name__ == "__main__":
print("1. CORRELATION EXPERIMENTS")
print("--------------------------")
print()
# correlation_experiment("../data/finnish","FI",getsvdembs,"SVD")
# correlation_experiment("../data/turkish","TUR",getsvdembs,"SVD")
# correlation_experiment("../data/spanish","ES",getsvdembs,"SVD")
# correlation_experiment("../data/finnish","FI",getw2vembs,"W2V")
# correlation_experiment("../data/turkish","TUR",getw2vembs,"W2V")
# correlation_experiment("../data/spanish","ES",getw2vembs,"W2V")
# correlation_experiment("../data/finnish","FI",getrnnembs,"RNN")
# correlation_experiment("../data/turkish","TUR",getrnnembs,"RNN")
# correlation_experiment("../data/spanish","ES",getrnnembs,"RNN")
data, cencoder, tencoder, embchars = readdata('../data/finnish', "FI")
modeld = initmodel(cencoder, tencoder, 15)
encoded = encode(data[0][1], data[0][2], modeld)
train(data, modeld)
# for i in range(100):
# print(update(data[0][1],data[0][2],data[0][0],modeld))