Initial version

iamontheinet · iamontheinet · commit bd96add94770 · 2023-06-06T10:52:37.000-07:00
diff --git a/.gitignore b/.gitignore
@@ -0,0 +1,2 @@
+connection.json
+.DS_Store
diff --git a/app/V1/libraries/environment.yml b/app/V1/libraries/environment.yml
@@ -0,0 +1,5 @@
+name: sf_env
+channels:
+- snowflake
+dependencies:
+- snowflake-native-apps-permission
diff --git a/app/V1/libraries/procs.py b/app/V1/libraries/procs.py
@@ -0,0 +1,5 @@
+def billing_event(session,number_of_rows):
+    import time
+    dts = int(time.time() *1000)
+    # session.sql(f"CALL SYSTEM$CREATE_BILLING_EVENT('NUM_ROWS', '', {dts}, {dts}, {number_of_rows * .1}, '', '')").collect()
+    return "Ok"
diff --git a/app/V1/libraries/streamlit.py b/app/V1/libraries/streamlit.py
@@ -0,0 +1,114 @@
+import streamlit as st
+import pandas as pd
+import altair as alt
+from snowflake.snowpark.context import get_active_session
+from snowflake.snowpark.functions import count_distinct,col,sum
+import snowflake.permissions as permission
+
+st.set_page_config(layout="wide")
+st.title("Where Are My Ski Goggles?")
+session = get_active_session()
+
+# def configure_reference_button_click():
+#     permission.request_reference("enrichment_table")
+
+# st.button("Request Reference", on_click=permission.request_reference, args=['enrichment_table'], key="single-valued")
+# st.button("Request Reference", on_click=configure_reference_button_click)
+
+def load_app(orders_table,site_recovery_table):
+    with st.spinner("Loading lead time, order status, and supplier performance. Please wait..."):
+        df = session.sql(f"SELECT t1.order_id,t2.ship_order_id,t1.material_name,t1.supplier_name, t1.quantity, t1.cost, t2.status, t2.lat, t2.lon FROM {orders_table} as t1 INNER JOIN MFG_SHIPPING as t2 ON t2.ORDER_ID = t1.ORDER_ID ORDER BY t1.order_id")
+        session.call("billing_event",df.count())
+        df_order_status = df.group_by('status').agg(count_distinct('order_id').as_('TOTAL RECORDS')).order_by('status').to_pandas()
+
+        df_cal_lead_time = session.sql(f"SELECT t1.order_id,t2.ship_order_id,t1.material_name,t1.supplier_name,t1.quantity,t1.cost,t2.status,t2.lat,t2.lon,cal_lead_time(t1.process_supply_day,t2.duration,t2.recovery_days) as lead_time FROM {orders_table} as t1 INNER JOIN (SELECT order_id, ship_order_id, status, duration, MFG_SHIPPING.lat, MFG_SHIPPING.lon, IFF({site_recovery_table}.recovery_weeks * 7::int = {site_recovery_table}.recovery_weeks * 7,{site_recovery_table}.recovery_weeks * 7,0) as recovery_days from MFG_SHIPPING LEFT OUTER JOIN {site_recovery_table} ON MFG_SHIPPING.lon = {site_recovery_table}.lon AND MFG_SHIPPING.lat = {site_recovery_table}.lat) as t2 ON t2.ORDER_ID = t1.ORDER_ID ORDER BY t1.order_id")
+        df_supplier_perf = df_cal_lead_time.group_by('supplier_name').agg(sum(col('lead_time')).as_('TOTAL LEAD TIME')).sort('TOTAL LEAD TIME', ascending=True).limit(20).to_pandas()
+        df_lead_time = df_cal_lead_time.select('order_id','lead_time').sort('order_id', ascending=True).to_pandas()
+        
+        with st.container():
+            col1,col2 = st.columns(2,gap='small')
+            with col1:
+                # Display Lead Time Status chart
+                st.subheader("Lead Time Status")
+                lead_time_base = alt.Chart(df_lead_time).encode(alt.X("ORDER_ID", title="ORDER ID", sort=None))
+                lead_time_base_bars = lead_time_base.mark_bar().encode(
+                    color=alt.value("#249DC9"),
+                    y=alt.Y("LEAD_TIME", title="LEAD TIME DAYS")
+                )
+                line = alt.Chart(pd.DataFrame({'y': [60]})).mark_rule(color='rgb(249,158,54)').encode(y='y')
+                lead_time_chart = alt.layer(lead_time_base_bars)
+                st.altair_chart(lead_time_chart + line, use_container_width=True)
+        
+            def color_lead_time(val):
