Update app.py
Browse files
app.py
CHANGED
@@ -72,24 +72,27 @@ with st.expander("ℹ️ - About this app", expanded=False):
|
|
72 |
to ‘improve efficiency’, ‘develop renewable energy’, etc. \
|
73 |
The terms come from the World Bank's NDC platform and WRI's publication.
|
74 |
""")
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
|
|
|
|
|
|
93 |
|
94 |
st.write("")
|
95 |
apps = [processing.app, target_extraction.app, netzero.app, ghg.app,
|
|
|
72 |
to ‘improve efficiency’, ‘develop renewable energy’, etc. \
|
73 |
The terms come from the World Bank's NDC platform and WRI's publication.
|
74 |
""")
|
75 |
+
c1, c2, c3 = st.columns([10,1,10])
|
76 |
+
with c1:
|
77 |
+
image = Image.open('docStore/img/flow.jpg')
|
78 |
+
st.image(image)
|
79 |
+
with c3:
|
80 |
+
st.write("""
|
81 |
+
What Happens in background?
|
82 |
+
|
83 |
+
|
84 |
+
|
85 |
+
- Step 1: Once the document is provided to app, it undergoes *Pre-processing*.\
|
86 |
+
In this step the document is broken into smaller paragraphs \
|
87 |
+
(based on word/sentence count).
|
88 |
+
- Step 2: The paragraphs are fed to **Target Classifier** which detects if
|
89 |
+
the paragraph contains any *Target* related information or not.
|
90 |
+
- Step 3: The paragraphs which are detected containing some target \
|
91 |
+
related information are then fed to multiple classifier to enrich the
|
92 |
+
Information Extraction.
|
93 |
+
|
94 |
+
The Step 2 and 3 are repated then similarly for Action and Policies & Plans.
|
95 |
+
""")
|
96 |
|
97 |
st.write("")
|
98 |
apps = [processing.app, target_extraction.app, netzero.app, ghg.app,
|