NN implementation

app.py

@@ -2,6 +2,7 @@ import altair as alt
 import pandas as pd
 import plotly.graph_objects as go
 import streamlit as st
+
 from src.helper_functions import custom_metric_box, pollution_box
 from src.predict import get_data_and_predictions, update_data_and_predictions
 
@@ -44,7 +45,8 @@ col1, col2 = st.columns((1, 3))
 # Create a 3-column layout
 with col1:
     st.subheader("Current Weather")
-
+    
+    
     custom_metric_box(
         label="🥵 Temperature",
         value=f"{round(today['mean_temp'] * 0.1)} °C",
@@ -74,38 +76,38 @@ with col1:
 with col2:
     st.subheader("Current Pollution Levels")
     sub1, sub2 = st.columns((1, 1))
-
+    
     # Ozone (O₃) Pollution Box
     with sub1:
         pollution_box(
             label="O<sub>3</sub>",
             value=f"{round(today['O3'])} µg/m³",
             delta=f"{round(int(today['O3']) - int(previous_day['O3']))} µg/m³",
-            threshold=120,
+            threshold=120
         )
         with st.expander("Learn more about O3", expanded=False):
             st.markdown(
                 """
                 *Ozone (O<sub>3</sub>)*: A harmful gas at ground level that can irritate the respiratory system and aggravate asthma.<br>
                 **Good/Bad**: "Good" means safe levels for most people, while "Bad" suggests harmful levels, especially for sensitive groups.
-                """,
+                """, 
                 unsafe_allow_html=True,
             )
-
+    
     # Nitrogen Dioxide (NO₂) Pollution Box
     with sub2:
         pollution_box(
             label="NO<sub>2</sub>",
             value=f"{round(today['NO2'])} µg/m³",
             delta=f"{round(int(today['NO2']) - int(previous_day['NO2']))} µg/m³",
-            threshold=40,
+            threshold=40
         )
         with st.expander("Learn more about NO2", expanded=False):
             st.markdown(
                 """
                 *Nitrogen Dioxide (NO<sub>2</sub>)*: A toxic gas that contributes to lung irritation and worsens asthma and other respiratory issues.<br>
                 **Good/Bad**: "Good" means safe air quality, while "Bad" indicates levels that could cause respiratory problems, especially for vulnerable individuals.
-                """,
+                """, 
                 unsafe_allow_html=True,
             )
 
@@ -116,12 +118,9 @@ with col2:
     def get_simple_color_scale(values, threshold):
         """Returns green for values below the threshold, orange for values between the threshold and 2x the threshold, and red for values above 2x the threshold."""
         return [
-            "#77C124"
-            if v < threshold
-            else "#E68B0A"
-            if v < 2 * threshold
-            else "#E63946"
-            for v in values
+            "#77C124" if v < threshold else 
+            "#E68B0A" if v < 2 * threshold else 
+            "#E63946" for v in values
         ]
 
     # O3 Bar Plot (threshold: 40)
@@ -143,17 +142,13 @@ with col2:
     )
 
     # Add predicted values with reduced opacity
-    predicted_o3_colors = get_simple_color_scale(
-        o3_future_values, 40
-    )  # Color for future values
+    predicted_o3_colors = get_simple_color_scale(o3_future_values, 40)  # Color for future values
     fig_o3.add_trace(
         go.Bar(
             x=df["Date"][-3:],  # Dates for predicted values
             y=o3_future_values,
             name="O3 Predicted",
-            marker=dict(
-                color=predicted_o3_colors, opacity=0.5
-            ),  # Set opacity to 0.5 for predictions
+            marker=dict(color=predicted_o3_colors, opacity=0.5),  # Set opacity to 0.5 for predictions
             hovertemplate="%{x|%d-%b-%Y}<br>%{y} µg/m³<extra></extra>",
         )
     )
@@ -184,7 +179,7 @@ with col2:
             tickangle=-45,
             tickcolor="gray",
         ),
-        showlegend=False,  # Disable legend
+        showlegend=False  # Disable legend
     )
 
     st.plotly_chart(fig_o3, key="fig_o3")
@@ -209,17 +204,13 @@ with col2:
     )
 
     # Add predicted values with reduced opacity
-    predicted_no2_colors = get_simple_color_scale(
-        no2_future_values, 120
-    )  # Color for future values
+    predicted_no2_colors = get_simple_color_scale(no2_future_values, 120)  # Color for future values
     fig_no2.add_trace(
         go.Bar(
             x=df["Date"][-3:],  # Dates for predicted values
             y=no2_future_values,
             name="NO2 Predicted",
-            marker=dict(
-                color=predicted_no2_colors, opacity=0.5
-            ),  # Set opacity to 0.5 for predictions
+            marker=dict(color=predicted_no2_colors, opacity=0.5),  # Set opacity to 0.5 for predictions
             hovertemplate="%{x|%d-%b-%Y}<br>%{y} µg/m³<extra></extra>",
         )
     )
@@ -250,7 +241,7 @@ with col2:
             tickangle=-45,
             tickcolor="gray",
         ),
-        showlegend=False,  # Disable legend
+        showlegend=False  # Disable legend
     )
 
