Update functions.py

functions.py

@@ -3,7 +3,6 @@ import requests
 import os
 import joblib
 import pandas as pd
-
 import json
 
 
@@ -11,9 +10,9 @@ def decode_features(df, feature_view):
     """Decodes features in the input DataFrame using corresponding Hopsworks Feature Store transformation functions"""
     df_res = df.copy()
 
+    print(df_res)
     import inspect
 
-
     td_transformation_functions = feature_view._batch_scoring_server._transformation_functions
 
     res = {}
@@ -25,7 +24,6 @@ def decode_features(df, feature_view):
             if td_transformation_function.name == "min_max_scaler":
                 df_res[feature_name] = df_res[feature_name].map(
                     lambda x: x * (param_dict["max_value"] - param_dict["min_value"]) + param_dict["min_value"])
-
             elif td_transformation_function.name == "standard_scaler":
                 df_res[feature_name] = df_res[feature_name].map(
                     lambda x: x * param_dict['std_dev'] + param_dict["mean"])
@@ -36,115 +34,53 @@ def decode_features(df, feature_view):
                     lambda x: dictionary_[x])
     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"""
-    TARGET_FILE = "model_temp.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_temp.pkl")
-
-    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_csv():
+    return requests.get(f'https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/shanghai?unitGroup=metric&include=days&key=FYYH5HKD9558HBXD2D6KWXDGH&contentType=csv').csv()
 
-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]
+def get_weather_json_quick(date):
+    return requests.get(f'https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/shanghai/{date}?unitGroup=metric&include=days&key=FYYH5HKD9558HBXD2D6KWXDGH&contentType=json').json()
 
-    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_data(json):
+    #WEATHER_API_KEY = os.getenv('WEATHER_API_KEY')
+    
+    #csv = get_weather_csv()
+    data = json['days'][0]
+    print("data parsed sccessfully")
+    #return [
+    #    #json['address'].capitalize(),
+    #    data['datetime'],
+    #    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']
+    #]
+    return data
 
 
 def get_weather_df(data):
     col_names = [
-        'city',
-        'date',
+        'name',
+        'datetime',
         'tempmax',
         'tempmin',
         'temp',
@@ -161,7 +97,7 @@ def get_weather_df(data):
         'windgust',
         'windspeed',
         'winddir',
-        'pressure',
+        'sealevelpressure',
         'cloudcover',
         'visibility',
         'solarradiation',
@@ -170,12 +106,14 @@ def get_weather_df(data):
         'conditions'
     ]
 
+    
+
     new_data = pd.DataFrame(
         data,
         columns=col_names
     )
-    new_data.date = new_data.date.apply(timestamp_2_time1)
-
+    new_data.datetime = new_data.datetime.apply(timestamp_2_time1)
+    #new_data.rename(columes={'pressure':'sealevelpressure'})
     return new_data
 
 def timestamp_2_time1(x):