diff --git a/.gitignore b/.gitignore
index 0e7aa1d08cda06ed1bba177262ea792e02b5673f..4a97748395d8d5b4ee3b6fd348a997ed58c6a753 100644
--- a/.gitignore
+++ b/.gitignore
@@ -13,7 +13,7 @@ __pycache__/
!/tests/
.DS_Store
.Rproj.user
-.vscode/*
+.vscode/
data/
csv_results
depreciated
diff --git a/README.md b/README.md
index 64fd0dea1431c013b12fde4a8887ba0a178a65de..207a27090dcdf0dd72b93f19531217b8cadcd7de 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-#STR
+# STR
This repository contains all the work on STR or Spatial Textual Representation. The file
hierarchy is divided in multiple modules such as :
diff --git a/auto_fill_annotation.py b/auto_fill_annotation.py
index 52b49c85898725f0cb52056ad57a44dddc71c055..abcddfc4360113ace74adbd1c394de06ef2ca487 100644
--- a/auto_fill_annotation.py
+++ b/auto_fill_annotation.py
@@ -38,17 +38,17 @@ for file in glob.glob(os.path.join(str_graph_path, "*.gexf")):
def foo(x):
try:
return annotater.all(strs[x.G1], strs[x.G2],x.G1, x.G2)
- except Exception as e:
+ except KeyError as e:
print(e)
return [0, 0, 0, 0]
df["res"] = df.progress_apply(lambda x: foo(x), axis=1)
-df.res=df.res.apply(lambda x :list(map(int,x)))
-df[["c1"]] = df.res.apply(lambda x: x[0])
-df[["c2"]] = df.res.apply(lambda x: x[1])
-df[["c3"]] = df.res.apply(lambda x: x[2])
-df[["c4"]] = df.res.apply(lambda x: x[3])
+df.res=df.res.apply(lambda x :list(map(int,x)) if x else [])
+df[["c1"]] = df.res.apply(lambda x: x[0] if len(x)>0 else 0)
+df[["c2"]] = df.res.apply(lambda x: x[1] if len(x)>0 else 0)
+df[["c3"]] = df.res.apply(lambda x: x[2] if len(x)>0 else 0)
+df[["c4"]] = df.res.apply(lambda x: x[3] if len(x)>0 else 0)
del df["res"]
save_cache()
diff --git a/generate_annotation_file.py b/generate_annotation_file.py
index ec00d2ae907ca6ec8aa4e47553b1a34e37540c93..d18abc9fb23dcda85f217a1160cb181397950562 100644
--- a/generate_annotation_file.py
+++ b/generate_annotation_file.py
@@ -33,10 +33,7 @@ selected = json.load(open(args.selectedFile))
for fn in matrix_fns:
measure = os.path.basename(fn).split("_")[0]
- if os.path.basename(fn).split("_")[-2] in ["extension","gen"] or os.path.basename(fn).split("_")[-1].replace(".npy.bz2", "") in ["window"]:
- type_ = "_".join(os.path.basename(fn).split("_")[-2:]).replace(".npy.bz2", "")
- else:
- type_ = "_".join(os.path.basename(fn).split("_")[-1:]).replace(".npy.bz2", "")
+ type_= "_".join(fn.split("_")[1:]).replace(".npy.bz2","")
print("Proceeding...",measure, type_)
df = matrix_to_pandas_dataframe(np.nan_to_num(read_bz2_matrix(fn)),
selected,
diff --git a/generate_selected_document.py b/generate_selected_document.py
index 2a5762352eb5adfbb1ec4df4f022754083a4edd2..cfbc56b61313878e85a39ff9f9799b32379e85c0 100644
--- a/generate_selected_document.py
+++ b/generate_selected_document.py
@@ -8,7 +8,7 @@ parser.add_argument("graph_input_dir")
args=parser.parse_args()
graphs={}
-for file in glob.glob(args.graph_input_dir+"/normal/*.gexf"):
+for file in glob.glob(args.graph_input_dir+"/*.gexf"):
id=int(re.findall("\d+",file)[-1])
graphs[id]=nx.read_gexf(file)
diff --git a/notebooks/MatchingAnalysis/Result_AnaysisV2_MADA.ipynb b/notebooks/MatchingAnalysis/Result_AnaysisV2_MADA.ipynb
index 81d283c3a269c0bc4b3624d79bc0bf30a7589935..836ce6f015255c22c9e87f85a4eea3d0aa3b0939 100644
--- a/notebooks/MatchingAnalysis/Result_AnaysisV2_MADA.ipynb
+++ b/notebooks/MatchingAnalysis/Result_AnaysisV2_MADA.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 13,
+ "execution_count": 1,
"metadata": {
"ExecuteTime": {
"end_time": "2018-09-28T05:03:07.327486Z",
@@ -27,7 +27,7 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2018-09-28T05:03:09.093753Z",
@@ -36,7 +36,7 @@
},
"outputs": [],
"source": [
- "data=pd.read_csv(\"../../result_debug.csv\",index_col=0)\n",
+ "data=pd.read_csv(\"../../final_test.csv\",index_col=0)\n",
"data=data[data.mesure != \"BP\"]\n",
"data[\"mean\"]=np.mean(data[\"c1 c2 c3 c4\".split()].values,axis=1)\n",
"data[\"sum\"]=np.sum(data[\"c1 c2 c3 c4\".split()].values,axis=1)\n",
@@ -47,7 +47,7 @@
},
{
"cell_type": "code",
- "execution_count": 11,
+ "execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@@ -67,7 +67,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 4,
"metadata": {
"ExecuteTime": {
"end_time": "2018-09-26T12:55:10.491478Z",
@@ -122,7 +122,7 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 5,
"metadata": {
"ExecuteTime": {
"end_time": "2018-09-26T12:55:10.899176Z",
@@ -134,148 +134,121 @@
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
- " #T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row0_col0 {\n",
+ " #T_fa7389a2_43d2_11e9_991b_6a0002e84820row0_col3 {\n",
" background-color: yellow;\n",
" : ;\n",
- " } #T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row0_col2 {\n",
- " background-color: yellow;\n",
+ " } #T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col0 {\n",
" : ;\n",
- " } #T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row0_col3 {\n",
- " background-color: yellow;\n",
- " : ;\n",
- " } #T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row4_col0 {\n",
+ " background-color: #d64541;\n",
+ " color: white;\n",
+ " } #T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col1 {\n",
" : ;\n",
" background-color: #d64541;\n",
" color: white;\n",
- " } #T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row4_col1 {\n",
+ " } #T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col2 {\n",
" : ;\n",
" background-color: #d64541;\n",
" color: white;\n",
- " } #T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row4_col2 {\n",
+ " } #T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col3 {\n",
" : ;\n",
" background-color: #d64541;\n",
" color: white;\n",
- " } #T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row4_col5 {\n",
+ " } #T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col5 {\n",
" : ;\n",
" background-color: #d64541;\n",
" color: white;\n",
- " } #T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row7_col5 {\n",
+ " } #T_fa7389a2_43d2_11e9_991b_6a0002e84820row5_col5 {\n",
" background-color: yellow;\n",
" : ;\n",
- " } #T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row10_col1 {\n",
+ " } #T_fa7389a2_43d2_11e9_991b_6a0002e84820row6_col0 {\n",
" background-color: yellow;\n",
" : ;\n",
- " } #T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row10_col3 {\n",
+ " } #T_fa7389a2_43d2_11e9_991b_6a0002e84820row7_col1 {\n",
+ " background-color: yellow;\n",
" : ;\n",
- " background-color: #d64541;\n",
- " color: white;\n",
- " }</style><table id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >c1</th> <th class=\"col_heading level0 col1\" >c2</th> <th class=\"col_heading level0 col2\" >c3</th> <th class=\"col_heading level0 col3\" >c4</th> <th class=\"col_heading level0 col4\" >mean</th> <th class=\"col_heading level0 col5\" >sum</th> </tr> <tr> <th class=\"index_name level0\" >mesure</th> <th class=\"blank\" ></th> <th class=\"blank\" ></th> <th class=\"blank\" ></th> <th class=\"blank\" ></th> <th class=\"blank\" ></th> <th class=\"blank\" ></th> </tr></thead><tbody>\n",
+ " } #T_fa7389a2_43d2_11e9_991b_6a0002e84820row7_col2 {\n",
+ " background-color: yellow;\n",
+ " : ;\n",
+ " }</style><table id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >c1</th> <th class=\"col_heading level0 col1\" >c2</th> <th class=\"col_heading level0 col2\" >c3</th> <th class=\"col_heading level0 col3\" >c4</th> <th class=\"col_heading level0 col4\" >mean</th> <th class=\"col_heading level0 col5\" >sum</th> </tr> <tr> <th class=\"index_name level0\" >mesure</th> <th class=\"blank\" ></th> <th class=\"blank\" ></th> <th class=\"blank\" ></th> <th class=\"blank\" ></th> <th class=\"blank\" ></th> <th class=\"blank\" ></th> </tr></thead><tbody>\n",
" <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row0\" class=\"row_heading level0 row0\" >BOW</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row0_col0\" class=\"data row0 col0\" >0.953636</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row0_col1\" class=\"data row0 col1\" >0.26</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row0_col2\" class=\"data row0 col2\" >0.926</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row0_col3\" class=\"data row0 col3\" >0.473091</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row0_col4\" class=\"data row0 col4\" >0.653182</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row0_col5\" class=\"data row0 col5\" >2.61273</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row1\" class=\"row_heading level0 row1\" >BagOfCliques</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row1_col0\" class=\"data row1 col0\" >0.8932</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row1_col1\" class=\"data row1 col1\" >0.3072</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row1_col2\" class=\"data row1 col2\" >0.8188</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row1_col3\" class=\"data row1 col3\" >0.3532</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row1_col4\" class=\"data row1 col4\" >0.5931</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row1_col5\" class=\"data row1 col5\" >2.3724</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row2\" class=\"row_heading level0 row2\" >GraphEditDistance</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row2_col0\" class=\"data row2 col0\" >0.918909</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row2_col1\" class=\"data row2 col1\" >0.227091</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row2_col2\" class=\"data row2 col2\" >0.891818</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row2_col3\" class=\"data row2 col3\" >0.458182</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row2_col4\" class=\"data row2 col4\" >0.624</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row2_col5\" class=\"data row2 col5\" >2.496</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row3\" class=\"row_heading level0 row3\" >GraphEditDistanceW</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row3_col0\" class=\"data row3 col0\" >0.926333</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row3_col1\" class=\"data row3 col1\" >0.2</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row3_col2\" class=\"data row3 col2\" >0.901</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row3_col3\" class=\"data row3 col3\" >0.469333</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row3_col4\" class=\"data row3 col4\" >0.624167</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row3_col5\" class=\"data row3 col5\" >2.49667</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row4\" class=\"row_heading level0 row4\" >GreedyEditDistance</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row4_col0\" class=\"data row4 col0\" >0.0315385</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row4_col1\" class=\"data row4 col1\" >0.0472308</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row4_col2\" class=\"data row4 col2\" >0.0723077</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row4_col3\" class=\"data row4 col3\" >0.0124615</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row4_col4\" class=\"data row4 col4\" >0.0408846</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row4_col5\" class=\"data row4 col5\" >0.163538</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row5\" class=\"row_heading level0 row5\" >HED</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row5_col0\" class=\"data row5 col0\" >0.887636</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row5_col1\" class=\"data row5 col1\" >0.237091</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row5_col2\" class=\"data row5 col2\" >0.826</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row5_col3\" class=\"data row5 col3\" >0.363636</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row5_col4\" class=\"data row5 col4\" >0.578591</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row5_col5\" class=\"data row5 col5\" >2.31436</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row6\" class=\"row_heading level0 row6\" >Jaccard</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row6_col0\" class=\"data row6 col0\" >0.938</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row6_col1\" class=\"data row6 col1\" >0.4326</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row6_col2\" class=\"data row6 col2\" >0.9052</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row6_col3\" class=\"data row6 col3\" >0.2934</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row6_col4\" class=\"data row6 col4\" >0.6423</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row6_col5\" class=\"data