-    st.plotly_chart(fig_no2, key="fig_no2")
+    st.plotly_chart(fig_no2, key="fig_no2")

past_pollution_data.csv

@@ -10,21 +10,9 @@ date,NO2,O3
 2023-10-26,21.53175675675676,13.3216
 2023-10-27,23.07226666666666,16.15416666666666
 2023-10-28,24.89121621621622,24.59040816326531
-2023-10-29,9.724428571428572,51.525200000000005
+2023-10-29,9.724428571428573,51.525200000000005
 2023-10-30,11.20205479452055,52.820600000000006
 2023-10-31,17.494666666666667,44.458541666666655
 2023-11-01,21.588095238095235,29.20631578947369
 2023-11-02,9.745714285714286,48.39760869565216
-2023-11-03,7.163243243243244,61.4216
-2023-11-04,12.660666666666666,45.56104166666666
-2023-11-05,9.990135135135136,48.3988
-2023-11-06,10.36972972972973,49.495
-2023-11-07,16.654864864864866,39.8696
-2023-11-08,15.846986301369862,44.5525
-2023-11-09,14.630533333333332,46.897551020408166
-2023-11-10,16.8868,46.03939999999999
-2023-11-10,16.8868,46.03939999999999
-2023-11-11,20.2668,40.0496
-2023-11-12,22.7086301369863,25.88854166666667
-2023-11-13,20.707466666666665,14.094000000000001
-2023-11-14,10.368082191780822,59.828599999999994
+2023-11-03,7.163243243243242,61.421599999999984

past_weather_data.csv

@@ -15,17 +15,4 @@ date,temp,humidity,precip,windspeed,sealevelpressure,visibility,solarradiation
 2023-10-30,11.2,90.4,13.0,18.4,997.5,28.8,27.0
 2023-10-31,11.0,93.7,18.6,18.0,1000.7,17.9,29.8
 2023-11-01,12.4,88.5,4.9,25.9,997.8,32.6,31.5
-2023-11-02,11.0,80.0,8.7,46.4,976.4,33.6,21.5
-2023-11-03,9.6,83.3,7.9,32.4,981.6,31.0,40.1
-2023-11-04,9.3,88.7,10.7,25.9,977.6,35.3,20.4
-2023-11-05,10.5,88.4,5.6,25.2,977.1,29.0,25.6
-2023-11-06,9.9,86.5,1.8,31.7,998.2,37.3,45.2
-2023-11-07,9.7,85.1,0.4,22.3,1007.3,41.1,63.6
-2023-11-08,9.3,91.9,17.0,28.8,1008.2,21.2,37.0
-2023-11-09,9.7,89.2,8.5,22.3,999.0,24.2,37.3
-2023-11-10,7.5,90.0,4.4,22.3,995.3,36.0,20.8
-2023-11-11,7.5,87.1,5.7,14.8,1003.3,40.0,25.2
-2023-11-12,5.7,96.8,0.1,14.8,1006.4,8.8,26.2
-2023-11-13,9.5,90.3,5.2,31.7,1000.8,9.6,9.8
-2023-11-14,12.2,84.4,11.1,29.5,1001.4,14.8,16.0
-2023-11-15,11.1,84.6,5.3,18.4,1011.9,21.4,22.8
+2023-11-02,11,80,8.7,46.4,976.4,33.6,21.5

pollution_data.csv

@@ -12,17 +12,4 @@ date,NO2,O3
 2024-10-27,27.53722134983982,20.80809239842384
 2024-10-28,23.337567567567568,26.82861788617886
 2024-10-29,16.53533209586906,23.28254887605004
-2024-10-30,22.26162162162162,18.03443548387097
-2024-10-31,24.919333333333334,20.79696
-2024-11-01,25.08013698630137,8.923140495867766
-2024-11-02,12.71013698630137,42.33314049586777
-2024-11-03,16.46013698630137,17.923140495867766
-2024-11-04,17.54013698630137,15.923140495867768
-2024-11-05,21.96013698630137,9.083140495867768
-2024-11-06,28.70013698630137,19.313140495867767
-2024-11-07,26.071060606060605,17.701454545454546
-2024-11-08,17.671060606060603,14.171454545454546
-2024-11-09,18.131060606060604,3.701454545454546
-2024-11-10,17.83082191780822,12.727355371900826
-2024-11-11,12.75082191780822,39.257355371900826
-2024-11-12,8.180147058823529,23.352807017543856
+2024-10-30,22.26162162162162,18.03443548387097

