Spaces:
Runtime error
Runtime error
naveed-stockmark
commited on
Commit
•
3cf5a8c
1
Parent(s):
e1ca1e7
Update app.py
Browse files
app.py
CHANGED
@@ -10,8 +10,21 @@ ENTITY_LINKING_PATH = "./linking_df_technical_min.csv"
|
|
10 |
|
11 |
st.title("Materials use case search app")
|
12 |
|
13 |
-
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
# filter out technical articles
|
17 |
exclude_ids = set(wiki_df[(wiki_df.exclude == True) | (wiki_df.technical == False)].page_id.to_list())
|
@@ -22,14 +35,22 @@ wiki_df = wiki_df.rename(columns={'title_x': 'en_title'})
|
|
22 |
|
23 |
# load kg df
|
24 |
|
25 |
-
""
|
26 |
-
|
|
|
|
|
|
|
|
|
27 |
|
28 |
# filter technical wikidata
|
29 |
wikidata_df = wikidata_df[wikidata_df.apply(lambda x: x.source_skpe in include_skpes and x.target_skpe in include_skpes, axis=1)]
|
30 |
|
31 |
-
""
|
32 |
-
|
|
|
|
|
|
|
|
|
33 |
|
34 |
# filter technical
|
35 |
rebel_infer_df = rebel_infer_df[rebel_infer_df.apply(lambda x: type(x.source_skpe_id) == str and type(x.target_skpe_id) == str, axis=1)]
|
@@ -45,16 +66,12 @@ rebel_infer_df = rebel_infer_df[rebel_infer_df.source_skpe != rebel_infer_df.tar
|
|
45 |
|
46 |
kg_df = pd.concat([wikidata_df, rebel_infer_df])
|
47 |
|
|
|
|
|
|
|
|
|
48 |
|
49 |
-
|
50 |
-
linking_df = pd.read_csv(ENTITY_LINKING_PATH)
|
51 |
-
|
52 |
-
# User Input
|
53 |
-
input_text = st.text_input(
|
54 |
-
label="Enter the name of a material i.e steel, sand, plastic, etc and press Enter",
|
55 |
-
value="steel",
|
56 |
-
key="ent",
|
57 |
-
)
|
58 |
|
59 |
# normalise and match
|
60 |
text_norm = normalize_text(input_text)
|
|
|
10 |
|
11 |
st.title("Materials use case search app")
|
12 |
|
13 |
+
# User Input
|
14 |
+
input_text = st.text_input(
|
15 |
+
label="Enter the name of a material i.e steel, sand, plastic, etc and press Enter",
|
16 |
+
value="steel",
|
17 |
+
key="ent",
|
18 |
+
)
|
19 |
+
|
20 |
+
st.write("preparing data ...")
|
21 |
+
|
22 |
+
@st.cache_data(persist="disk")
|
23 |
+
def get_wiki_df():
|
24 |
+
wiki_df = pd.read_csv(WIKIPEDIA_PATH)
|
25 |
+
return wiki_df
|
26 |
+
|
27 |
+
wiki_df = get_wiki_df()
|
28 |
|
29 |
# filter out technical articles
|
30 |
exclude_ids = set(wiki_df[(wiki_df.exclude == True) | (wiki_df.technical == False)].page_id.to_list())
|
|
|
35 |
|
36 |
# load kg df
|
37 |
|
38 |
+
@st.cache_data(persist="disk")
|
39 |
+
def get_wikidata_df():
|
40 |
+
wikidata_df = pd.read_csv(WIKIDATA_PATH)
|
41 |
+
return wikidata_df
|
42 |
+
|
43 |
+
wikidata_df = get_wikidata_df()
|
44 |
|
45 |
# filter technical wikidata
|
46 |
wikidata_df = wikidata_df[wikidata_df.apply(lambda x: x.source_skpe in include_skpes and x.target_skpe in include_skpes, axis=1)]
|
47 |
|
48 |
+
@st.cache_data(persist="disk")
|
49 |
+
def get_rebel_infer_df():
|
50 |
+
rebel_infer_df = pd.read_csv(REBEL_INFER_PATH)
|
51 |
+
return rebel_infer_df
|
52 |
+
|
53 |
+
rebel_infer_df = get_rebel_infer_df()
|
54 |
|
55 |
# filter technical
|
56 |
rebel_infer_df = rebel_infer_df[rebel_infer_df.apply(lambda x: type(x.source_skpe_id) == str and type(x.target_skpe_id) == str, axis=1)]
|
|
|
66 |
|
67 |
kg_df = pd.concat([wikidata_df, rebel_infer_df])
|
68 |
|
69 |
+
@st.cache_data(persist="disk")
|
70 |
+
def get_entity_linking_df():
|
71 |
+
linking_df = pd.read_csv(ENTITY_LINKING_PATH)
|
72 |
+
return linking_df
|
73 |
|
74 |
+
linking_df = get_entity_linking_df()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
|
76 |
# normalise and match
|
77 |
text_norm = normalize_text(input_text)
|