Update app.py

app.py

@@ -4,26 +4,54 @@ import plotly.express as px
 from datetime import datetime, timedelta
 from simple_salesforce import Salesforce
 from transformers import pipeline
-from reportlab.lib.pagesizes import letter
-from reportlab.platypus import SimpleDocTemplate, Table, TableStyle, Paragraph
-from reportlab.lib import colors
-from reportlab.lib.styles import getSampleStyleSheet
 from utils import fetch_salesforce_data, detect_anomalies, generate_pdf_report
 
 # Streamlit app configuration
 st.set_page_config(page_title="LabOps Dashboard", layout="wide")
 
-# Salesforce authentication (replace with your credentials)
-sf = Salesforce(
-    username=st.secrets["sf_username"],
-    password=st.secrets["sf_password"],
-    security_token=st.secrets["sf_security_token"]
-)
+# Cache Salesforce connection
+@st.cache_resource
+def init_salesforce():
+    try:
+        return Salesforce(
+            username=st.secrets["sf_username"],
+            password=st.secrets["sf_password"],
+            security_token=st.secrets["sf_security_token"]
+        )
+    except Exception as e:
+        st.error(f"Failed to connect to Salesforce: {e}")
+        return None
 
-# Initialize Hugging Face anomaly detection pipeline
-anomaly_detector = pipeline("text-classification", model="bert-base-uncased", tokenizer="bert-base-uncased")
+# Cache Hugging Face model
+@st.cache_resource
+def init_anomaly_detector():
+    return pipeline("text-classification", model="distilbert-base-uncased", tokenizer="distilbert-base-uncased")
+
+# Initialize connections
+sf = init_salesforce()
+anomaly_detector = init_anomaly_detector()
+
+# Cache data fetching
+@st.cache_data(ttl=10)  # Cache for 10 seconds to meet refresh requirement
+def get_filtered_data(lab_site, equipment_type, date_start, date_end):
+    query = f"""
+        SELECT Equipment__c, Log_Timestamp__c, Status__c, Usage_Count__c, Lab__c, Equipment_Type__c
+        FROM SmartLog__c
+        WHERE Log_Timestamp__c >= {date_start.strftime('%Y-%m-%d')}
+        AND Log_Timestamp__c <= {date_end.strftime('%Y-%m-%d')}
+    """
+    if lab_site != "All":
+        query += f" AND Lab__c = '{lab_site}'"
+    if equipment_type != "All":
+        query += f" AND Equipment_Type__c = '{equipment_type}'"
+    query += " LIMIT 1000"  # Mitigate data overload
+    return fetch_salesforce_data(sf, query)
 
 def main():
+    if sf is None:
+        st.error("Cannot proceed without Salesforce connection.")
+        return
+
     st.title("Multi-Device LabOps Dashboard")
     
     # Filters
@@ -33,63 +61,89 @@ def main():
     with col2:
         equipment_type = st.selectbox("Equipment Type", ["All", "Cell Analyzer", "Weight Log", "UV Verification"])
     with col3:
-        date_range = st.date_input("Date Range", [datetime.now() - timedelta(days=7), datetime.now()])
+        default_start = datetime.now() - timedelta(days=7)
+        default_end = datetime.now()
+        date_range = st.date_input("Date Range", [default_start, default_end])
     
-    # Fetch data from Salesforce
-    query = f"""
-        SELECT Equipment__c, Log_Timestamp__c, Status__c, Usage_Count__c
-        FROM SmartLog__c
-        WHERE Log_Timestamp__c >= {date_range[0].strftime('%Y-%m-%d')}
-        AND Log_Timestamp__c <= {date_range[1].strftime('%Y-%m-%d')}
-    """
-    if lab_site != "All":
-        query += f" AND Lab__c = '{lab_site}'"
-    if equipment_type != "All":
-        query += f" AND Equipment_Type__c = '{equipment_type}'"
-    
-    data = fetch_salesforce_data(sf, query)
-    df = pd.DataFrame(data)
-    
-    if df.empty:
+    # Validate date range
+    if len(date_range) != 2:
+        st.warning("Please select a valid date range.")
+        return
+    date_start, date_end = date_range
+
+    # Fetch and process data
+    data = get_filtered_data(lab_site, equipment_type, date_start, date_end)
+    if not data:
         st.warning("No data available for the selected filters.")
         return
     
