diff --git a/auto_fill_annotation.py b/auto_fill_annotation.py
index a06b2f2179e1c14e87ff2a0c64655a970464fc17..f6b0f29c4692083232f2fe9f5a32b4db4d944731 100644
--- a/auto_fill_annotation.py
+++ b/auto_fill_annotation.py
@@ -28,8 +28,11 @@ def main(dataset, matrix_sim_dir, raw_graph_dir, selected_graphs, threshold, inc
if not os.path.exists(last_step_output):
os.makedirs(last_step_output)
- for fn in tqdm(glob.glob(os.path.join(first_step_output,"*.csv")),desc="Annotate sample"):
- annotate_eval_sample(annotater, fn, os.path.join(last_step_output, os.path.basename(fn)),size_str)
+ from joblib import Parallel,delayed
+ #
+ Parallel(n_jobs=4,backend="threading")(delayed(annotate_eval_sample)(annotater, fn, os.path.join(last_step_output, os.path.basename(fn)),size_str) for fn in tqdm(glob.glob(os.path.join(first_step_output,"*.csv")),desc="Annotate sample"))
+ #for fn in tqdm(glob.glob(os.path.join(first_step_output,"*.csv")),desc="Annotate sample"):
+ #annotate_eval_sample(annotater, fn, os.path.join(last_step_output, os.path.basename(fn)),size_str)
min_carac_dict=None
if min_carac_fn != "" and os.path.exists(min_carac_fn):
@@ -63,12 +66,15 @@ def generate_annotation_dataframe(matrix_sim_dir, selected_graphs, output_dir):
print("Proceeding...", measure, type_)
if os.path.exists(os.path.join(output_dir, "{0}_{1}.csv".format(measure, type_))):
continue
- df = matrix_to_pandas_dataframe(np.nan_to_num(read_bz2_matrix(fn)),
- selected_graphs,
- measure, type_)
- if not os.path.exists(output_dir):
- os.makedirs(output_dir)
- df.to_csv(os.path.join(output_dir, "{0}_{1}.csv".format(measure, type_)))
+ try:
+ df = matrix_to_pandas_dataframe(np.nan_to_num(read_bz2_matrix(fn)),
+ selected_graphs,
+ measure, type_)
+ if not os.path.exists(output_dir):
+ os.makedirs(output_dir)
+ df.to_csv(os.path.join(output_dir, "{0}_{1}.csv".format(measure, type_)))
+ except:
+ print("Could'not read {0}".format(fn))
def extract_criteria_4_all(annotater, csv_input_dir, raw_graph_dir, dataset, threshold, output_file="temp_out.csv"):
@@ -157,6 +163,7 @@ def annotate_eval_sample(annotater, csv_file, output_file, size_str):
try:
return annotater.all(None, None, x.G1, x.G2)
except Exception as e:
+ print("Error",e)
return [0, 0, 0, 0,300000,0]
df["res"] = df.apply(lambda x: foo(x), axis=1)
@@ -196,6 +203,14 @@ def synthesize(last_step_output,output_filename,min_size_G1=None,min_size_G2=Non
if min_carac_dict and ncar_min_doc2 > 0:
output_filename= output_filename+"_mindoc2len_{0}".format(ncar_min_doc2)
data = []
+
+ # min_c5,max_c5 = 2000,0
+ # min_c6, max_c6 = 2000, 0
+ # for fn in tqdm(fns,desc="Synthetise Results"):
+ # df = pd.read_csv(fn)
+ # min_c5, max_c5 = min(min_c5,df.c5.min()), max(max_c5,df.c5.max())
+ # min_c6, max_c6 = min(min_c6,df.c6.min()), max(max_c6,df.c6.max())
+
for fn in tqdm(fns,desc="Synthetise Results"):
df = pd.read_csv(fn)
if min_size_G1:
@@ -214,7 +229,7 @@ def synthesize(last_step_output,output_filename,min_size_G1=None,min_size_G2=Non
df = df.replace([np.inf, -np.inf], 300000)
