def main(path_file_in, path_file_out, N=800, sr=3, iss=0.1, leak=0.1, ridge=10**-1, plot=False, feedback=False, return_result=False, verbose=False): def write_list_in_file(l, file=None, file_path=None): """ Write a list in a file with with one item per line (like a one column csv). If file is given, then it assumes the file is already open for writing. If file_path is given, then it opens the file for writing, write the list, and then close the file. """ if file_path is not None: if file is not None: raise Exception, "Too much arguments. You must choose between file and file_path." else: file = open(file_path, 'w') if file is None: raise Exception, "No file given in input." for item in l: file.write("%s\n" % item) if file_path is not None: file.close() import io_language_coding as CtIolangcod sentence_to_meaning = False # Definning parameters of stimulus (in a dictionary) d = {} d['act_time'] = 5 d['pause'] = True d['suppl_pause_at_the_end'] = 1 * d['act_time'] d['initial_pause'] = True d['offset'] = False ## Random parameters import time millis = int(round(time.time())) seed = millis #2#4#2 if seed is not None: mdp.numx.random.seed(seed) np.random.seed(seed) [train_data_txt, test_data_txt, sent_form_info_train, sent_form_info_test] = extract_data_io(path_file=path_file_in) train_corpus, train_meaning = txt2corpus_and_meaning( train_txt=train_data_txt) if sentence_to_meaning: test_corpus = test_data_txt else: test_meaning = test_data_txt # making the list of constructions (refering to "construction grammar"), a construction is a sentence without its open class words (Nouns and Verbs) (l_construction_train, construction_words) = get_and_remove_ocw_in_corpus(corpus=train_corpus, _OCW='X') l_ocw_array_train = generate_l_ocw_array(sent_form_info_train, train_meaning) l_ocw_array_test = generate_l_ocw_array(sent_form_info_test, test_meaning) #print "**************************" #print "l_construction_train", l_construction_train #print "construction words", construction_words if sentence_to_meaning: (l_construction_test, construction_words_test) = get_and_remove_ocw_in_corpus( corpus=test_corpus, _OCW='X') #print "l_construction_test", l_construction_test if construction_words != construction_words_test: raise Exception, "The construction words are not the same for the train constructions and the test constructions. So the coding of sentences will be different and should provoque a future problem." ## Generating all the sentence stimulus (in order to have the same length for each sentence) if sentence_to_meaning: ## Generate the stimulus input for train and test data l_full_const = l_construction_train + l_construction_test slice_test = slice( len(l_construction_train), len(l_construction_train) + len(l_construction_test)) else: l_full_const = l_construction_train slice_train = slice(0, len(l_construction_train)) (stim_full_data, l_full_offset) = CtIolangcod.generate_stim_input_nodic( l_data=l_full_const, # act_time=d['act_time'], subset=None, l_input=None, act_time=d['act_time'], subset=None, l_input=construction_words, l_nr_word=None, mult=None, full_time=None, with_offset=d['offset'], pause=d['pause'], initial_pause=d['initial_pause'], suppl_pause_at_the_end=d['suppl_pause_at_the_end'], verbose=False) stim_sent_train = stim_full_data[slice_train] if sentence_to_meaning: stim_sent_test = stim_full_data[slice_test] l_m_elt = get_meaning_coding() (stim_mean_train, l_meaning_code_train) = generate_meaning_stim( l_structure=sent_form_info_train, full_time=stim_sent_train[0].shape[0], l_m_elt=l_m_elt) if not sentence_to_meaning: #print "*** Generating meaning for test set ... ***" (stim_mean_test, l_meaning_code_test) = generate_meaning_stim( l_structure=sent_form_info_test, full_time=stim_sent_train[0].shape[0], l_m_elt=l_m_elt) other_corpus_used = False # Reservoir and Read-out definitions res = reservoir.Reservoir(N, sr, iss, leak) #classic working of the reservoir if feedback == False: ## test set = train set states_out_train, internal_states_train = res.train( stim_mean_train, stim_sent_train) ## test set not train set states_out_test, internal_states_test = res.test(stim_mean_test) #feedback working of the reservoir. !! Should be implemented directly in the reservoir class !! else: delay = 1 nb_epoch_max = 4 dim_input = stim_mean_train[0].shape[1] dim_output = len(stim_sent_train[0][0]) input_train = [] for (x, y) in zip(np.copy(stim_mean_train), np.copy(stim_sent_train)): for time_step_delay in range(delay): y = np.concatenate(([[0.] * len(y[0])], y), axis=0) input_train.append( np.array(np.concatenate((x, y[:-delay]), axis=1))) nb_train = 0 while nb_train < nb_epoch_max: ## test set = train set states_out_train, internal_states_train = res.train( input_train, stim_sent_train) tab_feedback = [] for num_phrase in range(len(states_out_train)): #signal tresholded states_out_train[num_phrase] = np.array([ treshold_signal(signal_t, 1.5, -0.5) for signal_t in states_out_train[num_phrase] ]) if nb_train == 0: #feedback kept only for the first train #feedback assignation feedback = np.array(states_out_train[num_phrase]) #signal delayed for time_step_delay in range(delay): feedback = np.concatenate( ([[0.] * len(feedback[0])], feedback), axis=0) tab_feedback.append(feedback) input_train[num_phrase] = input_train[num_phrase].T input_train[num_phrase][dim_input:] = feedback[:-delay].T input_train[num_phrase] = input_train[num_phrase].T nb_train += 1 ## test set not train set for t in range(0, stim_mean_test[0].shape[0], 1): input_test = [] if t == 0: #A REMODIFIER for n_phrase in range(len(stim_mean_test)): input_test.append( np.concatenate((stim_mean_test[n_phrase][t:t + 1, :], [[0.] * len(stim_sent_train[0][0])]), axis=1)) states_out_test, internal_states_test = res.test(input_test) import copy states_out_test_def = copy.deepcopy(states_out_test) else: for n_phrase in range(len(stim_mean_test)): #feedback assignation feedback = np.array(states_out_test[n_phrase]) input_test.append( np.concatenate( (stim_mean_test[n_phrase][t:t + 1, :], feedback), axis=1)) states_out_test, internal_states_test = res.test(input_test) for n_phrase in range(len(stim_mean_test)): states_out_test_def[n_phrase] = np.concatenate( (states_out_test_def[n_phrase], states_out_test[n_phrase]), axis=0) states_out_test = states_out_test_def # Ecriture de la phrase de réponse if other_corpus_used: var_inutile = 0 else: l_recovered_construction_train = convert_l_output_activity_in_construction( l_out_act=states_out_train, construction_words=construction_words, min_nr_of_val_upper_thres=1) l_recovered_sentences_train = attribute_ocw_to_constructions( l_constructions=l_recovered_construction_train, l_ocw_array=l_ocw_array_train, _OCW='X') l_recovered_construction_test = convert_l_output_activity_in_construction( l_out_act=states_out_test, construction_words=construction_words, min_nr_of_val_upper_thres=2) l_recovered_sentences_test = attribute_ocw_to_constructions( l_constructions=l_recovered_construction_test, l_ocw_array=l_ocw_array_test, _OCW='X') ## Writting sentences to output file #print " *** Writting to output file ... *** " l_final_sent_test = [] for list_words in l_recovered_sentences_test: l_final_sent_test.append(" ".join(list_words)) #print " *** ... Writting done ***" #print "**********************************************" print "********************************************** " print " *** RECOGNIZED SENTENCES *** " print l_final_sent_test[0] write_list_in_file(l=l_final_sent_test, file_path=path_file_out) if return_result: return l_final_sent_test ## Plot inputs if plot: import plotting as plotting plotting.plot_array_in_file( root_file_name="../Results/states_out_train", array_=states_out_train, titles_subset=l_construction_train, legend_=construction_words, plot_slice=None, title="", subtitle="") plotting.plot_array_in_file( root_file_name="../Results/states_out_test", array_=states_out_test, titles_subset=l_recovered_sentences_test, legend_=construction_words, plot_slice=None, title="", subtitle="") print ""
def main(path_file_in, path_file_out, plot=False, fast=False, keep_internal_states=False, verbose=False): import os #sys.path.append(os.path.dirname(os.path.abspath(__file__))+"/..") #print "path ", os.path.dirname(os.path.abspath(__file__))+"/.." current_directory = os.path.dirname(os.path.abspath(__file__)) parent_directory = os.path.dirname(current_directory) sys.path.append(parent_directory) import io_language_coding as CtIolangcod # Definning parameters of stimulus (in a dictionary) d = {} d['act_time'] = 5 #2#1#5#10#2 d['pause'] = True #False d['suppl_pause_at_the_end'] = 1 * d['act_time'] d['initial_pause'] = False #True#False#False d['offset'] = True #False#True # Parameters for reservoir N = 500 #500#500#1000 #100 sr = 1 #3#3#2#1 iss = 0.25 #0.01#1 leak = 0.25 / float( d['act_time']) #0.75/float(d['act_time'])#0.75/2.