WORKINNGG

adjusted_predictions_O3_NO2.csv

@@ -1,59 +0,0 @@
-pollutant,date_predicted,date,prediction_value
-O3,2024-10-14,2024-10-17,37.50407
-NO2,2024-10-14,2024-10-17,31.70604
-O3,2024-10-15,2024-10-17,24.20011
-NO2,2024-10-15,2024-10-17,31.45461
-O3,2024-10-16,2024-10-17,9.6575
-NO2,2024-10-16,2024-10-17,17.0652
-O3,2024-10-15,2024-10-18,7.87344
-NO2,2024-10-15,2024-10-18,31.73243
-O3,2024-10-16,2024-10-18,21.76064
-NO2,2024-10-16,2024-10-18,40.0994
-O3,2024-10-17,2024-10-18,16.0884
-NO2,2024-10-17,2024-10-18,32.0458
-O3,2024-10-16,2024-10-19,28.83768
-NO2,2024-10-16,2024-10-19,24.10068
-O3,2024-10-17,2024-10-19,23.13454
-NO2,2024-10-17,2024-10-19,29.79229
-O3,2024-10-17,2024-10-19,22.53339
-NO2,2024-10-17,2024-10-19,26.22730
-O3,2024-10-18,2024-10-19,22.3045
-NO2,2024-10-18,2024-10-19,20.8002
-O3,2024-10-18,2024-10-20,31.34.37874
-NO2,2024-10-18,2024-10-20,32.70553
-O3,2024-10-18,2024-10-20,31.54536
-NO2,2024-10-18,2024-10-20,38.55104
-O3,2024-10-19,2024-10-20,26.4217
-NO2,2024-10-19,2024-10-20,27.3999
-O3,2024-10-19,2024-10-20,17.0652
-NO2,2024-10-19,2024-10-20,18.9924
-O3,2024-10-19,2024-10-21,19.13648
-NO2,2024-10-19,2024-10-21,25.13566
-O3,2024-10-19,2024-10-21,24.20011
-NO2,2024-10-19,2024-10-21,20.09909
-O3,2024-10-20,2024-10-21,29.0094
-NO2,2024-10-20,2024-10-21,19.5074
-O3,2024-10-20,2024-10-21,20.0621
-NO2,2024-10-20,2024-10-21,23.6575
-O3,2024-10-20,2024-10-22,19.24714
-NO2,2024-10-20,2024-10-22,31.45461
-O3,2024-10-21,2024-10-22,16.52
-NO2,2024-10-21,2024-10-22,30.1924
-O3,2024-10-21,2024-10-23,31.01934
-NO2,2024-10-21,2024-10-23,19.74775
-O3,2024-10-21,2024-10-23,17.70241
-NO2,2024-10-21,2024-10-23,27.73936
-O3,2024-10-22,2024-10-24,25.96605
-NO2,2024-10-22,2024-10-24,31.90517
-O3,2024-10-22,2024-10-24,29.22139
-NO2,2024-10-22,2024-10-24,22.16907
-O3,2024-10-23,2024-10-24,9.0905
-NO2,2024-10-23,2024-10-24,18.1749
-O3,2024-10-23,2024-10-24,20.205
-NO2,2024-10-23,2024-10-24,27.3349
-O3,2024-10-24,2024-10-25,9.090494810363
-NO2,2024-10-24,2024-10-25,18.174884683860732
-O3,2024-10-24,2024-10-26,20.2050211414084
-NO2,2024-10-24,2024-10-26,27.334877510848962
-O3,2024-10-24,2024-10-27,16.31643675723712
-NO2,2024-10-24,2024-10-27,23.015396915310056

pages/admin.py

@@ -5,7 +5,7 @@ import streamlit as st
 from sklearn.metrics import mean_squared_error
 
 USERNAME = "dragonkiller"
-PASSWORD = "password"
+PASSWORD = "donkey"
 
 st.title("Admin Panel")
 
@@ -30,7 +30,7 @@ if not st.session_state.login_success:
 else:
     # Actual data vs 1,2,3 days ahead predictions
     actual_data = pd.read_csv("pollution_data.csv")
-    prediction_data = pd.read_csv("prediction_history.csv")
+    prediction_data = pd.read_csv("predictions_history.csv")
 
     col1, col2 = st.columns(2)
     with col1:

past_weather_data.csv

@@ -9,4 +9,5 @@ date,temp,humidity,precip,windspeed,sealevelpressure,visibility,solarradiation
 2023-10-24,11.6,92.3,6.5,22.3,1001.3,23.1,32.6
 2023-10-25,9.3,96.8,15.3,18.0,996.8,15.7,14.5
 2023-10-26,9.4,97.6,0.1,11.2,995.6,4.8,36.0
-2023-10-27,10.6,97.9,11.4,14.8,992,9.5,20.5
+2023-10-27,10.6,97.9,11.4,14.8,992.0,9.5,20.5
+2023-10-28,11.4,88.6,3,18.4,994.4,29.3,48.5

