update app

app.py

@@ -8,21 +8,25 @@ split = st.sidebar.selectbox("Dataset Split", ["train", "test"])
 display = st.sidebar.selectbox("Source", ["All", "Only MRPC", "Only MRPC-R1"])
 
 ptype = st.sidebar.radio("Paraphrase Pair Types", ["All",
-                                      "Only Paraphrases (MRPC-R1)", 
-                                      "Only Paraphrases (MRPC)", 
-                                      "Rejected Paraphrases from MRPC",
-                                      "Corrected Paraphrases from MRPC"])
+                                                   "Only Paraphrases (MRPC-R1)",
+                                                   "Only Paraphrases (MRPC)",
+                                                   "Rejected Paraphrases from MRPC",
+                                                   "Corrected Paraphrases from MRPC"])
 
 st.sidebar.markdown("**Score Filter Options**")
 filter_by = st.sidebar.selectbox("Filter By Scores From", ["MRPC", "MRPC-R1"])
-display_range_wpd = st.sidebar.slider("Filter by WPD Scores", min_value=0.0, max_value=1.0, value=(0.1,0.7))
-display_range_ld = st.sidebar.slider("Filter by LD Scores", min_value=0.0, max_value=1.0, value=(0.1,0.4))
+display_range_wpd = st.sidebar.slider(
+    "Filter by WPD Scores", min_value=0.0, max_value=1.0, value=(0.1, 0.7))
+display_range_ld = st.sidebar.slider(
+    "Filter by LD Scores", min_value=0.0, max_value=1.0, value=(0.1, 0.4))
+display_scores = st.sidebar.checkbox("Display scores", value=False)
 
 st.sidebar.markdown("""**Explanation**
 This demo allows you to explore the data inside [MRPC](https://www.microsoft.com/en-us/download/details.aspx?id=52398), showing how we can use Word Position Deviation (WPD) and Lexical Deviation (LD) to find different types of paraphrases. By using what we observe from the data, we can also correct numerous labelling errors inside MRPC, presenting the a revision of MRPC termed as MRPC-R1. This demo accompanies the paper ["Towards Better Characterization of Paraphrases" (ACL 2022)](https://github.com/tlkh/paraphrase-metrics).""")
 
 st.markdown("**MRPC Paraphrase Data Explorer**")
 
+
 def load_df(split):
     if split == "train":
         df = pd.read_csv("./mrpc_train_scores.csv")
@@ -31,7 +35,8 @@ def load_df(split):
     df.reset_index(drop=True, inplace=True)
     return df
 
-def filter_df(df, display, ptype, filter_by):
+
+def filter_df(df, display, ptype, filter_by, display_scores):
     # filter data
     if display == "MRPC":
         df = df.drop(["new_s1", "new_s2"], axis=1)
@@ -56,17 +61,21 @@ def filter_df(df, display, ptype, filter_by):
     # sort by scores
     if filter_by == "MRPC":
         # wpd
-        condition = (df_sel.og_wpd >= display_range_wpd[0]) & (df_sel.og_wpd < display_range_wpd[1])
+        condition = (df_sel.og_wpd >= display_range_wpd[0]) & (
+            df_sel.og_wpd < display_range_wpd[1])
         df_sel = df_sel[condition]
         # ld
-        condition = (df_sel.og_ld >= display_range_ld[0]) & (df_sel.og_ld < display_range_ld[1])
+        condition = (df_sel.og_ld >= display_range_ld[0]) & (
+            df_sel.og_ld < display_range_ld[1])
         df_sel = df_sel[condition]
     else:
         # wpd
-        condition = (df_sel.new_wpd >= display_range_wpd[0]) & (df_sel.new_wpd < display_range_wpd[1])
+        condition = (df_sel.new_wpd >= display_range_wpd[0]) & (
+            df_sel.new_wpd < display_range_wpd[1])
         df_sel = df_sel[condition]
         # ld
-        condition = (df_sel.new_ld >= display_range_ld[0]) & (df_sel.new_ld < display_range_ld[1])
+        condition = (df_sel.new_ld >= display_range_ld[0]) & (
+            df_sel.new_ld < display_range_ld[1])
         df_sel = df_sel[condition]
     # filter scores
     if filter_by == "MRPC":
@@ -75,22 +84,18 @@ def filter_df(df, display, ptype, filter_by):
     else:
         df_sel.sort_values("new_ld", inplace=True)
         df_sel.sort_values("new_wpd", inplace=True)
+    if not display_scores:
+        df_sel.drop(["og_ld", "og_wpd", "new_ld", "new_wpd"], axis=1, inplace=True)
+    label_col = df_sel["og_label"].astype(str)+"->"+df_sel["new_label"].astype(str)
+    df_sel["og/new label"] = label_col
+    df_sel.drop(["remarks", "og_label", "new_label"], axis=1, inplace=True)
     return df_sel
-    
 
-df = load_df(split)
 
-df_sel = filter_df(df, display, ptype, filter_by)
+df = load_df(split)
 
-# CSS to inject contained in a string
-hide_table_row_index = """
-            <style>
-            tbody th {display:none}
-            .blank {display:none}
-            </style>
-            """
+df_sel = filter_df(df, display, ptype, filter_by, display_scores)
 
-# inject css at the end
-st.markdown("Total "+str(len(df_sel))+" items"+hide_table_row_index, unsafe_allow_html=True)
+st.markdown("Displaying "+str(len(df_sel))+" items")
 
 st.table(data=df_sel)