Spaces:
No application file
No application file
Delete functions.py
Browse files- functions.py +0 -138
functions.py
DELETED
@@ -1,138 +0,0 @@
|
|
1 |
-
import requests
|
2 |
-
import os
|
3 |
-
import joblib
|
4 |
-
import pandas as pd
|
5 |
-
import datetime
|
6 |
-
import numpy as np
|
7 |
-
import time
|
8 |
-
from sklearn.preprocessing import OrdinalEncoder
|
9 |
-
from dotenv import load_dotenv
|
10 |
-
load_dotenv(override=True)
|
11 |
-
|
12 |
-
|
13 |
-
def decode_features(df, feature_view):
|
14 |
-
"""Decodes features in the input DataFrame using corresponding Hopsworks Feature Store transformation functions"""
|
15 |
-
df_res = df.copy()
|
16 |
-
|
17 |
-
import inspect
|
18 |
-
|
19 |
-
|
20 |
-
td_transformation_functions = feature_view._batch_scoring_server._transformation_functions
|
21 |
-
|
22 |
-
res = {}
|
23 |
-
for feature_name in td_transformation_functions:
|
24 |
-
if feature_name in df_res.columns:
|
25 |
-
td_transformation_function = td_transformation_functions[feature_name]
|
26 |
-
sig, foobar_locals = inspect.signature(td_transformation_function.transformation_fn), locals()
|
27 |
-
param_dict = dict([(param.name, param.default) for param in sig.parameters.values() if param.default != inspect._empty])
|
28 |
-
if td_transformation_function.name == "min_max_scaler":
|
29 |
-
df_res[feature_name] = df_res[feature_name].map(
|
30 |
-
lambda x: x * (param_dict["max_value"] - param_dict["min_value"]) + param_dict["min_value"])
|
31 |
-
|
32 |
-
elif td_transformation_function.name == "standard_scaler":
|
33 |
-
df_res[feature_name] = df_res[feature_name].map(
|
34 |
-
lambda x: x * param_dict['std_dev'] + param_dict["mean"])
|
35 |
-
elif td_transformation_function.name == "label_encoder":
|
36 |
-
dictionary = param_dict['value_to_index']
|
37 |
-
dictionary_ = {v: k for k, v in dictionary.items()}
|
38 |
-
df_res[feature_name] = df_res[feature_name].map(
|
39 |
-
lambda x: dictionary_[x])
|
40 |
-
return df_res
|
41 |
-
|
42 |
-
|
43 |
-
def get_model(project, model_name, evaluation_metric, sort_metrics_by):
|
44 |
-
"""Retrieve desired model or download it from the Hopsworks Model Registry.
|
45 |
-
In second case, it will be physically downloaded to this directory"""
|
46 |
-
TARGET_FILE = "model.pkl"
|
47 |
-
list_of_files = [os.path.join(dirpath,filename) for dirpath, _, filenames \
|
48 |
-
in os.walk('.') for filename in filenames if filename == TARGET_FILE]
|
49 |
-
|
50 |
-
if list_of_files:
|
51 |
-
model_path = list_of_files[0]
|
52 |
-
model = joblib.load(model_path)
|
53 |
-
else:
|
54 |
-
if not os.path.exists(TARGET_FILE):
|
55 |
-
mr = project.get_model_registry()
|
56 |
-
# get best model based on custom metrics
|
57 |
-
model = mr.get_best_model(model_name,
|
58 |
-
evaluation_metric,
|
59 |
-
sort_metrics_by)
|
60 |
-
model_dir = model.download()
|
61 |
-
model = joblib.load(model_dir + "/model.pkl")
|
62 |
-
|
63 |
-
return model
|
64 |
-
|
65 |
-
|
66 |
-
def get_weather_data_weekly(city: str, start_date: datetime) -> pd.DataFrame:
|
67 |
-
