Assume upgrades are string

buildstock_query/aggregate_query.py

@@ -39,7 +39,7 @@ def aggregate_annual(self, *,
         enduse_selection = [safunc.sum(enduse * total_weight).label(self._bsq._simple_label(enduse.name))
                             for enduse in enduse_cols]
         if params.get_quartiles:
-            enduse_selection += [sa.func.approx_percentile(enduse, [0, 0.02, 0.25, 0.5, 0.75, 0.98, 1]).label(
+            enduse_selection += [sa.func.approx_percentile(enduse, [0, 0.02, 0.1, 0.25, 0.5, 0.75, 0.9, 0.98, 1]).label(
                 f"{self._bsq._simple_label(enduse.name)}__quartiles") for enduse in enduse_cols]
 
         if params.get_nonzero_count:

buildstock_query/main.py

@@ -399,14 +399,17 @@ def get_upgrades_csv(self, *, upgrade_id: Union[str, int] = '0',
         logger.info("Making results_csv query for upgrade ...")
         return self.execute(query).set_index(self.bs_bldgid_column.name)
 
-    def _download_upgrades_csv(self, upgrade_id: int) -> str:
+    def _download_upgrades_csv(self, upgrade_id: Union[int, str]) -> str:
         """ Downloads the upgrades csv from s3 and returns the path to the downloaded file.
         """
         if self.up_table is None:
             raise ValueError("This run has no upgrades")
 
         available_upgrades = list(self.get_available_upgrades())
         available_upgrades.remove('0')
+        if isinstance(upgrade_id, int):
+            upgrade_id = f"{upgrade_id:02}"
+
         if str(upgrade_id) not in available_upgrades:
             raise ValueError(f"Upgrade {upgrade_id} not found")
 
@@ -428,8 +431,8 @@ def _download_upgrades_csv(self, upgrade_id: int) -> str:
             raise ValueError(f"Results parquet not found in s3 at {upgrades_path}")
         # out of the contents find the key with name matching the pattern results_up{upgrade_id}.parquet
         matching_files = [path['Key'] for path in s3_data['Contents']
-                          if f"up{upgrade_id:02}.parquet" in path['Key'] or
-                          f"upgrade{upgrade_id:02}.parquet" in path['Key']]
+                          if f"up{upgrade_id}.parquet" in path['Key'] or
+                          f"upgrade{upgrade_id}.parquet" in path['Key']]
         if len(matching_files) > 1:
             raise ValueError(f"Multiple results parquet found in s3 at {upgrades_path} for upgrade {upgrade_id}."
                              f"These files matched: {matching_files}")
@@ -440,7 +443,7 @@ def _download_upgrades_csv(self, upgrade_id: int) -> str:
         self._aws_s3.download_file(bucket, matching_files[0], local_copy_path)
         return local_copy_path
 
-    def get_upgrades_csv_full(self, upgrade_id: int) -> pd.DataFrame:
+    def get_upgrades_csv_full(self, upgrade_id: Union[int, str]) -> pd.DataFrame:
         """ Returns the full results csv table for upgrades. This is the same as get_upgrades_csv without any
         restrictions. It uses the stored parquet files in s3 to download the results which is faster than querying
         athena.

buildstock_query/report_query.py

@@ -51,7 +51,7 @@ def _get_bs_success_report(self, get_query_only: bool = False):
             return self._bsq._compile(bs_query)
         df = self._bsq.execute(bs_query)
         df = self._rename_completed_status_column(df)
-        df.insert(0, 'upgrade', 0)
+        df.insert(0, 'upgrade', '0')
         return self._process_report(df)
 
     @typing.overload
@@ -93,7 +93,7 @@ def _get_change_report(self, get_query_only: bool = False):
         for chng_type, query in zip(chng_types, queries):
             df = self._bsq.execute(query)
             df.rename(columns={"change": chng_type}, inplace=True)
-            df['upgrade'] = df['upgrade'].map(int)
+            # df['upgrade'] = df['upgrade'].map(int)
             df = df.set_index('upgrade').sort_index()
             change_df = change_df.join(df, how='outer') if len(change_df) > 0 else df
         change_df = change_df.fillna(0)
@@ -103,7 +103,7 @@ def _get_change_report(self, get_query_only: bool = False):
         return change_df
 
     @validate_arguments(config=dict(arbitrary_types_allowed=True, smart_union=True))
-    def print_change_details(self, upgrade_id: int, yml_file: str, opt_sat_path: str,
+    def print_change_details(self, upgrade_id: Union[int, str], yml_file: str, opt_sat_path: str,
                              change_type: Literal["no-chng", "bad-chng", "ok-chng", "true-bad-chng",
                                                   "true-ok-chng", "null", "any"] = 'no-chng'):
         ua = self._bsq.get_upgrades_analyzer(yaml_file=yml_file,
@@ -113,21 +113,21 @@ def print_change_details(self, upgrade_id: int, yml_file: str, opt_sat_path: str
         ua.print_unique_characteristic(upgrade_id, change_type, good_bids, bad_bids)
 
     @typing.overload
-    def _get_upgrade_buildings(self, *, upgrade_id: int, trim_missing_bs: bool = True,
+    def _get_upgrade_buildings(self, *, upgrade_id: Union[int, str], trim_missing_bs: bool = True,
                                get_query_only: Literal[False] = False) -> list[int]:
         ...
 
     @typing.overload
-    def _get_upgrade_buildings(self, *, upgrade_id: int, get_query_only: Literal[True],
+    def _get_upgrade_buildings(self, *, upgrade_id: Union[int, str], get_query_only: Literal[True],
                                trim_missing_bs: bool = True) -> str:
         ...
 
     @typing.overload
-    def _get_upgrade_buildings(self, *, upgrade_id: int, get_query_only: bool,
+    def _get_upgrade_buildings(self, *, upgrade_id: Union[int, str], get_query_only: bool,
                                trim_missing_bs: bool = True) -> Union[list[int], str]:
         ...
 
-    def _get_upgrade_buildings(self, *, upgrade_id: int, trim_missing_bs: bool = True, get_query_only: bool = False):
+    def _get_upgrade_buildings(self, *, upgrade_id: Union[int, str], trim_missing_bs: bool = True, get_query_only: bool = False):
         if self._bsq.up_table is None:
             raise ValueError("No upgrade table is available .")
         up_query = sa.select([self._bsq.up_bldgid_column])
@@ -191,28 +191,28 @@ def _get_change_conditions(self, change_type: str):
         return conditions
 
     @typing.overload
-    def get_buildings_by_change(self, *, upgrade_id: int, get_query_only: Literal[True],
+    def get_buildings_by_change(self, *, upgrade_id: Union[int, str], get_query_only: Literal[True],
                                 change_type: Literal["no-chng", "bad-chng", "ok-chng", "true-bad-chng",
                                                      "true-ok-chng", "null", "any"] = 'no-chng'
                                 ) -> str:
         ...
 
     @typing.overload
-    def get_buildings_by_change(self, *,  upgrade_id: int, get_query_only: Literal[False] = False,
+    def get_buildings_by_change(self, *,  upgrade_id: Union[int, str], get_query_only: Literal[False] = False,
                                 change_type: Literal["no-chng", "bad-chng", "ok-chng", "true-bad-chng",
                                                      "true-ok-chng", "null", "any"] = 'no-chng'
                                 ) -> list[int]:
         ...
 
     @typing.overload
-    def get_buildings_by_change(self, *, upgrade_id: int, get_query_only: bool,
+    def get_buildings_by_change(self, *, upgrade_id: Union[int, str], get_query_only: bool,
                                 change_type: Literal["no-chng", "bad-chng", "ok-chng", "true-bad-chng",
                                                      "true-ok-chng", "null", "any"] = 'no-chng'
                                 ) -> Union[list[int], str]:
         ...
 