row6 col5\" >2.5692</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row7\" class=\"row_heading level0 row7\" >MCS</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row7_col0\" class=\"data row7 col0\" >0.9432</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row7_col1\" class=\"data row7 col1\" >0.4278</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row7_col2\" class=\"data row7 col2\" >0.9068</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row7_col3\" class=\"data row7 col3\" >0.3686</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row7_col4\" class=\"data row7 col4\" >0.6616</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row7_col5\" class=\"data row7 col5\" >2.6464</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row8\" class=\"row_heading level0 row8\" >PolyIntersect</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row8_col0\" class=\"data row8 col0\" >0.584</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row8_col1\" class=\"data row8 col1\" >0.4744</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row8_col2\" class=\"data row8 col2\" >0.6972</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row8_col3\" class=\"data row8 col3\" >0.1276</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row8_col4\" class=\"data row8 col4\" >0.4708</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row8_col5\" class=\"data row8 col5\" >1.8832</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row9\" class=\"row_heading level0 row9\" >VertexEdgeOverlap</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row9_col0\" class=\"data row9 col0\" >0.9458</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row9_col1\" class=\"data row9 col1\" >0.3588</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row9_col2\" class=\"data row9 col2\" >0.8928</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row9_col3\" class=\"data row9 col3\" >0.3574</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row9_col4\" class=\"data row9 col4\" >0.6387</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row9_col5\" class=\"data row9 col5\" >2.5548</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820level0_row10\" class=\"row_heading level0 row10\" >WeisfeleirLehmanKernel</th>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row10_col0\" class=\"data row10 col0\" >0.594167</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row10_col1\" class=\"data row10 col1\" >0.762667</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row10_col2\" class=\"data row10 col2\" >0.831333</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row10_col3\" class=\"data row10 col3\" >0.004</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row10_col4\" class=\"data row10 col4\" >0.548042</td>\n",
- " <td id=\"T_d79cca2c_2f61_11e9_a1d4_6a0002e84820row10_col5\" class=\"data row10 col5\" >2.19217</td>\n",
+ " <th id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820level0_row0\" class=\"row_heading level0 row0\" >BOW</th>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row0_col0\" class=\"data row0 col0\" >0.158</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row0_col1\" class=\"data row0 col1\" >0.088</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row0_col2\" class=\"data row0 col2\" >0.15925</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row0_col3\" class=\"data row0 col3\" >0.064</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row0_col4\" class=\"data row0 col4\" >0.117313</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row0_col5\" class=\"data row0 col5\" >0.46925</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820level0_row1\" class=\"row_heading level0 row1\" >DeepWalk</th>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row1_col0\" class=\"data row1 col0\" >0.1425</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row1_col1\" class=\"data row1 col1\" >0.12375</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row1_col2\" class=\"data row1 col2\" >0.15875</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row1_col3\" class=\"data row1 col3\" >0.02</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row1_col4\" class=\"data row1 col4\" >0.11125</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row1_col5\" class=\"data row1 col5\" >0.445</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820level0_row2\" class=\"row_heading level0 row2\" >Graph2Vec</th>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col0\" class=\"data row2 col0\" >0.00775</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col1\" class=\"data row2 col1\" >0.00775</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col2\" class=\"data row2 col2\" >0.00875</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col3\" class=\"data row2 col3\" >0.0005</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col4\" class=\"data row2 col4\" >0.0061875</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row2_col5\" class=\"data row2 col5\" >0.02475</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820level0_row3\" class=\"row_heading level0 row3\" >GraphEditDistance</th>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row3_col0\" class=\"data row3 col0\" >0.141333</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row3_col1\" class=\"data row3 col1\" >0.0846667</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row3_col2\" class=\"data row3 col2\" >0.158667</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row3_col3\" class=\"data row3 col3\" >0.06</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row3_col4\" class=\"data row3 col4\" >0.111167</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row3_col5\" class=\"data row3 col5\" >0.444667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820level0_row4\" class=\"row_heading level0 row4\" >Jaccard</th>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row4_col0\" class=\"data row4 col0\" >0.156</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row4_col1\" class=\"data row4 col1\" >0.091</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row4_col2\" class=\"data row4 col2\" >0.156</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row4_col3\" class=\"data row4 col3\" >0.0575</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row4_col4\" class=\"data row4 col4\" >0.115125</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row4_col5\" class=\"data row4 col5\" >0.4605</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820level0_row5\" class=\"row_heading level0 row5\" >MCS</th>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row5_col0\" class=\"data row5 col0\" >0.156889</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row5_col1\" class=\"data row5 col1\" >0.0911111</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row5_col2\" class=\"data row5 col2\" >0.158889</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row5_col3\" class=\"data row5 col3\" >0.0626667</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row5_col4\" class=\"data row5 col4\" >0.117389</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row5_col5\" class=\"data row5 col5\" >0.469556</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820level0_row6\" class=\"row_heading level0 row6\" >VertexEdgeOverlap</th>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row6_col0\" class=\"data row6 col0\" >0.15925</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row6_col1\" class=\"data row6 col1\" >0.089</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row6_col2\" class=\"data row6 col2\" >0.15925</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row6_col3\" class=\"data row6 col3\" >0.0615</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row6_col4\" class=\"data row6 col4\" >0.11725</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row6_col5\" class=\"data row6 col5\" >0.469</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820level0_row7\" class=\"row_heading level0 row7\" >WeisfeleirLehmanKernel</th>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row7_col0\" class=\"data row7 col0\" >0.142</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row7_col1\" class=\"data row7 col1\" >0.1595</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row7_col2\" class=\"data row7 col2\" >0.16</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row7_col3\" class=\"data row7 col3\" >0.004</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row7_col4\" class=\"data row7 col4\" >0.116375</td>\n",
+ " <td id=\"T_fa7389a2_43d2_11e9_991b_6a0002e84820row7_col5\" class=\"data row7 col5\" >0.4655</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
- "<pandas.io.formats.style.Styler at 0x12a4146d8>"
+ "<pandas.io.formats.style.Styler at 0x12c4d2518>"
]
},
- "execution_count": 10,
+ "execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
@@ -327,7 +300,7 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 6,
"metadata": {
"ExecuteTime": {
"end_time": "2018-09-26T12:55:10.937714Z",
@@ -339,93 +312,176 @@
"data": {
"text/html": [
"<style type=\"text/css\" >\n",
- " #T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col2 {\n",
+ " #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row1_col2 {\n",
" background-color: yellow;\n",
" : ;\n",
- " } #T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col3 {\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row1_col4 {\n",
" background-color: yellow;\n",
" : ;\n",
- " } #T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col4 {\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col3 {\n",
" background-color: yellow;\n",
" : ;\n",
- " } #T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col7 {\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col4 {\n",
" background-color: yellow;\n",
" : ;\n",
- " } #T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col2 {\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col5 {\n",
" : ;\n",
" background-color: #d64541;\n",
" color: white;\n",
- " } #T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col3 {\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col7 {\n",
+ " background-color: yellow;\n",
+ " : ;\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row3_col7 {\n",
" : ;\n",
" background-color: #d64541;\n",
" color: white;\n",
- " } #T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col4 {\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col3 {\n",
+ " background-color: yellow;\n",
+ " : ;\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col4 {\n",
+ " background-color: yellow;\n",
+ " : ;\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col5 {\n",
+ " : ;\n",
+ " background-color: #d64541;\n",
+ " color: white;\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col7 {\n",
+ " background-color: yellow;\n",
+ " : ;\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row5_col5 {\n",
+ " background-color: yellow;\n",
+ " : ;\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col2 {\n",
+ " background-color: yellow;\n",
+ " : ;\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col4 {\n",
+ " background-color: yellow;\n",
+ " : ;\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col5 {\n",
+ " background-color: yellow;\n",
+ " : ;\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row7_col4 {\n",
" : ;\n",
" background-color: #d64541;\n",
" color: white;\n",
- " } #T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col5 {\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col2 {\n",
" : ;\n",
" background-color: #d64541;\n",
" color: white;\n",
- " } #T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col7 {\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col3 {\n",
" : ;\n",
" background-color: #d64541;\n",
" color: white;\n",
- " } #T_d92e5b58_2f61_11e9_ba72_6a0002e84820row3_col5 {\n",
+ " } #T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col4 {\n",
" background-color: yellow;\n",
" : ;\n",
- " }</style><table id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >mesure</th> <th class=\"col_heading level0 col1\" >type</th> <th class=\"col_heading level0 col2\" >c1</th> <th class=\"col_heading level0 col3\" >c2</th> <th class=\"col_heading level0 col4\" >c3</th> <th class=\"col_heading level0 col5\" >c4</th> <th class=\"col_heading level0 col6\" >mean</th> <th class=\"col_heading level0 col7\" >sum</th> </tr></thead><tbody>\n",
+ " }</style><table id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >mesure</th> <th class=\"col_heading level0 col1\" >type</th> <th class=\"col_heading level0 col2\" >c1</th> <th class=\"col_heading level0 col3\" >c2</th> <th class=\"col_heading level0 col4\" >c3</th> <th class=\"col_heading level0 col5\" >c4</th> <th class=\"col_heading level0 col6\" >mean</th> <th class=\"col_heading level0 col7\" >sum</th> </tr></thead><tbody>\n",