pollution_data.csv

@@ -7,3 +7,4 @@ date,NO2,O3
 2024-10-22,21.776579804560274,23.33588571428572
 2024-10-23,21.974793814433,22.21468879668051
 2024-10-24,25.51256756756757,20.91370967741937
+2024-10-25,21.72051282051282,22.33230769230769

prediction_history.csv

@@ -1,55 +0,0 @@
-pollutant,date_predicted,date,prediction_value
-O3,2024-10-14,2024-10-17,31.253351852448926
-NO2,2024-10-14,2024-10-17,26.421736787446267
-O3,2024-10-15,2024-10-17,22.000057677604474
-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
-O3,2024-10-15,2024-10-18,6.561248
-NO2,2024-10-15,2024-10-18,26.443672
-O3,2024-10-16,2024-10-18,19.782418
-NO2,2024-10-16,2024-10-18,36.453956
-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
-NO2,2024-10-16,2024-10-19,20.083893955587914
-O3,2024-10-17,2024-10-19,21.031357603260783
-NO2,2024-10-17,2024-10-19,27.083893955587914
-O3,2024-10-17,2024-10-20,20.484862479793236
-NO2,2024-10-17,2024-10-20,23.84300578029378
-O3,2024-10-18,2024-10-19,22.304547122637445
-NO2,2024-10-18,2024-10-19,20.80017116560889
-O3,2024-10-18,2024-10-20,31.253351852448926
-NO2,2024-10-18,2024-10-20,29.732316066240582
-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
-O3,2024-10-19,2024-10-21,17.065168790519902
-NO2,2024-10-19,2024-10-21,18.992352714813563
-O3,2024-10-19,2024-10-22,17.39682962048955
-NO2,2024-10-19,2024-10-22,22.850616758859076
-O3,2024-10-20,2024-10-21,22.000057677604474
-NO2,2024-10-20,2024-10-21,18.27191592927812
-O3,2024-10-20,2024-10-22,29.00940466937953
-NO2,2024-10-20,2024-10-22,19.507397669634972
-O3,2024-10-20,2024-10-23,20.062134354543346
-NO2,2024-10-20,2024-10-23,23.657466070999735
-O3,2024-10-21,2024-10-22,17.497382318189132
-NO2,2024-10-21,2024-10-22,28.59511317503212
-O3,2024-10-21,2024-10-23,16.519952190354232
-NO2,2024-10-21,2024-10-23,30.192389708351822
-O3,2024-10-21,2024-10-24,28.199403851129034
-NO2,2024-10-21,2024-10-24,17.9525039623211
-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
-O3,2024-10-23,2024-10-24,26.56486295059828
-NO2,2024-10-23,2024-10-24,20.153737337472574
-O3,2024-10-24,2024-10-25,9.090494810363
-NO2,2024-10-24,2024-10-25,18.174884683860732
-O3,2024-10-24,2024-10-26,20.2050211414084
-NO2,2024-10-24,2024-10-26,27.334877510848962
-O3,2024-10-24,2024-10-27,16.31643675723712
-NO2,2024-10-24,2024-10-27,23.015396915310056

predictions_history.csv

@@ -1,7 +1,61 @@
 pollutant,date_predicted,date,prediction_value
+O3,2024-10-14,2024-10-17,31.25335185244893
+NO2,2024-10-14,2024-10-17,26.421736787446267
+O3,2024-10-15,2024-10-17,22.00005767760448
+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
+O3,2024-10-15,2024-10-18,6.561248
+NO2,2024-10-15,2024-10-18,26.443672
+O3,2024-10-16,2024-10-18,19.782418
+NO2,2024-10-16,2024-10-18,36.453956
+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
+NO2,2024-10-16,2024-10-19,20.083893955587914
+O3,2024-10-17,2024-10-19,21.031357603260783
+NO2,2024-10-17,2024-10-19,27.083893955587914
+O3,2024-10-17,2024-10-20,20.48486247979324
+NO2,2024-10-17,2024-10-20,23.84300578029378
+O3,2024-10-18,2024-10-19,22.304547122637445
+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
+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
+O3,2024-10-19,2024-10-21,17.065168790519902
+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
+O3,2024-10-20,2024-10-21,22.00005767760448
+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
+O3,2024-10-20,2024-10-23,20.062134354543343
+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
+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
+O3,2024-10-22,2024-10-23,16.093074246425157
+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
+O3,2024-10-23,2024-10-24,26.56486295059828
+NO2,2024-10-23,2024-10-24,20.15373733747257
 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
+O3,2024-10-25,2024-10-26,20.48055947200643
+NO2,2024-10-25,2024-10-26,23.957239039864238
+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
+NO2,2024-10-25,2024-10-28,40.86107800019054

src/data_api_calls.py

@@ -118,6 +118,11 @@ def get_combined_data():
     update_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.insert(1, "NO2", None)
     weather_df.insert(2, "O3", None)
@@ -163,6 +168,10 @@ def get_combined_data():
     combined_df["global_radiation"] = combined_df["global_radiation"].astype(int)
 