predictions_history.csv

@@ -1,7 +1,7 @@
 pollutant,date_predicted,date,prediction_value
 O3,2024-10-14,2024-10-17,31.25335185244893
 NO2,2024-10-14,2024-10-17,26.421736787446267
-O3,2024-10-15,2024-10-17,25.00005767760448
+O3,2024-10-15,2024-10-17,22.00005767760448
 NO2,2024-10-15,2024-10-17,28.59511317503212
 O3,2024-10-16,2024-10-17,9.657466070999735
 NO2,2024-10-16,2024-10-17,17.065168790519902
@@ -13,11 +13,11 @@ O3,2024-10-17,2024-10-18,16.08841798553393
 NO2,2024-10-17,2024-10-18,32.0458143607889
 O3,2024-10-16,2024-10-19,24.031357603260783
 NO2,2024-10-16,2024-10-19,20.08389395558791
-O3,2024-10-17,2024-10-19,20.031357603260783
+O3,2024-10-17,2024-10-19,21.031357603260783
 NO2,2024-10-17,2024-10-19,27.08389395558791
-O3,2024-10-17,2024-10-20,18.48486247979324
+O3,2024-10-17,2024-10-20,20.48486247979324
 NO2,2024-10-17,2024-10-20,23.84300578029378
-O3,2024-10-18,2024-10-19,25.304547122637445
+O3,2024-10-18,2024-10-19,22.304547122637445
 NO2,2024-10-18,2024-10-19,20.80017116560889
 O3,2024-10-18,2024-10-20,31.25335185244893
 NO2,2024-10-18,2024-10-20,29.732316066240585
@@ -25,15 +25,15 @@ O3,2024-10-18,2024-10-21,28.67755196805434
 NO2,2024-10-18,2024-10-21,35.04638743773354
 O3,2024-10-19,2024-10-20,26.421736787446267
 NO2,2024-10-19,2024-10-20,27.399885723190767
-O3,2024-10-19,2024-10-21,13.065168790519902
+O3,2024-10-19,2024-10-21,17.065168790519902
 NO2,2024-10-19,2024-10-21,18.992352714813563
 O3,2024-10-19,2024-10-22,17.39682962048955
 NO2,2024-10-19,2024-10-22,22.85061675885908
-O3,2024-10-20,2024-10-21,20.00005767760448
+O3,2024-10-20,2024-10-21,22.00005767760448
 NO2,2024-10-20,2024-10-21,18.27191592927812
 O3,2024-10-20,2024-10-22,29.00940466937953
 NO2,2024-10-20,2024-10-22,19.50739766963497
-O3,2024-10-20,2024-10-23,27.062134354543343
+O3,2024-10-20,2024-10-23,20.062134354543343
 NO2,2024-10-20,2024-10-23,23.65746607099973
 O3,2024-10-21,2024-10-22,17.497382318189132
 NO2,2024-10-21,2024-10-22,28.59511317503212
@@ -41,135 +41,32 @@ O3,2024-10-21,2024-10-23,16.519952190354232
 NO2,2024-10-21,2024-10-23,30.192389708351826
 O3,2024-10-21,2024-10-24,28.19940385112904
 NO2,2024-10-21,2024-10-24,17.9525039623211
-O3,2024-10-22,2024-10-23,14.093074246425155
+O3,2024-10-22,2024-10-23,16.093074246425157
 NO2,2024-10-22,2024-10-23,25.217639978187005
 O3,2024-10-22,2024-10-24,23.605545201596552
 NO2,2024-10-22,2024-10-24,29.004701753536988
-O3,2024-10-22,2024-10-25,27.9847340998457
-NO2,2024-10-22,2024-10-25,21.09454928349811
 O3,2024-10-23,2024-10-24,26.56486295059828
 NO2,2024-10-23,2024-10-24,20.15373733747257
-O3,2024-10-23,2024-10-25,23.7837523402934
-NO2,2024-10-23,2024-10-25,17.8934409250984
-O3,2024-10-23,2024-10-26,28.9427902487123
-NO2,2024-10-23,2024-10-26,18.4259830043909
 O3,2024-10-24,2024-10-25,10.33808859423279
 NO2,2024-10-24,2024-10-25,25.68519991558237
-O3,2024-10-24,2024-10-26,12.000984317626852
+O3,2024-10-24,2024-10-26,16.000984317626852
 NO2,2024-10-24,2024-10-26,25.760307451092384
-O3,2024-10-24,2024-10-27,17.64377495640328
+O3,2024-10-24,2024-10-27,19.64377495640328
 NO2,2024-10-24,2024-10-27,31.210576791105115
 O3,2024-10-25,2024-10-26,20.48055947200643
 NO2,2024-10-25,2024-10-26,23.95723903986424
 O3,2024-10-25,2024-10-27,11.088152958498888
 NO2,2024-10-25,2024-10-27,32.274494671100506
 O3,2024-10-25,2024-10-28,-0.7175631399505704
-NO2,2024-10-25,2024-10-28,40.8610780001905
-O3,2024-10-26,2024-10-27,17.489498527754026
-NO2,2024-10-26,2024-10-27,15.98010248203777
-O3,2024-10-26,2024-10-28,18.2072938736443
-NO2,2024-10-26,2024-10-28,20.8453424245324
-O3,2024-10-26,2024-10-29,29.0932876923023
-NO2,2024-10-26,2024-10-29,18.2090842283492
-O3,2024-10-27,2024-10-28,23.123594856598
-NO2,2024-10-27,2024-10-28,16.217932302093
-O3,2024-10-27,2024-10-29,19.503484893273
-NO2,2024-10-27,2024-10-29,22.023348685
-O3,2024-10-27,2024-10-30,21.6890289354354
-NO2,2024-10-27,2024-10-30,23.27534807834
+NO2,2024-10-25,2024-10-28,40.86107800019054
 O3,2024-10-28,2024-10-29,22.13652238154496
 NO2,2024-10-28,2024-10-29,31.608886931951144
 O3,2024-10-28,2024-10-30,15.841669224
 NO2,2024-10-28,2024-10-30,34.564284711452984
 O3,2024-10-28,2024-10-31,22.35944571003375
 NO2,2024-10-28,2024-10-31,34.37482132111927
-O3,2024-10-29,2024-10-30,20.53543580394545
-NO2,2024-10-29,2024-10-30,18.74548598422698
-O3,2024-10-29,2024-10-31,18.36287520452959
-NO2,2024-10-29,2024-10-31,17.2457634958273
-O3,2024-10-29,2024-11-01,16.9829845792475
-NO2,2024-10-29,2024-11-01,15.984094509529
 O3,2024-10-30,2024-10-31,15.98046542733637
 NO2,2024-10-30,2024-10-31,29.77507241979599
 O3,2024-10-30,2024-11-01,21.135906183680472
 NO2,2024-10-30,2024-11-01,28.38872595850704
 O3,2024-10-30,2024-11-02,19.67426015042635
-NO2,2024-10-30,2024-11-02,26.9572340984345
-O3,2024-10-31,2024-11-01,16.491393851863755
-NO2,2024-10-31,2024-11-01,17.22825222459993
-O3,2024-10-31,2024-11-02,16.874728806873033
-NO2,2024-10-31,2024-11-02,14.771381333796963
-O3,2024-10-31,2024-11-03,15.244292496093546
-NO2,2024-10-31,2024-11-03,14.606430068166452
-NO2,2024-11-01,2024-11-02,27.60903681874446
-O3,2024-11-01,2024-11-02,34.42005311364765
-NO2,2024-11-01,2024-11-03,27.60903681874446
-O3,2024-11-01,2024-11-03,11.420053113647649
-NO2,2024-11-01,2024-11-04,27.60903681874446
-O3,2024-11-01,2024-11-04,11.420053113647649
-NO2,2024-11-02,2024-11-03,28.648331465973826
-O3,2024-11-02,2024-11-03,19.22638136470001
-NO2,2024-11-02,2024-11-04,28.648331465973826
-O3,2024-11-02,2024-11-04,19.22638136470001
-NO2,2024-11-02,2024-11-05,28.648331465973826
-O3,2024-11-02,2024-11-05,19.22638136470001
-NO2,2024-11-03,2024-11-04,27.00186266225546
-O3,2024-11-03,2024-11-04,21.27062113852946
-NO2,2024-11-03,2024-11-05,27.00186266225546
-O3,2024-11-03,2024-11-05,26.27062113852946
-NO2,2024-11-03,2024-11-06,27.00186266225546
-O3,2024-11-03,2024-11-06,26.27062113852946
-NO2,2024-11-04,2024-11-05,15.639721183473046
-O3,2024-11-04,2024-11-05,17.485704138409645
-NO2,2024-11-04,2024-11-06,15.639721183473046
-O3,2024-11-04,2024-11-06,28.485704138409645
-NO2,2024-11-04,2024-11-07,15.639721183473046
-O3,2024-11-04,2024-11-07,28.485704138409645
-NO2,2024-11-05,2024-11-06,21.25135096675789
-O3,2024-11-05,2024-11-06,14.976870014538976
-NO2,2024-11-05,2024-11-07,21.25135096675789
-O3,2024-11-05,2024-11-07,14.976870014538976
-NO2,2024-11-05,2024-11-08,21.25135096675789
-O3,2024-11-05,2024-11-08,14.976870014538976
-O3,2024-11-06,2024-11-07,19.68971431379357
-NO2,2024-11-06,2024-11-07,23.084000795655953
-O3,2024-11-06,2024-11-08,13.40804818820844
-NO2,2024-11-06,2024-11-08,14.957130244115683
-O3,2024-11-06,2024-11-09,22.03985252007605
-NO2,2024-11-06,2024-11-09,10.588264867150572
-O3,2024-11-07,2024-11-08,10.140579432131872
-NO2,2024-11-07,2024-11-08,26.943305282744824
-O3,2024-11-07,2024-11-09,14.726872459118134
-NO2,2024-11-07,2024-11-09,16.882629842776268
-O3,2024-11-07,2024-11-10,19.411520595892956
-NO2,2024-11-07,2024-11-10,11.844857190714402
-O3,2024-11-8,2024-11-9,6.594300618755156
-NO2,2024-11-8,2024-11-9,19.24076043419152
-O3,2024-11-8,2024-11-10,13.499823957840668
-NO2,2024-11-8,2024-11-10,18.48512032218451
-O3,2024-11-8,2024-11-11,11.875179042709217
-NO2,2024-11-8,2024-11-11,16.574502215589668
-O3,2024-11-9,2024-11-10,13.499823957840668
-NO2,2024-11-9,2024-11-10,18.48512032218451
-O3,2024-11-9,2024-11-11,9.499823957840668
-NO2,2024-11-9,2024-11-11,18.48512032218451
-O3,2024-11-9,2024-11-12,11.875179042709217
-NO2,2024-11-9,2024-11-12,16.574502215589668
-O3,2024-11-10,2024-11-11,16.594300618755156
-NO2,2024-11-10,2024-11-11,19.24076043419152
-O3,2024-11-10,2024-11-12,9.499823957840668
-NO2,2024-11-10,2024-11-12,18.48512032218451
-O3,2024-11-10,2024-11-13,11.875179042709217
-NO2,2024-11-10,2024-11-13,16.574502215589668
-O3,2024-11-11,2024-11-12,16.247626282257677
-NO2,2024-11-11,2024-11-12,19.094817776178502
-O3,2024-11-11,2024-11-13,16.676783602296
-NO2,2024-11-11,2024-11-13,16.50993839661109
-O3,2024-11-11,2024-11-14,24.877041509403615
-NO2,2024-11-11,2024-11-14,10.777386108715564
-O3,2024-11-12,2024-11-13,16.247626282257677
-NO2,2024-11-12,2024-11-13,19.094817776178502
-O3,2024-11-12,2024-11-14,16.676783602296
-NO2,2024-11-12,2024-11-14,16.50993839661109
-O3,2024-11-12,2024-11-15,24.877041509403615
-NO2,2024-11-12,2024-11-15,10.777386108715564

