ss

assets/quiz.json

@@ -1,92 +1,42 @@
 [
     {
-        "question": "Which of the following best describes emotion detection?",
-        "options": [
-            "Teaching computers to understand human emotions",
-            "Teaching humans to understand computer languages",
-            "Teaching computers to create video games",
-            "Teaching humans to recognize facial features"
-        ],
-        "answer": "Teaching computers to understand human emotions"
+      "question": "Which machine learning technique is commonly used for weather forecasting due to its ability to handle time series data efficiently?",
+      "options": ["Support Vector Machines (SVM)", "Decision Trees", "Random Forests", "Recurrent Neural Networks (RNN)"],
+      "answer": "Recurrent Neural Networks (RNN)"
     },
     {
-        "question": "What programming language is commonly used in developing emotion detection applications?",
-        "options": [
-            "Python",
-            "Java",
-            "C++",
-            "Ruby"
-        ],
-        "answer": "Python"
+      "question": "What type of weather data is typically used as input for machine learning models in weather forecasting?",
+      "options": ["Historical weather data", "Stock market data", "Social media posts", "Traffic congestion data"],
+      "answer": "Historical weather data"
     },
     {
-        "question": "What is the purpose of OpenCV in an emotion detection application?",
-        "options": [
-            "To analyze and manipulate images and videos",
-            "To recognize and understand human emotions",
-            "To create graphical user interfaces",
-            "To generate statistical reports"
-        ],
-        "answer": "To analyze and manipulate images and videos"
+      "question": "Which evaluation metric is commonly used to assess the performance of weather forecasting models, particularly for numerical predictions like temperature or precipitation?",
+      "options": ["Accuracy", "F1 score", "Mean Absolute Error (MAE)", "Precision"],
+      "answer": "Mean Absolute Error (MAE)"
     },
     {
-        "question": "Why is it important to have a diverse dataset when training an emotion detection model?",
-        "options": [
-            "It helps the model better understand different facial expressions",
-            "It improves the performance of the computer's processor",
-            "It makes the application run faster",
-            "It reduces the training time for the model"
-        ],
-        "answer": "It helps the model better understand different facial expressions"
+      "question": "In weather forecasting, what is the process of combining predictions from multiple models to improve overall accuracy and performance called?",
+      "options": ["Ensemble learning", "Feature engineering", "Gradient boosting", "Reinforcement learning"],
+      "answer": "Ensemble learning"
     },
     {
-        "question": "What is the final step after training the model in an emotion detection application?",
-        "options": [
-            "Collect more data for training",
-            "Test the model's accuracy and performance",
-            "Install additional software plugins",
-            "Optimize the application's user interface"
-        ],
-        "answer": "Test the model's accuracy and performance"
+      "question": "Which data visualization technique is often used to display the relationship between weather variables, such as temperature and humidity, over a specific period?",
+      "options": ["Bar chart", "Scatter plot", "Pie chart", "Line graph"],
+      "answer": "Line graph"
     },
     {
-        "question": "How does the inference process work in an emotion detection application?",
-        "options": [
-            "It analyzes facial features and predicts the associated emotion",
-            "It collects user feedback and improves the model's accuracy",
-            "It converts emotions into numerical values for analysis",
-            "It adjusts the application's settings based on user preferences"
-        ],
-        "answer": "It analyzes facial features and predicts the associated emotion"
+      "question": "What is the primary advantage of using deep learning models, such as Convolutional Neural Networks (CNN), for weather forecasting?",
+      "options": ["They require less computational power.", "They don't require historical weather data.", "They can automatically extract relevant features from raw data.", "They are not affected by missing data."],
+      "answer": "They can automatically extract relevant features from raw data."
     },
     {
-        "question": "What is an example of a real-world application of emotion detection technology?",
-        "options": [
-            "Virtual reality gaming",
-            "Weather forecasting",
-            "Online shopping",
-            "Recipe suggestions"
-        ],
-        "answer": "Virtual reality gaming"
+      "question": "Which step of the weather forecasting process involves gathering and processing data from various sources to initialize the models?",
+      "options": ["Post-processing", "Model evaluation", "Data assimilation", "Feature selection"],
+      "answer": "Data assimilation"
     },
     {
-        "question": "What is the importance of ethical considerations in emotion detection applications?",
-        "options": [
-            "Ensuring privacy and consent when collecting data",
-            "Optimizing the application's performance",
-            "Reducing the complexity of the model",
-            "Enhancing the visual appearance of the application"
-        ],
-        "answer": "Ensuring privacy and consent when collecting data"
-    },
-    {
-        "question": "What can students do to further explore and improve their emotion detection application?",
-        "options": [
-            "Experiment with different image preprocessing techniques",
-            "Rewrite the entire code from scratch",
-            "Avoid using real-time video feeds for testing",
-            "Skip the testing phase and move directly to deployment"
-        ],
-        "answer": "Experiment with different image preprocessing techniques"
+      "question": "Which machine learning algorithm is well-suited for short-term weather predictions, such as the next few hours or days?",
+      "options": ["K-Nearest Neighbors (KNN)", "Long Short-Term Memory (LSTM) networks", "Naive Bayes", "Principal Component Analysis (PCA)"],
+      "answer": "Long Short-Term Memory (LSTM) networks"
     }
 ]

pages/3_Training the Model.py

@@ -53,8 +53,8 @@ def create_model_inputs(data, lag, mean_period):
 
 
 def show_output(y_test, y_pred):
-    st.sidebar.subheader("Model Performance")
-    st.sidebar.write(f"Test R2 score: {r2_score(y_test, y_pred):.2f}")
+    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')
@@ -186,14 +186,14 @@ def step3_page():
             my_bar.progress(100, text="Training completed")
             state = "model predict"
             st.success("Model training successfully completed!")
-
-            # Display feature importance
-            if st.checkbox('Show feature importance'):
-                feature_names = ['Solar_Irradiance', 'Temperature', 'Rain_Fall', 'Wind_speed', 'PV_Output_lag',
-                                 'PV_Output_mean']
-                fig = feature_importance_plot(model, feature_names)
-                with _lock:
-                    st.pyplot(fig)
+            #
+            # # Display feature importance
+            # if st.checkbox('Show feature importance'):
+            #     feature_names = ['Solar_Irradiance', 'Temperature', 'Rain_Fall', 'Wind_speed', 'PV_Output_lag',
+            #                      'PV_Output_mean']
+            #     fig = feature_importance_plot(model, feature_names)
+            #     with _lock:
+            #         st.pyplot(fig)
 
     if state == "model predict":
         st.subheader("Step 5: Model Evaluation")