required=True,
help="number of action predicates in each rule")
cl_args = parser.parse_args()
background_fname_train = cl_args.background_train
facts_fname_train = cl_args.facts_train
pos_fname_train = cl_args.pos_train
neg_fname_train = cl_args.neg_train
background_fname_test = cl_args.background_test
facts_fname_test = cl_args.facts_test
pos_fname_test = cl_args.pos_test
neg_fname_test = cl_args.neg_test
rulelen = int(cl_args.rule_length)
numrules = int(cl_args.num_rules)
dfs_train = load_metadata(background_fname_train)
load_data(facts_fname_train, dfs_train)
load_labels(pos_fname_train, dfs_train, 1.0)
load_labels(neg_fname_train, dfs_train, 0.0)
tails_relation_train = None
labels_df_train = None
action_attr = None
sentence_attr = None
action_relations_train = []
action_rel_names_train = []
for name, df in dfs_train.items():
colnames = df.columns.values.tolist()
if "Label" in colnames:
labels_df_train = df
sentence_attr = colnames[0]
help="the target predicate")
parser.add_argument("-m",
"--model",
required=True,
help="file to read the model from")
cl_args = parser.parse_args()
background_fname = cl_args.background
facts_fname_test = cl_args.facts_test
target = cl_args.target
fin = cl_args.model
(attr_name, labels_df_train, disj,
rel_names_train) = dill.load(open(fin, 'rb'))
dfs_test = load_metadata(background_fname)
load_data(facts_fname_test, dfs_test)
labels_df_test = dfs_test[target]
labels_df_test.columns = [attr_name + "0", attr_name + "3"]
true_links = pd.concat([labels_df_train, labels_df_test])
true_links = true_links.loc[true_links['Relation'] == target]
true_links.drop(['Relation'], axis=1, inplace=True)
cols = true_links.columns.tolist()
inv_true_links = true_links[[cols[1], cols[0]]].copy()
inv_true_links.columns = [cols[0], cols[1]]
mask = [1] * len(rel_names_train)
pos = rel_names_train.index(target)
help="file containing schema information")
parser.add_argument("-ftr",
"--facts_train",
required=True,
help="file containing facts for training")
parser.add_argument("-m",
"--model",
required=True,
help="file to write the model in")
cl_args = parser.parse_args()
background_fname = cl_args.background
facts_fname_train = cl_args.facts_train
fout = cl_args.model
dfs_train = load_metadata(background_fname)
load_data(facts_fname_train, dfs_train)
attr_name = None
relations_train = []
rel_names_train = []
choices = []
for name, df in dfs_train.items():
colnames = df.columns.values.tolist()
attr_name = colnames[0]
df.columns = [attr_name + "0", attr_name + "1"]
choices.append(name)
rel_names_train.append(name)
relations_train.append(df)