-    # Detect anomalies using Hugging Face
-    df["Anomaly"] = df["Status__c"].apply(lambda x: detect_anomalies(x, anomaly_detector))
-    
+    df = pd.DataFrame(data)
+    df["Log_Timestamp__c"] = pd.to_datetime(df["Log_Timestamp__c"])
+    df["Anomaly"] = df["Status__c"].apply(lambda x: detect_anomalies(str(x), anomaly_detector))
+
+    # Pagination
+    page_size = 10
+    page = st.number_input("Page", min_value=1, value=1, step=1)
+    start_idx = (page - 1) * page_size
+    end_idx = start_idx + page_size
+    paginated_df = df[start_idx:end_idx]
+
     # Device Cards
     st.subheader("Device Status")
-    for equipment in df["Equipment__c"].unique():
-        device_data = df[df["Equipment__c"] == equipment]
-        latest_log = device_data.iloc[-1]
-        anomaly = "⚠️ Anomaly" if latest_log["Anomaly"] == "POSITIVE" else "✅ Normal"
+    for _, row in paginated_df.iterrows():
+        anomaly = "⚠️ Anomaly" if row["Anomaly"] == "POSITIVE" else "✅ Normal"
         st.markdown(f"""
-            **{equipment}** | Health: {latest_log["Status__c"]} | Usage: {latest_log["Usage_Count__c"]} | Last Log: {latest_log["Log_Timestamp__c"]} | {anomaly}
+            **{row['Equipment__c']}** | Lab: {row['Lab__c']} | Health: {row['Status__c']} | 
+            Usage: {row['Usage_Count__c']} | Last Log: {row['Log_Timestamp__c'].strftime('%Y-%m-%d %H:%M:%S')} | {anomaly}
         """)
     
     # Usage Chart
     st.subheader("Usage Trends")
-    fig = px.line(df, x="Log_Timestamp__c", y="Usage_Count__c", color="Equipment__c", title="Daily Usage Trends")
+    fig = px.line(
+        df, 
+        x="Log_Timestamp__c", 
+        y="Usage_Count__c", 
+        color="Equipment__c", 
+        title="Daily Usage Trends",
+        labels={"Log_Timestamp__c": "Timestamp", "Usage_Count__c": "Usage Count"}
+    )
+    fig.update_layout(xaxis_title="Timestamp", yaxis_title="Usage Count")
     st.plotly_chart(fig, use_container_width=True)
-    
+
     # Downtime Chart
+    st.subheader("Downtime Patterns")
     downtime_df = df[df["Status__c"] == "Down"]
     if not downtime_df.empty:
-        fig_downtime = px.histogram(downtime_df, x="Log_Timestamp__c", color="Equipment__c", title="Downtime Patterns")
+        fig_downtime = px.histogram(
+            downtime_df, 
+            x="Log_Timestamp__c", 
+            color="Equipment__c", 
+            title="Downtime Patterns",
+            labels={"Log_Timestamp__c": "Timestamp"}
+        )
+        fig_downtime.update_layout(xaxis_title="Timestamp", yaxis_title="Downtime Count")
         st.plotly_chart(fig_downtime, use_container_width=True)
-    
+    else:
+        st.info("No downtime events found for the selected filters.")
+
     # AMC Reminders
     st.subheader("AMC Reminders")
     amc_query = "SELECT Equipment__c, AMC_Expiry_Date__c FROM Equipment__c WHERE AMC_Expiry_Date__c <= NEXT_N_DAYS:14"
-    amc_data = fetch_salesforce_data(sf, amc_query)
-    for record in amc_data:
-        st.write(f"Equipment {record['Equipment__c']} - AMC Expiry: {record['AMC_Expiry_Date__c']}")
-    
+    amc_data = fetch_salesforce_data(sf, amc_query, retries=3)
+    if amc_data:
+        for record in amc_data:
+            st.write(f"Equipment {record['Equipment__c']} - AMC Expiry: {record['AMC_Expiry_Date__c']}")
+    else:
+        st.info("No AMC expiries within the next 14 days.")
+
     # Export PDF
     if st.button("Export PDF Report"):
-        pdf_file = generate_pdf_report(df, lab_site, equipment_type, date_range)
-        with open(pdf_file, "rb") as f:
-            st.download_button("Download PDF", f, file_name="LabOps_Report.pdf")
+        try:
+            pdf_file = generate_pdf_report(df, lab_site, equipment_type, [date_start, date_end])
+            with open(pdf_file, "rb") as f:
+                st.download_button("Download PDF", f, file_name="LabOps_Report.pdf", mime="application/pdf")
+        except Exception as e:
+            st.error(f"Failed to generate PDF: {e}")
 
 if __name__ == "__main__":
     main()