" <tr>\n",
- " <th id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820level0_row0\" class=\"row_heading level0 row0\" >6</th>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col0\" class=\"data row0 col0\" >MCS</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col1\" class=\"data row0 col1\" >extension_2</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col2\" class=\"data row0 col2\" >0.962</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col3\" class=\"data row0 col3\" >0.426</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col4\" class=\"data row0 col4\" >0.912</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col5\" class=\"data row0 col5\" >0.38</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col6\" class=\"data row0 col6\" >0.67</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row0_col7\" class=\"data row0 col7\" >2.68</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820level0_row1\" class=\"row_heading level0 row1\" >21</th>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col0\" class=\"data row1 col0\" >GreedyEditDistance</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col1\" class=\"data row1 col1\" >biotexlda_window</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col2\" class=\"data row1 col2\" >0.078</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col3\" class=\"data row1 col3\" >0.1</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col4\" class=\"data row1 col4\" >0.142</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col5\" class=\"data row1 col5\" >0.018</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col6\" class=\"data row1 col6\" >0.0845</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row1_col7\" class=\"data row1 col7\" >0.338</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820level0_row2\" class=\"row_heading level0 row2\" >22</th>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row2_col0\" class=\"data row2 col0\" >HED</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row2_col1\" class=\"data row2 col1\" >devdu_window</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row2_col2\" class=\"data row2 col2\" >0.914</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row2_col3\" class=\"data row2 col3\" >0.192</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row2_col4\" class=\"data row2 col4\" >0.826</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row2_col5\" class=\"data row2 col5\" >0.366</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row2_col6\" class=\"data row2 col6\" >0.5745</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row2_col7\" class=\"data row2 col7\" >2.298</td>\n",
- " </tr>\n",
- " <tr>\n",
- " <th id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820level0_row3\" class=\"row_heading level0 row3\" >49</th>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row3_col0\" class=\"data row3 col0\" >HED</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row3_col1\" class=\"data row3 col1\" >all</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row3_col2\" class=\"data row3 col2\" >0.924</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row3_col3\" class=\"data row3 col3\" >0.2</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row3_col4\" class=\"data row3 col4\" >0.828</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row3_col5\" class=\"data row3 col5\" >0.384</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row3_col6\" class=\"data row3 col6\" >0.584</td>\n",
- " <td id=\"T_d92e5b58_2f61_11e9_ba72_6a0002e84820row3_col7\" class=\"data row3 col7\" >2.336</td>\n",
+ " <th id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820level0_row0\" class=\"row_heading level0 row0\" >1</th>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row0_col0\" class=\"data row0 col0\" >VertexEdgeOverlap</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row0_col1\" class=\"data row0 col1\" >gen_country</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row0_col2\" class=\"data row0 col2\" >0.158</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row0_col3\" class=\"data row0 col3\" >0.092</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row0_col4\" class=\"data row0 col4\" >0.158</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row0_col5\" class=\"data row0 col5\" >0.06</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row0_col6\" class=\"data row0 col6\" >0.117</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row0_col7\" class=\"data row0 col7\" >0.468</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820level0_row1\" class=\"row_heading level0 row1\" >2</th>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row1_col0\" class=\"data row1 col0\" >MCS</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row1_col1\" class=\"data row1 col1\" >object</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row1_col2\" class=\"data row1 col2\" >0.16</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row1_col3\" class=\"data row1 col3\" >0.088</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row1_col4\" class=\"data row1 col4\" >0.16</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row1_col5\" class=\"data row1 col5\" >0.056</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row1_col6\" class=\"data row1 col6\" >0.116</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row1_col7\" class=\"data row1 col7\" >0.464</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820level0_row2\" class=\"row_heading level0 row2\" >3</th>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col0\" class=\"data row2 col0\" >WeisfeleirLehmanKernel</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col1\" class=\"data row2 col1\" >gen_country</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col2\" class=\"data row2 col2\" >0.154</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col3\" class=\"data row2 col3\" >0.16</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col4\" class=\"data row2 col4\" >0.16</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col5\" class=\"data row2 col5\" >0.006</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col6\" class=\"data row2 col6\" >0.12</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row2_col7\" class=\"data row2 col7\" >0.48</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820level0_row3\" class=\"row_heading level0 row3\" >7</th>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row3_col0\" class=\"data row3 col0\" >DeepWalk</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row3_col1\" class=\"data row3 col1\" >ext_1</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row3_col2\" class=\"data row3 col2\" >0.136</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row3_col3\" class=\"data row3 col3\" >0.11</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row3_col4\" class=\"data row3 col4\" >0.158</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row3_col5\" class=\"data row3 col5\" >0.018</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row3_col6\" class=\"data row3 col6\" >0.1055</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row3_col7\" class=\"data row3 col7\" >0.422</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820level0_row4\" class=\"row_heading level0 row4\" >8</th>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col0\" class=\"data row4 col0\" >WeisfeleirLehmanKernel</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col1\" class=\"data row4 col1\" >gen_region</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col2\" class=\"data row4 col2\" >0.154</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col3\" class=\"data row4 col3\" >0.16</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col4\" class=\"data row4 col4\" >0.16</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col5\" class=\"data row4 col5\" >0.006</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col6\" class=\"data row4 col6\" >0.12</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row4_col7\" class=\"data row4 col7\" >0.48</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820level0_row5\" class=\"row_heading level0 row5\" >10</th>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row5_col0\" class=\"data row5 col0\" >MCS</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row5_col1\" class=\"data row5 col1\" >bvlac</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row5_col2\" class=\"data row5 col2\" >0.154</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row5_col3\" class=\"data row5 col3\" >0.092</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row5_col4\" class=\"data row5 col4\" >0.158</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row5_col5\" class=\"data row5 col5\" >0.066</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row5_col6\" class=\"data row5 col6\" >0.1175</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row5_col7\" class=\"data row5 col7\" >0.47</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820level0_row6\" class=\"row_heading level0 row6\" >12</th>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col0\" class=\"data row6 col0\" >BOW</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col1\" class=\"data row6 col1\" >ext_1</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col2\" class=\"data row6 col2\" >0.16</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col3\" class=\"data row6 col3\" >0.084</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col4\" class=\"data row6 col4\" >0.16</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col5\" class=\"data row6 col5\" >0.066</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col6\" class=\"data row6 col6\" >0.1175</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row6_col7\" class=\"data row6 col7\" >0.47</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820level0_row7\" class=\"row_heading level0 row7\" >13</th>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row7_col0\" class=\"data row7 col0\" >Jaccard</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row7_col1\" class=\"data row7 col1\" >object</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row7_col2\" class=\"data row7 col2\" >0.152</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row7_col3\" class=\"data row7 col3\" >0.09</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row7_col4\" class=\"data row7 col4\" >0.152</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row7_col5\" class=\"data row7 col5\" >0.054</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row7_col6\" class=\"data row7 col6\" >0.112</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row7_col7\" class=\"data row7 col7\" >0.448</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820level0_row8\" class=\"row_heading level0 row8\" >26</th>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col0\" class=\"data row8 col0\" >GraphEditDistance</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col1\" class=\"data row8 col1\" >inra</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col2\" class=\"data row8 col2\" >0.132</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col3\" class=\"data row8 col3\" >0.078</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col4\" class=\"data row8 col4\" >0.16</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col5\" class=\"data row8 col5\" >0.06</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col6\" class=\"data row8 col6\" >0.1075</td>\n",
+ " <td id=\"T_06bfa4d4_43d3_11e9_a30b_6a0002e84820row8_col7\" class=\"data row8 col7\" >0.43</td>\n",
" </tr>\n",
" </tbody></table>"
],
"text/plain": [
- "<pandas.io.formats.style.Styler at 0x12a4142e8>"
+ "<pandas.io.formats.style.Styler at 0x102c12cf8>"
]
},
- "execution_count": 12,
+ "execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
diff --git a/strpython/models/node2vec.py b/strpython/models/node2vec.py
deleted file mode 100644
index b36e7e5ffc62f489bd434c82828bcdf76f7c5c5b..0000000000000000000000000000000000000000
--- a/strpython/models/node2vec.py
+++ /dev/null
@@ -1,191 +0,0 @@
-import random
-
-import numpy as np
-from gensim.models import Word2Vec
-
-
-class Graph():
- def __init__(self, nx_G, is_directed, p, q):
- self.G = nx_G
- self.is_directed = is_directed
- self.p = p
- self.q = q
-
- def node2vec_walk(self, walk_length, start_node):
- '''
- Simulate a random walk starting from start node.
