Killian / decodopr

Blame view

BOTTLENECK/02c-tsne_mlproj.py 4.34 KB
edit raw normal view history
d414b83e1   Killian   add Botttleneck M... 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
 
  
  # coding: utf-8
  
  # In[2]:
  
  # Import
  import gensim
  from scipy import sparse
  import itertools
  from sklearn import preprocessing
  from keras.models import Sequential
  from keras.optimizers import SGD,Adam
  from keras.layers.advanced_activations import ELU,PReLU
  from keras.callbacks import ModelCheckpoint
  from mlp import *
  import pandas as pd
  import sklearn.metrics
  from sklearn.preprocessing import LabelBinarizer
  from sklearn.manifold import TSNE
  import shelve
  import pickle
  from utils import *
  import sys
  import os
  import json
  # In[4]:
  
  in_dir = sys.argv[1]
  #['ASR', 'TRS', 'LABEL']
  # In[6]:
  json_conf =json.load(open(sys.argv[2]))
  
  mlp_conf = json_conf["transfert"]
  hidden_size = mlp_conf["hidden_size"]
  loss = mlp_conf["loss"]
  patience = mlp_conf["patience"]
  dropouts = mlp_conf["do"]
  epochs = mlp_conf["epochs"]
  batch_size = mlp_conf["batch"]
  input_activation=mlp_conf["input_activation"]
  output_activation=mlp_conf["output_activation"]
  
  try:
      k = mlp_conf["sgd"]
      if mlp_conf["sgd"]["name"] == "adam":
          sgd = Adam(lr=mlp_conf["sgd"]["lr"])#SGD(lr=0.00001,nesterov=False) #'rmsprop'# Adam(lr=0.00001)#SGD(lr=0.001, momentum=0.9, nesterov=True)
      elif mlp_conf["sgd"]["name"] == "sgd":
          sgd = SGD(lr=mlp_conf["sgd"]["lr"])
  except: 
      sgd = mlp_conf["sgd"]
  name = json_conf["name"]
  
  #
  print " MLP" 
  proj_hdf = pandas.HDFStore("{}/{}/MLP_proj_df.hdf".format(in_dir,name))
  hdf_keys = proj_hdf.keys()
  proj_hdf.close()
  hdf_mods = set([ x.split("/")[1] for x in hdf_keys ])
  hdf_lvl = set( [ x.split("/")[2] for x in hdf_keys ])
  hdf_crossval =  set([ x.split("/")[3] for x in hdf_keys ])
  print hdf_mods
  print hdf_lvl
  print hdf_crossval
  
  hdf_proj_path = "{}/{}/MLP_proj_df.hdf".format(in_dir,name)
  tsne_proj_path = "{}/{}/tsne_proj_df.hdf".format(in_dir,name)
  for mod in hdf_mods:
      for lvl in hdf_lvl :
          x_train = pandas.read_hdf(hdf_proj_path,key="/{}/{}/{}".format(mod,lvl,"TRAIN"))
          x_dev = pandas.read_hdf(hdf_proj_path,key="/{}/{}/{}".format(mod,lvl,"DEV"))
          x_test = pandas.read_hdf(hdf_proj_path,key="/{}/{}/{}".format(mod,lvl,"TEST"))
  
          if x_train.shape[1] <= 8 :
              continue
          tsne= TSNE()
          tsne_train=tsne.fit_transform(x_train.values)
          pd.DataFrame(tsne_train).to_hdf(tsne_proj_path,key="MLP/{}/{}/{}".format(mod,lvl,"TRAIN"))
          tsne= TSNE()
          tsne_dev=tsne.fit_transform(x_dev.values)
          pd.DataFrame(tsne_dev).to_hdf(tsne_proj_path,key="MLP/{}/{}/{}".format(mod,lvl,"DEV"))
          tsne= TSNE()
          tsne_test=tsne.fit_transform(x_test.values)
          pd.DataFrame(tsne_test).to_hdf(tsne_proj_path,key="MLP/{}/{}/{}".format(mod,lvl,"TEST"))
          tsne = TSNE()
          tsne_all = tsne.fit_transform(pd.concat([x_train,x_dev,x_test]).values)
          pd.DataFrame(tsne_all).to_hdf(tsne_proj_path,key="MLP/{}/{}/{}".format(mod,lvl,"CONCAT"))
  
  print " TRANSFERT"
  
  hdf_proj_path = "{}/{}/transfert_proj_df.hdf".format(in_dir,name)
  proj_hdf = pandas.HDFStore(hdf_proj_path)
  print proj_hdf
  hdf_keys = proj_hdf.keys()
  proj_hdf.close()
  print hdf_keys
  hdf_lvl = set([ x.split("/")[1] for x in hdf_keys ])
  hdf_layer = set( [ x.split("/")[2] for x in hdf_keys ])
  hdf_crossval =  set([ x.split("/")[3] for x in hdf_keys ])
  print hdf_lvl
  print hdf_layer
  print hdf_crossval
  
  tsne_proj_path = "{}/{}/tsne_proj_df.hdf".format(in_dir,name)
  for lvl in hdf_lvl :
      for layer in hdf_layer:
          x_train = pandas.read_hdf(hdf_proj_path,key="/{}/{}/{}".format(lvl,layer,"TRAIN"))
          x_dev = pandas.read_hdf(hdf_proj_path,key="/{}/{}/{}".format(lvl,layer,"DEV"))
          x_test = pandas.read_hdf(hdf_proj_path,key="/{}/{}/{}".format(lvl,layer,"TEST"))
  
          if x_train.shape[1] <= 8 :
              continue
          tsne= TSNE()
          tsne_train=tsne.fit_transform(x_train.values)
          pd.DataFrame(tsne_train).to_hdf(tsne_proj_path,key="transfert/{}/{}/{}".format(mod,lvl,"TRAIN"))
          tsne= TSNE()
          tsne_dev=tsne.fit_transform(x_dev.values)
          pd.DataFrame(tsne_dev).to_hdf(tsne_proj_path,key="transfert/{}/{}/{}".format(mod,lvl,"DEV"))
          tsne= TSNE()
          tsne_test=tsne.fit_transform(x_test.values)
          pd.DataFrame(tsne_test).to_hdf(tsne_proj_path,key="transfert/{}/{}/{}".format(mod,lvl,"TEST"))
          tsne = TSNE()
          tsne_all = tsne.fit_transform(pd.concat([x_train,x_dev,x_test]).values)
          pd.DataFrame(tsne_all).to_hdf(tsne_proj_path,key="transfert/{}/{}/{}".format(mod,lvl,"CONCAT"))