requirements.txt

@@ -10,5 +10,3 @@ http.client
 datetime
 huggingface-hub
 python-dotenv
-torch
-safetensors

src/data_api_calls.py

@@ -14,11 +14,7 @@ WEATHER_DATA_FILE = "weather_data.csv"
 POLLUTION_DATA_FILE = "pollution_data.csv"
 
 
-def update_weather_data() -> None:
-    """
-    Updates weather data by fetching data.
-    If the data file exists, it appends new data. If not, it creates a new file.
-    """
+def update_weather_data():
     today = date.today().isoformat()
 
     if os.path.exists(WEATHER_DATA_FILE):
@@ -54,11 +50,7 @@ def update_weather_data() -> None:
         sys.exit()
 
 
-def update_pollution_data() -> None:
-    """
-    Updates pollution data for NO2 and O3.
-    The new data is appended to the existing pollution data file.
-    """
+def update_pollution_data():
     O3 = []
     NO2 = []
     particles = ["NO2", "O3"]
@@ -121,21 +113,14 @@ def update_pollution_data() -> None:
     updated_data.to_csv(POLLUTION_DATA_FILE, index=False)
 
 
-def get_combined_data() -> pd.DataFrame:
-    """
-    Combines weather and pollution data for the last 7 days.
+def get_combined_data():
 