#0.5#0.05 ## Random parameters seed = 5 if seed is not None: mdp.numx.random.seed(seed) np.random.seed(seed) [train_data_txt, test_data_txt, sent_form_info_test] = common.extract_data_io(path_file=path_file_in) train_corpus, train_meaning = common.txt2corpus_and_meaning( train_txt=train_data_txt) test_corpus = test_data_txt # making the list of constructions (refering to "construction grammar"), a construction is a sentence without its open class words (Nouns and Verbs) (l_construction_train, l_ocw_array_train, construction_words) = common.get_and_remove_ocw_in_corpus( corpus=train_corpus, _OCW='X', l_closed_class=get_closed_class_words()) (l_construction_test, l_ocw_array_test, construction_words_test) = common.get_and_remove_ocw_in_corpus( corpus=test_corpus, _OCW='X', l_closed_class=get_closed_class_words()) if construction_words != construction_words_test: raise Exception, "The construction words are not the same for the train constructions and the test constructions. So the coding of sentences will be different and should provoque a future problem." ################################################# ## Generating all the sentence stimulus (in order to have the same length for each sentence) l_full_const = l_construction_train + l_construction_test slice_test = slice(len(l_construction_train), len(l_construction_train) + len(l_construction_test)) slice_train = slice(0, len(l_construction_train)) (stim_full_data, l_full_offset) = CtIolangcod.generate_stim_input_nodic( l_data=l_full_const, # act_time=d['act_time'], subset=None, l_input=None, act_time=d['act_time'], subset=None, l_input=construction_words, l_nr_word=None, mult=None, full_time=None, with_offset=d['offset'], pause=d['pause'], initial_pause=d['initial_pause'], suppl_pause_at_the_end=d['suppl_pause_at_the_end'], verbose=False) stim_sent_train = stim_full_data[slice_train] stim_sent_test = stim_full_data[slice_test] ################################################# ## Generating all the meaning stimulus ################################################# l_m_elt = common.get_meaning_coding( max_nr_ocw=max_nr_ocw, max_nr_actionrelation=max_nr_actionrelation, elt_pred=elt_pred) (stim_mean_train, l_meaning_code_train) = common.generate_meaning_stim( l_data=train_meaning, l_ocw_array=l_ocw_array_train, full_time=stim_sent_train[0].shape[0], l_m_elt=l_m_elt, l_offset=l_full_offset[slice_train], verbose=False, initial_pause=d['initial_pause'], pause=d['pause'], act_time=d['act_time']) ## Defining reservoir, readout and flow reservoir = Oger.nodes.LeakyReservoirNode(output_dim=N, spectral_radius=sr, input_scaling=iss, nonlin_func=np.tanh, leak_rate=leak) read_out = mdp.nodes.LinearRegressionNode(use_pinv=True, with_bias=True) flow = mdp.Flow([reservoir, read_out]) if keep_internal_states: Oger.utils.make_inspectable(mdp.Flow) ## Trainning and testing print "Train and test" if not fast: (states_out_train, internal_states_train, internal_outputs_train, neuron_states_train) = \ common._teach_and_test_flow(inputs_train_set=stim_sent_train, teacher_outputs_train_set=stim_mean_train, inputs_test_set=stim_sent_train, _flow=flow, _reservoir=reservoir, keep_internal_states=keep_internal_states) else: raise Exception, "have to define what to do for fast mode" ## test set not train set (states_out_test, internal_states_test, internal_outputs_test, neuron_states_test) = \ common._test_flow(inputs_test_set=stim_sent_test, _flow=flow, _reservoir=reservoir, keep_internal_states=keep_internal_states) if verbose: for i in range(len(stim_mean_train)): print "len(stim_mean_train)", len(stim_mean_train) print "len(l_meaning_code_train)", len(l_meaning_code_train) print l_meaning_code_train[i] print(stim_mean_train[0] == stim_mean_train[i]) print(l_meaning_code_train[0] == l_meaning_code_train[i]) ## Writting output meaning l_recovered_meaning_test = convert_l_output_activity_in_meaning( l_out_act=states_out_test, l_ocw_array=l_ocw_array_test, l_m_elt=l_m_elt) if verbose: print "l_recovered_meaning_test", l_recovered_meaning_test l_final_mean_test = [] for meanings in l_recovered_meaning_test: current_meanings = "" if verbose: print "meanings", meanings for i_m in range(len(meanings)): # if verbose: # print " i_m:",i_m # print " meanings[i_m]:",meanings[i_m] if i_m > 0: current_meanings += ',' current_meanings += " ".join(meanings[i_m]) l_final_mean_test.append(current_meanings) print "" print "**********************************************" print " *** RECOGNIZED MEANINGS *** " for elt in l_final_mean_test: print str(elt) print "**********************************************" ## Writting sentences to output file print " *** Writting to output file ... *** " #ecrire une seule ligne simple dans un fichier la phrase attendue en mode test common.write_list_in_file(l=l_final_mean_test, file_path=path_file_out) print " *** ... Writting done ***" print "**********************************************" ## Plot if plot: print " *** Plotting to output file ... *** " # import oct2011.plotting as plotting import plotting as plotting