Python Network.make_clust方法代码示例

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
def make_viz_json(inst_df, name):
  from clustergrammer import Network
  net = Network()

  filename = 'json/'+name
  load_df = {}
  load_df['mat'] = inst_df
  net.df_to_dat(load_df)
  net.swap_nan_for_zero()
  net.make_clust(views=[])
  net.write_json_to_file('viz', filename, 'no-indent')

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
def main( buff, inst_filename, mongo_address, viz_id):
  import numpy as np
  import flask
  from bson.objectid import ObjectId
  from pymongo import MongoClient
  from flask import request
  from clustergrammer import Network
  import StringIO

  client = MongoClient(mongo_address)
  db = client.clustergrammer

  viz_id = ObjectId(viz_id)
  found_viz = db.networks.find_one({'_id':viz_id})

  try:

    net = Network()
    net.load_tsv_to_net(buff)

    net.swap_nan_for_zero()

    views = ['N_row_sum', 'N_row_var']

    net.make_clust(dist_type='cosine', dendro=True, views=views, \
                   linkage_type='average')

    export_dat = {}
    export_dat['name'] = inst_filename
    export_dat['dat'] = net.export_net_json('dat')
    export_dat['source'] = 'user_upload'

    dat_id = db.network_data.insert(export_dat)

    update_viz = net.viz 
    update_dat = dat_id

  except:
    print('\n-----------------------')
    print('error in clustering')
    print('-----------------------\n')
    update_viz = 'error'
    update_dat = 'error'

  found_viz['viz'] = update_viz
  found_viz['dat'] = update_dat

  db.networks.update_one( {'_id':viz_id}, {'$set': found_viz} )

  client.close()


  

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
def cluster():
  from clustergrammer import Network

  net = Network()

  vect_post = net.load_json_to_dict('fake_vect_post.json')  

  net.load_vect_post_to_net(vect_post)

  net.swap_nan_for_zero()
  
  # net.N_top_views()
  net.make_clust(dist_type='cos',views=['N_row_sum','N_row_var'], dendro=True)

  net.write_json_to_file('viz','json/large_vect_post_example.json','indent')  

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
def clustergrammer_load():
  # import network class from Network.py
  from clustergrammer import Network

  net = Network()

  net.pandas_load_file('mat_cats.tsv')  

  net.make_clust(dist_type='cos',views=['N_row_sum','N_row_var'])

  net.write_json_to_file('viz','json/mult_cats.json','indent')  

  print('\n**********************')
  print(net.dat['node_info']['row'].keys())

  print('\n\n')

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
def main():

  import time
  start_time = time.time()
  import pandas as pd
  import StringIO

  # import network class from Network.py
  from clustergrammer import Network

  net = Network()

  # load data to dataframe 
  # net.load_tsv_to_net('txt/example_tsv_network.txt')
  # net.load_tsv_to_net('txt/mat_1mb.txt')

  # choose file 
  ################
  # file_buffer = open('txt/col_categories.txt')
  file_buffer = open('txt/example_tsv_network.txt'  )


  buff = StringIO.StringIO( file_buffer.read() )
  net.pandas_load_tsv_to_net(buff)

  # filter rows 
  views = ['filter_row_sum','N_row_sum']

  # distance metric 
  dist_type = 'cosine'

  # linkage type 
  linkage_type = 'average'


  net.make_clust(dist_type=dist_type, views=views, calc_col_cats=True,\
  linkage_type=linkage_type)

  net.write_json_to_file('viz', 'json/mult_view.json', 'no-indent')

  elapsed_time = time.time() - start_time
  print('\n\n\nelapsed time: '+str(elapsed_time))

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
def make_json_from_tsv(name):
  '''
  make a clustergrammer json from a tsv file
  '''
  from clustergrammer import Network

  print('\n' + name)

  net = Network()

  filename = 'txt/'+ name + '.txt'

  net.load_file(filename)

  df = net.dat_to_df()

  net.swap_nan_for_zero()

  # zscore first to get the columns distributions to be similar
  net.normalize(axis='col', norm_type='zscore', keep_orig=True)

