def dump_dep_rstdt(corpus_dir, out_dir, nary_enc): """Convert and dump the RST-DT corpus as dependency trees.""" # convert and dump RST trees from train dir_train = os.path.join(corpus_dir, TRAIN_FOLDER) if not os.path.isdir(dir_train): raise ValueError('No such folder: {}'.format(dir_train)) reader_train = Reader(dir_train) trees_train = reader_train.slurp() dtrees_train = {doc_name: RstDepTree.from_rst_tree(rst_tree, nary_enc=nary_enc) for doc_name, rst_tree in trees_train.items()} dump_disdep_files(dtrees_train.values(), os.path.join(out_dir, os.path.basename(dir_train))) # convert and dump RST trees from test dir_test = os.path.join(corpus_dir, TEST_FOLDER) if not os.path.isdir(dir_test): raise ValueError('No such folder: {}'.format(dir_test)) reader_test = Reader(dir_test) trees_test = reader_test.slurp() dtrees_test = {doc_name: RstDepTree.from_rst_tree(rst_tree, nary_enc=nary_enc) for doc_name, rst_tree in trees_test.items()} dump_disdep_files(dtrees_test.values(), os.path.join(out_dir, os.path.basename(dir_test)))
def read_deps(corpus, section='all', nary_enc='chain', rew_pseudo_rels=False, mrg_same_units=False): """Collect dependencies from the corpus. Parameters ---------- corpus : dict from str to dict from FileId to RSTTree Corpus of RST c-trees indexed by {'train', 'test'} then FileId. section : str, one of {'train', 'test', 'all'} Section of interest in the RST-DT. nary_enc : str, one of {'tree', 'chain'} Encoding of n-ary relations used in the c-to-d conversion. rew_pseudo_rels : boolean, defaults to False If True, rewrite pseudo relations ; see `educe.rst_dt.pseudo_relations`. mrg_same_units : boolean, defaults to False If True, merge fragmented EDUs ; see `educe.rst_dt.pseudo_relations`. Returns ------- edu_df : pandas.DataFrame Table of EDUs read from the corpus. dep_df : pandas.DataFrame Table of dependencies read from the corpus. """ # experimental: rewrite pseudo-relations if rew_pseudo_rels: for sec_name, sec_corpus in corpus.items(): corpus[sec_name] = { doc_id: rewrite_pseudo_rels(doc_id, rst_ctree) for doc_id, rst_ctree in sec_corpus.items() } if mrg_same_units: for sec_name, sec_corpus in corpus.items(): corpus[sec_name] = { doc_id: merge_same_units(doc_id, rst_ctree) for doc_id, rst_ctree in sec_corpus.items() } # convert to d-trees, collect dependencies edus = [] deps = [] for sec_name, sec_corpus in corpus.items(): for doc_id, rst_ctree in sorted(sec_corpus.items()): doc_name = doc_id.doc doc_text = rst_ctree.text() # DIRTY infer (approximate) sentence and paragraph indices # from newlines in the text (\n and \n\n) sent_idx = 0 para_idx = 0 # end DIRTY rst_dtree = RstDepTree.from_rst_tree(rst_ctree, nary_enc='chain') for dep_idx, (edu, hd_idx, lbl, nuc, hd_order) in enumerate( zip(rst_dtree.edus[1:], rst_dtree.heads[1:], rst_dtree.labels[1:], rst_dtree.nucs[1:], rst_dtree.ranks[1:]), start=1): char_beg = edu.span.char_start char_end = edu.span.char_end edus.append((sec_name, doc_name, dep_idx, char_beg, char_end, sent_idx, para_idx)) deps.append((doc_name, dep_idx, hd_idx, lbl, nuc, hd_order)) # DIRTY search for paragraph or sentence breaks in the # text of the EDU *plus the next three characters* (yerk) edu_txt_plus = doc_text[char_beg:char_end + 3] if '\n\n' in edu_txt_plus: para_idx += 1 sent_idx += 1 # sometimes wrong ; to be fixed elif '\n' in edu_txt_plus: sent_idx += 1 # end DIRTY # turn into DataFrame edu_df = pd.DataFrame(edus, columns=[ 'section', 'doc_name', 'dep_idx', 'char_beg', 'char_end', 'sent_idx', 'para_idx' ]) dep_df = pd.DataFrame( deps, columns=['doc_name', 'dep_idx', 'hd_idx', 'rel', 'nuc', 'hd_order']) # additional columns # * attachment length in EDUs dep_df['len_edu'] = dep_df['dep_idx'] - dep_df['hd_idx'] dep_df['len_edu_abs'] = abs(dep_df['len_edu']) # * attachment length, in sentences and paragraphs if False: # TODO rewrite in a pandas-ic manner ; my previous attempts have # failed but I think I got pretty close # NB: the current implementation is *extremely* slow: 155 