plotting.plot_array_in_file( root_file_name="../RES_TEMP/states_out_train", array_=states_out_train, titles_subset=l_meaning_code_train, # legend_=l_m_elt, plot_slice=None, title="", subtitle="") legend_=None, plot_slice=None, title="", subtitle="") plotting.plot_array_in_file( root_file_name="../RES_TEMP/states_out_train_sent", array_=states_out_train, titles_subset=train_meaning, # legend_=l_m_elt, plot_slice=None, title="", subtitle="") legend_=None, plot_slice=None, title="", subtitle="") plotting.plot_array_in_file( root_file_name="../RES_TEMP/states_out_test", array_=states_out_test, titles_subset=l_final_mean_test, # legend_=l_m_elt, plot_slice=None, title="", subtitle="") legend_=None, plot_slice=None, title="", subtitle="") plotting.plot_array_in_file( root_file_name="../RES_TEMP/intern_states_test", array_=internal_states_test, titles_subset=None, plot_slice=None, title="", subtitle="") print " *** ... Plotting to output file done *** " print "**********************************************" return l_final_mean_test
def main(path_file_in, path_file_out,N=1200, sr=3, iss=0.1, leak=0.1, ridge=10**-1, plot=False, feedback=False, return_result=False, verbose=False): def write_list_in_file(l, file=None, file_path=None): """ Write a list in a file with with one item per line (like a one column csv). If file is given, then it assumes the file is already open for writing. If file_path is given, then it opens the file for writing, write the list, and then close the file. """ if file_path is not None: if file is not None: raise Exception, "Too much arguments. You must choose between file and file_path." else: file = open(file_path, 'w') if file is None: raise Exception, "No file given in input." for item in l: file.write("%s\n" % item) if file_path is not None: file.close() import io_language_coding as CtIolangcod sentence_to_meaning = False # Definning parameters of stimulus (in a dictionary) d = {} d['act_time'] = 5 d['pause'] = True d['suppl_pause_at_the_end'] = 1*d['act_time'] d['initial_pause'] = True d['offset'] = False ## Random parameters import time millis = int(round(time.time() )) seed = millis#2#4#2 if seed is not None: mdp.numx.random.seed(seed) np.random.seed(seed) [train_data_txt, test_data_txt, sent_form_info_train, sent_form_info_test] = extract_data_io(path_file=path_file_in) train_corpus, train_meaning = txt2corpus_and_meaning(train_txt=train_data_txt) if sentence_to_meaning: test_corpus = test_data_txt else: test_meaning = test_data_txt # making the list of constructions (refering to "construction grammar"), a construction is a sentence without its open class words (Nouns and Verbs) (l_construction_train, construction_words) = get_and_remove_ocw_in_corpus(corpus=train_corpus, _OCW='X') l_ocw_array_train=generate_l_ocw_array(sent_form_info_train, train_meaning) l_ocw_array_test=generate_l_ocw_array(sent_form_info_test, test_meaning) #print "**************************" #print "l_construction_train", l_construction_train #print "construction words", construction_words if sentence_to_meaning: (l_construction_test, construction_words_test) = get_and_remove_ocw_in_corpus(corpus=test_corpus, _OCW='X') #print "l_construction_test", l_construction_test if construction_words!=construction_words_test: raise Exception, "The construction words are not the same for the train constructions and the test constructions. So the coding of sentences will be different and should provoque a future problem." ## Generating all the sentence stimulus (in order to have the same length for each sentence) if sentence_to_meaning: ## Generate the stimulus input for train and test data l_full_const = l_construction_train + l_construction_test slice_test = slice(len(l_construction_train),len(l_construction_train)+len(l_construction_test)) else: l_full_const = l_construction_train slice_train = slice(0,len(l_construction_train)) (stim_full_data, l_full_offset) = CtIolangcod.generate_stim_input_nodic(l_data=l_full_const, # act_time=d['act_time'], subset=None, l_input=None, act_time=d['act_time'], subset=None, l_input=construction_words, l_nr_word=None, mult=None, full_time=None, with_offset=d['offset'], pause=d['pause'], initial_pause=d['initial_pause'], suppl_pause_at_the_end=d['suppl_pause_at_the_end'], verbose=False) stim_sent_train = stim_full_data[slice_train] if sentence_to_meaning: stim_sent_test = stim_full_data[slice_test] l_m_elt = get_meaning_coding() (stim_mean_train, l_meaning_code_train) = generate_meaning_stim(l_structure=sent_form_info_train, full_time=stim_sent_train[0].shape[0], l_m_elt=l_m_elt) if not sentence_to_meaning: #print "*** Generating meaning for test set ... ***" (stim_mean_test, l_meaning_code_test) = generate_meaning_stim(l_structure=sent_form_info_test, full_time=stim_sent_train[0].shape[0], l_m_elt=l_m_elt) other_corpus_used = False # Reservoir and Read-out definitions res = reservoir.Reservoir(N, sr, iss, leak) #classic working of the reservoir if feedback==False: ## test set = train set states_out_train, internal_states_train = res.train (stim_mean_train, stim_sent_train) ## test set not train set states_out_test, internal_states_test = res.test(stim_mean_test) #feedback working of the reservoir. !! Should be implemented directly in the reservoir class !! else: delay=1 nb_epoch_max=4 dim_input = stim_mean_train[0].shape[1] dim_output = len(stim_sent_train[0][0]) input_train=[] for (x,y) in zip( np.copy(stim_mean_train), np.copy(stim_sent_train)): for time_step_delay in range(delay): y=np.concatenate( ([[0.]