Update app.py

app.py

@@ -1,95 +1,41 @@
 import streamlit as st
 import pandas as pd
-import numpy as np
-import matplotlib.pyplot as plt
-import seaborn as sns
-from groq import Groq  # Assuming this is the correct import
-import requests
+from groq import Groq  # Ensure Groq client library is installed
 
 # Initialize Groq API
-GROQ_API_KEY = "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"
+GROQ_API_KEY = "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"
 client = Groq(api_key=GROQ_API_KEY)
 
-st.title("Space Mission Analysis Dashboard")
+st.title("AI Prediction with Groq API")
+uploaded_file = st.file_uploader("Upload your mission dataset (CSV)", type=["csv"])
 
-# Load dataset
-data = pd.DataFrame({
-    "Mission ID": [],
-    "Mission Name": [],
-    "Launch Date": [],
-    "Target Type": [],
-    "Target Name": [],
-    "Mission Type": [],
-    "Distance from Earth (light-years)": [],
-    "Mission Duration (years)": [],
-    "Mission Cost (billion USD)": [],
-    "Scientific Yield (points)": [],
-    "Crew Size": [],
-    "Mission Success (%)": [],
-    "Fuel Consumption (tons)": [],
-    "Payload Weight (tons)": [],
-    "Launch Vehicle": []
-})
-
-# Upload dataset
-uploaded_file = st.file_uploader("Upload your dataset (CSV format)", type=["csv"])
 if uploaded_file:
-    data = pd.read_csv(uploaded_file)
-    st.write("### Dataset Preview")
-    st.write(data.head())
-
-# Display basic statistics
-if not data.empty:
-    st.write("### Dataset Summary")
-    st.write(data.describe())
+    # Read the dataset
+    df = pd.read_csv(uploaded_file)
+    st.dataframe(df)
 
-    # Visualization: Mission Success vs. Scientific Yield
-    st.write("### Mission Success vs. Scientific Yield")
-    plt.figure(figsize=(10, 5))
-    sns.scatterplot(
-        data=data,
-        x="Mission Success (%)",
-        y="Scientific Yield (points)",
-        hue="Mission Type",
-        palette="viridis"
-    )
-    plt.title("Success Rate vs Yield")
-    st.pyplot(plt)
+    # Select mission ID for prediction
+    mission_ids = df["Mission ID"].unique()
+    selected_mission_id = st.selectbox("Select Mission ID for prediction:", mission_ids)
 
-    # Filterable Data Selection
-    st.write("### Filtered Data Selection")
-    mission_types = data["Mission Type"].unique()
-    selected_type = st.selectbox("Select Mission Type", mission_types)
-    filtered_data = data[data["Mission Type"] == selected_type]
-    st.write(filtered_data)
+    # Display selected mission details
+    mission_data = df[df["Mission ID"] == selected_mission_id].iloc[0]
+    st.write("Selected Mission Data:", mission_data)
 
-    # Groq API Call Example
-    st.write("### AI Prediction with Groq API")
-    sample_input = {
-        "mission_duration": filtered_data["Mission Duration (years)"].mean(),
-        "fuel_consumption": filtered_data["Fuel Consumption (tons)"].mean(),
-        "success_rate": filtered_data["Mission Success (%)"].mean(),
-    }
-    
     if st.button("Predict Resource Optimization"):
-        response = requests.post(
-            "https://api.groq.com/v1/predict",  # Replace with actual endpoint
-            headers={"Authorization": f"Bearer {GROQ_API_KEY}"},
-            json=sample_input
-        )
-        if response.status_code == 200:
-            prediction = response.json()
-            st.write("### AI Prediction Result")
-            st.json(prediction)
-        else:
-            st.error("Error: Could not get prediction")
-
-    # Insights: Fuel Efficiency Analysis
-    st.write("### Fuel Efficiency Analysis")
-    data["Fuel Efficiency (Yield per Ton)"] = (
-        data["Scientific Yield (points)"] / data["Fuel Consumption (tons)"]
-    ).replace([np.inf, -np.inf], np.nan).dropna()
-    st.line_chart(data["Fuel Efficiency (Yield per Ton)"])
-
-else:
-    st.warning("Please upload a valid CSV dataset.")
+        # Prepare data payload
+        payload = {
+            "id": int(mission_data["Mission ID"]),
+            "distance_from_earth": float(mission_data["Distance from Earth (light-years)"]),
+            "duration": float(mission_data["Mission Duration (years)"]),
+            "crew_size": int(mission_data["Crew Size"]),
+            "fuel_consumption": float(mission_data["Fuel Consumption (tons)"]),
+            "payload_weight": float(mission_data["Payload Weight (tons)"])
+        }
+
+        # Call the Groq API
+        try:
+            response = client.predict(payload)
+            st.success(f"Prediction Result: {response}")
+        except Exception as e:
+            st.error(f"Error: {str(e)}")