- '''
- G = self.G
- alias_nodes = self.alias_nodes
- alias_edges = self.alias_edges
-
- walk = [start_node]
-
- while len(walk) < walk_length:
- cur = walk[-1]
- cur_nbrs = sorted(G.neighbors(cur))
- if len(cur_nbrs) > 0:
- if len(walk) == 1:
- walk.append(
- cur_nbrs[alias_draw(alias_nodes[cur][0], alias_nodes[cur][1])])
- else:
- prev = walk[-2]
- next = cur_nbrs[alias_draw(alias_edges[(prev, cur)][0],
- alias_edges[(prev, cur)][1])]
- walk.append(next)
- else:
- break
-
- return walk
-
- def simulate_walks(self, num_walks, walk_length):
- '''
- Repeatedly simulate random walks from each node.
- '''
- # sys.stdout.write("\r")
- G = self.G
- walks = []
- nodes = list(G.nodes)
- for walk_iter in range(num_walks):
- # sys.stdout.write(
- # '\rWalk iteration: {0}/{1}'.format(walk_iter + 1, num_walks))
- random.shuffle(nodes)
- for node in nodes:
- walks.append(self.node2vec_walk(
- walk_length=walk_length, start_node=node))
-
- return walks
-
- def get_alias_edge(self, src, dst):
- '''
- Get the alias edge setup lists for a given edge.
- '''
- G = self.G
- p = self.p
- q = self.q
-
- unnormalized_probs = []
- for dst_nbr in sorted(G.neighbors(dst)):
- if dst_nbr == src:
- unnormalized_probs.append(G[dst][dst_nbr]['weight'] / p)
- elif G.has_edge(dst_nbr, src):
- unnormalized_probs.append(G[dst][dst_nbr]['weight'])
- else:
- unnormalized_probs.append(G[dst][dst_nbr]['weight'] / q)
- norm_const = sum(unnormalized_probs)
- normalized_probs = [
- float(u_prob) / norm_const for u_prob in unnormalized_probs]
-
- return alias_setup(normalized_probs)
-
- def preprocess_transition_probs(self):
- '''
- Preprocessing of transition probabilities for guiding the random walks.
- '''
- G = self.G
- is_directed = self.is_directed
-
- alias_nodes = {}
- for node in list(G.nodes):
- unnormalized_probs = [G[node][nbr]['weight']
- for nbr in sorted(G.neighbors(node))]
- norm_const = sum(unnormalized_probs)
- normalized_probs = [
- float(u_prob) / norm_const for u_prob in unnormalized_probs]
- alias_nodes[node] = alias_setup(normalized_probs)
-
- alias_edges = {}
- triads = {}
-
- if is_directed:
- for edge in list(G.edges()):
- alias_edges[edge] = self.get_alias_edge(edge[0], edge[1])
- else:
- for edge in list(G.edges()):
- alias_edges[edge] = self.get_alias_edge(edge[0], edge[1])
- alias_edges[(edge[1], edge[0])] = self.get_alias_edge(
- edge[1], edge[0])
-
- self.alias_nodes = alias_nodes
- self.alias_edges = alias_edges
-
- return
-
-
-def alias_setup(probs):
- '''
- Compute utility lists for non-uniform sampling from discrete distributions.
- Refer to https://hips.seas.harvard.edu/blog/2013/03/03/the-alias-method-efficient-sampling-with-many-discrete-outcomes/
- for details
- '''
- K = len(probs)
- q = np.zeros(K)
- J = np.zeros(K, dtype=np.int)
-
- smaller = []
- larger = []
- for kk, prob in enumerate(probs):
- q[kk] = K * prob
- if q[kk] < 1.0:
- smaller.append(kk)
- else:
- larger.append(kk)
-
- while len(smaller) > 0 and len(larger) > 0:
- small = smaller.pop()
- large = larger.pop()
-
- J[small] = large
- q[large] = q[large] + q[small] - 1.0
- if q[large] < 1.0:
- smaller.append(large)
- else:
- larger.append(large)
-
- return J, q
-
-
-def alias_draw(J, q):
- '''
- Draw sample from a non-uniform discrete distribution using alias sampling.
- '''
- K = len(J)
-
- kk = int(np.floor(np.random.rand() * K))
- if np.random.rand() < q[kk]:
- return kk
- else:
- return J[kk]
-
-
-def learn_embeddings(walks, dimensions, window_size, nb_workers, nb_iter):
- '''
- Learn embeddings by optimizing the Skipgram objective using SGD.
- '''
- walks_ = [list(map(str, walk)) for walk in walks]
- model = Word2Vec(walks_, size=dimensions, window=window_size,
- min_count=0, sg=1, workers=nb_workers, iter=nb_iter)
- return model
-
-
-def compute_graph_model(nx_graph, **kwargs):
- '''
- Pipeline for representational learning for all nodes in a graph.
- @param nx_graph
- @kwarg p: int
- @kwarg q: int
- '''
- p = kwargs.get("p", 1)
- q = kwargs.get("q", 1)
- dimensions = kwargs.get("dimensions", 128)
- window_size = kwargs.get("window_size", 10)
- nb_workers = kwargs.get("nb_workers", 8)
- nb_iter = kwargs.get("nb_iter", 1)
- num_walks = kwargs.get("num_walks", 10)
- walk_length = kwargs.get("walk_length", 80)
- directed = kwargs.get("directed", False)
-
- G = Graph(nx_graph, directed, p, q)
- G.preprocess_transition_probs()
- walks = G.simulate_walks(num_walks, walk_length)
- return learn_embeddings(walks, dimensions, window_size, nb_workers, nb_iter)
diff --git a/strpython/models/str.py b/strpython/models/str.py
index 9e14fba7f2811d7444ab282c8f228cdb978f381d..6bfbed91c620be11f8d1e0ab7c3a256bdbca449b 100644
--- a/strpython/models/str.py
+++ b/strpython/models/str.py
@@ -5,7 +5,6 @@ import os
import time
import warnings
-from tqdm import tqdm
import folium
import geopandas as gpd
import networkx as nx
@@ -22,7 +21,6 @@ import numpy as np
# logging.basicConfig(filename=config.log_file,level=logging.INFO)
-
def get_inclusion_chain(id_, prop):
"""
For an entity return it geographical inclusion tree using a property.
@@ -42,28 +40,10 @@ class STR(object):
"""
Str basic structure
"""
- __cache_inclusion = {} # Store inclusion relations found between spaital entities
- __cache_adjacency = {} # Store adjacency relations found between spaital entities
- __cache_entity_data = {} #Â Store data about entity requested
-
+ __cache_inclusion = {}
def __init__(self, tagged_text, spatial_entities):
- """
- Constructir
-
- Parameters
- ----------
- tagged_text : list
- Text in forms of token associated with tag (2D array 2*t where t == |tokens| )
- spatial_entities : dict
- spatial entities associated with a text. Follow this structure {"<id>: <label>"}
-
- """
-
self.tagged_text = tagged_text
self.spatial_entities = spatial_entities
- for k in list(spatial_entities.keys()):
- if not k[:2] == "GD":
- del spatial_entities[k]
self.adjacency_relationships = {}
self.inclusion_relationships = {}
@@ -71,21 +51,11 @@ class STR(object):
@staticmethod
def from_networkx_graph(g: nx.Graph, tagged_: list = []):
"""
- Build a STR based on networkx graph
-
- Parameters
- ----------
- g : nx.Graph
- input graph
- tagged_ : list, optional
- tagged text (the default is []). A 2D array 2*t where t == |tokens|.
-
- Returns
- -------
- STR
- resulting STR
+ Return a STR built from a Networkx imported graph
+ :param g:
+ :param tagged_:
+ :return:
"""
-
sp_en = {}
for nod in g:
try:
@@ -93,7 +63,7 @@ class STR(object):
except KeyError: # If no label found, grab one from the geo-database
data = gazetteer.get_by_id(nod)
if data:
- sp_en[nod] = data[0].name
+ sp_en[nod] = data[0].label
str_ = STR(tagged_, sp_en)
str_.set_graph(g)
@@ -102,19 +72,10 @@ class STR(object):
@staticmethod
def from_dict(spat_ent: dict, tagged_: list = []):
"""
- Build a STR based on networkx graph
-
- Parameters
- ----------
- spat_ent : dict
- Dict of patial entities associated with a text. Follow this structure {"<id>: <label>"}
- tagged_ : list, optional
- tagged text (the default is []). A 2D array 2*t where t == |tokens|.
-
- Returns
- -------
- STR
- resulting STR
+ Return a STR built from a Networkx imported graph
+ :param g:
+ :param tagged_:
+ :return:
"""
sp_en = {}
for id_, label in spat_ent.items():
@@ -126,59 +87,16 @@ class STR(object):
@staticmethod
def from_pandas(dataf: pd.DataFrame, tagged: list = []):
- """
- Build a STR from a Pandas Dataframe with two column : id and label.
-
- Parameters
- ----------
- dataf : pd.DataFrame
- dataframe containing the spatial entities
- tagged : list, optional
- tagged text (the default is []). A 2D array 2*t where t == |tokens|.
-
- Returns
- -------
- STR
- resulting STR
- """
-
return STR.from_dict(pd.Series(dataf.label.values, index=dataf.id).to_dict(), tagged)
- def set_graph(self, g):
- """
- Apply changes to the current STR based on Networkx Graph.