     @validate_arguments(config=dict(arbitrary_types_allowed=True, smart_union=True))
-    def get_buildings_by_change(self, *, upgrade_id: int,
+    def get_buildings_by_change(self, *, upgrade_id: Union[int, str],
                                 change_type: Literal["no-chng", "bad-chng", "ok-chng", "true-bad-chng",
                                                      "true-ok-chng", "null", "any"] = 'no-chng',
                                 get_query_only: bool = False):
@@ -276,7 +276,7 @@ def _get_up_success_report(self, *, trim_missing_bs: bool = True, get_query_only
         return self._process_report(df)
 
     def _process_report(self, df: DataFrame):
-        df['upgrade'] = df['upgrade'].map(int)
+        # df['upgrade'] = df['upgrade'].map(int)
         pf = df.pivot(index=['upgrade'], columns=['completed_status'],
                       values=['count'])
         pf.columns = [c[1] for c in pf.columns]
@@ -317,7 +317,7 @@ def _get_full_options_report(self, trim_missing_bs: bool = True, get_query_only:
         df = self._bsq.execute(query)
         simple_names = [f"option{i+1}" for i in range(len(opt_name_cols))]
         df.columns = ['upgrade'] + simple_names + ['success', "applied_buildings"]
-        df['upgrade'] = df['upgrade'].map(int)
+        # df['upgrade'] = df['upgrade'].map(int)
         df['applied_buildings'] = df['applied_buildings'].map(lambda x: literal_eval(x))
         applied_rows = df[simple_names].any(axis=1)  # select only rows with at least one option applied
         return df[applied_rows]
@@ -570,7 +570,7 @@ def _get_ts_report(self, get_query_only: bool = False):
         if get_query_only:
             return self._bsq._compile(ts_query)
         df = self._bsq.execute(ts_query)
-        df['upgrade'] = df['upgrade'].map(int)
+        # df['upgrade'] = df['upgrade'].map(int)
         df = df.set_index('upgrade')
         df = df.rename(columns={'count': 'success'})
         return df
@@ -660,7 +660,7 @@ def get_applied_options(self, upgrade_id: Union[str, int], bldg_ids: list[int],
         Returns:
             list[set|dict]: List of options (along with baseline chars, if include_base_opt is true)
         """
-        up_csv = self._bsq.get_upgrades_csv_full(upgrade_id=int(upgrade_id))
+        up_csv = self._bsq.get_upgrades_csv_full(upgrade_id=upgrade_id)
         rel_up_csv = up_csv.loc[bldg_ids]
         upgrade_cols = [key for key in up_csv.columns
                         if key.startswith("upgrade_costs.option_") and key.endswith("_name")]
@@ -702,7 +702,7 @@ def get_enduses_buildings_map_by_change(self, upgrade_id: Union[str, int],
         Returns:
             dict[str, pd.Index]: Dict mapping enduses that had a given change and building ids showing that change.
         """
-        up_csv = self._bsq.get_upgrades_csv_full(upgrade_id=int(upgrade_id))
+        up_csv = self._bsq.get_upgrades_csv_full(upgrade_id=upgrade_id)
         bs_csv = self._bsq.get_results_csv_full()
         if bldg_list:
             up_csv = up_csv.loc[bldg_list]

buildstock_query/tools/upgrades_analyzer.py

@@ -366,7 +366,7 @@ def get_report(self, upgrade_num: Optional[int] = None) -> pd.DataFrame:
         """
 
         self._logic_cache = {}
-        if upgrade_num not in self.upgrade_names:
+        if upgrade_num is not None and upgrade_num not in self.upgrade_names:
             raise ValueError(f"Invalid upgrade {upgrade_num}. Valid upgrade_num = {self.upgrade_names.keys()}.")
 
         record_dfs = []