  # filter the rows to keep the perts with the largest normalizes values
  net.filter_N_top('row', 1000)

  num_rows = net.dat['mat'].shape[0]
  num_cols = net.dat['mat'].shape[1]

  print('num_rows ' + str(num_rows))
  print('num_cols ' + str(num_cols))

  if num_cols < 50 or num_rows < 1000:

    views = ['N_row_sum']
    net.make_clust(dist_type='cos', views=views)
    export_filename = 'json/' + name + '.json'
    net.write_json_to_file('viz', export_filename)

  else:
    print('did not cluster, too many columns ')

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
def make_viz_from_df(df, filename):
  from clustergrammer import Network

  net = Network()

  net.df_to_dat(df)
  net.swap_nan_for_zero()

  # zscore first to get the columns distributions to be similar
  net.normalize(axis='col', norm_type='zscore', keep_orig=True)

  # filter the rows to keep the perts with the largest normalizes values
  net.filter_N_top('row', 2000)

  num_coluns = net.dat['mat'].shape[1]

  if num_coluns < 50:
    # views = ['N_row_sum', 'N_row_var']
    views = ['N_row_sum']
    net.make_clust(dist_type='cos', views=views)

    filename = 'json/' + filename.split('/')[1].replace('.gct','') + '.json'

    net.write_json_to_file('viz', filename)

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
net.load_file('txt/rc_two_cats.txt')
# net.load_file('txt/example_tsv.txt')
# net.load_file('txt/col_categories.txt')
# net.load_file('txt/mat_cats.tsv')
# net.load_file('txt/mat_1mb.Txt')
# net.load_file('txt/mnist.txt')
# net.load_file('txt/sim_mat_4_cats.txt')

views = ['N_row_sum','N_row_var']

# # filtering rows and cols by sum 
# net.filter_sum('row', threshold=20)
# net.filter_sum('col', threshold=30)
  
# # keep top rows based on sum 
# net.filter_N_top('row', 10, 'sum')

net.make_clust(dist_type='cos',views=views , dendro=True,
               sim_mat=True, filter_sim=0.1)

# net.produce_view({'N_row_sum':10,'dist':'euclidean'})

net.write_json_to_file('viz', 'json/mult_view.json', 'no-indent')
net.write_json_to_file('sim_row', 'json/mult_view_sim_row.json', 'no-indent')
net.write_json_to_file('sim_col', 'json/mult_view_sim_col.json', 'no-indent')

elapsed_time = time.time() - start_time

print('\n\nelapsed time')
print(elapsed_time)

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]

#.........这里部分代码省略.........
  for inst_enr_score in top_terms:
    for tmp_num in num_dict.keys():
      keep_terms.extend( top_terms[inst_enr_score][tmp_num] )

  keep_terms = list(set(keep_terms))

  # keep enriched terms that are at the top 10 based on at least one score
  keep_enr = []
  for inst_enr in enr:
    if inst_enr['name'] in keep_terms:
      keep_enr.append(inst_enr)


  # fill in full matrix
  #######################

  # genes
  row_node_names = []
  # enriched terms
  col_node_names = []

  # gather information from the list of enriched terms
  for inst_enr in keep_enr:
    col_node_names.append(inst_enr['name'])
    row_node_names.extend(inst_enr['int_genes'])

  row_node_names = sorted(list(set(row_node_names)))

  net = Network()
  net.dat['nodes']['row'] = row_node_names
  net.dat['nodes']['col'] = col_node_names
  net.dat['mat'] = scipy.zeros([len(row_node_names),len(col_node_names)])

  for inst_enr in keep_enr:

    inst_term = inst_enr['name']
    col_index = col_node_names.index(inst_term)

    # use combined score for full matrix - will not be seen in viz
    tmp_score = scores['combined_score'][inst_term]
    net.dat['node_info']['col']['value'].append(tmp_score)

    for inst_gene in inst_enr['int_genes']:
      row_index = row_node_names.index(inst_gene)

      # save association
      net.dat['mat'][row_index, col_index] = 1

  # cluster full matrix
  #############################
  # do not make multiple views
  views = ['']

  if len(net.dat['nodes']['row']) > 1:
    net.make_clust(dist_type='jaccard', views=views, dendro=False)
  else:
    net.make_clust(dist_type='jaccard', views=views, dendro=False, run_clustering=False)

  # get dataframe from full matrix
  df = net.dat_to_df()

  for score_type in score_types:

    for num_terms in num_dict:

      inst_df = deepcopy(df)
      inst_net = deepcopy(Network())

      inst_df['mat'] = inst_df['mat'][top_terms[score_type][num_terms]]

