Push.

app.py

@@ -1,4 +1,119 @@
 import streamlit as st
+import hopsworks
+import pandas as pd
+import os
+import time
+import matplotlib.pyplot as plt
+import seaborn as sns
+from datetime import datetime, timedelta
 
-x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)
+# Constants
+DATA_DIR = "data"
+TIMESTAMP_FILE = "last_download_time.txt"
+
+# Initialize Hopsworks connection
+def connect_to_hopsworks():
+    st.write("Connecting to Hopsworks...")
+    project_name = "id2223AirQuality"
+    api_key = os.getenv("HOPSWORKS_API_KEY")
+    conn = hopsworks.connection(api_key_value=api_key)
+    project = conn.get_project(project_name)
+    return project
+
+# Fetch data from Hopsworks feature group
+def fetch_data_from_feature_group(project, feature_group_name, version):
+    feature_store = project.get_feature_store()
+    feature_group = feature_store.get_feature_group(name=feature_group_name, version=version)
+    data = feature_group.read()
+    return data
+
+# Save data locally
+def save_data_locally(data, filename):
+    os.makedirs(DATA_DIR, exist_ok=True)
+    filepath = os.path.join(DATA_DIR, filename)
+    data.to_csv(filepath, index=False)
+    
+    # Save timestamp
+    timestamp_path = os.path.join(DATA_DIR, TIMESTAMP_FILE)
+    with open(timestamp_path, "w") as f:
+        f.write(str(datetime.now()))
+    return filepath
+
+# Load local data
+def load_local_data(filename):
+    filepath = os.path.join(DATA_DIR, filename)
+    if os.path.exists(filepath):
+        return pd.read_csv(filepath)
+    else:
+        return None
+
+# Check if local data is valid
+def is_local_data_valid():
+    timestamp_path = os.path.join(DATA_DIR, TIMESTAMP_FILE)
+    if not os.path.exists(timestamp_path):
+        return False
+    try:
+        with open(timestamp_path, "r") as f:
+            last_download_time = datetime.fromisoformat(f.read().strip())
+        # Check if the data is more than a day old
+        if datetime.now() - last_download_time > timedelta(days=1):
+            return False
+        return True
+    except Exception as e:
+        st.warning(f"Error reading timestamp: {e}")
+        return False
+
+# Plot graphs
+def plot_graphs(data):
+    st.write("### Data Preview")
+    st.dataframe(data.head())
+
+    #st.write("### Histogram")
+    #column = st.selectbox("Select column for histogram", data.columns)
+    #fig, ax = plt.subplots()
+    #sns.histplot(data[column], kde=True, ax=ax)
+    #st.pyplot(fig)
+
+    #st.write("### Correlation Matrix")
+    #fig, ax = plt.subplots()
+    #sns.heatmap(data.corr(), annot=True, cmap="coolwarm", ax=ax)
+    #st.pyplot(fig)
+
+# Streamlit UI
+def main():
+    st.title("Hopsworks Feature Group Explorer")
+    
+    # Initialize session state
+    if "hopsworks_project" not in st.session_state:
+        st.session_state.hopsworks_project = None
+    if "data" not in st.session_state:
+        st.session_state.data = None
+
+    # User inputs for feature group and version
+    st.sidebar.title("Data Settings")
+    feature_group_name = st.sidebar.text_input("Feature Group Name", value="predictions")
+    version = st.sidebar.number_input("Feature Group Version", value=1, min_value=1)
+    filename = st.sidebar.text_input("Local Filename", value="data.csv")
+
+    # Check for valid local data
+    if is_local_data_valid():
+        st.write("Using cached local data.")
+        st.session_state.data = load_local_data(filename)
+    else:
+        # Fetch data if local data is invalid
+        if st.session_state.hopsworks_project is None:
+            st.write("Initializing Hopsworks connection...")
+            st.session_state.hopsworks_project = connect_to_hopsworks()
+            st.success("Connected to Hopsworks!")
+        
+        project = st.session_state.hopsworks_project
+        data = fetch_data_from_feature_group(project, feature_group_name, version)
+        filepath = save_data_locally(data, filename)
+        st.session_state.data = data
+        st.success(f"Data fetched and saved locally at {filepath}")
+
+    # Display data and graphs
+    if st.session_state.data is not None:
+        plot_graphs(st.session_state.data)
+
+main()