def analyzeClusters(n_loops=1, cl=None, sp=None, shuffled=False, spShuff=False):
results = {}
n = n_loops
bins = [i for i in drange(0.0, 1.0, 0.1)]
total_hist = [0 for i in bins]
data = win.getData(shuffle=shuffled, class_=cl, spec=sp)
if spShuff is True:
win.shuffleIt(data, mode=2)
Z = hie.linkage(data, method='average', metric='correlation')
D = hie.dendrogram(Z, orientation='left', no_plot=True)
total_ys = [0 for d in D['dcoord']]
total_z = [0 for d in Z[::-1, 2]]
total_acc = [0 for d in np.diff(Z[::-1, 2], 2)]
for ii in range(0, n): # for loop added to average shuffled results
# data = win.getData(shuffle=True, class_='J')
# labels = win.getStudents(class_=classes[0])
# labels = [str(st.class_) + " " + str(st.spec) for st in labels]
Z = hie.linkage(data, method='average', metric='correlation')
D = hie.dendrogram(Z, orientation='left', no_plot=True)
# print(data[40, :])
# print(data[42, :])
# freq method
ys = [d[1] for d in D['dcoord']]
total_ys = [a + b for a, b in zip(ys, total_ys)]
hist, bins = np.histogram(ys, bins=bins)
total_hist = [a + b for a, b in zip(hist, total_hist)]
# elbow method (sort of)
z = Z[::-1, 2]
total_z = [a + b for a, b in zip(z, total_z)]
# inv elbow
acceleration = np.diff(Z[::-1, 2], 2) # 2nd derivative of distances
total_acc = [a + b for a, b in zip(acceleration, total_acc)]
if ii < n - 1: # dont get new data if there wont be another loop
data = win.getData(shuffle=shuffled, class_=cl, spec=sp)
total_hist = [a / n for a in total_hist]
total_ys = [a / n for a in total_ys]
total_z = [a / n for a in total_z]
total_acc = [a / n for a in total_acc]
results['bins'] = (bins[:-1] + bins[1:]) / 2
results['hist'] = total_hist
results['ys'] = total_ys
results['z'] = total_z
results['acc'] = total_acc
return results
data = win.getData(class_=None)
co_corr = np.corrcoef(data, rowvar=0)
print(np.mean(co_corr), scp.sem(co_corr, axis=None), sep=' +/- ')
print('var: ', np.var(co_corr, axis=None))
n = 10000
'''c shuff'''
m = 0
e = 0
v = 0
for ii in range(n):
data = win.getData(class_=None)
win.shuffleIt(data, 2)
co_corr = np.corrcoef(data, rowvar=0)
m += np.mean(co_corr)
e += scp.sem(co_corr, axis=None)
v += np.var(co_corr, axis=None)
m /= n
e /= n
v /= n
print(m, e, sep=' +/- ')
print('var: ', v)
'''s shuff'''
m = 0
e = 0
v = 0
for ii in range(n):
# for ii, st in enumerate(students):
# if st.class_ != cl:
# anno.append((ii - 1, students[ii - 1].class_))
# cl = st.class_
# if st.spec != sp:
# anno2.append((ii - 1, students[ii - 1].spec))
# sp = st.spec
# anno.append(((len(students) - 1), students[-1].class_))
# anno2.append(((len(students) - 1), students[-1].spec))
# anno = anno + anno2
"""set up ranges"""
students = win.getData()
co_corr = np.corrcoef(students, rowvar=0)
vmin, vmax = co_corr.min(), co_corr.max()
win.shuffleIt(students, 2)
co_corr = np.corrcoef(students, rowvar=0)
vmin = vmin if co_corr.min() >= vmin else co_corr.min()
vmax = vmax if co_corr.min() <= vmax else co_corr.max()
students = win.getData()
win.shuffleIt(students, 1)
co_corr = np.corrcoef(students, rowvar=0)
vmin = vmin if co_corr.min() >= vmin else co_corr.min()
vmax = vmax if co_corr.min() <= vmax else co_corr.max()
vmin, vmax = vmin - 0.0001, vmax + 0.0001
"""plot heatmap"""
font = {"family": "normal", "weight": "bold", "size": 22}
matplotlib.rc("font", **font)
matplotlib.rcParams["ps.useafm"] = True