File size: 4,686 Bytes
69a2a60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
from datetime import datetime
import requests
import os
import joblib
import pandas as pd

import json


def decode_features(df, feature_view):
    """Decodes features in the input DataFrame using corresponding Hopsworks Feature Store transformation functions"""
    df_res = df.copy()

    import inspect


    td_transformation_functions = feature_view._batch_scoring_server._transformation_functions

    res = {}
    for feature_name in td_transformation_functions:
        if feature_name in df_res.columns:
            td_transformation_function = td_transformation_functions[feature_name]
            sig, foobar_locals = inspect.signature(td_transformation_function.transformation_fn), locals()
            param_dict = dict([(param.name, param.default) for param in sig.parameters.values() if param.default != inspect._empty])
            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"])
            elif td_transformation_function.name == "label_encoder":
                dictionary = param_dict['value_to_index']
                dictionary_ = {v: k for k, v in dictionary.items()}
                df_res[feature_name] = df_res[feature_name].map(
                    lambda x: dictionary_[x])
    return df_res


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_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)