#WEATHER_API_KEY = os.getenv('WEATHER_API_KEY')
|
68 |
-
##end_date = f"{start_date + datetime.timedelta(days=6):%Y-%m-%d}"
|
69 |
-
next7days_weather=pd.read_csv('https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/Beijing/next7days?unitGroup=metric&include=days&key=5WNL2M94KKQ4R4F32LFV8DPE4&contentType=csv')
|
70 |
-
#answer = requests.get(f'https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/{city}/{start_date}/{end_date}?unitGroup=metric&include=days&key={WEATHER_API_KEY}&contentType=json').json()
|
71 |
-
|
72 |
-
|
73 |
-
df_weather = pd.DataFrame(next7days_weather)
|
74 |
-
df_weather.rename(columns = {"datetime": "date"},
|
75 |
-
inplace = True)
|
76 |
-
df_weather.rename(columns = {"name": "city"},
|
77 |
-
inplace = True)
|
78 |
-
df_weather.rename(columns = {"sealevelpressure": "pressure"},
|
79 |
-
inplace = True)
|
80 |
-
df_weather = df_weather.drop(labels=['city','dew','precip','tempmax','pressure','tempmin','temp','feelslikemax','feelslikemin','feelslike','precipprob','precipcover','snow','snowdepth','cloudcover','severerisk','moonphase','preciptype','sunrise','sunset','conditions','description','icon','stations'], axis=1) #删除不用的列
|
81 |
-
|
82 |
-
return df_weather
|
83 |
-
|
84 |
-
def get_weather_df(data):
|
85 |
-
col_names = [
|
86 |
-
'name',
|
87 |
-
'date',
|
88 |
-
'tempmax',
|
89 |
-
'tempmin',
|
90 |
-
'temp',
|
91 |
-
'feelslikemax',
|
92 |
-
'feelslikemin',
|
93 |
-
'feelslike',
|
94 |
-
'dew',
|
95 |
-
'humidity',
|
96 |
-
'precip',
|
97 |
-
'precipprob',
|
98 |
-
'precipcover',
|
99 |
-
'snow',
|
100 |
-
'snowdepth',
|
101 |
-
'windgust',
|
102 |
-
'windspeed',
|
103 |
-
'winddir',
|
104 |
-
'pressure',
|
105 |
-
'cloudcover',
|
106 |
-
'visibility',
|
107 |
-
'solarradiation',
|
108 |
-
'solarenergy',
|
109 |
-
'uvindex',
|
110 |
-
'conditions'
|
111 |
-
]
|
112 |
-
|
113 |
-
new_data = pd.DataFrame(
|
114 |
-
data
|
115 |
-
).T
|
116 |
-
new_data.columns = col_names
|
117 |
-
for col in col_names:
|
118 |
-
if col not in ['name', 'date', 'conditions']:
|
119 |
-
new_data[col] = pd.to_numeric(new_data[col])
|
120 |
-
|
121 |
-
return new_data
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
def get_aplevel(temps:np.ndarray) -> list:
|
126 |
-
boundary_list = np.array([0, 50, 100, 150, 200, 300]) # assert temps.shape == [x, 1]
|
127 |
-
redf = np.logical_not(temps<=boundary_list) # temps.shape[0] x boundary_list.shape[0] ndarray
|
128 |
-
hift = np.concatenate((np.roll(redf, -1)[:, :-1], np.full((temps.shape[0], 1), False)), axis = 1)
|
129 |
-
cat = np.nonzero(np.not_equal(redf,hift))
|
130 |
-
|
131 |
-
air_pollution_level = ['Good', 'Moderate', 'Unhealthy for sensitive Groups','Unhealthy' ,'Very Unhealthy', 'Hazardous']
|
132 |
-
level = [air_pollution_level[el] for el in cat[1]]
|
133 |
-
return level
|
134 |
-
|
135 |
-
def timestamp_2_time(x):
|
136 |
-
dt_obj = datetime.datetime.strptime(str(x), '%Y-%m-%d')
|
137 |
-
dt_obj = dt_obj.timestamp() * 1000
|
138 |
-
return int(dt_obj)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|