data finally working

app.py

@@ -15,6 +15,7 @@ st.set_page_config(
 
 alt.themes.enable("dark")
 
+model_NO2, model_O3 = load_models()
 week_data, predictions_O3, predictions_NO2 = get_data_and_predictions()
 today = week_data.iloc[-1]
 previous_day = week_data.iloc[-2]

predictions_history.csv

@@ -0,0 +1,7 @@
+pollutant,date_predicted,date,prediction_value
+O3,2024-10-24,2024-10-25,10.33808859423279
+NO2,2024-10-24,2024-10-25,25.68519991558237
+O3,2024-10-24,2024-10-26,16.000984317626852
+NO2,2024-10-24,2024-10-26,25.760307451092384
+O3,2024-10-24,2024-10-27,19.64377495640328
+NO2,2024-10-24,2024-10-27,31.210576791105115

src/predict.py

@@ -3,43 +3,53 @@ from datetime import date, timedelta
 
 import joblib
 import pandas as pd
+import streamlit as st
 from dotenv import load_dotenv
 from huggingface_hub import hf_hub_download, login
+
 from src.data_api_calls import get_combined_data
 from src.features_pipeline import create_features
 
+load_dotenv()
+
 
-def load_model(particle):
-    load_dotenv()
+st.cache_resource()
+def load_models():
     login(token=os.getenv("HUGGINGFACE_DOWNLOAD_TOKEN"))
 
-    repo_id = f"elisaklunder/Utrecht-{particle}-Forecasting-Model"
-    if particle == "O3":
-        file_name = "O3_svr_model.pkl"
-    elif particle == "NO2":
-        file_name = "NO2_svr_model.pkl"
+    model_path = hf_hub_download(
+        repo_id="elisaklunder/Utrecht-O3-Forecasting-Model", filename="O3_svr_model.pkl"
+    )
+    model_NO2 = joblib.load(model_path)
+
+    model_path = hf_hub_download(
+        repo_id="elisaklunder/Utrecht-NO2-Forecasting-Model",
+        filename="NO2_svr_model.pkl",
+    )
+    model_O3 = joblib.load(model_path)
+    return model_NO2, model_O3
 
-    model_path = hf_hub_download(repo_id=repo_id, filename=file_name)
-    model = joblib.load(model_path)
-    return model
 
+def run_models(model_NO2, model_O3, data):
+    input_data = create_features(data=data, target_particle="NO2")
+    prediction = model_NO2.predict(input_data)
+    target_scaler = joblib.load("scalers/target_scaler_NO2.joblib")
+    prediction_NO2 = target_scaler.inverse_transform(prediction)
 
-def run_model(particle, data):
-    input_data = create_features(data=data, target_particle=particle)
-    model = load_model(particle)
-    prediction = model.predict(input_data)
-    target_scaler = joblib.load(f"scalers/target_scaler_{particle}.joblib")
-    prediction = target_scaler.inverse_transform(prediction)
-    return prediction
+    input_data = create_features(data=data, target_particle="O3")
+    prediction = model_O3.predict(input_data)
+    target_scaler = joblib.load("scalers/target_scaler_O3.joblib")
+    prediction_O3 = target_scaler.inverse_transform(prediction)
 
+    return prediction_NO2, prediction_O3
 
-def get_data_and_predictions():
+st.cache_resource(ttl=300 * 24)
+def get_data_and_predictions(model_NO2, model_O3):
     PREDICTIONS_FILE = "predictions_history.csv"
 
     week_data = get_combined_data()
 
-    o3_predictions = run_model("O3", data=week_data)
-    no2_predictions = run_model("NO2", data=week_data)
+    o3_predictions, no2_predictions = run_models(model_NO2, model_O3, week_data)
 
     prediction_data = []
     for i in range(3):