Dev postgres

flagging_site/blueprints/flagging.py

@@ -68,15 +68,18 @@ def add_to_dict(models, df, reach) -> None:
 @bp.route('/')
 def index() -> str:
     """
-    Retrieves data from hobolink and usgs and processes data, then displays data 
-    on `index_model.html`     
+    Retrieves data from database, 
+    then displays data on `index_model.html`     
 
     returns: render model on index.html
     """
+
+    df = latest_model_outputs()
+    df = df.set_index('reach')
     flags = {
         key: val['safe']
         for key, val
-        in latest_model_outputs().items()
+        in df.to_dict(orient='index').items()
     }
     return render_template('index.html', flags=flags)
 
@@ -113,27 +116,20 @@ def output_model() -> str:
     # Look at no more than 72 hours.
     hours = min(max(hours, 1), 72)
 
-    df = get_data()
+    df = latest_model_outputs(hours)
 
-    reach_model_mapping = {
-        2: reach_2_model,
-        3: reach_3_model,
-        4: reach_4_model,
-        5: reach_5_model
-    }
-
-    if reach in reach_model_mapping:
-        reach_func = reach_model_mapping[int(reach)]
-        reach_html_tables = {
-            reach: stylize_model_output(reach_func(df, rows=hours))
-        }
-    else:
-        reach_html_tables = {
-            reach: stylize_model_output(reach_func(df, rows=hours))
-            for reach, reach_func
-            in reach_model_mapping.items()
-        }
+    # reach_html_tables is a dict where the index is the reach number
+    # and the values are HTML code for the table of data to display for
+    # that particular reach
+    reach_html_tables = {}
 
+    # loop through each reach in df
+    #    extract the subset from the df for that reach
+    #    then convert that df subset to HTML code
+    #    and then add that HTML subset to reach_html_tables
+    for i in df.reach.unique():
+        reach_html_tables[i] = stylize_model_output(  df.loc[df['reach'] == i ]  )
+
     return render_template('output_model.html', tables=reach_html_tables)
 
 
@@ -174,4 +170,4 @@ def get(self):
         return self.model_api()
 
 
-api.add_resource(ReachApi, '/api/v1/model')
+api.add_resource(ReachApi, '/api/v1/model')

flagging_site/data/database.py

@@ -61,7 +61,7 @@ def update_database():
 
     # Populate the `hobolink` table.
     from .hobolink import get_live_hobolink_data
-    df_hobolink = get_live_hobolink_data()
+    df_hobolink = get_live_hobolink_data('code_for_boston_export_21d')
     df_hobolink.to_sql('hobolink', **options)
 
     from .model import process_data

flagging_site/data/model.py

@@ -145,7 +145,7 @@ def process_data(
     return df
 
 
-def reach_2_model(df: pd.DataFrame, rows: int = 24) -> pd.DataFrame:
+def reach_2_model(df: pd.DataFrame, rows: int = 48) -> pd.DataFrame:
     """Model params:
     a- rainfall sum 0-24 hrs
     d- Days since last rain
@@ -172,7 +172,7 @@ def reach_2_model(df: pd.DataFrame, rows: int = 24) -> pd.DataFrame:
     return df[['reach', 'time', 'log_odds', 'probability', 'safe']]
 
 
-def reach_3_model(df: pd.DataFrame, rows: int = 24) -> pd.DataFrame:
+def reach_3_model(df: pd.DataFrame, rows: int = 48) -> pd.DataFrame:
     """
     a- rainfall sum 0-24 hrs
     b- rainfall sum 24-48 hr
@@ -201,7 +201,7 @@ def reach_3_model(df: pd.DataFrame, rows: int = 24) -> pd.DataFrame:
     return df[['reach', 'time', 'log_odds', 'probability', 'safe']]
 
 
-def reach_4_model(df: pd.DataFrame, rows: int = 24) -> pd.DataFrame:
+def reach_4_model(df: pd.DataFrame, rows: int = 48) -> pd.DataFrame:
     """
     a- rainfall sum 0-24 hrs
     b- rainfall sum 24-48 hr
@@ -230,7 +230,7 @@ def reach_4_model(df: pd.DataFrame, rows: int = 24) -> pd.DataFrame:
     return df[['reach', 'time', 'log_odds', 'probability', 'safe']]
 
 
-def reach_5_model(df: pd.DataFrame, rows: int = 24) -> pd.DataFrame:
+def reach_5_model(df: pd.DataFrame, rows: int = 48) -> pd.DataFrame:
     """
     c- rainfall sum 0-48 hr
     d- Days since last rain
@@ -269,9 +269,17 @@ def all_models(df: pd.DataFrame, *args, **kwargs):
 
 
 def latest_model_outputs(hours: int = 1) -> dict:
-    if hours != 1:
-        raise NotImplementedError('Need to work on this!')
     from .database import execute_sql_from_file
-    df = execute_sql_from_file('latest_model.sql')
-    df = df.set_index('reach')
-    return df.to_dict(orient='index')
+
+    if hours == 1:
+        df = execute_sql_from_file('return_1_hour_of_model_outputs.sql')
+    elif hours > 1:
+        df = execute_sql_from_file('return_48_hours_of_model_outputs.sql') # pull out 48 hours of model outputs
+        latest_time = max(df['time']) # find most recent timestamp
+        time_interval = pd.Timedelta(str(hours) + ' hours') # create pandas Timedelta, based on input parameter hours
+        df = df[ latest_time - df['time']< time_interval ] # reset df to exclude anything from before time_interval ago
+
+    else:
+        raise ValueError('hours of data to pull cannot be less than one')
+
+    return df

flagging_site/data/queries/return_48_hours_of_model_outputs.sql

@@ -0,0 +1,8 @@
+-- This query returns up to 48 hours of the latest data
+
+SELECT *
+FROM model_outputs
+WHERE time BETWEEN 
+	(SELECT MAX(time) - interval '47 hours' FROM model_outputs)
+	AND 
+	(SELECT MAX(time) FROM model_outputs)