Update functions.py

functions.py

@@ -1,13 +1,13 @@
-from datetime import datetime
+import datetime
 import requests
 import os
 import joblib
 import pandas as pd
-
 import json
-
+import numpy as np
+from sklearn.preprocessing import OrdinalEncoder
 from dotenv import load_dotenv
-load_dotenv()
+load_dotenv(override=True)
 
 
 def decode_features(df, feature_view):
@@ -89,9 +89,9 @@ def get_air_quality_data1():
 def get_air_quality_data():
     AIR_QUALITY_API_KEY = os.getenv('AIR_QUALITY_API_KEY')
     json = get_air_json(AIR_QUALITY_API_KEY)
-    print(json)
+    #print(json)
     iaqi = json['iaqi']
-    orecast = json['forecast']['daily']
+    forecast = json['forecast']['daily']
     return [
         json['aqi'],                 # AQI
         json['time']['s'][:10],      # Date
@@ -128,7 +128,7 @@ def get_air_quality_df1(data):
         data,
         columns=col_names
     )
-    new_data.date = new_data.date.apply(timestamp_2_time1)
+    new_data.date = new_data.date.apply(timestamp_2_time)
 
     return new_data
 
@@ -170,13 +170,13 @@ def get_weather_data_weekly(start_date: datetime) -> pd.DataFrame:
     WEATHER_API_KEY = os.getenv('WEATHER_API_KEY')
     end_date = f"{start_date + datetime.timedelta(days=6):%Y-%m-%d}"
     json = requests.get(f'https://weather.visualcrossing.com/VisualCrossingWebServices/rest/services/timeline/Helsinki/{start_date}/{end_date}?unitGroup=metric&include=days&key={WEATHER_API_KEY}&contentType=json').json()
-    weather_data = answer['days']
+    weather_data = json['days']
     final_df = pd.DataFrame()
 
     for i in range(7):
         data = weather_data[i]
         list_of_data = [
-        json['address'].capitalize(),
+        #json['address'].lower(),
         data['datetime'],
         data['tempmax'],
         data['tempmin'],
@@ -202,7 +202,7 @@ def get_weather_data_weekly(start_date: datetime) -> pd.DataFrame:
         data['uvindex'],
         data['conditions']
     ]
-        weather_df = get_weather_df(list_of_data)
+        weather_df = get_weather_df_weekly(list_of_data)
         final_df = pd.concat([final_df, weather_df])
     return final_df
 
@@ -210,6 +210,7 @@ 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]
+    #print(data)
 
     return [
         json['address'].capitalize(),
@@ -240,6 +241,45 @@ def get_weather_data(date):
     ]
 
 
+def get_weather_df_weekly(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
+    ).T
+    new_data.columns = col_names
+    for col in col_names:
+        if col not in ['name', 'date', 'conditions']:
+            new_data[col] = pd.to_numeric(new_data[col])
+
+    return new_data
+
 def get_weather_df(data):
     col_names = [
         'city',
@@ -273,16 +313,49 @@ def get_weather_df(data):
         data,
         columns=col_names
     )
-    new_data.date = new_data.date.apply(timestamp_2_time1)
+    new_data.date = new_data.date.apply(timestamp_2_time)
 
     return new_data
 
 def timestamp_2_time1(x):
-    dt_obj = datetime.strptime(str(x), '%Y-%m-%d')
+    dt_obj = datetime.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 = datetime.datetime.strptime(str(x), '%Y-%m-%d')
     dt_obj = dt_obj.timestamp() * 1000
     return int(dt_obj)
+
+def data_encoder(X):
+    #print(X)
+    X.drop(columns=['date'], inplace=True)
+    X['conditions'] = OrdinalEncoder().fit_transform(X[['conditions']])
+    return X
+
+def transform(df):
+    df.loc[df["windgust"].isna(),'windgust'] = df['windspeed']
+    df['snow'].fillna(0,inplace=True)
+    df['snowdepth'].fillna(0, inplace=True)
+    df['pressure'].fillna(df['pressure'].mean(), inplace=True)
+    return df
+
+
+def get_aplevel(temps:np.ndarray) -> list:
+    boundary_list = np.array([0, 50, 100, 150, 200, 300]) # assert temps.shape == [x, 1]
+    redf = np.logical_not(temps<=boundary_list) # temps.shape[0] x boundary_list.shape[0] ndarray
+    hift = np.concatenate((np.roll(redf, -1)[:, :-1], np.full((temps.shape[0], 1), False)), axis = 1)
+    cat = np.nonzero(np.not_equal(redf,hift))
+
+    air_pollution_level = ['Good', 'Moderate', 'Unhealthy for sensitive Groups','Unhealthy' ,'Very Unhealthy', 'Hazardous']
+    level = [air_pollution_level[el] for el in cat[1]]
+    return level
+
+def encoder_range(temps):
+    boundary_list = np.array([0, 50, 100, 150, 200, 300]) 
+    redf = np.logical_not(temps<=boundary_list) 
+    hift = np.concatenate((np.roll(redf, -1)[:, :-1], np.full((temps.shape[0], 1), False)), axis = 1)
+    cat = np.nonzero(np.not_equal(redf,hift))
+    air_pollution_level = ['Good', 'Moderate', 'Unhealthy for sensitive Groups','Unhealthy' ,'Very Unhealthy', 'Hazardous']
+    level = [air_pollution_level[el] for el in cat[1]]
+    return level