      # load back into net
      inst_net.df_to_dat(inst_df)

      # make views
      if len(net.dat['nodes']['row']) > 1:
        inst_net.make_clust(dist_type='jaccard', views=['N_row_sum'], dendro=False)
      else:
        inst_net.make_clust(dist_type='jaccard', views=['N_row_sum'], dendro=False, run_clustering = False)

      inst_views = inst_net.viz['views']

      # add score_type to views
      for inst_view in inst_views:

        inst_view['N_col_sum'] = num_dict[num_terms]

        inst_view['enr_score_type'] = score_type

        # add values to col_nodes and order according to rank
        for inst_col in inst_view['nodes']['col_nodes']:

          inst_col['rank'] = len(top_terms[score_type][num_terms]) - top_terms[score_type][num_terms].index(inst_col['name'])

          inst_name = inst_col['name']
          inst_col['value'] = scores[score_type][inst_name]

      # add views to main network
      net.viz['views'].extend(inst_views)

  return net

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
# net.normalize(axis='row', norm_type='qn')
# net.normalize(axis='col', norm_type='zscore', keep_orig=True)

# net.filter_N_top('row', 100, rank_type='var')
# net.filter_N_top('col', 3, rank_type='var')

# net.filter_threShold('col', threshold=2, num_occur=3
# net.filter_threshold('row', threshold=3.0, num_occur=4)

net.swap_nan_for_zero()

# df = net.dat_to_df()

views = ['N_row_sum', 'N_row_var']

net.make_clust(dist_type='cos',views=views , dendro=True,
               sim_mat=True, filter_sim=0.1, calc_cat_pval=False)

               # run_enrichr=['ChEA_2015'])
               # run_enrichr=['ENCODE_TF_ChIP-seq_2014'])
               # run_enrichr=['KEA_2015'])
               # run_enrichr=['GO_Biological_Process_2015'])

net.write_json_to_file('viz', 'json/mult_view.json', 'no-indent')
net.write_json_to_file('sim_row', 'json/mult_view_sim_row.json', 'no-indent')
net.write_json_to_file('sim_col', 'json/mult_view_sim_col.json', 'no-indent')

# net.write_matrix_to_tsv ('txt/export_tmp.txt')

elapsed_time = time.time() - start_time
print('\n\nelapsed time: '+str(elapsed_time))

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
import time
start_time = time.time()

from clustergrammer import Network
net = Network()

net.load_file('txt/rc_two_cats.txt')
# net.load_file('txt/tmp.txt')

views = ['N_row_sum','N_row_var']

net.make_clust(dist_type='cos',views=views , dendro=True, sim_mat=True)

net.write_json_to_file('viz', 'json/mult_view.json')
net.write_json_to_file('sim_row', 'json/mult_view_sim_row.json')
net.write_json_to_file('sim_col', 'json/mult_view_sim_col.json')

elapsed_time = time.time() - start_time

print('\n\nelapsed time')
print(elapsed_time)

# 需要导入模块: from clustergrammer import Network [as 别名]
# 或者: from clustergrammer.Network import make_clust [as 别名]
		# Remove names for clustergrammer
		gene_attribute_matrix.index.name = ""
		gene_attribute_matrix.columns.name = ""
		# Write to file
		# fp = StringIO()
		# gene_attribute_matrix.to_csv(fp, sep='\t')
		gene_attribute_matrix.to_csv('tmp.txt', sep='\t')

		# Custergrammer
		from clustergrammer import Network
		net = Network()
		# net.load_tsv_to_net(fp, name) # StringIO
		net.load_file('tmp.txt')
		net.swap_nan_for_zero()
		# Generate
		net.make_clust(dist_type='cos',views=['N_row_sum', 'N_row_var'], dendro=True,
					   sim_mat=True, filter_sim=0.1, calc_cat_pval=False)

		# Insert into database
		cur.execute('insert into `datasets` (`Name`, `prot_att`, `att_att`, `prot_prot`) values (?, ?, ?, ?)',
			(name,
			 net.export_net_json('viz', indent='no-indent'),
			 net.export_net_json('sim_col', indent='no-indent'),
			 net.export_net_json('sim_row', indent='no-indent')))
		con.commit()
	except Exception as e:
		print "Couldn't process %s (%s)" % (name, e)
		continue
	print "Processed %s" % (name)
con.close()