+                return f'background-color: rgb(249,158,54)'
+        
+            with col2:
+                # Underlying Data
+                st.subheader("Orders with Lead Time Status >= 60days")
+                df_lead_time_60_days = df_cal_lead_time.select('lead_time','order_id','ship_order_id','material_name','supplier_name','quantity','cost').filter(col('lead_time') > 60).sort('lead_time').to_pandas()
+                df_lead_time_60_days['LEAD_TIME'] = df_lead_time_60_days['LEAD_TIME'].astype('int')
+                st.dataframe(df_lead_time_60_days.style.applymap(color_lead_time, subset=['LEAD_TIME']))
+        
+        with st.container():
+            col1,col2 = st.columns(2,gap='small')
+            with col1:
+                # Display Supplier Performance
+                st.subheader("Supplier Performance")
+                supplier_perf_base = alt.Chart(df_supplier_perf).encode(alt.X("SUPPLIER_NAME:N", title="SUPPLIER NAME", sort=None))
+                supplier_perf_base_bars = supplier_perf_base.mark_bar().encode(
+                    color=alt.value("#249DC9"),
+                    y=alt.Y("TOTAL LEAD TIME", title="TOTAL LEAD TIME")
+                )
+                supplier_perf_chart = alt.layer(supplier_perf_base_bars)
+                st.altair_chart(supplier_perf_chart, use_container_width=True)
+                
+                # Underlying Data
+                # st.subheader("Underlying Data")
+                # st.dataframe(df_lead_time)
+        
+            with col2:
+                # Display Purchase Order Status 
+                st.subheader("Purchase Order Status")
+                order_status_base = alt.Chart(df_order_status).encode(alt.X("STATUS", sort=['Order_confirmed','Shipped','In_Transit','Out_for_delivery','Delivered']))
+                order_status_base_bars = order_status_base.mark_bar().encode(
+                    color=alt.value("#249DC9"),
+                    y=alt.Y("TOTAL RECORDS", title="TOTAL RECORDS")
+                )
+                order_status_chart = alt.layer(order_status_base_bars)
+                st.altair_chart(order_status_chart, use_container_width=True)
+                
+                # Underlying Data
+                # st.subheader("Underlying Data")
+                # st.dataframe(df_order_status)
+
+if ('merge' in st.session_state and st.session_state.merge):
+    src_db = st.session_state.src_db
+    src_schema = st.session_state.src_schema
+    src_orders_table = st.session_state.src_orders_table
+    src_site_recovery_table = st.session_state.src_site_recovery_table
+    orders_table = f"{src_db}.{src_schema}.{src_orders_table}"
+    site_recovery_table = f"{src_db}.{src_schema}.{src_site_recovery_table}"
+    load_app(orders_table,site_recovery_table)
+else:
+    with st.expander("Select Orders and Site Recovery Datasets"):
+        src_db = st.text_input('Database',value='DASH_DB')
+        src_schema = st.text_input('Schema',value='DASH_SCHEMA')
+        src_orders_table = st.text_input('Orders Table',value='MFG_ORDERS')
+        src_site_recovery_table = st.text_input('Site Recovery Table',value='MFG_SITE_RECOVERY')
+        orders_table = ""
+        site_recovery_table = ""
+        if st.button("Merge Orders with Shipping Data"):
+          try:
+            st.session_state.merge = 'merge'
+            st.session_state.src_db = src_db
+            st.session_state.src_schema = src_schema
+            st.session_state.src_orders_table = src_orders_table
+            st.session_state.src_site_recovery_table = src_site_recovery_table
+            orders_table = f"{src_db}.{src_schema}.{src_orders_table}"
+            site_recovery_table = f"{src_db}.{src_schema}.{src_site_recovery_table}"
+          except Exception as e:
+            st.write(f"Source datasets in {src_db}.{src_schema} not found. Cannot proceed!")
