def create_biplot(sIn, lWanted):
"""Run a PCA on state.x77 from R and generate its biplot. Color
observations by k-means clustering."""
from scipy.cluster.vq import kmeans, vq
from statsmodels.sandbox.tools.tools_pca import pcasvd
aData, sComponent, sValue = csv2np(sIn)
aDataReshape = aData.reshape((-1, len(lWanted)))
dDataReshaped = dict(
zip(lWanted,
np.array([aDataReshape[:, i] for i in range(len(lWanted))])))
df = pd.DataFrame(dDataReshaped)
#df = pd.io.parsers.read_csv(sIn, ',')
#print df.describe()
#print df.head()
data = df[lWanted]
data = (data - data.mean()) / data.std()
pca = pcasvd(data, keepdim=0, demean=False)
plt.figure(2)
lX, lY = biplot(plt, pca, labels=data.index, xpc=0, ypc=1, bPoints=False)
if sComponent != "":
"get dot product for a variable - investigative tool for categorical units"
#sComponent = "PrimaryUsage_Previous30days"
iIndex1 = lWanted.index(sComponent)
xVar = lX[iIndex1]
yVar = lY[iIndex1]
print('{}: {}, {}'.format(sComponent, xVar, yVar))
sTot = "TotalSpend"
iIndex2 = lWanted.index(sTot)
xTot = lX[iIndex2]
yTot = lY[iIndex2]
print('{}: {}, {}'.format(sTot, xTot, yTot))
rDotProd = (xVar * xTot) + (yVar * yTot)
print("Dot product = ", rDotProd)
plt.suptitle('"{}" for ({} . {})'.format(sValue, sComponent, sTot))
plt.title("Dot product = {}".format(round(rDotProd, 4)))
plt.axis([-1.2, 1.2, -1.2, 1.2])
plt.show()
def create_biplot(sIn, lWanted):
"""Run a PCA on state.x77 from R and generate its biplot. Color
observations by k-means clustering."""
from scipy.cluster.vq import kmeans, vq
from statsmodels.sandbox.tools.tools_pca import pcasvd
aData, sComponent, sValue = csv2np(sIn)
aDataReshape = aData.reshape((-1,len(lWanted)))
dDataReshaped = dict(zip(lWanted, np.array([aDataReshape[:,i] for i in range(len(lWanted)) ])))
df = pd.DataFrame( dDataReshaped )
#df = pd.io.parsers.read_csv(sIn, ',')
#print df.describe()
#print df.head()
data = df[lWanted]
data = (data - data.mean()) / data.std()
pca = pcasvd(data, keepdim=0, demean=False)
plt.figure(2)
lX,lY = biplot(plt, pca, labels=data.index, xpc=0, ypc=1, bPoints=False)
if sComponent != "":
"get dot product for a variable - investigative tool for categorical units"
#sComponent = "PrimaryUsage_Previous30days"
iIndex1 = lWanted.index(sComponent)
xVar = lX[iIndex1]
yVar = lY[iIndex1]
print('{}: {}, {}'.format(sComponent,xVar, yVar))
sTot = "TotalSpend"
iIndex2 = lWanted.index(sTot)
xTot = lX[iIndex2]
yTot = lY[iIndex2]
print('{}: {}, {}'.format(sTot, xTot, yTot))
rDotProd = (xVar * xTot) + (yVar * yTot)
print("Dot product = ", rDotProd)
plt.suptitle('"{}" for ({} . {})'.format(sValue, sComponent, sTot))
plt.title("Dot product = {}".format(round(rDotProd, 4)))
plt.axis([-1.2,1.2,-1.2,1.2])
plt.show()
def main():
"""Run a PCA on state.x77 from R and generate its biplot. Color
observations by k-means clustering."""
df = pd.io.parsers.read_csv('data/state.x77')
print df.describe()
print df.head()
columns = ['Population', 'Income', 'Illiteracy',
'Life Exp', 'Murder', 'HS Grad']
data = df[columns]
data = (data - data.mean()) / data.std()
pca = pcasvd(data, keepdim=0, demean=False)
values = data.values
centroids, _ = kmeans(values, 3)
idx, _ = vq(values, centroids)
colors = ['gby'[i] for i in idx]
plt.figure(1)
biplot(plt, pca, labels=data.index, colors=colors,
xpc=1, ypc=2)
plt.show()
def main():
"""Run a PCA on state.x77 from R and generate its biplot. Color
observations by k-means clustering."""
df = pd.io.parsers.read_csv('data/state.x77')
print df.describe()
print df.head()
columns = [
'Population', 'Income', 'Illiteracy', 'Life Exp', 'Murder', 'HS Grad'
]
data = df[columns]
data = (data - data.mean()) / data.std()
pca = pcasvd(data, keepdim=0, demean=False)
values = data.values
centroids, _ = kmeans(values, 3)
idx, _ = vq(values, centroids)
colors = ['gby'[i] for i in idx]
plt.figure(1)
biplot(plt, pca, labels=data.index, colors=colors, xpc=1, ypc=2)
plt.show()
# f.write("];\n")
# f.write("criteria = {")
# for crit in criteria:
# f.write("'" + crit + "' ")
# f.write('};')
# f.close()
#
uninetflows.insert(0,criteria)
with open("uninetflows.csv", "w") as f:
writer = csv.writer(f)
writer.writerows(uninetflows)
df = pd.io.parsers.read_csv('uninetflows.csv')
data = df[criteria]
# data = (data - data.mean()) / data.std()
pca = pcasvd(data, keepdim=0, demean=False)
colors = ['kcgrbmykcgrbmykcgrbmykcgrbmykcgrbmykcgrbmykcgrbmykcgrbmykcgrbmykcgrbmykcgrbmykcgrbmy'[i] for i in clust_repart]
labels = ['************************************************************************************'[i] for i in clust_repart]
plt.figure(1)
# biplot(plt, pca, labels=data.index, colors=colors, xpc=1, ypc=2)
biplot(plt, pca, labels=labels, colors=colors, xpc=1, ypc=2)
plt.show()
# iter = 0
# sols = []
# while iter < 5:
# prob.solve(pulp.GLPK())
# print(LpStatus[prob.status])
# sols.append(prob.variables())
#
# iter += 1