-    Returns:
-        pd.DataFrame: A DataFrame containing the combined weather and pollution data.
-    """
     weather_df = pd.read_csv(WEATHER_DATA_FILE)
-
+    
     today = pd.Timestamp.now().normalize()
     seven_days_ago = today - pd.Timedelta(days=7)
     weather_df["date"] = pd.to_datetime(weather_df["date"])
-    weather_df = weather_df[
-        (weather_df["date"] >= seven_days_ago) & (weather_df["date"] <= today)
-    ]
+    weather_df = weather_df[(weather_df["date"] >= seven_days_ago) & (weather_df["date"] <= today)]
 
     weather_df.insert(1, "NO2", None)
     weather_df.insert(2, "O3", None)
@@ -183,9 +168,7 @@ def get_combined_data() -> pd.DataFrame:
     pollution_df = pd.read_csv(POLLUTION_DATA_FILE)
 
     pollution_df["date"] = pd.to_datetime(pollution_df["date"])
-    pollution_df = pollution_df[
-        (pollution_df["date"] >= seven_days_ago) & (pollution_df["date"] <= today)
-    ]
+    pollution_df = pollution_df[(pollution_df["date"] >= seven_days_ago) & (pollution_df["date"] <= today)]
 
     combined_df["NO2"] = pollution_df["NO2"]
     combined_df["O3"] = pollution_df["O3"]

src/features_pipeline.py

@@ -6,6 +6,7 @@ import numpy as np
 import pandas as pd
 from dotenv import load_dotenv
 from huggingface_hub import hf_hub_download, login
+
 from src.past_data_api_calls import get_past_combined_data
 
 warnings.filterwarnings("ignore")
@@ -15,44 +16,11 @@ login(token=os.getenv("HUGGINGFACE_DOWNLOAD_TOKEN"))
 
 
 def create_features(
-    data: pd.DataFrame,
-    target_particle: str,  # Added this parameter
-    lag_days: int = 7,
-    sma_days: int = 7,
-) -> pd.DataFrame:
-    """
-    Create features for predicting air quality particles (NO2 or O3) based on historical weather data.
-
-    This function performs several feature engineering tasks, including:
-    - Creating lagged features for specified pollutants.
-    - Calculating rolling mean (SMA) features.
-    - Adding sine and cosine transformations of the weekday and month.
-    - Incorporating historical data for the same date in the previous year.
-
-    Parameters:
-    ----------
-    data : pd.DataFrame
-        A DataFrame containing historical weather and air quality data with a 'date' column.
-
-    target_particle : str
-        The target particle for prediction, must be either 'O3' or 'NO2'.
-
-    lag_days : int, optional
-        The number of days for which lagged features will be created. Default is 7.
-
-    sma_days : int, optional
-        The window size for calculating the simple moving average (SMA). Default is 7.
-
-    Returns:
-    -------
-    pd.DataFrame
-        A DataFrame containing the transformed features, ready for modeling.
-
-    Raises:
-    ------
-    ValueError
-        If target_particle is not 'O3' or 'NO2'.
-    """
+    data,
+    target_particle,  # Added this parameter
+    lag_days=7,
+    sma_days=7,
+):
     lag_features = [
         "NO2",
         "O3",

src/helper_functions.py

@@ -1,26 +1,9 @@
 import streamlit as st
 
 
-def custom_metric_box(label: str, value: str) -> None:
-    """
-    Create a styled metric box with a compact layout.
-
-    This function generates a styled markdown box displaying a label and its corresponding value.
-
-    Parameters:
-    ----------
-    label : str
-        The text label to display in the metric box.
-
-    value : str
-        The value to be displayed in the metric box, typically representing a metric.
-
-    Returns:
-    -------
-    None
-    """
-    st.markdown(
-        f"""
+# Custom function to create styled metric boxes with compact layout
+def custom_metric_box(label, value):
+    st.markdown(f"""
         <div style="
             padding: 5px;
             margin-bottom: 5px;
@@ -36,42 +19,17 @@ def custom_metric_box(label: str, value: str) -> None:
                 <p style="font-size: 18px; font-weight: bold; margin: 0;">{value}</p>  <!-- Smaller metric -->
             </div>
         </div>
-    """,
-        unsafe_allow_html=True,
-    )
-
-
-def pollution_box(label: str, value: str, delta: str, threshold: float) -> None:
-    """
-    Create a pollution metric box with a side-by-side layout and fixed width.
-
-    This function generates a styled markdown box displaying pollution level status, value, and other related information.
-
-    Parameters:
-    ----------
-    label : str
-        The text label representing the type of pollution or metric.
-
-    value : str
-        The value of the pollution metric, typically a string that can be converted to a float.
-
-    delta : str
-        A string representing the change in pollution level, though not currently used in the rendering.
-
-    threshold : float
-        The threshold value to determine if the pollution level is "Good" or "Bad".
+    """, unsafe_allow_html=True)
 
-    Returns:
-    -------
-    None
-    """
+# Custom function to create pollution metric boxes with side-by-side layout for label and value
+# Custom function to create pollution metric boxes with side-by-side layout and fixed width
+def pollution_box(label, value, delta, threshold):
     # Determine if the pollution level is "Good" or "Bad"
     status = "Good" if float(value.split()[0]) < threshold else "Bad"
     status_color = "#77C124" if status == "Good" else "#E68B0A"
 
     # Render the pollution box
-    st.markdown(
-        f"""
+    st.markdown(f"""
         <div style="
             background: rgba(255, 255, 255, 0.05);
             border-radius: 16px;
@@ -86,6 +44,4 @@ def pollution_box(label: str, value: str, delta: str, threshold: float) -> None:
             <p style="font-size: 36px; font-weight: bold; color: {status_color}; margin: 0;">{status}</p>  <!-- Good/Bad with color -->
             <p style="font-size: 18px; margin: 0;">{value}</p>  <!-- Smaller value where delta used to be -->
         </div>
-    """,
-        unsafe_allow_html=True,
-    )
+    """, unsafe_allow_html=True)

src/past_data_api_calls.py

@@ -14,11 +14,7 @@ PAST_WEATHER_DATA_FILE = "past_weather_data.csv"
 PAST_POLLUTION_DATA_FILE = "past_pollution_data.csv"
 
 
-def update_past_weather_data() -> None:
-    """
-    Updates past weather data.
-    The data is saved to a CSV file. If the file already exists, new data is appended.
-    """
+def update_past_weather_data():
     last_year_date = date.today() - timedelta(days=365)
 
     if os.path.exists(PAST_WEATHER_DATA_FILE):
@@ -55,13 +51,7 @@ def update_past_weather_data() -> None:
         sys.exit()
 
