def display(self, states_out_train, states_out_test, l_meaning_code_train, train_meaning, l_final_mean_test, internal_states_test): print " *** Plotting to output file ... *** " import oct2011.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 "**********************************************"
def display(self, states_out_train, states_out_test, l_meaning_code_train, train_meaning, l_final_mean_test, internal_states_test): print " *** Plotting to output file ... *** " import oct2011.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 "**********************************************"
def main(path_file_in, path_file_out, sentence_to_meaning=True, plot=False, fast=False, keep_internal_states=False, verbose=False): import sys,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) print "sys.path.append(parent_directory)", parent_directory import Common_Tools.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, sentence_to_meaning=sentence_to_meaning) # print "**************************" # print "train data_txt", train_data_txt # print "test data_txt", test_data_txt # print "sent_form_info_test", sent_form_info_test train_corpus, train_meaning = common.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, 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()) # print "**************************" # print "l_construction_train", l_construction_train # print "l_ocw_array_train", l_ocw_array_train if sentence_to_meaning: (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()) # 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." else: # check if a special form of sentence is requested (canonical or non-canonical form) # i.e. check if there is at least one element that is not None print "" print "*** Managing sentence form ... ***" print "sent_form_info_test:", sent_form_info_test # if all sentence information is None (not attributed) if all(elt is None for elt in sent_form_info_test): # generate default form of sentence l_ocw_array_test = generate_l_ocw_array_in_canonical_order(l_meaning=test_meaning) # if at least one element is not None else: # call specific method to deal with the specified order of each meanings in the list l_ocw_array_test = generate_l_ocw_array_in_specified_order(l_meaning=test_meaning, l_sent_form = sent_form_info_test) print "*** ... sentence form managed ***" # print "l_ocw_array_test", l_ocw_array_test ################################################# ## 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_train = slice(0,len(l_construction_train)) slice_test = slice(len(l_construction_train),len(l_construction_train)+len(l_construction_test)) # print "slice_train", slice_train print "slice_test", slice_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] ################################################# ## Generating all the meaning stimulus ################################################# # l_m_elt = common.get_meaning_coding() # elt_pred=['P','F','O','R'] l_m_elt = common.get_meaning_coding(max_nr_ocw=8, max_nr_actionrelation=2, elt_pred=elt_pred) # print "" # print "*** Generating meaning for train set ... ***" # (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, verbose=False) (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']) # print "*** ... meaning generated for train set ***" # print "l_m_elt", l_m_elt # print "stim_mean_train[0].shape", stim_mean_train[0].shape # print "l_meaning_code_train", l_meaning_code_train # print "" if not sentence_to_meaning: print "*** Generating meaning for test set ... ***" (stim_mean_test, l_meaning_code_test) = common.generate_meaning_stim(l_data=test_meaning, l_ocw_array=l_ocw_array_test, full_time=stim_sent_train[0].shape[0], l_m_elt=l_m_elt, verbose=False) print "*** ... meaning generated for test set ***" print "" ## 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: ## test set = train set if sentence_to_meaning: (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: (states_out_train, internal_states_train, internal_outputs_train, neuron_states_train) = \ common._teach_and_test_flow(inputs_train_set=stim_mean_train, teacher_outputs_train_set=stim_sent_train, inputs_test_set=stim_mean_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 if sentence_to_meaning: (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) else: (states_out_test, internal_states_test, internal_outputs_test, neuron_states_test) = \ common._test_flow(inputs_test_set=stim_mean_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 if sentence_to_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 output sentence if not sentence_to_meaning: if not fast and (verbose or plot): print "" print "**********************************************" print "*** Processing recovery of train sentences ..." 