seconds # on my laptop for the RST-DT, just for this (minor) computation len_sent = [] len_para = [] for _, row in dep_df[['doc_name', 'dep_idx', 'hd_idx']].iterrows(): edu_dep = edu_df[(edu_df['doc_name'] == row['doc_name']) & (edu_df['dep_idx'] == row['dep_idx'])] if row['hd_idx'] == 0: # {sent,para}_idx + 1 for dependents of the fake root lsent = edu_dep['sent_idx'].values[0] + 1 lpara = edu_dep['para_idx'].values[0] + 1 else: edu_hd = edu_df[(edu_df['doc_name'] == row['doc_name']) & (edu_df['dep_idx'] == row['hd_idx'])] lsent = (edu_dep['sent_idx'].values[0] - edu_hd['sent_idx'].values[0]) lpara = (edu_dep['para_idx'].values[0] - edu_hd['para_idx'].values[0]) len_sent.append(lsent) len_para.append(lpara) dep_df['len_sent'] = pd.Series(len_sent) dep_df['len_sent_abs'] = abs(dep_df['len_sent']) dep_df['len_para'] = pd.Series(len_para) dep_df['len_para_abs'] = abs(dep_df['len_para']) # * class of relation (FIXME we need to handle interaction with # rewrite_pseudo_rels) rel_conv = RstRelationConverter(RELMAP_112_18_FILE).convert_label dep_df['rel_class'] = dep_df['rel'].apply(rel_conv) # * boolean indicator for pseudo-relations ; NB: the 'Style-' prefix # can only apply if rew_pseudo_rels (otherwise no occurrence) dep_df['pseudo_rel'] = ( (dep_df['rel'].str.startswith('Style')) | (dep_df['rel'].str.endswith('Same-Unit')) | (dep_df['rel'].str.endswith('TextualOrganization'))) return edu_df, dep_df
doc_name + '.out.xml') core_reader = PreprocessingSource() core_reader.read(core_fname, suffix='') corenlp_doc = read_corenlp_result(None, core_reader) core_toks = corenlp_doc.tokens core_toks_beg = [x.span.char_start for x in core_toks] core_toks_end = [x.span.char_end for x in core_toks] # PTB stuff # * create DocumentPlus (adapted from educe.rst_dt.corpus) rst_context = rst_tree.label().context ptb_docp = DocumentPlus(key, doc_name, rst_context) # * attach EDUs (yerk) # FIXME we currently get them via an RstDepTree created from # the original RSTTree, so as to get the left padding EDU rst_dtree = RstDepTree.from_rst_tree(rst_tree) ptb_docp.edus = rst_dtree.edus # * setup a PtbParser (re-yerk) ptb_parser = PtbParser(PTB_DIR) ptb_parser.tokenize(ptb_docp) # get PTB toks ; skip left padding token ptb_toks = ptb_docp.tkd_tokens[1:] ptb_toks_beg = ptb_docp.toks_beg[1:] ptb_toks_end = ptb_docp.toks_end[1:] # compare ! core2ptb_beg = np.searchsorted(ptb_toks_beg, core_toks_beg, side='left') core2ptb_end = np.searchsorted(ptb_toks_end, core_toks_end, side='right') - 1 # TODO maybe use np.diff?
doc_name + '.out.xml') core_reader = PreprocessingSource() core_reader.read(core_fname, suffix='') corenlp_doc = read_corenlp_result(None, core_reader) core_toks = corenlp_doc.tokens core_toks_beg = [x.span.char_start for x in core_toks] core_toks_end = [x.span.char_end for x in core_toks] # PTB stuff # * create DocumentPlus (adapted from educe.rst_dt.corpus) rst_context = rst_tree.label().context ptb_docp = DocumentPlus(key, doc_name, rst_context) # * attach EDUs (yerk) # FIXME we currently get them via an RstDepTree created from # the original RSTTree, so as to get the left padding EDU rst_dtree = RstDepTree.from_rst_tree(rst_tree) ptb_docp.edus = rst_dtree.edus # * setup a PtbParser (re-yerk) ptb_parser = PtbParser(PTB_DIR) ptb_parser.tokenize(ptb_docp) # get PTB toks ; skip left padding token ptb_toks = ptb_docp.tkd_tokens[1:] ptb_toks_beg = ptb_docp.toks_beg[1:] ptb_toks_end = ptb_docp.toks_end[1:] # compare ! core2ptb_beg = np.searchsorted(ptb_toks_beg, core_toks_beg, side='left') core2ptb_end = np.searchsorted( ptb_toks_end, core_toks_end, side='right') - 1