 
-def update_past_pollution_data() -> tuple[list[float], list[float]]:
-    """
-    Updates past pollution data for NO2 and O3.
-
-    Returns:
-        tuple: A tuple containing two lists with NO2 and O3 average values.
-    """
+def update_past_pollution_data():
     O3 = []
     NO2 = []
     particles = ["NO2", "O3"]
@@ -75,7 +65,7 @@ def update_past_pollution_data() -> tuple[list[float], list[float]]:
         last_date = pd.to_datetime(existing_data["date"]).max()
         if last_date >= pd.to_datetime(last_year_date):
             print("Data is already up to date.")
-            return [], []
+            return
         else:
             start_date = last_date.date()
             end_date = last_year_date + timedelta(days=3)
@@ -139,13 +129,7 @@ def update_past_pollution_data() -> tuple[list[float], list[float]]:
     return NO2, O3
 
 
-def get_past_combined_data() -> pd.DataFrame:
-    """
-    Retrieves and combines past weather and pollution data.
-
-    Returns:
-        pd.DataFrame: A DataFrame containing the combined past weather and pollution data.
-    """
+def get_past_combined_data():
     update_past_weather_data()
     update_past_pollution_data()
 

src/predict.py

@@ -3,9 +3,9 @@ from datetime import date, datetime, timedelta
 
 import joblib
 import pandas as pd
-import torch
 from dotenv import load_dotenv
 from huggingface_hub import hf_hub_download, login
+
 from src.data_api_calls import (
     get_combined_data,
     update_pollution_data,
@@ -17,110 +17,33 @@ load_dotenv()
 login(token=os.getenv("HUGGINGFACE_DOWNLOAD_TOKEN"))
 
 
-def load_nn() -> torch.nn.Module:
-    """
-    Loads the neural network model for air pollution forecasting.
-
-    Returns:
-        torch.nn.Module: The loaded neural network model.
-    """
-    import torch.nn as nn
-    from huggingface_hub import PyTorchModelHubMixin
-
-    class AirPollutionNet(nn.Module, PyTorchModelHubMixin):
-        def __init__(self, input_size: int, layers: list[int], dropout_rate: float):
-            super(AirPollutionNet, self).__init__()
-            self.layers_list = nn.ModuleList()
-            in_features = input_size
-
-            for units in layers:
-                self.layers_list.append(nn.Linear(in_features, units))
-                self.layers_list.append(nn.ReLU())
-                self.layers_list.append(nn.Dropout(p=dropout_rate))
-                in_features = units
-
-            self.output = nn.Linear(in_features, 3)  # Output size is 3 for next 3 days
-
-        def forward(self, x: torch.Tensor) -> torch.Tensor:
-            """
-            Forward pass of the neural network.
-
-            Args:
-                x (torch.Tensor): Input tensor.
-
-            Returns:
-                torch.Tensor: Output tensor after passing through the network.
-            """
-            for layer in self.layers_list:
-                x = layer(x)
-            x = self.output(x)
-            return x
-
-    model = AirPollutionNet.from_pretrained(
-        "akseljoonas/Utrecht_pollution_forecasting_NO2"
-    )
-    return model
-
-
-def load_model(particle: str) -> object:
-    """
-    Loads the forecasting model based on the specified particle.
-
-    Args:
-        particle (str): The type of particle ("O3" or "NO2").
-
-    Returns:
-        object: The loaded model (either a neural network or a support vector regression model).
-    """
+def load_model(particle):
     repo_id = f"elisaklunder/Utrecht-{particle}-Forecasting-Model"
     if particle == "O3":
         file_name = "O3_svr_model.pkl"
-        model_path = hf_hub_download(repo_id=repo_id, filename=file_name)
-        model = joblib.load(model_path)
-    else:
-        model = load_nn()
+    elif particle == "NO2":
+        file_name = "NO2_svr_model.pkl"
 
+    model_path = hf_hub_download(repo_id=repo_id, filename=file_name)
+    model = joblib.load(model_path)
     return model
 
 
-def run_model(particle: str, data: pd.DataFrame) -> list:
-    """
-    Runs the model for the specified particle and makes predictions based on the input data.
-
-    Args:
-        particle (str): The type of particle ("O3" or "NO2").
-        data (pd.DataFrame): The input data for making predictions.
-
-    Returns:
-        list: The predictions for the specified particle.
-    """
+def run_model(particle, data):
     input_data = create_features(data=data, target_particle=particle)
     model = load_model(particle)
+    prediction = model.predict(input_data)
 
-    if particle == "NO2":
-        with torch.no_grad():
-            prediction = model(torch.tensor(input_data.values, dtype=torch.float32))
-        repo_id = "akseljoonas/Utrecht_pollution_forecasting_NO2"
-        file_name = "target_scaler_NO2.joblib"
-        path = hf_hub_download(repo_id=repo_id, filename=file_name)
-    else:
-        prediction = model.predict(input_data)
-
-        repo_id = f"elisaklunder/Utrecht-{particle}-Forecasting-Model"
-        file_name = f"target_scaler_{particle}.joblib"
-        path = hf_hub_download(repo_id=repo_id, filename=file_name)
-
+    repo_id = f"elisaklunder/Utrecht-{particle}-Forecasting-Model"
+    file_name = f"target_scaler_{particle}.joblib"
+    path = hf_hub_download(repo_id=repo_id, filename=file_name)
     target_scaler = joblib.load(path)
     prediction = target_scaler.inverse_transform(prediction)
 
     return prediction
 
 
-def update_data_and_predictions() -> None:
-    """
-    Updates the weather and pollution data, makes predictions for O3 and NO2,
-    and stores them in a CSV file.
-    """
+def update_data_and_predictions():
     update_weather_data()
     update_pollution_data()
 
@@ -166,16 +89,7 @@ def update_data_and_predictions() -> None:
     combined_data.to_csv(PREDICTIONS_FILE, index=False)
 
 
-def get_data_and_predictions() -> tuple[pd.DataFrame, list, list]:
-    """
-    Retrieves combined data and today's predictions for O3 and NO2.
-
-    Returns:
-        tuple: A tuple containing:
-            - week_data (pd.DataFrame): The combined data for the week.
-            - list: Predictions for O3.
-            - list: Predictions for NO2.
-    """
+def get_data_and_predictions():
     week_data = get_combined_data()
 