*len(y[0])] , y), axis=0) input_train.append(np.array( np.concatenate( (x, y[:-delay]), axis=1 ) )) nb_train=0 while nb_train < nb_epoch_max: ## test set = train set states_out_train, internal_states_train = res.train (input_train, stim_sent_train) tab_feedback=[] for num_phrase in range(len(states_out_train)): #signal tresholded states_out_train[num_phrase]=np.array([treshold_signal(signal_t,1.5,-0.5) for signal_t in states_out_train[num_phrase]]) if nb_train==0: #feedback kept only for the first train #feedback assignation feedback=np.array(states_out_train[num_phrase]) #signal delayed for time_step_delay in range(delay): feedback=np.concatenate( ([[0.]*len(feedback[0])] , feedback), axis=0) tab_feedback.append(feedback) input_train[num_phrase]=input_train[num_phrase].T input_train[num_phrase][dim_input:] = feedback[:-delay].T input_train[num_phrase]=input_train[num_phrase].T nb_train+=1 ## test set not train set for t in range(0,stim_mean_test[0].shape[0],1): input_test=[] if t==0: #A REMODIFIER for n_phrase in range(len(stim_mean_test)): input_test.append(np.concatenate( (stim_mean_test[n_phrase][t:t+1,:] , [[0.]*len(stim_sent_train[0][0])] ) , axis=1 ) ) states_out_test, internal_states_test = res.test(input_test) import copy states_out_test_def=copy.deepcopy(states_out_test) else: for n_phrase in range(len(stim_mean_test)): #feedback assignation feedback=np.array(states_out_test[n_phrase]) input_test.append(np.concatenate( (stim_mean_test[n_phrase][t:t+1,:] , feedback ) , axis=1 ) ) states_out_test, internal_states_test = res.test(input_test) for n_phrase in range(len(stim_mean_test)): states_out_test_def[ n_phrase ]=np.concatenate( (states_out_test_def[n_phrase] , states_out_test[n_phrase]), axis=0 ) states_out_test=states_out_test_def # Ecriture de la phrase de réponse if other_corpus_used: var_inutile=0 else: l_recovered_construction_train = convert_l_output_activity_in_construction(l_out_act=states_out_train, construction_words=construction_words, min_nr_of_val_upper_thres=1) l_recovered_sentences_train = attribute_ocw_to_constructions(l_constructions=l_recovered_construction_train, l_ocw_array=l_ocw_array_train, _OCW='X') l_recovered_construction_test = convert_l_output_activity_in_construction(l_out_act=states_out_test, construction_words=construction_words, min_nr_of_val_upper_thres=2) l_recovered_sentences_test = attribute_ocw_to_constructions(l_constructions=l_recovered_construction_test, l_ocw_array=l_ocw_array_test, _OCW='X') ## Writting sentences to output file #print " *** Writting to output file ... *** " l_final_sent_test = [] for list_words in l_recovered_sentences_test: l_final_sent_test.append(" ".join(list_words)) #print " *** ... Writting done ***" #print "**********************************************" print "********************************************** " print " *** RECOGNIZED SENTENCES *** " print l_final_sent_test[0] write_list_in_file(l=l_final_sent_test, file_path=path_file_out) if return_result: return l_final_sent_test ## Plot inputs if plot: import plotting as plotting plotting.plot_array_in_file(root_file_name="../Results/states_out_train", array_=states_out_train, titles_subset=l_construction_train, legend_=construction_words, plot_slice=None, title="", subtitle="") plotting.plot_array_in_file(root_file_name="../Results/states_out_test", array_=states_out_test, titles_subset=l_recovered_sentences_test, legend_=construction_words, plot_slice=None, title="", subtitle="") print ""
