def load_tsv_to_net(net, file_buffer):
import pandas as pd
import categories
lines = file_buffer.getvalue().split('\n')
num_labels = categories.check_categories(lines)
row_arr = range(num_labels['row'])
col_arr = range(num_labels['col'])
tmp_df = {}
# use header if there are col categories
if len(col_arr) > 1:
tmp_df['mat'] = pd.read_table(file_buffer, index_col=row_arr,
header=col_arr)
else:
tmp_df['mat'] = pd.read_table(file_buffer, index_col=row_arr)
# remove columns with all nans, occurs when there are trailing
# tabs on rows
tmp_df['mat'] = tmp_df['mat'].dropna(axis=1)
net.df_to_dat(tmp_df)
def load_tsv_to_net(net, file_buffer, filename=None):
import pandas as pd
import categories
import proc_df_labels
lines = file_buffer.getvalue().split('\n')
num_labels = categories.check_categories(lines)
row_arr = range(num_labels['row'])
col_arr = range(num_labels['col'])
tmp_df = {}
# use header if there are col categories
if len(col_arr) > 1:
tmp_df['mat'] = pd.read_table(file_buffer, index_col=row_arr,
header=col_arr)
else:
tmp_df['mat'] = pd.read_table(file_buffer, index_col=row_arr)
tmp_df = proc_df_labels.main(tmp_df)
net.df_to_dat(tmp_df)
net.dat['filename'] = filename
def load_tsv_to_net(net, file_buffer, filename=None):
import pandas as pd
import categories
import proc_df_labels
lines = file_buffer.getvalue().split('\n')
num_labels = categories.check_categories(lines)
row_arr = range(num_labels['row'])
col_arr = range(num_labels['col'])
tmp_df = {}
# use header if there are col categories
if len(col_arr) > 1:
tmp_df['mat'] = pd.read_table(file_buffer,
index_col=row_arr,
header=col_arr)
else:
tmp_df['mat'] = pd.read_table(file_buffer, index_col=row_arr)
tmp_df = proc_df_labels.main(tmp_df)
net.df_to_dat(tmp_df)
net.dat['filename'] = filename
def load_tsv_to_net(net, file_buffer, filename=None):
import numpy as np
import pandas as pd
import categories
from ast import literal_eval as make_tuple
lines = file_buffer.getvalue().split('\n')
num_labels = categories.check_categories(lines)
row_arr = range(num_labels['row'])
col_arr = range(num_labels['col'])
tmp_df = {}
# use header if there are col categories
if len(col_arr) > 1:
tmp_df['mat'] = pd.read_table(file_buffer, index_col=row_arr,
header=col_arr)
else:
tmp_df['mat'] = pd.read_table(file_buffer, index_col=row_arr)
# 1) check that rows are strings (in case of numerical names)
# 2) check for tuples, and in that case load tuples to categories
test = {}
test['row'] = tmp_df['mat'].index.tolist()
test['col'] = tmp_df['mat'].columns.tolist()
# if type( test_row ) is not str and type( test_row ) is not tuple:
found_tuple = {}
found_number = {}
for inst_rc in ['row','col']:
inst_name = test[inst_rc][0]
found_tuple[inst_rc] = False
found_number[inst_rc] = False
if type(inst_name) != tuple:
if type(inst_name) is int or type(inst_name) is float or type(inst_name) is np.int64:
found_number[inst_rc] = True
else:
check_open = inst_name[0]
check_comma = inst_name.find(',')
check_close = inst_name[-1]
if check_open == '(' and check_close == ')' and check_comma > 0 \
and check_comma < len(inst_name):
found_tuple[inst_rc] = True
# convert to tuple if necessary
#################################################
if found_tuple['row']:
row_names = tmp_df['mat'].index.tolist()
row_names = [make_tuple(x) for x in row_names]
tmp_df['mat'].index = row_names
if found_tuple['col']:
col_names = tmp_df['mat'].columns.tolist()
col_names = [make_tuple(x) for x in col_names]
tmp_df['mat'].columns = col_names
# convert numbers to string if necessary
#################################################
if found_number['row']:
row_names = tmp_df['mat'].index.tolist()
row_names = [str(x) for x in row_names]
tmp_df['mat'].index = row_names
if found_number['col']:
col_names = tmp_df['mat'].columns.tolist()
col_names = [str(x) for x in col_names]
tmp_df['mat'].columns = col_names
# # remove columns with all nans, occurs when there are trailing
# # tabs on rows
# tmp_df['mat'] = tmp_df['mat'].dropna(axis=1, how='all')
net.df_to_dat(tmp_df)
net.dat['filename'] = filename
def load_tsv_to_net(net, file_buffer, filename=None):
import numpy as np
import pandas as pd
import categories
from ast import literal_eval as make_tuple
lines = file_buffer.getvalue().split('\n')
num_labels = categories.check_categories(lines)
row_arr = range(num_labels['row'])
col_arr = range(num_labels['col'])
tmp_df = {}
# use header if there are col categories
if len(col_arr) > 1:
tmp_df['mat'] = pd.read_table(file_buffer,
index_col=row_arr,
header=col_arr)
else:
tmp_df['mat'] = pd.read_table(file_buffer, index_col=row_arr)
# 1) check that rows are strings (in case of numerical names)
# 2) check for tuples, and in that case load tuples to categories
test = {}
test['row'] = tmp_df['mat'].index.tolist()
test['col'] = tmp_df['mat'].columns.tolist()
# if type( test_row ) is not str and type( test_row ) is not tuple:
found_tuple = {}
found_number = {}
for inst_rc in ['row', 'col']:
inst_name = test[inst_rc][0]
found_tuple[inst_rc] = False
found_number[inst_rc] = False
if type(inst_name) != tuple:
if type(inst_name) is int or type(inst_name) is float or type(
inst_name) is np.int64:
found_number[inst_rc] = True
else:
check_open = inst_name[0]
check_comma = inst_name.find(',')
check_close = inst_name[-1]
if check_open == '(' and check_close == ')' and check_comma > 0 \
and check_comma < len(inst_name):
found_tuple[inst_rc] = True
# convert to tuple if necessary
#################################################
if found_tuple['row']:
row_names = tmp_df['mat'].index.tolist()
row_names = [make_tuple(x) for x in row_names]
tmp_df['mat'].index = row_names
if found_tuple['col']:
col_names = tmp_df['mat'].columns.tolist()
col_names = [make_tuple(x) for x in col_names]
tmp_df['mat'].columns = col_names
# convert numbers to string if necessary
#################################################
if found_number['row']:
row_names = tmp_df['mat'].index.tolist()
row_names = [str(x) for x in row_names]
tmp_df['mat'].index = row_names
if found_number['col']:
col_names = tmp_df['mat'].columns.tolist()
col_names = [str(x) for x in col_names]
tmp_df['mat'].columns = col_names
# # remove columns with all nans, occurs when there are trailing
# # tabs on rows
# tmp_df['mat'] = tmp_df['mat'].dropna(axis=1, how='all')
net.df_to_dat(tmp_df)
net.dat['filename'] = filename
