policy download

appStore/policyaction.py

@@ -1,5 +1,6 @@
 # set path
-import glob, os, sys; 
+import glob, os, sys
+from keras.engine.base_layer import policy; 
 sys.path.append('../utils')
 
 #import needed libraries
@@ -79,7 +80,28 @@ def to_excel(df):
                                 'Policies_Plans Score','Conditional Score'],inplace=True)
         action_hits = action_hits.sort_values(by=['Action Score'], ascending=False)
         action_hits = action_hits.reset_index(drop=True)
-        action_hits.to_excel(writer,index=False,sheet_name = 'Action') 
+        action_hits.to_excel(writer,index=False,sheet_name = 'Action')
+
+    if 'policy_hits' in st.session_state:
+        policy_hits = st.session_state['policy_hits']
+        if 'keep' in policy_hits.columns:
+            policy_hits = policy_hits[policy_hits.keep == True]
+            policy_hits = policy_hits.reset_index(drop=True)
+            policy_hits.drop(columns = ['keep'], inplace=True)
+            policy_hits.to_excel(writer,index=False,sheet_name = 'Policy')  
+        else:
+            policy_hits = policy_hits.sort_values(by=['Policies_Plans Score'], ascending=False)
+            policy_hits = policy_hits.reset_index(drop=True)
+            policy_hits.to_excel(writer,index=False,sheet_name = 'Policy') 
+    else:
+        policy_hits = df[df['Action Label'] == True]
+        policy_hits.drop(columns=['Target Label','Target Score','Netzero Score',
+                                'Netzero Label','GHG Label',
+                                'GHG Score','Action Label','Policies_Plans Label',
+                                'Action Score','Conditional Score'],inplace=True)
+        policy_hits = policy_hits.sort_values(by=['Policies_Plans Score'], ascending=False)
+        policy_hits = policy_hits.reset_index(drop=True)
+        policy_hits.to_excel(writer,index=False,sheet_name = 'Policy') 
             
     # hits = hits.drop(columns = ['Target Score','Netzero Score','GHG Score'])
     workbook = writer.book
@@ -176,7 +198,7 @@ def action_display():
 
 
             st.caption("Filter table to select rows to keep for Action category")
-            filter_dataframe(hits)
+            filter_dataframe_action(hits)
             # filtered_df = filtered_df[filtered_df.keep == True]
             # st.write('Explore the data')
             # AgGrid(hits)
@@ -189,7 +211,7 @@ def action_display():
                             data=df_xlsx ,
                             file_name= os.path.splitext(os.path.basename(st.session_state['filename']))[0]+'.xlsx')
 
-def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
+def filter_dataframe_action(df: pd.DataFrame) -> pd.DataFrame:
     """
     Adds a UI on top of a dataframe to let viewers filter columns
 
@@ -293,6 +315,111 @@ def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
         st.session_state['action_hits'] = df
         
     return
+def filter_dataframe_policy(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Adds a UI on top of a dataframe to let viewers filter columns
+
+    Args:
+        df (pd.DataFrame): Original dataframe
+
+    Returns:
+        pd.DataFrame: Filtered dataframe
+    """
+    modify = st.checkbox("Add filters")
+
+    if not modify:
+        st.session_state['policy_hits'] = df
+        return 
+
+
+    df = df.copy()
+
+    # Try to convert datetimes into a standard format (datetime, no timezone)
+    # for col in df.columns:
+    #     if is_object_dtype(df[col]):
+    #         try:
+    #             df[col] = pd.to_datetime(df[col])
+    #         except Exception:
+    #             pass
+
+    #     if is_datetime64_any_dtype(df[col]):
+    #         df[col] = df[col].dt.tz_localize(None)
+
+    modification_container = st.container()
+
+    with modification_container:
+        to_filter_columns = st.multiselect("Filter dataframe on", df.columns)
+        for column in to_filter_columns:
+            left, right = st.columns((1, 20))
+            left.write("↳")
+            # Treat columns with < 10 unique values as categorical
+            if is_categorical_dtype(df[column]):
+                user_cat_input = right.multiselect(
+                    f"Values for {column}",
+                    df[column].unique(),
+                    default=list(df[column].unique()),
+                )
+                df = df[df[column].isin(user_cat_input)]
+            elif is_numeric_dtype(df[column]):
+                _min = float(df[column].min())
+                _max = float(df[column].max())
+                step = (_max - _min) / 100
+                user_num_input = right.slider(
+                    f"Values for {column}",
+                    _min,
+                    _max,
+                    (_min, _max),
+                    step=step,
+                )
+                df = df[df[column].between(*user_num_input)]
+            elif is_list_like(df[column]):
+                list_vals = set(x for lst in df[column].tolist() for x in lst)
+                user_multi_input = right.multiselect(
+                    f"Values for {column}",
+                    list_vals,
+                    default=list_vals,
+                )   
+                df['check'] = df[column].apply(lambda x: any(i in x for i in user_multi_input))
+                df = df[df.check == True]
+                df.drop(columns = ['check'],inplace=True)
+            
+                # df[df[column].between(*user_num_input)]
+            # elif is_datetime64_any_dtype(df[column]):
+            #     user_date_input = right.date_input(
+            #         f"Values for {column}",
+            #         value=(
+            #             df[column].min(),
+            #             df[column].max(),
+            #         ),
+            #     )
+            #     if len(user_date_input) == 2:
+            #         user_date_input = tuple(map(pd.to_datetime, user_date_input))
+            #         start_date, end_date = user_date_input
+            #         df = df.loc[df[column].between(start_date, end_date)]
+            else:
+                user_text_input = right.text_input(
+                    f"Substring or regex in {column}",
+                )
+                if user_text_input:
+                    df = df[df[column].str.contains(user_text_input)]
+        df['keep'] = True
+        df = df[['keep','text','Policies_Plans Score','Conditional Label',
+        'Sector Label','Adapt-Mitig Label','Indicator Label','page']]
+        df = st.data_editor(
+                  df,
+                  column_config={
+                      "keep": st.column_config.CheckboxColumn(
+                          help="Select which rows to keep",
+                          default=False,
+                      )
+                  },
+                  disabled=list(set(df.columns) - {'keep'}),
+                  hide_index=True,
+                    )
+        st.session_state['policy_hits'] = df
+        
+    return
+
 def policy_display():
     if  'key1' in st.session_state:
         df = st.session_state.key1   
@@ -314,7 +441,7 @@ def policy_display():
 
 
             st.caption("Filter table to select rows to keep for Policies and Plans category")
-            filter_dataframe(hits)
+            filter_dataframe_policy(hits)
             # filtered_df = filtered_df[filtered_df.keep == True]
             # st.write('Explore the data')
             # AgGrid(hits)