def main(path_file_in, path_file_out, plot=False, fast=False, keep_internal_states=False, verbose=False): import os #sys.path.append(os.path.dirname(os.path.abspath(__file__))+"/..") #print "path ", os.path.dirname(os.path.abspath(__file__))+"/.." current_directory = os.path.dirname(os.path.abspath(__file__)) parent_directory = os.path.dirname(current_directory) sys.path.append(parent_directory) import io_language_coding as CtIolangcod # Definning parameters of stimulus (in a dictionary) d = {} d['act_time'] = 5#2#1#5#10#2 d['pause'] = True#False d['suppl_pause_at_the_end'] = 1*d['act_time'] d['initial_pause'] = False#True#False#False d['offset'] = True#False#True # Parameters for reservoir N = 500#500#500#1000 #100 sr = 1#3#3#2#1 iss = 0.25#0.01#1 leak = 0.25/float(d['act_time'])#0.75/float(d['act_time'])#0.75/2.#0.5#0.05 ## Random parameters seed = 5 if seed is not None: mdp.numx.random.seed(seed) np.random.seed(seed) [train_data_txt, test_data_txt, sent_form_info_test] = common.extract_data_io(path_file=path_file_in) train_corpus, train_meaning = common.txt2corpus_and_meaning(train_txt=train_data_txt) test_corpus = test_data_txt # making the list of constructions (refering to "construction grammar"), a construction is a sentence without its open class words (Nouns and Verbs) (l_construction_train, l_ocw_array_train, construction_words) = common.get_and_remove_ocw_in_corpus(corpus=train_corpus, _OCW='X', l_closed_class=get_closed_class_words()) (l_construction_test, l_ocw_array_test, construction_words_test) = common.get_and_remove_ocw_in_corpus(corpus=test_corpus, _OCW='X', l_closed_class=get_closed_class_words()) if construction_words!=construction_words_test: raise Exception, "The construction words are not the same for the train constructions and the test constructions. So the coding of sentences will be different and should provoque a future problem." ################################################# ## Generating all the sentence stimulus (in order to have the same length for each sentence) l_full_const = l_construction_train + l_construction_test slice_test = slice(len(l_construction_train),len(l_construction_train)+len(l_construction_test)) slice_train = slice(0,len(l_construction_train)) (stim_full_data, l_full_offset) = CtIolangcod.generate_stim_input_nodic(l_data=l_full_const, # act_time=d['act_time'], subset=None, l_input=None, act_time=d['act_time'], subset=None, l_input=construction_words, l_nr_word=None, mult=None, full_time=None, with_offset=d['offset'], pause=d['pause'], initial_pause=d['initial_pause'], suppl_pause_at_the_end=d['suppl_pause_at_the_end'], verbose=False) stim_sent_train = stim_full_data[slice_train] stim_sent_test = stim_full_data[slice_test] ################################################# ## Generating all the meaning stimulus ################################################# l_m_elt = common.get_meaning_coding(max_nr_ocw=max_nr_ocw, max_nr_actionrelation=max_nr_actionrelation, elt_pred=elt_pred) (stim_mean_train, l_meaning_code_train) = common.generate_meaning_stim(l_data=train_meaning, l_ocw_array=l_ocw_array_train, full_time=stim_sent_train[0].shape[0], l_m_elt=l_m_elt, l_offset=l_full_offset[slice_train], verbose=False, initial_pause=d['initial_pause'], pause=d['pause'], act_time=d['act_time']) ## Defining reservoir, readout and flow reservoir = Oger.nodes.LeakyReservoirNode(output_dim = N, spectral_radius = sr, input_scaling =iss, nonlin_func = np.tanh, leak_rate = leak) read_out = mdp.nodes.LinearRegressionNode(use_pinv=True, with_bias=True) flow = mdp.Flow([reservoir, read_out]) if keep_internal_states: Oger.utils.make_inspectable(mdp.Flow) ## Trainning and testing print "Train and test" if not fast: (states_out_train, internal_states_train, internal_outputs_train, neuron_states_train) = \ common._teach_and_test_flow(inputs_train_set=stim_sent_train, teacher_outputs_train_set=stim_mean_train, inputs_test_set=stim_sent_train, _flow=flow, _reservoir=reservoir, keep_internal_states=keep_internal_states) else: raise Exception, "have to define what to do for fast mode" ## test set not train set (states_out_test, internal_states_test, internal_outputs_test, neuron_states_test) = \ common._test_flow(inputs_test_set=stim_sent_test, _flow=flow, _reservoir=reservoir, keep_internal_states=keep_internal_states) if verbose: for i in range(len(stim_mean_train)): print "len(stim_mean_train)", len(stim_mean_train) print "len(l_meaning_code_train)", len(l_meaning_code_train) print l_meaning_code_train[i] print (stim_mean_train[0]==stim_mean_train[i]) print (l_meaning_code_train[0]==l_meaning_code_train[i]) ## Writting output meaning l_recovered_meaning_test = convert_l_output_activity_in_meaning(l_out_act=states_out_test, l_ocw_array=l_ocw_array_test, l_m_elt=l_m_elt) if verbose: print "l_recovered_meaning_test", l_recovered_meaning_test l_final_mean_test = [] for meanings in l_recovered_meaning_test: current_meanings = "" if verbose: print "meanings", meanings for i_m in range(len(meanings)): # if verbose: # print " i_m:",i_m # print " meanings[i_m]:",meanings[i_m] if i_m>0: current_meanings+=',' current_meanings+=" ".join(meanings[i_m]) l_final_mean_test.append(current_meanings) print "" print "**********************************************" print " *** RECOGNIZED MEANINGS *** " for elt in l_final_mean_test: print str(elt) print "**********************************************" ## Writting sentences to output file print " *** Writting to output file ... *** " #ecrire une seule ligne simple dans un fichier la phrase attendue en mode test common.write_list_in_file(l=l_final_mean_test, file_path=path_file_out) print " *** ... Writting done ***" print "**********************************************" ## Plot if plot: print " *** Plotting to output file ... *** " # import oct2011.plotting as plotting import plotting as plotting plotting.plot_array_in_file(root_file_name="../RES_TEMP/states_out_train", array_=states_out_train, titles_subset=l_meaning_code_train, # legend_=l_m_elt, plot_slice=None, title="", subtitle="") legend_=None, plot_slice=None, title="", subtitle="") plotting.plot_array_in_file(root_file_name="../RES_TEMP/states_out_train_sent", array_=states_out_train, titles_subset=train_meaning, # legend_=l_m_elt, plot_slice=None, title="", subtitle="") legend_=None, plot_slice=None, title="", subtitle="") plotting.plot_array_in_file(root_file_name="../RES_TEMP/states_out_test", array_=states_out_test, titles_subset=l_final_mean_test, # legend_=l_m_elt, plot_slice=None, title="", subtitle="") legend_=None, plot_slice=None, title="", subtitle="") plotting.plot_array_in_file(root_file_name="../RES_TEMP/intern_states_test", array_=internal_states_test, titles_subset=None, plot_slice=None, title="", subtitle="") print " *** ... Plotting to output file done *** " print "**********************************************" return l_final_mean_test
def test(self, test_corpus, sent_form_info_test, shelf, plot=False, feedback=False): l_ocw_array_test = self.generate_l_ocw_array(sent_form_info_test, test_corpus) (stim_mean_test, l_meaning_code_test) = self.generate_meaning_stim( l_structure=sent_form_info_test, full_time=shelf["stim_sent_train"][0].shape[0], l_m_elt=shelf["l_m_elt"]) #classic working of the reservoir if feedback == False: ## test set not train set states_out_test, internal_states_test = shelf["res"].test( stim_mean_test) #feedback working of the reservoir. !! Should be implemented directly in the reservoir class !! else: delay = 1 nb_epoch_max = 4 dim_input = shelf["stim_sent_train"][0].shape[1] #dim_output = len(stim_sent_train[0][0]) input_train = [] for (x, y) in zip(np.copy(shelf["stim_sent_train"]), np.copy(shelf["stim_sent_train"])): for time_step_delay in range(delay): y = np.concatenate(([[0.] * len(y[0])], y), axis=0) input_train.append( np.array(np.concatenate((x, y[:-delay]), axis=1))) nb_train = 0 while nb_train < nb_epoch_max: ## test set = train set states_out_train, internal_states_train = shelf["res"].train( input_train, shelf["stim_sent_train"]) tab_feedback = [] for num_phrase in range(len(states_out_train)): #signal tresholded states_out_train[num_phrase] = np.array([ self.treshold_signal(signal_t, 1.5, -0.5) for signal_t in states_out_train[num_phrase] ]) if nb_train == 0: #feedback kept only for the first train #feedback assignation feedback = np.array(states_out_train[num_phrase]) #signal delayed for time_step_delay in range(delay): feedback = np.concatenate( ([[0.] * len(feedback[0])], feedback), axis=0) tab_feedback.append(feedback) input_train[num_phrase] = input_train[num_phrase].T input_train[num_phrase][dim_input:] = feedback[:-delay].T input_train[num_phrase] = input_train[num_phrase].T nb_train += 1 ## test set not train set for t in range(0, stim_mean_test[0].shape[0], 1): input_test = [] if t == 0: #A REMODIFIER for n_phrase in range(len(stim_mean_test)): input_test.append( np.concatenate( (stim_mean_test[n_phrase][t:t + 1, :], [[0.] * len(shelf["stim_sent_train"][0][0])]), axis=1)) states_out_test, internal_states_test = shelf["res"].test( input_test) import copy states_out_test_def = copy.deepcopy(states_out_test) else: for n_phrase in range(len(stim_mean_test)): #feedback assignation feedback = np.array(states_out_test[n_phrase]) input_test.append( np.concatenate( (stim_mean_test[n_phrase][t:t + 1, :], feedback), axis=1)) states_out_test, internal_states_test = shelf["res"].test( input_test) for n_phrase in range(len(stim_mean_test)): states_out_test_def[n_phrase] = np.concatenate( (states_out_test_def[n_phrase], states_out_test[n_phrase]), axis=0) states_out_test = states_out_test_def # l_recovered_construction_train = self.convert_l_output_activity_in_construction(l_out_act=states_out_train, # construction_words=construction_words, # min_nr_of_val_upper_thres=1) # l_recovered_sentences_train = self.attribute_ocw_to_constructions(l_constructions=l_recovered_construction_train, # l_ocw_array=l_ocw_array_train, _OCW='X') l_recovered_construction_test = self.convert_l_output_activity_in_construction( l_out_act=states_out_test, construction_words=shelf["construction_words"], min_nr_of_val_upper_thres=2) l_recovered_sentences_test = self.attribute_ocw_to_constructions( l_constructions=l_recovered_construction_test, l_ocw_array=l_ocw_array_test, _OCW='X') ## Plot inputs if plot: import plotting as plotting plotting.plot_array_in_file( root_file_name="../Results/states_out_train", array_=shelf["states_out_train"], titles_subset=shelf["l_construction_train"], legend_=shelf["construction_words"], plot_slice=None, title="", subtitle="") plotting.plot_array_in_file( root_file_name="../Results/states_out_test", array_=states_out_test, titles_subset=l_recovered_sentences_test, legend_=shelf["construction_words"], plot_slice=None, title="", subtitle="") return l_recovered_sentences_test
def test(self, test_corpus, sent_form_info_test, shelf, plot=False, feedback=False ): l_ocw_array_test = self.generate_l_ocw_array(sent_form_info_test, test_corpus) (stim_mean_test, l_meaning_code_test) = self.generate_meaning_stim(l_structure=sent_form_info_test, full_time=shelf["stim_sent_train"][0].shape[0], l_m_elt=shelf["l_m_elt"]) #classic working of the reservoir if feedback==False: ## test set not train set states_out_test, internal_states_test = shelf["res"].test(stim_mean_test) #feedback working of the reservoir. !! Should be implemented directly in the reservoir class !! else: delay=1 nb_epoch_max=4 dim_input = shelf["stim_sent_train"][0].shape[1] #dim_output = len(stim_sent_train[0][0]) input_train=[] for (x,y) in zip( np.copy(shelf["stim_sent_train"]), np.copy(shelf["stim_sent_train"])): for time_step_delay in range(delay): y=np.concatenate( ([[0.]*len(y[0])] , y), axis=0) input_train.append(np.array( np.concatenate( (x, y[:-delay]), axis=1 ) )) nb_train=0 while nb_train < nb_epoch_max: ## test set = train set states_out_train, internal_states_train = shelf["res"].train (input_train, shelf["stim_sent_train"]) tab_feedback=[] for num_phrase in range(len(states_out_train)): #signal tresholded states_out_train[num_phrase]=np.array([self.treshold_signal(signal_t,1.5,-0.5) for signal_t in states_out_train[num_phrase]]) if nb_train==0: #feedback kept only for the first train #feedback assignation feedback=np.array(states_out_train[num_phrase]) #signal delayed for time_step_delay in range(delay): feedback=np.concatenate( ([[0.]*len(feedback[0])] , feedback), axis=0) tab_feedback.append(feedback) input_train[num_phrase]=input_train[num_phrase].T input_train[num_phrase][dim_input:] = feedback[:-delay].T input_train[num_phrase]=input_train[num_phrase].T nb_train+=1 ## test set not train set for t in range(0,stim_mean_test[0].shape[0],1): input_test=[] if t==0: #A REMODIFIER for n_phrase in range(len(stim_mean_test)): input_test.append(np.concatenate( (stim_mean_test[n_phrase][t:t+1,:] , [[0.]*len(shelf["stim_sent_train"][0][0])] ) , axis=1 ) ) states_out_test, internal_states_test = shelf["res"].test(input_test) import copy states_out_test_def=copy.deepcopy(states_out_test) else: for n_phrase in range(len(stim_mean_test)): #feedback assignation feedback=np.array(states_out_test[n_phrase]) input_test.append(np.concatenate( (stim_mean_test[n_phrase][t:t+1,:] , feedback ) , axis=1 ) ) states_out_test, internal_states_test = shelf["res"].test(input_test) for n_phrase in range(len(stim_mean_test)): states_out_test_def[ n_phrase ]=np.concatenate( (states_out_test_def[n_phrase] , states_out_test[n_phrase]), axis=0 ) states_out_test=states_out_test_def # l_recovered_construction_train = self.convert_l_output_activity_in_construction(l_out_act=states_out_train, # construction_words=construction_words, # min_nr_of_val_upper_thres=1) # l_recovered_sentences_train = self.attribute_ocw_to_constructions(l_constructions=l_recovered_construction_train, # l_ocw_array=l_ocw_array_train, _OCW='X') l_recovered_construction_test = self.convert_l_output_activity_in_construction(l_out_act=states_out_test, construction_words=shelf["construction_words"], min_nr_of_val_upper_thres=2) l_recovered_sentences_test = self.attribute_ocw_to_constructions(l_constructions=l_recovered_construction_test, l_ocw_array=l_ocw_array_test, _OCW='X') ## Plot inputs if plot: import plotting as plotting plotting.plot_array_in_file(root_file_name="../Results/states_out_train", array_=shelf["states_out_train"], titles_subset=shelf["l_construction_train"], legend_=shelf["construction_words"], plot_slice=None, title="", subtitle="") plotting.plot_array_in_file(root_file_name="../Results/states_out_test", array_=states_out_test, titles_subset=l_recovered_sentences_test, legend_=shelf["construction_words"], plot_slice=None, title="", subtitle="") return l_recovered_sentences_test