-
- Parameters
- ----------
- g : networkx.Graph
- input graph
-
- """
-
- self.graph = g
- rel_ = self.graph.edges(data=True)
- for edge in rel_:
- id1, id2 = edge[0], edge[1]
- if edge[2]["color"] == "green":
- self.add_adjacency_rel(edge[0],edge[1])
- self.add_cache__adjacency(id1, id2,True)
- elif edge[2]["color"] == "red":
- self.add_inclusion_rel(edge[0], edge[1])
- self.add_cache_inclusion(id1,id2,True)
-
def add_spatial_entity(self, id, label=None, v=True):
"""
- Add a spatial entity to the current STR
-
- Parameters
- ----------
- id : str
- identifier of the spatial entity in Geodict
- label : str, optional
- if not available in Geodict (the default is None)
-
+ Adding a spatial entity to the current STR
+ :param id:
+ :param label:
+ :return:
"""
- data_ = self.get_data(id)
+ data_ = gazetteer.get_by_id(id)
if not data_:
warnings.warn("{0} wasn't found in Geo-Database".format(id))
return False
@@ -192,14 +110,9 @@ class STR(object):
def add_spatial_entities(self, ids: list, labels: list = []):
"""
Add spatial entities to the current STR
-
- Parameters
- ----------
- ids : list
- list of identifiers of each spatial entity
- labels : list, optional
- list of labels of each spatial entity
-
+ :param ids:
+ :param label:
+ :return:
"""
if not labels:
warnings.warn("Labels list is empty. @en labels from Geo-Database will be used by default")
@@ -212,121 +125,27 @@ class STR(object):
self.add_spatial_entity(id, label, False)
# print(self.graph.nodes(data=True))
- def add_adjacency_rel(self, se1, se2):
- """
- Add a adjacency relationship to the current STR.
-
- Parameters
- ----------
- se1 : str
- Identifier of the first spatial entity
- se2 : str
- Identifier of the second spatial entity
-
- """
-
- if not se1 in self.adjacency_relationships: self.adjacency_relationships[se1] = {}
- if not se2 in self.adjacency_relationships: self.adjacency_relationships[se2] = {}
- self.adjacency_relationships[se1][se2],self.adjacency_relationships[se2][se1] = True, True
- self.add_cache__adjacency(se1,se2,True)
+ def add_adjacency_rel(self, se1, se2,v=True):
+ if not se1 in self.adjacency_relationships:
+ self.adjacency_relationships[se1] = {}
+ self.adjacency_relationships[se1][se2]=v
- def add_inclusion_rel(self, se1, se2):
- """
- Add a inclusion relationship to the current STR.
-
- Parameters
- ----------
- se1 : str
- Identifier of the first spatial entity
- se2 : str
- Identifier of the second spatial entity
-
- """
+ def add_inclusion_rel(self, se1, se2,v=True):
if not se1 in self.inclusion_relationships:
self.inclusion_relationships[se1] = {}
- self.inclusion_relationships[se1][se2]=True
- self.add_cache_inclusion(se1,se2,True)
+ self.inclusion_relationships[se1][se2]=v
- def add_cache_inclusion(self,id1, id2, v=True):
+ def transform_spatial_entities(self, transform_map):
"""
- Add a relation of inclusion in a cache variable
-
- Parameters
- ----------
- id1 : str
- id of the first spatial entity
- id2 : str
- id of the second spatial entity
- v : bool, optional
- if the relation exists between the two spatial entities. Default is True
-
+ Apply transformation to a STR
+ :param transform_map:
+ :return:
"""
-
- if not id1 in STR.__cache_inclusion:
- STR.__cache_inclusion[id1] = {}
- STR.__cache_inclusion[id1][id2] = v
-
- def add_cache__adjacency(self,se1,se2,v=True):
- """
- Add a relation of adjacency in a cache variable
-
- Parameters
- ----------
- id1 : str
- id of the first spatial entity
- id2 : str
- id of the second spatial entity
- v : bool, optional
- if the relation exists between the two spatial entities. Default is True
-
- """
- if not se1 in STR.__cache_adjacency:
- STR.__cache_adjacency[se1] = {}
- if not se2 in STR.__cache_adjacency:
- STR.__cache_adjacency[se2] = {}
- STR.__cache_adjacency[se1][se2]=v
- STR.__cache_adjacency[se2][se1]=v
-
- def get_data(self,id_se):
- """
- Return an gazpy.Element object containing information about a spatial entity.
-
- Parameters
- ----------
- id_se : str
- Identifier of the spatial entity
-
- Returns
- -------
- gazpy.Element
- data
- """
-
- if id_se in STR.__cache_entity_data:
- return STR.__cache_entity_data[id_se]
- data=gazetteer.get_by_id(id_se)
- if len(data) > 0:
- STR.__cache_entity_data[id_se]= data[0]
-
-
- def transform_spatial_entities(self, transform_map : dict):
- """
- Replace or delete certain spatial entities based on a transformation map
-
- Parameters
- ----------
- transform_map : dict
- New mapping for the spatial entities in the current STR. Format required : {"<id of the old spatial entity>":"<id of the new spatial entity>"}
-
- """
-
final_transform_map = {}
# Erase old spatial entities
new_label = {}
- to_del=set([])
for old_se, new_se in transform_map.items():
- data = self.get_data(new_se)
- to_del.add(old_se)
+ data = gazetteer.get_by_id(new_se)
if data:
data = data[0]
final_transform_map[old_se] = new_se
@@ -334,70 +153,59 @@ class STR(object):
self.add_spatial_entity(new_se, data.label.en)
del self.spatial_entities[old_se]
-
new_label[new_se] = data.label.en
else:
warnings.warn("{0} doesn't exists in the geo database!".format(new_se))
-
self.graph = nx.relabel_nodes(self.graph, final_transform_map)
-
- for es in to_del:
- if es in self.graph._node:
- self.graph.remove_node(es)
-
for se_ in new_label:
self.graph.nodes[se_]["label"] = new_label[se_]
def update(self):
"""
- Update the relationship between spatial entities in the STR. Used when transforming the STR.
+ Method for updating links between spatial entities
+ :return:
"""
-
nodes = copy.deepcopy(self.graph.nodes(data=True))
self.graph.clear()
self.graph.add_nodes_from(nodes)
+ print("inclusion")
self.get_inclusion_relationships()
for se1 in self.inclusion_relationships:
for se2 in self.inclusion_relationships[se1]:
- if not se1 in self.graph.nodes or not se2 in self.graph.nodes:
- continue
if self.inclusion_relationships[se1][se2]:
self.graph.add_edge(se1, se2, key=0, color="red")
-
+ print("adjacency")
self.get_adjacency_relationships()
for se1 in self.adjacency_relationships:
for se2 in self.adjacency_relationships[se1]:
- if not se1 in self.graph.nodes or not se2 in self.graph.nodes:
- continue
if self.adjacency_relationships[se1][se2]:
self.graph.add_edge(se1, se2, key=0, color="green")
+ print("fin adj")
-
+
+ def add_cache_inclusion(self,id1, id2):
+ if not id1 in STR.__cache_inclusion:
+ STR.__cache_inclusion[id1] = set([])
+ STR.__cache_inclusion[id1].add(id2)
def is_included_in(self, se1_id, se2_id):
+ global __cache_inclusion
"""
- Return True if a spatial entity is included within another one.
-
- Parameters
- ----------
- se1_id : str
- id of the contained entity
- se2_id : str
- id of the entity container
-
- Returns
- -------
- bool
- if se1 included in se2
+ Return true if the two spatial entities identified by @se1_id and @se2_id share an inclusion relationship
+ :param se1_id:
+ :param se2_id:
+ :return:
"""
-
if se1_id in self.inclusion_relationships:
if se2_id in self.inclusion_relationships[se1_id]:
return self.inclusion_relationships[se1_id][se2_id]
+ if se1_id in STR.__cache_inclusion:
+ if se2_id in STR.__cache_inclusion[se1_id]:
+ return True
inc_chain_P131 = get_inclusion_chain(se1_id, "P131")
inc_chain_P706 = get_inclusion_chain(se1_id, "P706")
@@ -405,120 +213,18 @@ class STR(object):
inc_chain.extend(inc_chain_P706)
inc_chain = set(inc_chain)
if se2_id in inc_chain:
- self.add_cache_inclusion(se1_id,se2_id,True)
- return True
-
- return False
-
- def is_adjacent_cache(self,se1,se2):
- """
- Return true if two spatial entities were found adjacent previously.
-
- Parameters
- ----------
- se1 : str
- id of the first spatial entity
- se2 : str
- id of the second spatial entity
-
- Returns
- -------
- bool
- if se1 adjacent to se2
- """
-
- if se1 in STR.__cache_adjacency:
- if se2 in STR.__cache_adjacency[se1]:
- return STR.__cache_adjacency[se1][se2]
- if se2 in STR.__cache_adjacency:
- if se1 in STR.__cache_adjacency[se2]:
- return STR.__cache_adjacency[se2][se1]
- return False
-
- def is_included_cache(self,se1,se2):
- """
- Return true if a spatial entity were found included previously in an other one.
-
- Parameters
- ----------
- se1 : str
- id of the first spatial entity
- se2 : str
- id of the second spatial entity
-
- Returns
- -------
- bool
- if se1 included to se2
- """
- if se1 in STR.__cache_inclusion:
- if se2 in STR.__cache_inclusion[se1]:
- return STR.__cache_inclusion[se1][se2]
- return False
-
- def is_adjacent(self,se1,se2,datase1=None,datase2=None):
- """
- Return true if se1 is adjacent to se2.
-
- Parameters
- ----------
- se1 : str
- id of the first spatial entity
- se2 : str
- id of the second spatial entity
- datase1 : gazpy.Element, optional
- if given cached data concerning the spatial entity with id = se1 (the default is None)
- datase2 : gazpy.Element, optional
- if given cached data concerning the spatial entity with id = se2 (the default is None)
-
- Returns
- -------
- bool
- true if adjacent
- """
-
- stop_class = set(["A-PCLI", "A-ADM1"])
-
- def get_p47_adjacency_data(self, data):
- p47se1 = []
- for el in data.other.P47:
- d = gazetteer.get_by_other_id(el,"wikidata")
- if not d:continue
- p47se1.append(d[0].id)
- return p47se1
-
- if self.is_adjacent_cache(se1,se2):
- return False
-
- if self.is_included_in(se1, se2) or self.is_included_in(se2, se1):
- return False
-
- data_se1, data_se2 = self.get_data(se1), self.get_data(se2)
-
- if "P47" in data_se2 and se1 in self.get_p47_adjacency_data(data_se2):
- return True
- # print("P47")
- elif "P47" in data_se1 and se2 in self.get_p47_adjacency_data(data_se1):
- return True
- # print("P47")
-
- if collisionTwoSEBoundaries(se1, se2):
+ self.add_cache_inclusion(se1_id,se2_id)
return True
- if "coord" in data_se1 and "coord" in data_se2:
- if Point(data_se1.coord.lon, data_se1.coord.lat).distance(
- Point(data_se2.coord.lon, data_se2.coord.lat)) < 1 and len(
- set(data_se1.class_) & stop_class) < 1 and len(set(data_se2.class_) & stop_class) < 1:
- return True
return False
def get_inclusion_relationships(self):
"""
- Find all the inclusion relationships between the spatial entities declared in the current STR.
-
+ Return all the inclusion relationships between all the spatial entities in the STR.
+ :return:
"""
-
- for se_ in tqdm(self.spatial_entities,desc="Extract Inclusion"):
+ inclusions_ = []
+ for se_ in self.spatial_entities:
inc_chain_P131 = get_inclusion_chain(se_, "P131")
inc_chain_P706 = get_inclusion_chain(se_, "P706")
@@ -529,19 +235,61 @@ class STR(object):
for se2_ in self.spatial_entities:
if se2_ in inc_chain:
self.add_inclusion_rel(se_,se2_)
+ return inclusions_
+
+ def getP47AdjacencyData(self, data):
+ p47se1 = []
+ for el in data.other.P47:
+ d = gazetteer.get_by_other_id(el,"wikidata")
+ if not d:continue
+ p47se1.append(d[0].id)
+ return p47se1
+
+ def is_adjacent(self,se1,se2,datase1=None,datase2=None):
+ f = False
+ stop_class = set(["A-PCLI", "A-ADM1"])
+ if self.is_included_in(se1, se2):
+ return f
+
+ elif self.is_included_in(se2, se1):
+ return f
+
+ data_se1 = gazetteer.get_by_id(se1)[0] if not datase1 else datase1 # Évite de recharger à chaque fois -_-
+ data_se2 = gazetteer.get_by_id(se2)[0] if not datase2 else datase2
+
+ # print("testP47")
+ if "P47" in data_se2.other:
+ if se1 in self.getP47AdjacencyData(data_se2):
+ return True
+ # print("P47")
+ if not f:
+ if "P47" in data_se1.other:
+ if se2 in self.getP47AdjacencyData(data_se1):
+ return True
+ # print("P47")
+ if not f:
+ # print("test collision")
+ if collisionTwoSEBoundaries(se1, se2):
+ return True
+ if not f:
+ if "coord" in data_se1.other and "coord" in data_se2.other:
+ if Point(data_se1.coord.lon, data_se1.coord.lat).distance(
+ Point(data_se2.coord.lon, data_se2.coord.lat)) < 1 and len(
+ set(data_se1.class_) & stop_class) < 1 and len(set(data_se2.class_) & stop_class) < 1:
+ return True
+ return f
-
def get_adjacency_relationships(self):
"""
- Find all the adjacency relationships between the spatial entities declared in the current STR.
+ Return all the adjacency relationships between all the spatial entities in the STR.
+ :return:
"""
-
- data={se:self.get_data(se) for se in self.spatial_entities}
-
- for se1 in tqdm(self.spatial_entities,desc="Extract Adjacency Relationship"):
+ data={se:gazetteer.get_by_id(se)[0] for se in self.spatial_entities}
+ for se1 in self.spatial_entities:
data_se1 = data[se1]
for se2 in self.spatial_entities:
if se1 == se2: continue
+ # print("test adjacency")
if se1 in self.adjacency_relationships:
if se2 in self.adjacency_relationships[se1]:
continue
@@ -556,22 +304,11 @@ class STR(object):
def build(self, inc=True, adj=True, verbose=False):
"""
Build the STR
-
- Parameters
- ----------
- inc : bool, optional
- if inclusion relationship have to be included in the STR (the default is True)
- adj : bool, optional
- if adjacency relationship have to be included in the STR (the default is True)
- verbose : bool, optional
- Verbose mode activated (the default is False)
-
- Returns
- -------
- networkx.Graph
- graph representing the STR
+ :param inc:
+ :param adj:
+ :param verbose:
+ :return:
"""
-
nodes = []
for k, v in self.spatial_entities.items():
nodes.append((k, {"label": v}))
@@ -588,7 +325,7 @@ class STR(object):
graph.add_edge(se1,se2, key=0, color="green")
graph.add_edge(se2, se1, key=0, color="green")
-
+ logging.info("Extract Adjacency Rel\t{0}".format(time.time()-debut))
if inc:
debut=time.time()
self.get_inclusion_relationships()
@@ -596,20 +333,18 @@ class STR(object):
for se2 in self.inclusion_relationships[se1]:
if self.inclusion_relationships[se1][se2]:
graph.add_edge(se1,se2, key=0, color="red")
-
+ logging.info("Extract Inclusion Rel\t{0}".format(time.time() - debut))
self.graph = graph
return graph
def save_graph_fig(self, output_fn, format="svg"):
"""
- Save the graphiz reprensentation of the STR graph.
+ Save the graph graphiz reprensentation
Parameters
----------
output_fn : string
Output filename
- format : str
- Output format (svg or pdf)
"""
try:
@@ -622,33 +357,28 @@ class STR(object):
print("Error while saving STR to {0}".format(format))
def getUndirected(self):
- """
- Return the Undirected form of a STR graph.
-
- Returns
- -------
- networkx.Graph
- unidirected graph
- """
-
return nx.Graph(self.graph)
- def get_geo_data_of_se(self):
- """
- Return Geographical information for each spatial entities in the STR
-
- Returns
- -------
- geopandas.GeoDataFrame
- dataframe containing geographical information of each entity in the STR
- """
+ def set_graph(self, g):
+ self.graph = g
+ rel_ = self.graph.edges(data=True)
+ for edge in rel_:
+ id1, id2 = edge[0], edge[1]
+ if edge[2]["color"] == "green":
+ self.add_adjacency_rel(edge[0],edge[1])
+ add_cache_adjacency(id1, id2)
+ elif edge[2]["color"] == "red":
+ self.add_inclusion_rel(edge[0], edge[1])
+ self.add_cache_inclusion(id1,id2)
+
+ def get_geo_data_of_se(self):
points,label,class_ = [], [], []
for se in self.spatial_entities:
data = gazetteer.get_by_id(se)[0]
try:
points.append(Point(data.coord.lon, data.coord.lat))
- label.append(data.name)
+ label.append(data.label)
# class_.append(most_common(data["class"]))
except KeyError:
pass
@@ -659,21 +389,7 @@ class STR(object):
return df
def get_cluster(self,id_=None):
- """
- Return the cluster detected using spatial entities position.
-
- Parameters
- ----------
- id_ : temp_file_id, optional
- if cached version of geoinfo (the default is None)
-
- Returns
- -------
- gpd.GeoDataFrame
- cluster geometry
- """
-
- if os.path.exists("./temp_cluster/{0}.geojson".format(id_)):
+ if id_ and os.path.exists("./temp_cluster/{0}.geojson".format(id_)):
return gpd.read_file("./temp_cluster/{0}.geojson".format(id_))
data=self.get_geo_data_of_se()
@@ -689,6 +405,22 @@ class STR(object):
samples,labels=dbscan(X)
data["cluster"] = labels
+ """
+
+ # deuxième découpe en cluster
+ c=data['cluster'].value_counts().idxmax()
+ X=data[data["cluster"] == c]
+ X=X[["x","y"]]
+ bandwidth = estimate_bandwidth(X.values)
+ ms = MeanShift(bandwidth=bandwidth, bin_seeding=True)
+ ms.fit(X.values)
+ X["cluster"]=ms.labels_+(data['cluster'].max()+1)
+ lab=ms.labels_
+ lab+=data['cluster'].max()+1
+
+ data["cluster"][data["cluster"] == c]=X["cluster"]
+ """
+
geo = data.groupby("cluster").apply(to_Polygon)
cluster_polybuff = gpd.GeoDataFrame(geometry=geo)
if id_:
@@ -697,15 +429,6 @@ class STR(object):
def to_folium(self):
- """
- Use the folium package to project the STR on a map
-
- Returns
- -------
- folium.Map
- folium map instance
- """
-
points = []
for se in self.spatial_entities:
data = gazetteer.get_by_id(se)[0]
@@ -755,20 +478,6 @@ class STR(object):
def map_projection(self,plt=False):
- """
- Return a matplotlib figure of the STR
-
- Parameters
- ----------
- plt : bool, optional
- if the user wish to use the plt.show() (the default is False)
-
- Returns
- -------
- plt.Figure
- Matplotlib figure instance
- """
-
import matplotlib.pyplot as plt
world = gpd.read_file(gpd.datasets.get_path('naturalearth_lowres'))
base = world.plot(color='white', edgecolor='black', figsize=(16, 9))
@@ -811,39 +520,11 @@ class STR(object):
plt.show()
-# def to_Multipoints(x):
-# """
-# Return a polygon buffered representation for a set of point
-
-# Parameters
-# ----------
-# x : pandas.Series
-# coordinates columns
-
-# Returns
-# -------
-# shapely.geometry.Polygon
-# polygon
-# """
-
-# #print(x[["x","y"]].values)
-# return Polygon([Point(z) for z in x[["x","y"]].values]).buffer(1)
+def to_Multipoints(x):
+ #print(x[["x","y"]].values)
+ return Polygon([Point(z) for z in x[["x","y"]].values]).buffer(1)
def to_Polygon(x):
- """
- Return a polygon buffered representation for a set of points.
