def main():
#nr=input('Enter the dimension N of the square lattice -->')
nr=4
reps=nr*nr # number of lattice sites
# generate complete dataset
(training_data,training_H,training_M)=mh.complete_dataset(reps)
train_labels=mh.gen_train_labels(training_data, training_H, training_M)
# compute frequesncies
counter=collections.Counter(train_labels)
val=counter.values()
freq=np.array(val)/np.float(len(train_labels))
#partition into training 90% and testing 10% datasets
[train,test]=mh.partition(training_data,train_labels)
train_set=train[0]
train_y=train[1]
test_set=test[0]
test_y=test[1]
test_classes=np.unique(test_y)
train_classes=np.unique(train_y)
training=[]
testing=[]
for i in range(len(train_set)):
row=train_set[i]
training.append(np.hstack((row,train_y[i])))
for i in range(len(test_set)):
row2=test_set[i]
testing.append(np.hstack((row2,test_y[i])))
np.reshape(testing,(len(testing),17))
np.reshape(training,(len(training),17))
train2=sorted(training,key=itemgetter(-1))
test2=sorted(testing,key=itemgetter(-1))
print "Initial number of random seeds is set to 10"
print "It yields a training dataset of 10,000 samples per temperature"
print "The temperature range is set to [0.1 40.0] with step size 0.5"
expr=input("Would you like to increase the training dataset size? 'y'/'n'")
if expr=='y':
r=input("Enter a factor (integer) by which to increase the sample size")
elif expr=='n':
r=1
else:
r=1
train_res=get_MH_sampled_IDs(train2,train_classes,freq,r)
test_res=get_MH_sampled_IDs(test2,test_classes,freq,1)
write_to_csv(train_res, "training")
write_to_csv(test_res, "testing")
import ising_model_princeton2 as I
import matplotlib.pyplot as plt
from sklearn.tree import DecisionTreeClassifier
from sklearn.decomposition import PCA
from sklearn.preprocessing import scale
from operator import itemgetter
nr=input('Enter the dimension N of the square lattice -->')
reps=nr*nr # number of lattice sites
# generate complete dataset
(training_data,training_H,training_M)=mh.complete_dataset(reps)
train_labels=mh.gen_train_labels(training_data, training_H, training_M)
#partition into training 90% and testing 10% datasets
[train,test]=mh.partition(training_data,train_labels)
train_set=train[0]
train_y=train[1]
test_set=test[0]
test_y=test[1]
training=[]
testing=[]
for i in range(len(train_set)):
row=train_set[i]
training.append(np.hstack((row,train_y[i])))
for i in range(len(test_set)):
row2=test_set[i]
testing.append(np.hstack((row2,test_y[i])))
np.reshape(testing,(len(testing),17))
np.reshape(training,(len(training),17))
