hotfix/24h (#3)

- changes (531e6a3e742127ce79b765a0ee13632ef01160b2)
- completed jobs logic (539357a1d564a51d449f6943469b0e1d09242192)

api.py

@@ -8,8 +8,7 @@ import utils
 import pandas as pd
 import uvicorn
 
-from classes import Productivity, Throughput
-
+from classes import Productivity, ProductivityData, Throughput
 
 
 # Global variables (saves time on loading data)
@@ -32,7 +31,6 @@ def load_data():
     data_all = utils.preload_data()
     
     data_24h = data_all[(pd.Timestamp.now() -  data_all['updated_at'].apply(lambda x: pd.Timestamp(x)) < pd.Timedelta('1 days'))]
-
     reload_timestamp = datetime.datetime.now().strftime('%D %T')
 
     print(f'Reloaded data at {reload_timestamp}')
@@ -63,7 +61,12 @@ def productivity_metrics():
     Get the productivity metrics
     """
 
-    return Productivity(all_time=utils.get_productivity(data_all), last_24h=utils.get_productivity(data_24h))
+    # Unpack the metrics using the correct keys
+    result = utils.get_productivity(df_all=data_all, df_24h=data_24h)
+    all_time = ProductivityData(**result['all_time'])
+    last_24h = ProductivityData(**result['last_24h'])
+
+    return Productivity(all_time=all_time, last_24h=last_24h)
 
 
 @app.get("/throughput", response_model=Throughput)

app.py

@@ -34,10 +34,15 @@ productivity_all = requests.get(f'{BASE_URL}/productivity').json()
 productivity = productivity_all['all_time']
 productivity_24h = productivity_all['last_24h']
 
+# st.write(productivity_all)
+# # st.write(productivity)
+# st.write(productivity_24h)
 
 m1, m2 = st.columns(2)
-m1.metric('Unique proteins folded', f'{productivity["unique_folded"]:,.0f}', delta=f'{productivity_24h["unique_folded"]:,.0f} (24h)')
-m2.metric('Total jobs completed', f'{productivity["total_completed_jobs"]:,.0f}', delta=f'{productivity_24h["total_completed_jobs"]:,.0f} (24h)')
+
+m1.metric('Unique proteins folded', f'{productivity.get("unique_folded", 0):,.0f}', delta=f'{productivity_24h.get("unique_folded", 0):,.0f} (24h)')
+m2.metric('Total jobs completed', f'{productivity.get("total_completed_jobs", 0):,.0f}', delta=f'{productivity_24h.get("total_completed_jobs", 0):,.0f} (24h)')
+
 # m3.metric('Total simulation steps', f'{productivity.get("total_md_steps"):,.0f}', delta=f'{productivity_24h.get("total_md_steps"):,.0f} (24h)')
 
 # st.markdown('<br>', unsafe_allow_html=True)

ecosystem.config.js

@@ -1,14 +1,14 @@
 module.exports = {
-    apps: [
-      {
-        name: 'hf-dashboard-api',   
-        script: '/home/spunion/Sn25/api.py',   
-        interpreter: '/home/spunion/Sn25/venv/bin/python', 
-        autorestart: true,    
-        watch: false,         
-        env: {
-          NODE_ENV: 'production',
-        },
+  apps: [
+    {
+      name: 'hf-dashboard-api',   
+      script: '/home/spunion/Sn25/api.py',   
+      interpreter: '/home/spunion/Sn25/venv/bin/python', 
+      autorestart: true,    
+      watch: false,         
+      env: {
+        NODE_ENV: 'production',
       },
-    ],
-  };
+    },
+  ],
+};

utils.py

@@ -153,21 +153,37 @@ def get_data_transferred(df, unit='GB'):
     }
 
 
-def get_productivity(df):
-
-    # Estimate the number of unique pdbs folded using our heuristic
-    unique_folded = len(df.pdb_id.value_counts())
-    # Estimate the total number of jobs completed using our heuristic
-    completed_jobs = len(df[df.active == False])
-
-    total_historical_run_updates = df.active.isna().sum() 
-    total_historical_completed_jobs = total_historical_run_updates//10 # this is an estimate based on minimum number of updates per pdb    
-    
- 
-    return {
-        'unique_folded': unique_folded,
-        'total_completed_jobs': (completed_jobs + total_historical_completed_jobs).item(),
+def get_productivity(df_all, df_24h): 
+    result = {
+        'all_time': {
+            'unique_folded': 0,
+            'total_completed_jobs': 0
+        },
+        'last_24h': {
+            'unique_folded': 0,
+            'total_completed_jobs': 0
+        }
     }
+    if df_all is not None:
+        unique_folded_all = len(df_all.pdb_id.value_counts())
+        completed_jobs_all = len(df_all[df_all.active == False])
+
+        total_historical_run_updates = df_all.active.isna().sum() 
+        total_historical_completed_jobs = total_historical_run_updates//10 # this is an estimate based on minimum number of updates per pdb    
+        
+        result['all_time'].update({
+            'unique_folded': unique_folded_all,
+            'total_completed_jobs': (completed_jobs_all + total_historical_completed_jobs).item(),
+        })
+        
+    if df_24h is not None:
+        completed_jobs_24h = df_24h[df_24h['updated_count'] >= 10]
+        unique_completed_jobs_24h = completed_jobs_24h.drop_duplicates(subset=['pdb_id'], keep='first')
+        result['last_24h'].update({
+            'unique_folded': len(unique_completed_jobs_24h),
+            'total_completed_jobs': len(completed_jobs_24h)
+        })
+    return result
 
 def get_leaderboard(df, ntop=10, entity_choice='identity'):