-
- Parameters
- ----------
- x : pandas.Series
- coordinates columns
-
- Returns
- -------
- shapely.geometry.Polygon
- polygon
- """
-
points = [Point(z) for z in x[["x","y"]].values]
if len(points) > 2:
coords = [p.coords[:][0] for p in points]
diff --git a/strpython/models/word2vec.py b/strpython/models/word2vec.py
deleted file mode 100644
index c0904f7514f64eec46f32f1371c64b5bf878ead2..0000000000000000000000000000000000000000
--- a/strpython/models/word2vec.py
+++ /dev/null
@@ -1,178 +0,0 @@
-# coding = utf-8
-
-# -*- coding: utf-8 -*-
-
-from glob import glob
-from tqdm import tqdm
-import numpy as np
-from gensim.models.word2vec import Word2Vec
-from polyglot.text import Text
-from pycorenlp import StanfordCoreNLP
-
-
-def getDependant(output_core_nlp, deps_list=["compound", "amod", "advmod"]):
-
- """
- Filter dependencies from Stanford NLP output
- :param output_core_nlp: output of stanford nlp request
- :param deps_list: list of tags that correspond to wanted dependencies
- :return:
- """
- dependencies = []
- i = 0
- for s in output_core_nlp["sentences"]:
- for dep in s["basicDependencies"]:
- if dep["dep"] in deps_list:
- dependencies.append([dep["governor"], dep["dependent"], i])
- i += 1
- return dependencies
-
-
-def filter_dependenciesV1(dependencies):
- """
- Filter Dependencies to be sure to get compound words !
- :param dependencies: getDependant() output
- :return:
- """
- d_temp = {}
- for d in dependencies:
- if not d[-1] in d_temp: d_temp[d[-1]] = {}
- if not d[0] in d_temp[d[-1]]: d_temp[d[-1]][d[0]] = set([])
- d_temp[d[-1]][d[0]].add(d[1])
- to_del = []
- for d_1 in d_temp:
- for d_2 in d_temp[d_1]:
- d_temp[d_1][d_2] = sorted(d_temp[d_1][d_2])
- if len(d_temp[d_1][d_2]) < 2:
- continue
- sorted_ = d_temp[d_1][d_2]
- s_ = 0
- for i in range(len(sorted_)):
- if not i + 1 == len(sorted_):
- s_ += abs(sorted_[i] - sorted_[i + 1])
- if not s_ == len(sorted_) - 1:
- to_del.append([d_1, d_2])
-
- for d in to_del: del d_temp[d[0]][d[1]]
- return d_temp
-
-
-def filter_dependencies(dependencies):
- """
- Same as filter_dependenciesV1(), except we fuse dependencies of compound word(two dependencies relation close to each other)
- :param dependencies:
- :return:
- """
- new_d = []
- d_temp = {}
- for d in dependencies:
- if not d[-1] in d_temp: d_temp[d[-1]] = {}
- if not d[0] in d_temp[d[-1]]: d_temp[d[-1]][d[0]] = set([])
- d_temp[d[-1]][d[0]].add(d[1])
- to_del = []
- for d_1 in d_temp:
- for d_2 in d_temp[d_1]:
- d_temp[d_1][d_2] = sorted(d_temp[d_1][d_2])
- if len(d_temp[d_1][d_2]) < 2:
- continue
- sorted_ = d_temp[d_1][d_2]
- s_ = 0
- for i in range(len(sorted_)):
- if not i + 1 == len(sorted_):
- s_ += abs(sorted_[i] - sorted_[i + 1])
- if not s_ == len(sorted_) - 1:
- to_del.append([d_1, d_2])
-
- for d in to_del: del d_temp[d[0]][d[1]]
- to_del = []
- for d_1 in d_temp:
- for d_2 in d_temp[d_1]:
- _depend = d_temp[d_1][d_2]
- for k in d_temp[d_1]:
- _depend2 = d_temp[d_1][k]
- if k == _depend[0]:
- for d in _depend2: _depend.insert(0, d)
- d_temp[d_1][d_2] = _depend
- to_del.append([d_1, k])
- elif k == _depend[-1]:
- _depend.extend(_depend2)
- d_temp[d_1][d_2] = _depend
- to_del.append([d_1, k])
- for d in to_del: del d_temp[d[0]][d[1]]
-
- return d_temp
-
-
-def transformed_sentences(output_core_nlp, dependencies):
- """
- Transform tokenized version to adapt word2vec input model
- :param output_core_nlp:
- :param dependencies:
- :return:
- """
- sentences = []
- j = 0
- for s in output_core_nlp["sentences"]:
- tokens = [t["originalText"].lower() for t in s["tokens"]]
- # print(tokens)
- if j in dependencies:
- # print(dependencies[j])
- to_tuple = []
- to_del = []
- for k, v in dependencies[j].items():
- tuple = list(v)
- tuple.append(k)
- to_tuple.append(tuple)
- if tuple[0] - 1 in to_del:
- set_ = set(to_del)
- set_.remove(tuple[0] - 1)
- to_del = list(set_)
- to_del.extend((np.array(tuple[1:]) - 1).tolist())
- for tup in to_tuple:
- tokens[tup[0] - 1] = "_".join([tokens[t - 1] for t in tup])
- k = 0
- for d in to_del:
- del tokens[d - k]
- k += 1
- sentences.append(tokens)
- j += 1
- return np.array(sentences)
-
-if __name__ == "__main__":
-
-
-
- files = glob("data/EPI_ELENA/raw_text/*.txt")
- nlp = StanfordCoreNLP("http://localhost:9000")
- texts = [open(f).read() for f in files]
- sentences = []
- # Classic tokenization of sentences
- for f in tqdm(texts):
- text = f
- if not text: continue
- try:
- text = Text(text)
-
- for s in text.sentences:
- tokens = []
- for t in s.tokens: tokens.append(t.lower())
- sentences.append(tokens)
- except:
- pass
-
- # Add compound word version of sentences
- for t in tqdm(texts):
- if not t: continue
- try:
- nlp_o = nlp.annotate(t, properties={'annotators': 'tokenize,ssplit,depparse', 'outputFormat': 'json'})
- dependenc = filter_dependencies(getDependant(nlp_o))
- dependenc2 = filter_dependenciesV1(getDependant(nlp_o))
- sentences.extend(transformed_sentences(nlp_o, dependenc)) # extend compound word
- sentences.extend(transformed_sentences(nlp_o, dependenc2)) # classic compound word
-
- except expression as identifier:
- pass
-
- model = Word2Vec(sentences, min_count=10)
- model.save("w2v_model_epi.w2v")
-
diff --git a/strpython/nlp/disambiguator/delozier/__init__.py b/strpython/nlp/disambiguator/delozier/__init__.py
deleted file mode 100644
index ec03d569f9032a54c2eb5a05fba3e6d671e7adca..0000000000000000000000000000000000000000
--- a/strpython/nlp/disambiguator/delozier/__init__.py
+++ /dev/null
@@ -1 +0,0 @@
-# coding = utf-8
diff --git a/strpython/nlp/disambiguator/delozier/grid.py b/strpython/nlp/disambiguator/delozier/grid.py
deleted file mode 100644
index 1d17059860e6ec9f918afb3eabed0c8fab978117..0000000000000000000000000000000000000000
--- a/strpython/nlp/disambiguator/delozier/grid.py
+++ /dev/null
@@ -1,78 +0,0 @@
-# coding = utf-8
-
-import geopandas as gpd
-import numpy as np
-from progressbar import ProgressBar
-from shapely.geometry import Point, Polygon
-
-
-class GeoGrid():
- """"""
-
- def __init__(self, upper_lat=70, bottom_lat=-70, step=2, square_size=0.25):
- """Constructor for GoeGrid"""
- self.h, self.w = (upper_lat * step) - (bottom_lat * step), 2 * 180 * step
- self.grid_points = np.indices((self.h, self.w))[1]
- # matrice avec indice de ligne
-
- self.upper_lat = upper_lat
- self.step = step
-
- self.world_borders_data = gpd.read_file("./world_borders.shp")
-
- def inside(self, point):
- poly_from_point = Polygon(self.create_square(point))
- for id_, row in self.world_borders_data.iterrows():
- if poly_from_point.within(row["geometry"]):
- return True
- return False
-
- def create_square(self, p1, size=0.25):
- x, y = p1.x, p1.y
- r = size / 2
- return [[x - r, y + r], [x + r, y + r], [x + r, y - r], [x - r, y - r]]
-
- def point_within(self, j, i):
- p = Point(-180 + (j * (1 / self.step)), self.upper_lat - i * (1 / self.step))
- if self.inside(p):
- return np.int(0)
- else:
- return np.int(-1)
-
- def createGeoGrid(self):
- with ProgressBar(max_value=len(self.grid_points)) as bar:
- for i in range(len(self.grid_points)):
- self.grid_points[i] = np.apply_along_axis(self.point_within, 0, self.grid_points[i].reshape(1, -1), i)
- bar.update(i)
- bar.finish()
- print("Geogrid Created")
-
- def loadGeoGrid(self):
- self.grid_points = np.load("./resources/grid_GEO.npy")
- # avoid frontier problem
- mask = np.arange(-1, 2)
- for i in range(len(self.grid_points)):
- for j in range(len(self.grid_points[i])):
- if self.grid_points[i][j] == -1:
- if i - 1 > 0 and i + 1 < len(self.grid_points) and j - 1 > 0 and j + 1 < len(self.grid_points[i]):
- sub = np.abs(self.grid_points[np.ix_(mask + i, mask + j)])
- if np.sum(sub) < 5:
- self.grid_points[i][j] = 0
-
- def get_points_coordinates(self, step=None):
- if not step:
- step = self.step
- coordinates = []
- for i in range(len(self.grid_points)):
- for j in range(len(self.grid_points[i])):
- if self.grid_points[i][j] == 0:
- p = [-180 + (j * (1 / step)), self.upper_lat - i * (1 / step)]
- coordinates.append(p)
- coordinates = np.array(coordinates)
- return coordinates
-
- def draw_grid(self, step=None):
- import matplotlib.pyplot as plt
- coordinates = self.get_points_coordinates()
- plt.scatter(coordinates[:, 0], coordinates[:, 1], s=0.5)
- plt.show()
diff --git a/strpython/nlp/disambiguator/delozier/utils.py b/strpython/nlp/disambiguator/delozier/utils.py
deleted file mode 100644
index 15c2f4f79da30a1e512c673c959941f605b5ab6c..0000000000000000000000000000000000000000
--- a/strpython/nlp/disambiguator/delozier/utils.py
+++ /dev/null
@@ -1,11 +0,0 @@
-# coding = utf-8
-
-def weight_i_j(i, j):
- dist = i.distance(j)
- if dist <= 1:
- return .75 * (1 - (dist))
- return False
-
-
-def Gi_star(x):
- pass
diff --git a/strpython/tt4py/__init__.py b/strpython/tt4py/__init__.py
deleted file mode 100644
index fec16bd317775c509c627a98d1a397f17029446c..0000000000000000000000000000000000000000
--- a/strpython/tt4py/__init__.py
+++ /dev/null
@@ -1,7 +0,0 @@
-# coding = utf-8
-
-"""
-tt4t is a Tagged Texy Manipulation module for Python.