     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)]
+
     combined_df["NO2"] = pollution_df["NO2"]
     combined_df["O3"] = pollution_df["O3"]
 

src/features_pipeline.py

@@ -77,7 +77,8 @@ def create_features(
     data = data.dropna().reset_index(drop=True)
     rows_after = data.shape[0]
     rows_dropped = rows_before - rows_after
-    print(f"Number of rows with missing values dropped: {rows_dropped}")
+    print(f"Number of rows with missing values dropped: {rows_dropped}/{rows_before}")
+    print(data)
 
     # Ensure the data is sorted by date in ascending order
     data = data.sort_values("date").reset_index(drop=True)

src/past_data_api_calls.py

@@ -136,8 +136,8 @@ def get_past_combined_data():
     combined_df = pd.read_csv(PAST_WEATHER_DATA_FILE)
     pollution_data = pd.read_csv(PAST_POLLUTION_DATA_FILE)
 
-    combined_df["NO2"] = pollution_data["NO2"]
-    combined_df["O3"] = pollution_data["O3"]
+    combined_df = combined_df.merge(pollution_data, on="date", how="inner")
+    combined_df = combined_df.tail(11)
 
     # Apply scaling and renaming similar to the scale function from previous code
     combined_df = combined_df.rename(

src/predict.py

@@ -47,7 +47,7 @@ def get_data_and_predictions():
         prediction_data.append(
             {
                 "pollutant": "O3",
-                "predicted_on": date.today(),
+                "date_predicted": date.today(),
                 "date": date.today() + timedelta(days=i + 1),
                 "prediction_value": o3_predictions[0][i],
             }
@@ -55,7 +55,7 @@ def get_data_and_predictions():
         prediction_data.append(
             {
                 "pollutant": "NO2",
-                "predicted_on": date.today(),
+                "date_predicted": date.today(),
                 "date": date.today() + timedelta(days=i + 1),
                 "prediction_value": no2_predictions[0][i],
             }
@@ -67,7 +67,7 @@ def get_data_and_predictions():
         existing_data = pd.read_csv(PREDICTIONS_FILE)
         # Filter out predictions made today to avoid duplicates
         existing_data = existing_data[
-            ~(existing_data["predicted_on"] == str(date.today()))
+            ~(existing_data["date_predicted"] == str(date.today()))
         ]
         combined_data = pd.concat([existing_data, predictions_df])
     else:

weather_data.csv

@@ -1,18 +1,4 @@
 date,temp,humidity,precip,windspeed,sealevelpressure,visibility,solarradiation
-2024-10-03,9.9,78.9,0.0,25.9,1020.0,44.0,81.8
-2024-10-04,7.7,86.2,0.0,11.2,1022.0,25.0,86.3
-2024-10-05,8.0,83.2,0.0,14.8,1019.0,26.0,76.5
-2024-10-06,10.0,82.7,0.0,25.9,1007.7,36.5,77.2
-2024-10-07,15.3,81.0,0.4,22.3,1000.8,37.5,65.6
-2024-10-08,16.0,83.4,0.6,18.4,997.4,40.0,55.6
-2024-10-09,14.2,88.3,1.0,22.3,990.1,37.2,38.2
-2024-10-10,12.3,83.6,1.0,18.4,997.3,28.2,52.5
-2024-10-11,8.5,84.4,1.0,14.8,1015.3,36.1,62.9
-2024-10-12,7.8,89.4,0.0,21.6,1011.3,25.5,49.3
-2024-10-13,10.5,75.8,3.7,18.4,1013.2,36.8,49.9
-2024-10-14,7.9,89.8,0.0,10.8,1018.3,24.3,44.1
-2024-10-15,8.7,86.9,0.0,18.4,1019.4,29.0,71.2
-2024-10-16,15.1,82.2,0.0,22.3,1010.3,35.8,40.8
 2024-10-17,16.9,86.0,0.6,18.4,1010.0,37.1,43.0
 2024-10-18,15.5,97.3,3.9,7.6,1014.0,4.5,42.9
 2024-10-19,14.7,89.9,1.6,14.8,1014.1,22.8,43.5
@@ -21,3 +7,4 @@ date,temp,humidity,precip,windspeed,sealevelpressure,visibility,solarradiation
 2024-10-22,11.4,92.8,4.9,19.4,1026.9,22.6,57.0
 2024-10-23,11.2,97.3,0.0,13.0,1032.8,6.5,12.5
 2024-10-24,10.4,94.0,0.0,20.5,1024.7,13.0,62.5
+2024-10-25,13.6,92.2,0.5,11.9,1016.8,24.0,93.0