functions.py

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()

    print(df_res)
    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_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_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()


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 = [
        'name',
        'datetime',
        'tempmax',
        'tempmin',
        'temp',
        'feelslikemax',
        'feelslikemin',
        'feelslike',
        'dew',
        'humidity',
        'precip',
        'precipprob',
        'precipcover',
        'snow',
        'snowdepth',
        'windgust',
        'windspeed',
        'winddir',
        'sealevelpressure',
        'cloudcover',
        'visibility',
        'solarradiation',
        'solarenergy',
        'uvindex',
        'conditions'
    ]

    

    new_data = pd.DataFrame(
        data,
        columns=col_names
    )
    new_data.datetime = new_data.datetime.apply(timestamp_2_time1)
    #new_data.rename(columes={'pressure':'sealevelpressure'})
    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)