-
-tt4t was conceived in order to search through tokenized/pos-tagged version of texts.
-"""
\ No newline at end of file
diff --git a/strpython/tt4py/helpers.py b/strpython/tt4py/helpers.py
deleted file mode 100644
index 0e739d4a86327f6643ed94afb89e35f113332ede..0000000000000000000000000000000000000000
--- a/strpython/tt4py/helpers.py
+++ /dev/null
@@ -1,30 +0,0 @@
-# coding = utf-8
-
-import numpy as np
-
-
-def dict_to_array(var):
- res = []
- for i, j in var.items():
- res.append([i, j])
- return np.array(res)
-
-
-def list_to_array(var):
- return np.array(var)
-
-
-def flattern(A):
- rt = []
- for i in A:
- if isinstance(i, list):
- rt.extend(flattern(i))
- elif isinstance(i, np.ndarray):
- rt.extend(flattern(i.tolist()))
- else:
- rt.append(i)
- return rt
-
-
-def flatten(var):
- return flattern(var)
diff --git a/strpython/tt4py/tt4py.py b/strpython/tt4py/tt4py.py
deleted file mode 100644
index 889a2bf62beec6b445ca10bf51134aaab442a49c..0000000000000000000000000000000000000000
--- a/strpython/tt4py/tt4py.py
+++ /dev/null
@@ -1,239 +0,0 @@
-# coding = utf-8
-
-from enum import Enum
-
-from nltk.stem import WordNetLemmatizer, SnowballStemmer
-from termcolor import colored
-
-from .helpers import *
-
-_wn_lem = WordNetLemmatizer()
-_snowball_stemmer = SnowballStemmer("english")
-
-
-class TaggedType(Enum):
- TOK = 2
- POS = 2
- POS_LEM = 3
- POS_TAG = 3 # length of each token data
- MIX_POS_TAG = 2
-
-
-class SearchFlag(Enum):
- NO_CASE = lambda x: x.lower()
- SP_WS = lambda x: x.split(" ") # split using whitespaces
- SP_P = lambda x: x.split(".") # split using point
- SP_D = lambda x: x.split("-") # split using dash
- WN_LEM = lambda x: _wn_lem.lemmatize(x)
- SNW_STEM = lambda x: _snowball_stemmer.stem(x)
-
-
-class TaggedInputError(Exception):
- def __init__(self):
- super(Exception, self).__init__(
- colored("Wrong input : check your input data type or the size for each token data ", "red"))
-
-
-class WrongThesaurusFormatError(Exception):
- def __init__(self, var):
- super(Exception, self).__init__(
- colored(
- "Wrong thesaurus format: use dict format instead of {0}. Ex. {'id_1':'label'}".format(str(type(var))),
- "red"))
-
-
-class Text(object):
- def __init__(self, tagged_text, type=TaggedType.MIX_POS_TAG):
- # check if 'tagged_text' is an iterable object
- try:
- some_object_iterator = iter(tagged_text)
- except TypeError:
- raise TaggedInputError
-
- # Convert input into numpy array
- self.tagged_text = tagged_text
-
- if isinstance(tagged_text, dict):
- self.tagged_text = dict_to_array(tagged_text)
- elif isinstance(tagged_text, list):
- self.tagged_text = list_to_array(tagged_text)
- else:
- try:
- self.tagged_text = np.array(list(tagged_text))
- except:
- print("Can't convert iterable given into a np array")
-
- if not type.value == self.tagged_text.shape[1]:
- raise TaggedInputError
-
- self._original = self.tagged_text.copy()
- self.flag_applied = []
-
- def transform_tagged(self, flags=[SearchFlag.NO_CASE, SearchFlag.SP_WS, SearchFlag.SP_D]):
- tagged = self._original.copy().tolist()
- # Apply necessary for string search
- for flag in flags:
- tagged_t = []
- for token in tagged:
- res_ = flag(token[0])
- if len(res_) > 1 and not isinstance(res_, str):
- res_ = []
- tagged_t.extend([[j, token[1]] for j in res_])
- elif isinstance(res_, list):
- tagged_t.extend([[res_[-1], token[1]]])
- else:
- tagged_t.extend([[res_, token[1]]])
- tagged = tagged_t
-
- self.tagged_text = np.array(tagged)
- self.flag_applied = flags
-
- def hasSameFlags(self, flags):
- for f in flags:
- if not f in self.flag_applied:
- return False
- return True
-
- def get_occurrences(self, string, flags=[SearchFlag.NO_CASE, SearchFlag.SP_WS, SearchFlag.SP_D]):
- if not self.hasSameFlags(flags):
- self.transform_tagged(flags)
-
- positions_list = []
- t_1 = [string]
- tagged = self.tagged_text[:, 0].copy()
- # Apply necessary for string search
- for flag in flags:
- t_1 = flatten([flag(i) for i in t_1])
- gram_1 = (True if len(t_1) == 1 else False)
- t = 0
- while t < (len(tagged)):
- token = tagged[t]
- if token == t_1[0] or token == t_1[0].rstrip("s") + "s":
- if gram_1:
- positions_list.append([t, t])
- t += 1
- else:
- j, f = 0, True
- while t + j < len(tagged) and j < len(t_1):
- if not tagged[t + j] == t_1[j]:
- f = False
- break
- j += 1
- if f:
- positions_list.append([t, t + j])
- t += j
- else:
- t += 1
- else:
- t += 1
-
- return positions_list
-
- def get_neighbor_words(self, window_size, pos1, pos2=None):
- if not pos2:
- pos2 = pos1
- return self.tagged_text[pos1 - window_size:window_size + pos2]
-
- def extract_token_by_tag(self, *tags):
- res, posis_ = [], []
- for tag in tags:
- posis_.extend(np.argwhere(self.tagged_text[:, -1] == tag).flatten())
- posis_ = sorted(posis_)
-
- for pos in posis_:
- pp = self.tagged_text[pos].tolist()
- pp.append(pos)
- res.append(pp)
- return res
-
- def tag_item_in_thesaurus(self, thesaurus, flags=[SearchFlag.NO_CASE, SearchFlag.SP_WS, SearchFlag.SP_D],
- prefix_="th_", stop_tag=["BEG-LOC", "LOC", "END-LOC"]):
- if not self.hasSameFlags(flags):
- self.transform_tagged(flags)
-
- if not isinstance(thesaurus, dict):
- raise WrongThesaurusFormatError(thesaurus)
-
- t = " ".join(self.tagged_text[:, 0].tolist())
- for id_, element in thesaurus.items():
- if element.lower() in t:
- positions_ = self.get_occurrences(element)
- for d_ in positions_:
- f = True
- x, y = d_[0], d_[1]
- c = 0
- if not self.isWorthIt(x, y, prefix_):
- break
- for st in stop_tag:
- if x != y and st in self.tagged_text[x:y][:, 1]:
- f = False
- elif x == y and st in self.tagged_text[x][1]:
- f = False
- if f:
- if abs(x - y) > 0:
- self.tagged_text[x:y][:, 1] = prefix_ # prefix_ + id_
- else:
- self.tagged_text[x][1] = prefix_ # prefix_ + id_
- new_tagged_ = []
- j = 0
- while j < len(self.tagged_text):
- tag = self.tagged_text[j]
- if prefix_ in tag[-1]:
- curr = tag[-1]
- t = 1
- while j + t < len(self.tagged_text):
- if self.tagged_text[j + t][-1] != curr:
- break
- t += 1
-
- new_tagged_.append([self.reconstruct_str(self.tagged_text[j:j + t][:, 0]), curr])
- j += t
- else:
- new_tagged_.append(tag.tolist())
- j += 1
- self.tagged_text = np.array(new_tagged_)
-
- def reconstruct_str(self, list_):
- res = ""
- no_sp_char = ["-"]
- no_sp_bf = [","]
- for ch in list_:
- if not ch in no_sp_char and res:
- if res[-1] in no_sp_char or ch in no_sp_bf:
- res += ch
- if not res:
- res += ch
- else:
- res += " " + ch
-
- return res
-
- def isWorthIt(self, x, y, prefix):
- taille = abs(x - y)
- count = 0
- if x == y:
- if prefix in self.tagged_text[x]:
- count += 1
- taille = 1
- else:
- # c=None
- for item in self.tagged_text[x:y]:
- if prefix in item[-1]:
- count += 1
-
- decx, decy = 0, 0
- fx, fy = True, True
- while fx or fy:
- fx, fy = False, False
- if x - (decx + 1) > 0:
- if prefix in self.tagged_text[x - (decx + 1)][-1]:
- fx = True
- decx += 1
- if y + decy + 1 < len(self.tagged_text):
- if prefix in self.tagged_text[y + decy + 1][-1]:
- fy = True
- decy += 1
-
- if taille < count + decx + decy:
- return False
- return True