def attach_user_act(X, month):
col_names = np.genfromtxt(
paths.my_path +
'user_act_counts_month_{0}{1}_col_names.csv'.format(1, month - 1),
delimiter=',',
dtype=str)
full_act = Matrix(
np.genfromtxt(paths.my_path +
'user_act_counts_month_{0}{1}.csv'.format(1, month - 1),
delimiter=',',
dtype=float),
col_names[0, :],
col_formats=["%s" for i in xrange(col_names.shape[1] - 1)])
full_act_hash = HashSet()
for i in xrange(full_act.ndata):
if i % 100000 == 0:
print i
uid = full_act.get_cell(i, "uid")
full_act_hash.set(uid, full_act.matrix[i, 1:])
X_full_act = np.zeros((X.ndata, col_names.shape[1] - 1))
for i in xrange(X.ndata):
if i % 100000 == 0:
print i
uid = X.get_cell(i, "uid")
X_full_act[i, :] = full_act_hash.get(uid,
np.zeros(col_names.shape[1] - 1))
col_names_check_point = []
for name in col_names[0, 1:]:
col_names_check_point.append('{0}_user_all_month'.format(name))
X.cat_col(X_full_act, col_names_check_point,
["%s" for i in xrange(len(col_names_check_point))])
def attach_user_act_history(X, month):
for k in xrange(month - 1, 0, -1):
print k
col_names_history = np.genfromtxt(
paths.my_path +
'user_act_counts_month_{0}_col_names.csv'.format(k),
delimiter=',',
dtype=str)
history = Matrix(
np.genfromtxt(paths.my_path +
'user_act_counts_month_{0}.csv'.format(k),
delimiter=',',
dtype=float), col_names_history[0, :],
["%s" for i in xrange(col_names_history.shape[1])])
history_hash = HashSet()
for i in xrange(history.ndata):
if i % 100000 == 0:
print i
uid = history.get_cell(i, "uid")
history_hash.set(uid, history.matrix[i, 2:])
X_history = np.zeros((X.ndata, col_names_history.shape[1] - 2))
for i in xrange(X.ndata):
if i % 100000 == 0:
print i
uid = X.get_cell(i, "uid")
X_history[i, :] = history_hash.get(
uid, np.zeros(col_names_history.shape[1] - 2))
col_names = []
for name in col_names_history[0, 2:]:
col_names.append('{0}_user_month_{1}'.format(name, month - k))
X.cat_col(X_history, col_names, ["%s" for i in xrange(len(col_names))])
for k in xrange(7 - month):
col_names = []
for name in col_names_history[0, 2:]:
col_names.append('{0}_user_month_{1}'.format(name, month - k))
X_history = np.zeros((X.ndata, len(col_names)))
X.cat_col(X_history, col_names, ["%s" for i in xrange(len(col_names))])