     PREDICTIONS_FILE = "predictions_history.csv"
@@ -193,7 +107,3 @@ def get_data_and_predictions() -> tuple[pd.DataFrame, list, list]:
     ].values
 
     return week_data, [o3_predictions], [no2_predictions]
-
-
-if __name__ == "__main__":
-    update_data_and_predictions()

test.ipynb

@@ -0,0 +1,327 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
+   "source": [
+    "from src.predict import get_data_and_predictions\n",
+    "from src.data_api_calls import get_combined_data\n",
+    "from src.past_data_api_calls import get_past_combined_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data is already up to date.\n",
+      "Data is already up to date.\n",
+      "Number of rows with missing values dropped: 7\n",
+      "Data is already up to date.\n",
+      "Number of rows with missing values dropped: 7\n"
+     ]
+    }
+   ],
+   "source": [
+    "week_data, predictions_O3, predictions_NO2 = get_data_and_predictions()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>date</th>\n",
+       "      <th>NO2</th>\n",
+       "      <th>O3</th>\n",
+       "      <th>wind_speed</th>\n",
+       "      <th>mean_temp</th>\n",
+       "      <th>global_radiation</th>\n",
+       "      <th>percipitation</th>\n",
+       "      <th>pressure</th>\n",
+       "      <th>minimum_visibility</th>\n",
+       "      <th>humidity</th>\n",
+       "      <th>weekday</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2024-10-17</td>\n",
+       "      <td>22.804605</td>\n",
+       "      <td>22.769160</td>\n",
+       "      <td>51</td>\n",
+       "      <td>169</td>\n",
+       "      <td>43</td>\n",
+       "      <td>6</td>\n",
+       "      <td>10100</td>\n",
+       "      <td>371</td>\n",
+       "      <td>86</td>\n",
+       "      <td>Thursday</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2024-10-18</td>\n",
+       "      <td>23.268500</td>\n",
+       "      <td>23.307332</td>\n",
+       "      <td>21</td>\n",
+       "      <td>155</td>\n",
+       "      <td>42</td>\n",
+       "      <td>39</td>\n",
+       "      <td>10140</td>\n",
+       "      <td>45</td>\n",
+       "      <td>97</td>\n",
+       "      <td>Friday</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2024-10-19</td>\n",
+       "      <td>23.910064</td>\n",
+       "      <td>23.171714</td>\n",
+       "      <td>41</td>\n",
+       "      <td>147</td>\n",
+       "      <td>43</td>\n",
+       "      <td>16</td>\n",
+       "      <td>10141</td>\n",
+       "      <td>228</td>\n",
+       "      <td>89</td>\n",
+       "      <td>Saturday</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2024-10-20</td>\n",
+       "      <td>22.573238</td>\n",
+       "      <td>23.537845</td>\n",
+       "      <td>81</td>\n",
+       "      <td>155</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5</td>\n",
+       "      <td>10160</td>\n",
+       "      <td>415</td>\n",
+       "      <td>83</td>\n",
+       "      <td>Sunday</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2024-10-21</td>\n",
+       "      <td>21.145700</td>\n",
+       "      <td>24.020696</td>\n",
+       "      <td>58</td>\n",
+       "      <td>144</td>\n",
+       "      <td>27</td>\n",
+       "      <td>43</td>\n",
+       "      <td>10206</td>\n",
+       "      <td>220</td>\n",
+       "      <td>92</td>\n",
+       "      <td>Monday</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>2024-10-22</td>\n",
+       "      <td>21.776580</td>\n",
+       "      <td>23.335886</td>\n",
+       "      <td>53</td>\n",
+       "      <td>114</td>\n",
+       "      <td>57</td>\n",
+       "      <td>49</td>\n",
+       "      <td>10269</td>\n",
+       "      <td>226</td>\n",
+       "      <td>92</td>\n",
+       "      <td>Tuesday</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>2024-10-23</td>\n",
+       "      <td>21.974794</td>\n",
+       "      <td>22.214689</td>\n",
+       "      <td>36</td>\n",
+       "      <td>112</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>10328</td>\n",
+       "      <td>65</td>\n",
+       "      <td>97</td>\n",
+       "      <td>Wednesday</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>2024-10-24</td>\n",
+       "      <td>25.512568</td>\n",
+       "      <td>20.913710</td>\n",
+       "      <td>56</td>\n",
+       "      <td>104</td>\n",
+       "      <td>62</td>\n",
+       "      <td>0</td>\n",
+       "      <td>10247</td>\n",
+       "      <td>130</td>\n",
+       "      <td>94</td>\n",
+       "      <td>Thursday</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        date        NO2         O3  wind_speed  mean_temp  global_radiation  \\\n",
+       "0 2024-10-17  22.804605  22.769160          51        169                43   \n",
+       "1 2024-10-18  23.268500  23.307332          21        155                42   \n",
+       "2 2024-10-19  23.910064  23.171714          41        147                43   \n",
+       "3 2024-10-20  22.573238  23.537845          81        155                 0   \n",
+       "4 2024-10-21  21.145700  24.020696          58        144                27   \n",
+       "5 2024-10-22  21.776580  23.335886          53        114                57   \n",
+       "6 2024-10-23  21.974794  22.214689          36        112                12   \n",
+       "7 2024-10-24  25.512568  20.913710          56        104                62   \n",
+       "\n",
+       "   percipitation  pressure  minimum_visibility  humidity    weekday  \n",
+       "0              6     10100                 371        86   Thursday  \n",
+       "1             39     10140                  45        97     Friday  \n",
+       "2             16     10141                 228        89   Saturday  \n",
+       "3              5     10160                 415        83     Sunday  \n",
+       "4             43     10206                 220        92     Monday  \n",
+       "5             49     10269                 226        92    Tuesday  \n",
+       "6              0     10328                  65        97  Wednesday  \n",
+       "7              0     10247                 130        94   Thursday  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "week_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[10.33808859, 16.00098432, 19.64377496]])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions_O3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[25.68519992, 25.76030745, 31.21057679]])"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions_NO2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from src.data_api_calls import get_combined_data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "'<' not supported between instances of 'Timestamp' and 'str'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[2], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[43mget_combined_data\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m2024-10-10\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\data_api_calls.py:136\u001b[0m, in \u001b[0;36mget_combined_data\u001b[1;34m(input_date)\u001b[0m\n\u001b[0;32m    133\u001b[0m     start_date \u001b[38;5;241m=\u001b[39m end_date \u001b[38;5;241m-\u001b[39m timedelta(\u001b[38;5;241m7\u001b[39m)\n\u001b[0;32m    135\u001b[0m update_weather_data(start_date, end_date)\n\u001b[1;32m--> 136\u001b[0m \u001b[43mupdate_pollution_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstart_date\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mend_date\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    138\u001b[0m weather_df \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mread_csv(WEATHER_DATA_FILE)\n\u001b[0;32m    140\u001b[0m weather_df\u001b[38;5;241m.\u001b[39minsert(\u001b[38;5;241m1\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNO2\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\src\\data_api_calls.py:123\u001b[0m, in \u001b[0;36mupdate_pollution_data\u001b[1;34m(start_date, end_date)\u001b[0m\n\u001b[0;32m    121\u001b[0m updated_data \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mconcat([existing_data, new_data], ignore_index\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m    122\u001b[0m updated_data\u001b[38;5;241m.\u001b[39mdrop_duplicates(subset\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdate\u001b[39m\u001b[38;5;124m\"\u001b[39m, keep\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlast\u001b[39m\u001b[38;5;124m\"\u001b[39m, inplace\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m--> 123\u001b[0m updated_data \u001b[38;5;241m=\u001b[39m \u001b[43mupdated_data\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msort_values\u001b[49m\u001b[43m(\u001b[49m\u001b[43mby\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdate\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m    124\u001b[0m updated_data\u001b[38;5;241m.\u001b[39mto_csv(POLLUTION_DATA_FILE, index\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\core\\frame.py:7200\u001b[0m, in \u001b[0;36mDataFrame.sort_values\u001b[1;34m(self, by, axis, ascending, inplace, kind, na_position, ignore_index, key)\u001b[0m\n\u001b[0;32m   7197\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(ascending, (\u001b[38;5;28mtuple\u001b[39m, \u001b[38;5;28mlist\u001b[39m)):\n\u001b[0;32m   7198\u001b[0m         ascending \u001b[38;5;241m=\u001b[39m ascending[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m-> 7200\u001b[0m     indexer \u001b[38;5;241m=\u001b[39m \u001b[43mnargsort\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   7201\u001b[0m \u001b[43m        \u001b[49m\u001b[43mk\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkind\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkind\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mascending\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mascending\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mna_position\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mna_position\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkey\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkey\u001b[49m\n\u001b[0;32m   7202\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   7203\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m   7204\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m inplace:\n",
+      "File \u001b[1;32mc:\\Users\\elikl\\Documents\\Uni\\yr3\\ML for industry\\utrecht-pollution-prediction\\.venv\\Lib\\site-packages\\pandas\\core\\sorting.py:439\u001b[0m, in \u001b[0;36mnargsort\u001b[1;34m(items, kind, ascending, na_position, key, mask)\u001b[0m\n\u001b[0;32m    437\u001b[0m     non_nans \u001b[38;5;241m=\u001b[39m non_nans[::\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\n\u001b[0;32m    438\u001b[0m     non_nan_idx \u001b[38;5;241m=\u001b[39m non_nan_idx[::\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\n\u001b[1;32m--> 439\u001b[0m indexer \u001b[38;5;241m=\u001b[39m non_nan_idx[\u001b[43mnon_nans\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43margsort\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkind\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkind\u001b[49m\u001b[43m)\u001b[49m]\n\u001b[0;32m    440\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m ascending:\n\u001b[0;32m    441\u001b[0m     indexer \u001b[38;5;241m=\u001b[39m indexer[::\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\n",
+      "\u001b[1;31mTypeError\u001b[0m: '<' not supported between instances of 'Timestamp' and 'str'"
+     ]
+    }
+   ],
+   "source": [
+    "get_combined_data(\"2024-10-10\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

