Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
def load_tsv_to_net(net, file_buffer, filename=None):
lines = file_buffer.getvalue().split('\n')
num_labels = categories.check_categories(lines)
row_arr = list(range(num_labels['row']))
col_arr = list(range(num_labels['col']))
# use header if there are col categories
if len(col_arr) > 1:
df = pd.read_table(file_buffer, index_col=row_arr,
header=col_arr)
else:
df = pd.read_table(file_buffer, index_col=row_arr)
df = proc_df_labels.main(df)
net.df_to_dat(df, True)
net.dat['filename'] = filename
def load_tsv_to_net(net, file_buffer, filename=None):
lines = file_buffer.getvalue().split('\n')
num_labels = categories.check_categories(lines)
row_arr = list(range(num_labels['row']))
col_arr = list(range(num_labels['col']))
# use header if there are col categories
if len(col_arr) > 1:
df = pd.read_table(file_buffer, index_col=row_arr,
header=col_arr)
else:
df = pd.read_table(file_buffer, index_col=row_arr)
df = proc_df_labels.main(df)
net.df_to_dat(df, True)
net.dat['filename'] = filename
def export_df(self):
'''
Export Pandas DataFrame/
'''
df = data_formats.dat_to_df(self)
# drop tuple categories if downsampling
if self.is_downsampled:
df.columns = self.dat['nodes']['col']
df.index = self.dat['nodes']['row']
return df
def dat_to_df(self):
'''
Export Pandas DataFrams (will be deprecated).
'''
return data_formats.dat_to_df(self)
else:
self.col_cats = col_cats
self.meta_cat = True
if isinstance(meta_row, pd.DataFrame):
self.meta_row = meta_row
if row_cats is None:
self.row_cats = meta_row.columns.tolist()
else:
self.row_cats = row_cats
self.meta_cat = True
data_formats.df_to_dat(self, df, define_cat_colors=True)
def df_to_dat(self, df, define_cat_colors=False):
'''
Load Pandas DataFrame (will be deprecated).
'''
data_formats.df_to_dat(self, df, define_cat_colors)
def main(real_net, vect_post):
import numpy as np
from copy import deepcopy
from .__init__ import Network
from . import proc_df_labels
net = deepcopy(Network())
sigs = vect_post['columns']
all_rows = []
all_sigs = []
for inst_sig in sigs:
all_sigs.append(inst_sig['col_name'])
col_data = inst_sig['data']
for inst_row_data in col_data:
all_rows.append(inst_row_data['row_name'])
all_rows = sorted(list(set(all_rows)))
all_sigs = sorted(list(set(all_sigs)))
all_filt = list(range(10))
all_filt = [i / float(10) for i in all_filt]
mat = deepcopy(df['mat'])
sum_row = np.sum(mat, axis=1)
max_sum = max(sum_row)
for inst_filt in all_filt:
cutoff = inst_filt * max_sum
copy_net = deepcopy(net)
inst_df = deepcopy(df)
inst_df = run_filter.df_filter_row_sum(inst_df, cutoff, take_abs=False)
tmp_net = deepcopy(Network())
tmp_net.df_to_dat(inst_df)
try:
try:
calc_clust.cluster_row_and_col(tmp_net, dist_type=dist_type,
run_clustering=True)
except:
calc_clust.cluster_row_and_col(tmp_net, dist_type=dist_type,
run_clustering=False)
inst_view = {}
inst_view['pct_row_' + rank_type] = inst_filt
inst_view['dist'] = 'cos'
inst_view['nodes'] = {}
inst_view['nodes']['row_nodes'] = tmp_net.viz['row_nodes']
from .__init__ import Network
from copy import deepcopy
from . import calc_clust
sim_dict = {}
for inst_rc in which_sim:
sim_dict[inst_rc] = dm_to_sim(inst_dm[inst_rc], make_squareform=True,
filter_sim=filter_sim)
sim_net = {}
for inst_rc in which_sim:
sim_net[inst_rc] = deepcopy(Network())
sim_net[inst_rc].dat['mat'] = sim_dict[inst_rc]
sim_net[inst_rc].dat['nodes']['row'] = net.dat['nodes'][inst_rc]
sim_net[inst_rc].dat['nodes']['col'] = net.dat['nodes'][inst_rc]
sim_net[inst_rc].dat['node_info']['row'] = net.dat['node_info'][inst_rc]
sim_net[inst_rc].dat['node_info']['col'] = net.dat['node_info'][inst_rc]
calc_clust.cluster_row_and_col(sim_net[inst_rc])
all_views = []
df = sim_net[inst_rc].dat_to_df()
send_df = deepcopy(df)
sim_net[inst_rc].viz['views'] = all_views
rows_sorted = run_filter.get_sorted_rows(df['mat'], rank_type)
for inst_keep in keep_top:
tmp_df = deepcopy(df)
check_keep_num = inst_keep
# convert 'all' to -1 to clean up checking mechanism
if check_keep_num == 'all':
check_keep_num = -1
if check_keep_num < len(rows_sorted):
tmp_net = deepcopy(Network())
if inst_keep != 'all':
keep_rows = rows_sorted[0:inst_keep]
tmp_df['mat'] = tmp_df['mat'].loc[keep_rows]
if 'mat_orig' in tmp_df:
tmp_df['mat_orig'] = tmp_df['mat_orig'].loc[keep_rows]
tmp_df = run_filter.df_filter_col_sum(tmp_df, 0.001)
tmp_net.df_to_dat(tmp_df)
else:
tmp_net.df_to_dat(tmp_df)