ss

.idea/sonarlint/issuestore/index.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f192a166326627fde11805cd80e2ecf025cd67b6c5340e631dce549929f014ac
-size 206
+oid sha256:c493d713dc16abecbcf2979862f605e2882a86c4027cec59edadf806b82f7144
+size 130

pages/3_Training the Model.py

@@ -24,9 +24,10 @@ LEVEL = 3
 File_PATH = 'datasets/Building_forcasting.csv'
 
 def process_file(csv_file):
-    data = pd.read_csv(csv_file, index_col='Timestamp')
-    data.index = pd.to_datetime(data.index)
-    data = data.fillna(0)
+    data = pd.read_csv(csv_file)
+    data['index'] = data['Date'].str.cat(data['Location'], sep='_')
+    data.set_index('index', inplace=True)
+    data['Date'] = pd.to_datetime(data['Date'])
     return data
 
 
@@ -41,38 +42,46 @@ def model_train(train_X, train_y, model_choice, train_size):
     return model, X_test, y_test
 
 
-def create_model_inputs(data, lag, mean_period):
+def create_model_inputs(data, lag, mean_period, target_variable):
     df_processed = data.copy()
-    df_processed['PV_Output_lag'] = df_processed['PV_Output'].shift(lag)
-    df_processed['PV_Output_mean'] = df_processed['PV_Output'].rolling(window=mean_period).mean()
-
-    X = df_processed[['Solar_Irradiance', 'Temperature', 'Rain_Fall', 'Wind_speed', 'PV_Output_lag', 'PV_Output_mean']].dropna()
-    y = df_processed[['PV_Output']].loc[X.index]
-
-    return X, y
-
-
-def show_output(y_test, y_pred):
+    selected_columns = ["MinTemp", "MaxTemp", "Rainfall", "WindGustSpeed", "WindSpeed9am", "WindSpeed3pm",
+                        "Humidity9am", "Humidity3pm", "Temp9am", "Temp3pm", "Pressure9am", "Pressure3pm"]
+    for col in selected_columns:
+        df_processed[col].fillna(df_processed[col].mean(), inplace=True)
+    df_processed[target_variable + "Tomorrow"] = df_processed[target_variable].shift(-1 * lag)
+    df_processed[target_variable + "_mean"] = df_processed[target_variable].rolling(window=mean_period).mean()
+    df_processed.drop(columns=['Evaporation', 'Sunshine', 'Cloud9am', 'Cloud3pm'], inplace=True)
+    X = df_processed[
+        ["Location", "MinTemp", "MaxTemp", "Rainfall", "WindGustDir", "WindGustSpeed", "WindDir9am", "WindDir3pm",
+         "WindSpeed9am", "WindSpeed3pm", "Humidity9am", "Humidity3pm", "Pressure9am", "Pressure3pm", "Temp9am",
+         "Temp3pm", "RainToday", target_variable + "_mean"]]
+    X = pd.get_dummies(X, columns=['Location', 'WindGustDir', 'WindDir9am', 'WindDir3pm'])
+    y = df_processed[target_variable + "Tomorrow"].loc[X.index]
+
+    return X, y, target_variable + "Tomorrow"
+
+
+def show_output(y_test, y_pred, target_variable_name):
     st.subheader("Model Performance")
     st.write(f"Test R2 score: {r2_score(y_test, y_pred):.2f}")
 
     fig, axs = plt.subplots(3, figsize=(12, 18))
-    axs[0].plot(y_test.index, y_pred/1000, label='Predicted')
-    axs[0].plot(y_test.index, y_test['PV_Output']/1000, label='Actual')
+    axs[0].plot(y_test.index, y_pred, label='Predicted')
+    axs[0].plot(y_test.index, y_test[target_variable_name], label='Actual')
     axs[0].legend()
-    axs[0].set_title('Prediction vs Actual (Solar Power Generation)')
-    axs[0].set_xlabel('Date')
-    axs[0].set_ylabel('Solar Power Generation (kW)')
+    axs[0].set_title(f'Prediction vs Actual ({target_variable_name})')
+    axs[0].set_xlabel('Date and Location')
+    axs[0].set_ylabel(f'{target_variable_name}')
 
-    axs[1].plot(y_test.index, y_pred/1000, label='Predicted')
-    axs[1].set_title('Predicted Solar Power Generation')
-    axs[1].set_xlabel('Date')
-    axs[1].set_ylabel('Solar Power Generation (kW)')
+    axs[1].plot(y_test.index, y_pred, label='Predicted')
+    axs[1].set_title(f'Predicted {target_variable_name}')
+    axs[1].set_xlabel('Date and Location')
+    axs[1].set_ylabel(f'{target_variable_name}')
 
-    axs[2].plot(y_test.index, y_test['PV_Output']/1000, label='Actual')
-    axs[2].set_title('Actual Solar Power Generation')
-    axs[2].set_xlabel('Date')
-    axs[2].set_ylabel('Solar Power Generation (kW)')
+    axs[2].plot(y_test.index, y_test[target_variable_name], label='Actual')
+    axs[2].set_title(f'Actual {target_variable_name}')
+    axs[2].set_xlabel('Date and Location')
+    axs[2].set_ylabel(f'{target_variable_name}')
 
     fig.tight_layout()
     with _lock:
@@ -151,8 +160,10 @@ def step3_page():
     if state == "preprocessing":
         st.subheader("Step 2: Data Preprocessing and Feature Engineering")
         st.write("Now let's preprocess our dataset to handle missing values, outliers and inconsistencies and then perform feature engineering tasks to extract meaningful features from the raw data. Finally we need to separate training variables (X) and target variable (y).")
-        # if st.button("Create Features and Target variable"):
-        X, y = create_model_inputs(data, 288, 288)
+        st.info("You can select the weather attribute that you want to forecast (WindSpeed/ Humidity/ Pressure/ Temperature) and the time of the forecast (9am tomorrow/ 3pm tomorrow)")
+        target_variables = ['WindSpeed9amTomorrow', 'WindSpeed3pmTomorrow', 'Humidity9amTomorrow', 'Humidity3pmTomorrow', 'Pressure9amTomorrow', 'Pressure3pmTomorrow', 'Temp9amTomorrow', 'Temp3pmTomorrow']
+        target_variable = st.selectbox('Select Target Variable', target_variables)
+        X, y, target_variable_name = create_model_inputs(data, 1, 30, target_variable)
         cols = st.columns(2)
         state = "splitting"
         with cols[0]:
@@ -199,7 +210,7 @@ def step3_page():
         st.subheader("Step 5: Model Evaluation")
         st.write("Now, let's evaluate our weather forecasting model's performance against the test data set.")
         y_pred = model.predict(X_test)
-        fig = show_output(y_test, y_pred)
+        fig = show_output(y_test, y_pred, target_variable_name)
         # download_link(y_test, y_pred)
         #
         # download_plot(fig)