def read_deps(corpus, section='all', nary_enc='chain', rew_pseudo_rels=False, mrg_same_units=False): """Collect dependencies from the corpus. Parameters ---------- corpus : dict from str to dict from FileId to RSTTree Corpus of RST c-trees indexed by {'train', 'test'} then FileId. section : str, one of {'train', 'test', 'all'} Section of interest in the RST-DT. nary_enc : str, one of {'tree', 'chain'} Encoding of n-ary relations used in the c-to-d conversion. rew_pseudo_rels : boolean, defaults to False If True, rewrite pseudo relations ; see `educe.rst_dt.pseudo_relations`. mrg_same_units : boolean, defaults to False If True, merge fragmented EDUs ; see `educe.rst_dt.pseudo_relations`. Returns ------- edu_df : pandas.DataFrame Table of EDUs read from the corpus. dep_df : pandas.DataFrame Table of dependencies read from the corpus. """ # experimental: rewrite pseudo-relations if rew_pseudo_rels: for sec_name, sec_corpus in corpus.items(): corpus[sec_name] = { doc_id: rewrite_pseudo_rels(doc_id, rst_ctree) for doc_id, rst_ctree in sec_corpus.items() } if mrg_same_units: for sec_name, sec_corpus in corpus.items(): corpus[sec_name] = { doc_id: merge_same_units(doc_id, rst_ctree) for doc_id, rst_ctree in sec_corpus.items() } # convert to d-trees, collect dependencies edus = [] deps = [] for sec_name, sec_corpus in corpus.items(): for doc_id, rst_ctree in sorted(sec_corpus.items()): doc_name = doc_id.doc doc_text = rst_ctree.text() # DIRTY infer (approximate) sentence and paragraph indices # from newlines in the text (\n and \n\n) sent_idx = 0 para_idx = 0 # end DIRTY rst_dtree = RstDepTree.from_rst_tree(rst_ctree, nary_enc='chain') for dep_idx, (edu, hd_idx, lbl, nuc, hd_order) in enumerate( zip(rst_dtree.edus[1:], rst_dtree.heads[1:], rst_dtree.labels[1:], rst_dtree.nucs[1:], rst_dtree.ranks[1:]), start=1): char_beg = edu.span.char_start char_end = edu.span.char_end edus.append( (sec_name, doc_name, dep_idx, char_beg, char_end, sent_idx, para_idx) ) deps.append( (doc_name, dep_idx, hd_idx, lbl, nuc, hd_order) ) # DIRTY search for paragraph or sentence breaks in the # text of the EDU *plus the next three characters* (yerk) edu_txt_plus = doc_text[char_beg:char_end + 3] if '\n\n' in edu_txt_plus: para_idx += 1 sent_idx += 1 # sometimes wrong ; to be fixed elif '\n' in edu_txt_plus: sent_idx += 1 # end DIRTY # turn into DataFrame edu_df = pd.DataFrame(edus, columns=[ 'section', 'doc_name', 'dep_idx', 'char_beg', 'char_end', 'sent_idx', 'para_idx'] ) dep_df = pd.DataFrame(deps, columns=[ 'doc_name', 'dep_idx', 'hd_idx', 'rel', 'nuc', 'hd_order'] ) # additional columns # * attachment length in EDUs dep_df['len_edu'] = dep_df['dep_idx'] - dep_df['hd_idx'] dep_df['len_edu_abs'] = abs(dep_df['len_edu']) # * attachment length, in sentences and paragraphs if False: # TODO rewrite in a pandas-ic manner ; my previous attempts have # failed but I think I got pretty close # NB: the current implementation is *extremely* slow: 155 seconds # on my laptop for the RST-DT, just for this (minor) computation len_sent = [] len_para = [] for _, row in dep_df[['doc_name', 'dep_idx', 'hd_idx']].iterrows(): edu_dep = edu_df[ (edu_df['doc_name'] == row['doc_name']) & (edu_df['dep_idx'] == row['dep_idx']) ] if row['hd_idx'] == 0: # {sent,para}_idx + 1 for dependents of the fake root lsent = edu_dep['sent_idx'].values[0] + 1 lpara = edu_dep['para_idx'].values[0] + 1 else: edu_hd = edu_df[ (edu_df['doc_name'] == row['doc_name']) & (edu_df['dep_idx'] == row['hd_idx']) ] lsent = (edu_dep['sent_idx'].values[0] - edu_hd['sent_idx'].values[0]) lpara = (edu_dep['para_idx'].values[0] - edu_hd['para_idx'].values[0]) len_sent.append(lsent) len_para.append(lpara) dep_df['len_sent'] = pd.Series(len_sent) dep_df['len_sent_abs'] = abs(dep_df['len_sent']) dep_df['len_para'] = pd.Series(len_para) dep_df['len_para_abs'] = abs(dep_df['len_para']) # * class of relation (FIXME we need to handle interaction with # rewrite_pseudo_rels) rel_conv = RstRelationConverter(RELMAP_112_18_FILE).convert_label dep_df['rel_class'] = dep_df['rel'].apply(rel_conv) # * boolean indicator for pseudo-relations ; NB: the 'Style-' prefix # can only apply if rew_pseudo_rels (otherwise no occurrence) dep_df['pseudo_rel'] = ( (dep_df['rel'].str.startswith('Style')) | (dep_df['rel'].str.endswith('Same-Unit')) | (dep_df['rel'].str.endswith('TextualOrganization')) ) return edu_df, dep_df