update to dropout model with oversampling

demo.py

@@ -28,7 +28,8 @@ st.set_page_config(page_title="ENGAGEMENT analyzer (beta ver 0.2)",
 
 @st.cache(allow_output_mutation=True)
 def load_model(spacy_model):
-    nlp = spacy.load("en_engagement_RoBERTa_context_flz")
+    # nlp = spacy.load("en_engagement_RoBERTa_context_flz")
+    nlp = spacy.load("en_engagement_spl_RoBERTa_acad_max1_do02")
     return (nlp)
 
 
@@ -115,7 +116,7 @@ TEXT_LIST = [
 ]
 
 
-@st.cache
+@st.cache(suppress_st_warning=True)
 def preprocess(text):
     text = re.sub("\n\n", ' &&&&&&&&#&#&#&#&', text)
     text = re.sub('\n', ' ', text)
@@ -237,8 +238,6 @@ cc = '<a rel="license" href="http://creativecommons.org/licenses/by-nc/4.0/"><im
 st.sidebar.markdown(cc, unsafe_allow_html=True)
 
 st.header("Engagement Analyzer (beta ver 0.2)")
-st.info('Updated on Nov. 18th, 2022')
-
 st.write(
     "Engagement Analyzer is a free tool that analyzes English texts for rhetorical strategies under the Engagement system framework (Martin & White, 2005). Martin and White (2005) propose two basic stance-taking strategies: expansion and contraction, which are in turn divided into finer-grained rhetorical strategies. The current tool allows you to analyze texts for a total of nine rhetorical strategies. The definitions of each category label can be found from the side bar"
 )
@@ -253,6 +252,14 @@ with st.expander("See more explanation"):
 
     """)
 
+st.info('''Updated on Dec. 4th, 2022\n
+The current version was trained on 1,333 sentences and tested on 323 sentences. It achieved the following benchmark:
+- Micro F1 = 68.94 
+- Micro Precision = 71.17
+- Micro Recall = 66.84
+I expect that the model's performance improves as the annotated dataset gets larger.
+''')
+
 with st.form("my_form"):
 
     st.subheader("Option 1: selecting example text from list")
@@ -310,14 +317,17 @@ visualize_spans(doc,
                         'start': TPL_SPAN_START,
                     },
                     "colors": {
-                        "ENTERTAIN": "#82b74b",
-                        "DENY": '#c94c4c',
-                        "COUNTER": "#eea29a",
-                        "PRONOUNCE": "#92a8d1",
-                        "ENDORSE": "#034f84",
-                        "CITATION": "#b2b2b2",
-                        "MONOGLOSS": "#3e4444",
-                        "ATTRIBUTE": "#f7786b"
+                        "ENTERTAIN": "#73C6B6",
+                        "DENY": '#CD6155',
+                        "COUNTER": "#D35400",
+                        "PRONOUNCE": "#2ECC71",
+                        "ENDORSE": "#A569BD",
+                        "CONCUR": "#F39C12",
+                        "CITATION": "#F8C471",
+                        "SOURCES": "#F7DC6F",
+                        "MONOGLOSS": "#85929E",
+                        "ATTRIBUTE": "#85C1E9",
+                        "JUSTIFYING": "#2ECC71",
                     },
                 })