df["c5"] = 1 - (df.c5 - df.c5.min()) / (df.c5.max() - df.c5.min())
- df["c6"] = (df.c6 - df.c6.min()) / (df.c6.max() - df.c6.min())
+ df["c6"] = (df.c6 - df.c6.min()) / (df.c6.max() -df.c6.min())
if len(df) <1:
continue
mes = np.unique(df.sim_measure)[0]
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..56520427730302f766194a32000db93ea14fa3d9
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,13 @@
+geopandas
+pandas
+nltk
+polyglot
+spacy
+https://github.com/Jacobe2169/my_toolbox.git
+termcolor
+pycorenlp
+https://github.com/Jacobe2169/Python-Inflector.git
+PyICU
+pycld2
+morfessor
+textblob
diff --git a/setup.py b/setup.py
index ac2185d7f24b139b0e9ab65f67c65dcbcd2734b6..f2d7456b06ab1c3c63dfb347405c2721ec899544 100644
--- a/setup.py
+++ b/setup.py
@@ -10,6 +10,5 @@ setup(
license='MIT',
author='Jacques Fize',
author_email='jacques.fize@cirad.fr',
- setup_require=['p'],
description=''
)
diff --git a/strpython/eval/automatic_annotation.py b/strpython/eval/automatic_annotation.py
index f07b2cc79b914ea3ff73e9549137b3e74fb08ff9..2d2760a0664650fa1d0a4d9b381f735204455022 100644
--- a/strpython/eval/automatic_annotation.py
+++ b/strpython/eval/automatic_annotation.py
@@ -219,7 +219,7 @@ class AnnotationAutomatic(object):
def criterion6(self, str1, str2):
"""
- Return True if both STR contains similar spatial entities.
+ Return the value of the dice coefficient between two str spatial entities set
Parameters
----------
str1
@@ -229,4 +229,6 @@ class AnnotationAutomatic(object):
-------
"""
- return len(set(str1.graph.nodes.keys()) & set(str2.graph.nodes.keys()))
\ No newline at end of file
+ G = set(str1.graph.nodes.keys())
+ H = set(str2.graph.nodes.keys())
+ return 2*(len(G & H))/(len(G)+len(H))
\ No newline at end of file
diff --git a/strpython/models/str.py b/strpython/models/str.py
index 1666854ee34df9350f715f4f961e77a6598653a1..828a000e9768362662c757d0583e99f11cceed07 100644
--- a/strpython/models/str.py
+++ b/strpython/models/str.py
@@ -189,7 +189,6 @@ class STR(object):
if not data_:
warnings.warn("{0} wasn't found in Geo-Database".format(id))
return False
- data_ = data_[0]
if not label and v == True:
warnings.warn("Label empty. @en label from Geo-Database will be used.")
label = data_["en"]
@@ -296,7 +295,6 @@ class STR(object):
data = self.get_data(new_se)
to_del.add(old_se)
if data:
- data = data[0]
final_transform_map[old_se] = new_se
if not new_se in self.spatial_entities:
self.add_spatial_entity(new_se, data.label.en)
diff --git a/strpython/models/transformation/transform.py b/strpython/models/transformation/transform.py
index df57d6300e134a04e2a6755e2ce70d8646c18224..607a4114eceb8a818ce6f13a44ff7520114831bb 100644
--- a/strpython/models/transformation/transform.py
+++ b/strpython/models/transformation/transform.py
@@ -73,10 +73,10 @@ class Generalisation(Transformation):
if not node in inclusion_dictionnary:
inc_list = []
data = gazetteer.get_by_id(node)
- if not data:continue
+ if len(data)<1:continue
data=data[0]
try:
- inc_list = data[0].other.inc_P131
+ inc_list = data.other.inc_P131
except:
pass
if not inc_list: