comments

score_app.py

@@ -6,7 +6,7 @@ from data import headers
 
 st.title("Production scores")
 st.sidebar.title("Parameters")
-source_type_value = st.sidebar.selectbox('Authority country', ['cftc', 'doj', 'cfbp'])
+source_type_value = st.sidebar.selectbox('Authority country', ['cftc', 'doj', 'cfbp', 'sec'])
 
 created_at = '2021-01-01'
 
@@ -35,7 +35,7 @@ def load_data(source_type):
 
 df_list = load_data(source_type_value)
 
-# filter to keep processing
+# filter to keep processing -- 45 is the airflow user id
 processed_decisions = {}
 for decision_id, decision in df_list:
     _df = decision[(decision.status == 'P') & (decision.history_user == 45)]
@@ -49,6 +49,7 @@ for decision_id, decision in df_list:
     if _df.shape[0] > 0:
         validated_decisions[decision_id] = _df
 
+# Intersection of the precessed and validated decisions
 scope = list(set(processed_decisions.keys()) & set(validated_decisions.keys()))
 st.metric(label="Number of elements", value=len(scope))
 
@@ -59,11 +60,15 @@ compare_list = st.sidebar.multiselect('Fields to evaluate',
                                        'currency',
                                        'justice_type',
                                        'decision_date',
-                                       'country_of_violation'], ['monetary_sanction', 'decision_date'])
+                                       'country_of_violation'],
+                                      ['monetary_sanction', 'decision_date'])
+
 result = {}
 details = {}
 for decision_id in scope:
+    # last processed version
     p = processed_decisions[decision_id].iloc[-1].to_dict()
+    # last validated version
     v = validated_decisions[decision_id].iloc[-1].to_dict()
     details[decision_id] = {col: (p[col], v[col]) for col in compare_list}
     result[decision_id] = {col: p[col] == v[col] for col in compare_list}