weather_data.csv

@@ -13,16 +13,3 @@ date,temp,humidity,precip,windspeed,sealevelpressure,visibility,solarradiation
 2024-10-28,12.4,91.8,1.1,31.7,1021.8,12.8,27.3
 2024-10-29,13.8,95.9,0.2,20.5,1023.1,8.1,16.0
 2024-10-30,12.7,92.9,0.6,9.4,1027.5,12.5,32.8
-2024-10-31,12.5,89.9,0.0,11.2,1027.1,17.1,70.6
-2024-11-01,9.9,96.9,0.0,14.4,1024.3,3.2,10.0
-2024-11-02,10.0,87.6,0.5,14.4,1030.9,17.9,36.1
-2024-11-03,5.7,91.3,0.0,7.2,1030.3,14.6,37.7
-2024-11-04,7.3,90.5,0.0,11.9,1027.6,24.1,38.4
-2024-11-05,7.0,89.9,0.0,13.0,1023.4,9.0,33.1
-2024-11-06,8.9,94.4,0.0,9.4,1029.7,12.6,54.7
-2024-11-07,7.2,90.8,0.0,13.7,1032.8,16.9,76.6
-2024-11-08,4.9,89.5,0.0,14.4,1028.3,21.5,10.8
-2024-11-09,6.3,93.0,0.0,11.2,1024.9,6.3,14.5
-2024-11-10,8.9,94.2,0.0,12.6,1026.6,14.3,32.7
-2024-11-11,10.6,84.7,2.1,27.7,1028.4,9.9,22.3
-2024-11-12,8.6,86.2,0.8,22.3,1032.3,18.8,33.2