import get_y
import sklearn.linear_model
from sklearn import preprocessing
from sklearn.linear_model import Lasso
import combineData as cd
import copy
folder = './data/'
#X = cd.loadFilesFrom(folder)
X = pd.read_csv('./data/education.csv', encoding='mac_roman')
X = X.set_index("Geography")
cols = X.columns
originalData = copy.deepcopy(X)
y = pd.read_csv('./election_results.csv')
X = cd.addYcol(X, y)
mat = X.as_matrix()
mat = list(mat)
for i in range(len(mat)):
for j in range(len(mat[i])):
val = mat[i][j]
try:
mat[i][j] = float(val)
except:
mat[i][j] = 0.0
mat = np.array(mat)
#np.random.shuffle(mat)
X = mat[:, :-1]
Y = mat[:, -1]
#Y = Y * 10000.0
import pdb
import get_y
import sklearn.linear_model
from sklearn import preprocessing
from sklearn.linear_model import Lasso
from sklearn.mixture import GaussianMixture as GM
import combineData as cd
import copy
import matplotlib.pyplot as plt
fname = './cleanedData/'
X = cd.loadFilesFrom(fname)
Y = pd.read_csv('./election_results.csv')
X = cd.addYcol(X,Y)
df = X.copy(deep=True)
Y = X.iloc[:,-1].as_matrix()
X = X.iloc[:,0:-1].as_matrix()
temp = np.nan_to_num(X)
for i in range(len(temp)):
for j in range(len(temp[0])):
if type(X[i,j]) == type('NaN') :
temp[i,j] = 0.0
if np.isnan(temp[i,j]):
temp[i,j] = 0.0