mpcaHydro 2.2.1__tar.gz → 2.2.3__tar.gz

{mpcahydro-2.2.1 → mpcahydro-2.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mpcaHydro
-Version: 2.2.1
+Version: 2.2.3
 Summary: Python package for downloading MPCA hydrology data
 Project-URL: Homepage, https://github.com/mfratkin1/mpcaHydro
 Author-email: Mulu Fratkin <michael.fratkin@state.mn.us>

{mpcahydro-2.2.1 → mpcahydro-2.2.3}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "hatchling.build"
 [project]
 name = "mpcaHydro"
 urls = { "Homepage" = "https://github.com/mfratkin1/mpcaHydro" }  # ? Add this!
-version = "2.2.1"
+version = "2.2.3"
 dependencies = [
   "pandas",
   "requests",

{mpcahydro-2.2.1 → mpcahydro-2.2.3}/src/mpcaHydro/data_manager.py

@@ -5,8 +5,6 @@ Created on Fri Jun  3 10:01:14 2022
 @author: mfratki
 """
 
-from copy import replace
-import pandas as pd
 #from abc import abstractmethod
 from pathlib import Path
 from mpcaHydro import etlSWD
@@ -84,6 +82,9 @@ class dataManager():
         self.outlets = outlets #TODO: implement outlets manager class
         self.reports = reportManager(self.db_path)
 
+    def _set_oracle_credentials(self, oracle_username, oracle_password):
+        self.oracle_username = oracle_username
+        self.oracle_password = oracle_password
     
     def connect_to_oracle(self):
         assert (self.credentials_exist(), 'Oracle credentials not found. Set ORACLE_USER and ORACLE_PASSWORD environment variables or use swd as station_origin')
@@ -235,6 +236,18 @@ class dataManager():
                            'baseflow_value': 'observed_baseflow'}, inplace=True) 
         return df.dropna(subset=['observed'])
     
+    def get_station_data(self,station_id,station_origin, to_csv = False):
+        with duckdb.connect(self.db_path,read_only=True) as con:
+            query = '''
+            SELECT *
+            FROM analytics.observations
+            WHERE station_id = ? AND station_origin = ?'''
+            df = con.execute(query,[station_id,station_origin]).fetch_df()    
+
+        if to_csv:
+            df.to_csv(self.folderpath.joinpath(f'{station_id}.csv'), index=False)
+        return df
+
     def get_raw_data(self,station_id,station_origin, to_csv = False):
         with duckdb.connect(self.db_path,read_only=True) as con:
             if station_origin.lower() == 'equis':
@@ -256,18 +269,6 @@ class dataManager():
             df.to_csv(self.folderpath.joinpath(f'{station_id}_raw.csv'), index=False)
         return df
 
-    def to_csv(self,station_id  ,station_origin,folderpath = None):
-        if folderpath is None:
-            folderpath = self.folderpath
-        else:
-            folderpath = Path(folderpath)
-        df = self.get_station_data([station_id],constituent = 'Q',agg_period = None)
-        if len(df) > 0:
-            df.to_csv(folderpath.joinpath(station_id + '.csv'))
-        else:
-            print(f'No {station_id} calibration data available at Station {station_id}')
-        
-        df.to_csv(folderpath.joinpath(station_id + '.csv'))
 
 
 # class database():

{mpcahydro-2.2.1 → mpcahydro-2.2.3}/src/mpcaHydro/reports.py

@@ -12,9 +12,9 @@ class reportManager():
         with duckdb.connect(self.db_path,read_only=True) as con:
             return wiski_qc_counts(con)
         
-    def constituent_summary(self,constituent: str = None):
+    def station_summary(self,constituent: str = None):
         with duckdb.connect(self.db_path,read_only=True) as con:
-            return constituent_summary(con,constituent)
+            return station_summary(con,constituent)
         
     def station_reach_pairs(self):
         with duckdb.connect(self.db_path,read_only=True) as con:
@@ -51,7 +51,7 @@ def wiski_qc_counts(con: duckdb.DuckDBPyConnection):
     df = con.execute(query).fetch_df()
     return df
 
-def constituent_summary(con: duckdb.DuckDBPyConnection,constituent: str = None):
+def station_summary(con: duckdb.DuckDBPyConnection,constituent: str = None):
     
     query = '''
     SELECT *,