def appendMatrix(matrix01, matrix02):
#Column-wise appends matrix02 columns to matrix01, where user indices are unaligned. Returns new matrix01.
hold_matrix = csr_matrix((1, csr_matrix.get_shape(matrix02)[1])) #Empty matrix with 1 row
for user in riskFactor_userIDs:
if user in regex_userIDs:
hold_matrix = vstack([hold_matrix, matrix02[numpy.where(regex_userIDs==user)[0][0],:]])
continue
hold_matrix = vstack([hold_matrix, numpy.zeros(csr_matrix.get_shape(matrix02)[1])])
hold_matrix = csr_matrix(hold_matrix)[1:,:] #convert to csr matrix and remove first row
matrix01 = csr_matrix(hstack([matrix01, hold_matrix]))
return matrix01
def _compute_heat_diffusion(self, lap):
eps = 1e-9
n_simplices = csr_matrix.get_shape(lap)[0]
norm = np.vectorize(lambda x: 0 if np.abs(x) < eps else x)
n_filters = len(self.taus_)
if self.proc_ == 'exact':
eigenvals, U = self._get_eigens(lap)
heat = list()
for i in range(n_filters):
temp = U.dot(np.diagflat(
np.exp(- self.taus_[i] * eigenvals).flatten())).dot(U.T).\
dot(self.initial_condition)
heat.append((norm(temp)))
else:
heat = [sp.sparse.csc_matrix((n_simplices, n_simplices)) for i in
range(n_filters)]
monome = {0: sp.sparse.eye(n_simplices),
1: lap - sp.sparse.eye(n_simplices)}
for k in range(2, self.order_ + 1):
monome[k] = 2 * (lap - sp.sparse.eye(n_simplices)).dot(
monome[k - 1]) - monome[k - 2]
for i in range(n_filters):
coeffs = self._compute_cheb_coeff_basis(
self.taus_[i], self.order_)
temp = sp.sum([coeffs[k] * monome[k] for k in
range(0, self.order_ + 1)])
heat[i] = norm(temp.A) # cleans up the small coefficients
return heat
import os, codecs
import numpy
from scipy.sparse import hstack, csr_matrix
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import roc_auc_score
# Loading pickle file data into numpy array called data
f = open("smoking_1_analytic_data_mapreduce.pkl", "rb")
data = numpy.load(f)
data = numpy.array(data)
f.close()
# Loading smoking posts_matrix data
posts_matrix = data[0] # 11616 rows x 605107 columns
rows = csr_matrix.get_shape(posts_matrix)[0]
users_vector = data[3]
labels_vector = data[4]
keywords_vector = data[2]
# Empty matrix for load columns
loader_matrix = numpy.empty([rows, 1])
# List of RegExs
with open("collocation_smoker_regexs.txt", "r") as f:
queries = [l.strip() for l in f]
keywords_vector.extend(queries) # Extend keywords list so all columns names accessible
# Appends each regex column to loader_matrix
for query in queries:
import codecs
import os
import string
import numpy
from scipy.sparse import csr_matrix
from nltk import sent_tokenize, word_tokenize
#Loading pickle file data into numpy array called data
f = open('smoking_1_analytic_data_mapreduce.pkl', 'rb')
data = numpy.load(f)
data = numpy.array(data)
f.close()
#Loading smoking posts_matrix data
posts_matrix = data[0] #11616 rows x 605107 columns
rows = csr_matrix.get_shape(posts_matrix)[0]
users_vector = data[3]
labels_vector = data[4]
keywords_vector = data[2]
#Empty matrix for load columns
loader_matrix = numpy.empty([1, 7])
def word_count(tokens):
count = len([token for token in tokens if token not in string.punctuation])
return count
def sent_per_status(file_text):
content = file_text.readlines()
