Update functions.py

functions.py

@@ -37,6 +37,48 @@ def decode_features(df, feature_view):
     return df_res
 
 
+def get_model1(project, model_name, evaluation_metric, sort_metrics_by):
+    """Retrieve desired model or download it from the Hopsworks Model Registry.
+    In second case, it will be physically downloaded to this directory"""
+    TARGET_FILE = "model_tempmax.pkl"
+    list_of_files = [os.path.join(dirpath,filename) for dirpath, _, filenames \
+                     in os.walk('.') for filename in filenames if filename == TARGET_FILE]
+
+    if list_of_files:
+        model_path = list_of_files[0]
+        model = joblib.load(model_path)
+    else:
+        if not os.path.exists(TARGET_FILE):
+            mr = project.get_model_registry()
+            # get best model based on custom metrics
+            model = mr.get_best_model(model_name,
+                                      evaluation_metric,
+                                      sort_metrics_by)
+            model_dir = model.download()
+            model = joblib.load(model_dir + "/model_tempmax.pkl")
+
+    return model
+def get_model2(project, model_name, evaluation_metric, sort_metrics_by):
+    """Retrieve desired model or download it from the Hopsworks Model Registry.
+    In second case, it will be physically downloaded to this directory"""
+    TARGET_FILE = "model_tempmin.pkl"
+    list_of_files = [os.path.join(dirpath,filename) for dirpath, _, filenames \
+                     in os.walk('.') for filename in filenames if filename == TARGET_FILE]
+
+    if list_of_files:
+        model_path = list_of_files[0]
+        model = joblib.load(model_path)
+    else:
+        if not os.path.exists(TARGET_FILE):
+            mr = project.get_model_registry()
+            # get best model based on custom metrics
+            model = mr.get_best_model(model_name,
+                                      evaluation_metric,
+                                      sort_metrics_by)
+            model_dir = model.download()
+            model = joblib.load(model_dir + "/model_tempmin.pkl")
+
+    return model
 def get_model(project, model_name, evaluation_metric, sort_metrics_by):
     """Retrieve desired model or download it from the Hopsworks Model Registry.
     In second case, it will be physically downloaded to this directory"""
@@ -59,89 +101,3 @@ def get_model(project, model_name, evaluation_metric, sort_metrics_by):
 
     return model
 
-
-
-def get_weather_json(date, WEATHER_API_KEY):
-    return requests.get(f'https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/helsinki/{date}?unitGroup=metric&include=days&key={WEATHER_API_KEY}&contentType=json').json()
-
-
-def get_weather_data(date):
-    WEATHER_API_KEY = os.getenv('WEATHER_API_KEY')
-    json = get_weather_json(date, WEATHER_API_KEY)
-    data = json['days'][0]
-
-    return [
-        json['address'].capitalize(),
-        data['datetime'],
-        data['tempmax'],
-        data['tempmin'],
-        data['temp'],
-        data['feelslikemax'],
-        data['feelslikemin'],
-        data['feelslike'],
-        data['dew'],
-        data['humidity'],
-        data['precip'],
-        data['precipprob'],
-        data['precipcover'],
-        data['snow'],
-        data['snowdepth'],
-        data['windgust'],
-        data['windspeed'],
-        data['winddir'],
-        data['pressure'],
-        data['cloudcover'],
-        data['visibility'],
-        data['solarradiation'],
-        data['solarenergy'],
-        data['uvindex'],
-        data['conditions']
-    ]
-
-
-def get_weather_df(data):
-    col_names = [
-        'city',
-        'date',
-        'tempmax',
-        'tempmin',
-        'temp',
-        'feelslikemax',
-        'feelslikemin',
-        'feelslike',
-        'dew',
-        'humidity',
-        'precip',
-        'precipprob',
-        'precipcover',
-        'snow',
-        'snowdepth',
-        'windgust',
-        'windspeed',
-        'winddir',
-        'pressure',
-        'cloudcover',
-        'visibility',
-        'solarradiation',
-        'solarenergy',
-        'uvindex',
-        'conditions'
-    ]
-
-    new_data = pd.DataFrame(
-        data,
-        columns=col_names
-    )
-    new_data.date = new_data.date.apply(timestamp_2_time1)
-
-    return new_data
-
-def timestamp_2_time1(x):
-    dt_obj = datetime.strptime(str(x), '%Y-%m-%d')
-    dt_obj = dt_obj.timestamp() * 1000
-    return int(dt_obj)
-
-def timestamp_2_time(x):
-    dt_obj = datetime.strptime(str(x), '%m/%d/%Y')
-    dt_obj = dt_obj.timestamp() * 1000
-    return int(dt_obj)