+            st.write(e)
+    
+    if len(orders_table) > 0:
+        load_app(orders_table,site_recovery_table)
diff --git a/app/V1/libraries/udf.py b/app/V1/libraries/udf.py
@@ -0,0 +1,14 @@
+def cal_distance(lat1,lon1,lat2,lon2):
+   import math
+   radius = 3959 # miles == 6371 km
+   dlat = math.radians(lat2-lat1)
+   dlon = math.radians(lon2-lon1)
+   a = math.sin(dlat/2) * math.sin(dlat/2) + math.cos(math.radians(lat1)) \
+        * math.cos(math.radians(lat2)) * math.sin(dlon/2) * math.sin(dlon/2)
+   c = 2 * math.atan2(math.sqrt(a), math.sqrt(1-a))
+   d = radius * c
+   return d
+
+# process_supply_day + duration + recovery_weeks * 7 (days)
+def cal_lead_time(i,j,k):
+   return i + j + k
diff --git a/app/V1/manifest.yml b/app/V1/manifest.yml
@@ -0,0 +1,31 @@
+#version identifier
+manifest_version: 1
+
+version:
+  name: V1
+  label: Version One
+  comment: The first version of the application
+
+#artifacts that are distributed from this version of the package
+artifacts:
+  setup_script: scripts/setup.sql
+  default_streamlit: app_instance_schema.streamlit
+  extension_code: true
+
+#runtime configuration for this version
+configuration:
+  log_level: debug
+  trace_level: off
+
+# references: # optional
+#   - enrichment_table:
+#       label: "Enrich Orders" # required subfield
+#       # description is a required subfield
+#       description: "Select orders table"
+#       privileges: # required subfield, must be length >= 1
+#         - SELECT
+#         - INSERT
+#         - UPDATE
+#       object_type: Table # required subfield
+#       multi_valued: true # optional (default: false)
+#       register_callback: config.register_reference # required
diff --git a/app/V1/scripts/setup.sql b/app/V1/scripts/setup.sql
@@ -0,0 +1,49 @@
+-- =================
+-- This script runs when the app is installed 
+-- =================
+
+-- Create Application Role and Schema
+create application role if not exists app_instance_role;
+create or alter versioned schema app_instance_schema;
+
+-- Share data
+create or replace view app_instance_schema.MFG_SHIPPING as select * from shared_content_schema.MFG_SHIPPING;
+
+-- Create Streamlit app
+create or replace streamlit app_instance_schema.streamlit from '/libraries' main_file='streamlit.py';
+
+-- Create UDFs
+create or replace function app_instance_schema.cal_lead_time(i int, j int, k int)
+returns float
+language python
+runtime_version = '3.8'
+packages = ('snowflake-snowpark-python')
+imports = ('/libraries/udf.py')
+handler = 'udf.cal_lead_time'
+
+;create or replace function app_instance_schema.cal_distance(slat float,slon float,elat float,elon float)
+returns float
+language python
+runtime_version = '3.8'
+packages = ('snowflake-snowpark-python','pandas','scikit-learn==1.1.1')
+imports = ('/libraries/udf.py')
+handler = 'udf.cal_distance'
+;
+
+-- Create Stored Procedure
+create or replace procedure app_instance_schema.billing_event(number_of_rows int)
+returns string
+language python
+runtime_version = '3.8'
+packages = ('snowflake-snowpark-python')
+imports = ('/libraries/procs.py')
+handler = 'procs.billing_event'
+;
+
+-- Grant usage and permissions on objects
+grant usage on schema app_instance_schema to application role app_instance_role;
+grant usage on function app_instance_schema.cal_lead_time(int,int,int) to application role app_instance_role;
+grant usage on procedure app_instance_schema.billing_event(int) to application role app_instance_role;
+grant usage on function app_instance_schema.cal_distance(float,float,float,float) to application role app_instance_role;
+grant SELECT on view app_instance_schema.MFG_SHIPPING to application role app_instance_role;
+grant usage on streamlit app_instance_schema.streamlit to application role app_instance_role;
