Update app.py

app.py

@@ -34,8 +34,9 @@ def call_ai_model(all_message):
 
     return response
 
-# Function to request performance data from AI
+# Function to get performance data from AI
 def get_performance_data(conditions):
+    url = "https://api.together.xyz/v1/chat/completions"
     all_message = (
         f"Provide the expected sports performance score at conditions: "
         f"Temperature {conditions['temperature']}°C, Humidity {conditions['humidity']}%, "
@@ -59,11 +60,7 @@ def get_performance_data(conditions):
             except json.JSONDecodeError:
                 continue
 
-    try:
-        return float(generated_text.strip())
-    except ValueError:
-        st.warning(f"Could not convert the response to a float: {generated_text}")
-        return None
+    return generated_text.strip()
 
 # Streamlit app layout
 st.title("Climate Impact on Sports Performance")
@@ -93,43 +90,54 @@ if st.button("Generate Prediction"):
     try:
         with st.spinner("Generating predictions..."):
             # Call AI model to get initial prediction and qualitative assessment
-            response = call_ai_model(f"Assess the impact on sports performance at conditions: "
-                                     f"Temperature {temperature}°C, Humidity {humidity}%, "
-                                     f"Wind Speed {wind_speed} km/h, UV Index {uv_index}, "
-                                     f"Air Quality Index {air_quality_index}, Precipitation {precipitation} mm, "
-                                     f"Atmospheric Pressure {atmospheric_pressure} hPa.")
+            qualitative_analysis = (
+                f"Assess the impact on sports performance at conditions: "
+                f"Temperature {temperature}°C, Humidity {humidity}%, "
+                f"Wind Speed {wind_speed} km/h, UV Index {uv_index}, "
+                f"Air Quality Index {air_quality_index}, Precipitation {precipitation} mm, "
+                f"Atmospheric Pressure {atmospheric_pressure} hPa."
+            )
+            qualitative_result = call_ai_model(qualitative_analysis)
+
+            # Get performance score for specified conditions
+            performance_score_text = get_performance_data(conditions)
 
-        st.success("Initial analysis complete.")
+        st.success("Predictions generated.")
 
-        # Get performance score for specified conditions
-        performance_score = get_performance_data(conditions)
-        if performance_score is not None:
-            st.success("Performance data fetched successfully.")
-        else:
-            st.warning("Failed to fetch performance data.")
+        # Display qualitative analysis
+        st.subheader("Qualitative Analysis")
+        st.write(qualitative_result)
+
+        # Display performance score
+        st.subheader("Performance Score")
+        st.write(f"Predicted Performance Score: {performance_score_text}")
 
         # Plotting the data
-        if performance_score is not None:
-            # Prepare data for plotting
-            climate_conditions = list(conditions.keys())
-            climate_values = list(conditions.values())
-
-            fig, ax1 = plt.subplots()
-
-            # Plot climate conditions on the primary y-axis
-            ax1.plot(climate_conditions, climate_values, marker='o', color='b', label='Climate Conditions')
-            ax1.set_xlabel('Climate Conditions')
-            ax1.set_ylabel('Values', color='b')
-            ax1.tick_params(axis='y', labelcolor='b')
-
-            # Create a secondary y-axis for performance score
-            ax2 = ax1.twinx()
-            ax2.plot(['Performance Score'], [performance_score], marker='s', color='r', label='Performance Score')
-            ax2.set_ylabel('Performance Score', color='r')
-            ax2.tick_params(axis='y', labelcolor='r')
-
-            fig.tight_layout()
-            st.pyplot(fig)
+        st.subheader("Performance Score vs Climate Conditions")
+
+        # Define some dummy data for the climate conditions
+        climate_conditions = list(conditions.keys())
+        climate_values = list(conditions.values())
+
+        # Prepare data for plotting (replace with actual performance scores from API)
+        performance_scores = [80, 75, 85, 70, 78, 82, 72]  # Replace with actual data from API
+
+        fig, ax1 = plt.subplots()
+
+        # Plot climate conditions on the primary y-axis
+        ax1.plot(climate_conditions, climate_values, marker='o', color='b', label='Climate Conditions')
+        ax1.set_xlabel('Climate Conditions')
+        ax1.set_ylabel('Values', color='b')
+        ax1.tick_params(axis='y', labelcolor='b')
+
+        # Create a secondary y-axis for performance score
+        ax2 = ax1.twinx()
+        ax2.plot(['Performance Score'], performance_scores, marker='s', color='r', label='Performance Score')
+        ax2.set_ylabel('Performance Score', color='r')
+        ax2.tick_params(axis='y', labelcolor='r')
+
+        fig.tight_layout()
+        st.pyplot(fig)
 
     except ValueError as ve:
         st.error(f"Configuration error: {ve}")