Merge pull request #10 from regulatorystudies/revisions_2024_05

README.md

@@ -11,6 +11,8 @@ python_version: 3.11
 
 ## Description
 
-Rules falling within the Congressional Review Act (CRA) window during presidential transitions.
+Dashboard app tracking rules falling within the Congressional Review Act (CRA) window during presidential transitions.
 
-Test.
+**[Link to web accessible dashboard](https://regulatorystudies-cra-window-rules.hf.space/)**
+
+Developed by the [GW Regulatory Studies Center](https://go.gwu.edu/regstudies).

app.py

@@ -34,7 +34,7 @@ with ui.sidebar(title="Settings"):
     
     ui.input_switch("switch", "Show significant rules in plots", False)
     
-    ui.input_select("menu_agency", "Select agencies", choices=["all"] + AGENCIES, selected="all")
+    ui.input_select("menu_agency", "Select agencies", choices=["all"] + AGENCIES, selected="all", multiple=True)
     
     #ui.input_checkbox_group(
     #    "significant",
@@ -150,9 +150,30 @@ with ui.accordion(open=False):
             label="Download data as CSV",
             filename=f"rules_in_cra_window_accessed_{date.today()}.csv",
         )
-        async def download():
+        async def download(
+            output_cols: tuple | list = (
+                "document_number", 
+                "citation", 
+                "publication_date", 
+                "title", 
+                "type", 
+                "action", 
+                "abstract", 
+                "docket_ids", 
+                "json_url", 
+                "html_url", 
+                "agencies", 
+                "independent_reg_agency", 
+                "parent_slug", 
+                "subagency_slug", 
+                "president_id", 
+                "significant", 
+                "3f1_significant", 
+                "other_significant"
+                )
+            ):
             await asyncio.sleep(0.25)
-            yield filtered_df().to_csv(index=False)
+            yield filtered_df().loc[:, output_cols].to_csv(index=False)
 
 with ui.accordion(open=False):
     
@@ -187,8 +208,8 @@ def filtered_df():
         filt_df = filt_df.loc[filt_df["publication_date"] >= datetime.combine(input.start_date(), time(0, 0))]
     
     # filter agencies
-    if input.menu_agency() != "all":
-        bool_agency = [True if input.menu_agency() in agency else False for agency in filt_df["parent_slug"]]
+    if (input.menu_agency() is not None) and ("all" not in input.menu_agency()):
+        bool_agency = [True if sum(selected in agency for selected in input.menu_agency()) > 0 else False for agency in filt_df["parent_slug"]]
         filt_df = filt_df.loc[bool_agency]
     
     return filt_df

modules/__init__.py

@@ -0,0 +1,6 @@
+# see: https://docs.python.org/3.11/tutorial/modules.html#packages
+__all__ = [
+    "get_rules_in_window", 
+    "search_columns", 
+    "significant", 
+    ]

modules/get_rules_in_window.py

@@ -18,13 +18,13 @@ from plotnine import (
 try:
     from search_columns import search_columns, SearchError
     from significant import get_significant_info
-except ModuleNotFoundError:
+except (ModuleNotFoundError, ImportError):
     from .search_columns import search_columns, SearchError
     from .significant import get_significant_info
 
 
 METADATA, _ = AgencyMetadata().get_agency_metadata()
-START_DATE = "2024-03-01"
+START_DATE = "2024-01-01"
 GET_SIGNIFICANT = True if date.fromisoformat(START_DATE) >= date(2023, 4, 6) else False
 
 
@@ -294,11 +294,8 @@ def get_rules_in_window(start_date: str, get_significant: bool = True):
 
 
 def get_list_agencies(start_date, agency_column: str = "agency", metadata: dict | None = None, significant: bool = True):
-    
     df, _ = get_rules_in_window(start_date, get_significant=significant)
-    df_agency = groupby_agency(df, metadata=metadata, significant=significant)
-    print(df_agency.columns)
-    
+    df_agency = groupby_agency(df, metadata=metadata, significant=significant)    
     return sorted(list(set(df_agency.loc[df_agency[agency_column].notna(), agency_column].to_list())))
 
 

tests/test_get_data.py

@@ -0,0 +1,32 @@
+from datetime import date
+
+from modules.get_rules_in_window import (
+    get_date_range, 
+    get_rules, 
+)
+
+
+def test_get_date_range(start_str: str = "2024-05-01"):
+    
+    start_date = date.fromisoformat(start_str)
+    end_year = start_date.year + 1
+    
+    dates_str = get_date_range(start_str)
+    assert isinstance(dates_str, dict)
+    assert (
+        dates_str.get("start") == start_str
+        and dates_str.get("end") == f"{end_year}-01-31"
+        and dates_str.get("transition_year") == end_year
+        )
+
+
+def test_get_rules(
+    date_range: dict = {
+        "start": "2024-05-01", 
+        "end": "2024-05-10", 
+        "transition_year": 2025, 
+        }
+    ):    
+    results = get_rules(date_range)
+    assert isinstance(results, list)
+    assert all(isinstance(item, dict) for item in results)

tests/test_process_data.py

@@ -0,0 +1,23 @@
+import pytest
+from fr_toolbelt.api_requests import get_documents_by_date
+from pandas import DataFrame
+
+from modules.get_rules_in_window import (
+    format_documents, 
+)
+
+
+START = "2024-03-01"
+END = "2024-04-30"
+
+
+#@pytest.fixture
+def temp_documents():
+    return get_documents_by_date(START, end_date=END, document_types=("RULE", ))[0]
+TEMP_DOCUMENTS = temp_documents()
+
+
+def test_format_documents():
+    
+    formatted = format_documents(TEMP_DOCUMENTS)
+    assert isinstance(formatted, DataFrame)