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') print "*** l_recovered_sentences_train: ***" for s in l_recovered_sentences_train: print s print "**********************************************" if verbose: print "" print "**********************************************" print "*** Processing recovery of test sentences ..." 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') if verbose: print "*** l_recovered_sentences_test: ***" for s in l_recovered_sentences_test: print s 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 if sentence_to_meaning: 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="") else: plotting.plot_array_in_file(root_file_name="../../RES_TEMP/states_out_train_recov", array_=states_out_train, titles_subset=l_recovered_sentences_train, legend_=l_m_elt, 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_recovered_sentences_test, legend_=construction_words, plot_slice=None, title="", subtitle="") ## Plot internal states if sentence_to_meaning: 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="") else: plotting.plot_array_in_file(root_file_name="../../RES_TEMP/intern_states_test", array_=internal_states_test, titles_subset=l_ocw_array_test, 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, plot=False, keep_internal_states=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, 'wb') 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 Common_Tools.io_language_coding as CtIolangcod import sys sys.path.append("../Common_Tools") print sys.path import io_language_coding as CtIolangcod sys.path.append("../iCub_language") sentence_to_meaning = False # Definning parameters of stimulus (in a dictionary) d = {} d['act_time'] = 5#10#2 d['pause'] = True#False d['suppl_pause_at_the_end'] = 1*d['act_time'] d['initial_pause'] = True#False#False d['offset'] = False#True # Parameters for reservoir N = 500#1000 #100 sr = 2#3#3#2#1 iss = 0.01#1 leak = 0.75#0.5#0.05 ## output dic # d['start_teacher'] = 1#'end' ## Random parameters seed = 5#2#4#2 # seed 2 works with 2 sentences : both with 1 relation, 1 Canonical, 1 Non-canonical if seed is not None: mdp.numx.random.seed(seed) np.random.seed(seed) # if verbose: # print "Spectra radius of generated matrix before applying another spectral radius: "+str(Oger.utils.get_spectral_radius(w)) # if spectral_radius is not None: # w *= d['spectral_radius'] / Oger.utils.get_spectral_radius(w) # if verbose: # print "Spectra radius matrix after applying another spectral radius: "+str(Oger.utils.get_spectral_radius(w)) # if randomize_seed_afterwards: # """ redifine randomly the seed in order to not fix the seed also for other methods that are using numpy.random methods. # """ # import time # mdp.numx.random.seed(int(time.time()*10**6)) # [train_data_txt, test_data_txt] = extract_data_io(path_file=path_file_in, sentence_to_meaning=sentence_to_meaning) [train_data_txt, test_data_txt, sent_form_info_test] = extract_data_io(path_file=path_file_in, sentence_to_meaning=sentence_to_meaning) print "**************************" print "train data_txt", train_data_txt print "test data_txt", test_data_txt print "sent_form_info_test", sent_form_info_test 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, l_ocw_array_train, construction_words) = get_and_remove_ocw_in_corpus(corpus=train_corpus, _OCW='X') print "**************************" print "l_construction_train", l_construction_train print "l_ocw_array_train", l_ocw_array_train if sentence_to_meaning: (l_construction_test, l_ocw_array_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." else: # check if a special form of sentence is requested (canonical or non-canonical form) # i.e. check if there is at least one element that is not None print "" print "*** Managing sentence form ... ***" print "sent_form_info_test:", sent_form_info_test # if all sentence information is None (not attributed) if all(elt is None for elt in sent_form_info_test): # generate default form of sentence l_ocw_array_test = generate_l_ocw_array_in_canonical_order(l_meaning=test_meaning) # if at least one element is not None else: # call specific method to deal with the specified order of each meanings in the list l_ocw_array_test = generate_l_ocw_array_in_specified_order(l_meaning=test_meaning, l_sent_form = sent_form_info_test) print "*** ... sentence form managed ***" print "l_ocw_array_test", l_ocw_array_test ## 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_train = slice(0,len(l_construction_train)) slice_test = slice(len(l_construction_train),len(l_construction_train)+len(l_construction_test)) # print "slice_train", slice_train print "slice_test", slice_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] print "stim_sent_train[0].shape", stim_sent_train[0].shape print "stim_sent_train[0].shape[0]", stim_sent_train[0].shape[0] l_m_elt = get_meaning_coding() print "" print "*** Generating meaning for train set ... ***" (stim_mean_train, l_meaning_code_train) = 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, verbose=False) print "*** ... meaning generated for train set ***" print "l_m_elt", l_m_elt print "stim_mean_train[0].shape", stim_mean_train[0].shape print "l_meaning_code_train", l_meaning_code_train print "" if not sentence_to_meaning: print "*** Generating meaning for test set ... ***" (stim_mean_test, l_meaning_code_test) = generate_meaning_stim(l_data=test_meaning, l_ocw_array=l_ocw_array_test, full_time=stim_sent_train[0].shape[0], l_m_elt=l_m_elt, verbose=False) print "*** ... meaning generated for test set ***" print "" 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) print "Train and test" # (states_out_test, internal_states_test, internal_outputs_test, neuron_states_test) = \ ## test set = train set (states_out_train, internal_states_train, internal_outputs_train, neuron_states_train) = \ _teach_and_test_flow(inputs_train_set=stim_mean_train, teacher_outputs_train_set=stim_sent_train, inputs_test_set=stim_mean_train, _flow=flow, _reservoir=reservoir, keep_internal_states=keep_internal_states) ## test set not train set (states_out_test, internal_states_test, internal_outputs_test, neuron_states_test) = \ _test_flow(inputs_test_set=stim_mean_test, _flow=flow, _reservoir=reservoir, keep_internal_states=keep_internal_states) # (states_out_test, internal_states_test, internal_outputs_test, neuron_states_test) = \ # _teach_and_test_flow(inputs_train_set=stim_mean_train, teacher_outputs_train_set=stim_sent_train, inputs_test_set=stim_mean_test, _flow=flow, _reservoir=reservoir, keep_internal_states=keep_internal_states) 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]) # Ecriture de la phrase de réponse print "" print "**********************************************" print "*** Processing recovery of train sentences ..." 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') print "*** l_recovered_sentences_train: ***" for s in l_recovered_sentences_train: print s print "**********************************************" print "" print "**********************************************" print "*** Processing recovery of test sentences ..." 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') print "*** l_recovered_sentences_test: ***" for s in l_recovered_sentences_test: print s print "**********************************************" ## 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)) #ecrire une seule ligne simple dans un fichier la phrase attendue en mode test write_list_in_file(l=l_final_sent_test, file_path=path_file_out) print " *** ... Writting done ***" print "**********************************************" ## Plot inputs if plot: print " *** Plotting to output file ... *** " import oct2011.plotting as plotting # plotting.plot_array_in_file(root_file_name="../../RES_TEMP/test_sent_train", array_=stim_sent_train, plot_slice=None, title="", subtitle="") # plotting.plot_array_in_file(root_file_name="../../RES_TEMP/test_sent_test", array_=stim_sent_test, plot_slice=None, title="", subtitle="") # plotting.plot_array_in_file(root_file_name="../../RES_TEMP/test_mean_train0", array_=stim_mean_train[0].T, plot_slice=None, title="", subtitle="") # plotting.plot_array_in_file(root_file_name="../../RES_TEMP/test_mean_train1", array_=stim_mean_train[1].T, plot_slice=None, title="", subtitle="") # plotting.plot_array_in_file(root_file_name="../../RES_TEMP/test_mean_train_T", array_=stim_mean_train[0].T, plot_slice=None, title="", subtitle="") # plotting.plot_array_in_file(root_file_name="../../RES_TEMP/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="../../RES_TEMP/states_out_train_recov", array_=states_out_train, titles_subset=l_recovered_sentences_train, legend_=construction_words, plot_slice=None, title="", subtitle="") # plotting.plot_array_in_file(root_file_name="../../RES_TEMP/states_out_train_detail", array_=states_out_train[0].T, titles_subset=l_construction_train[0], 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_recovered_sentences_test, legend_=construction_words, plot_slice=None, title="", subtitle="") ## Plot internal states # plotting.plot_array_in_file(root_file_name="../../RES_TEMP/intern_states_train", array_=internal_states_train, titles_subset=l_construction_train, plot_slice=None, title="", subtitle="") plotting.plot_array_in_file(root_file_name="../../RES_TEMP/intern_states_test", array_=internal_states_test, titles_subset=l_ocw_array_test, plot_slice=None, title="", subtitle="") # plotting.plot_array_in_file(root_file_name="../../RES_TEMP/test_int_states", array_=out, plot_slice=None, title="", subtitle="") # plotting.plot_array_in_file(root_file_name="../../RES_TEMP/test_int_states_T", array_=out.T, plot_slice=None, title="", subtitle="") print " *** ... Plotting to output file done *** " 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 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