update app

app.py

@@ -1,5 +1,3 @@
-"""Annotation Progress Dashboard - Simple & Elegant"""
-
 import re
 import os
 import pickle
@@ -10,10 +8,6 @@ import pandas as pd
 import plotly.graph_objects as go
 import requests
 
-# =============================================================================
-# Configuration
-# =============================================================================
-
 GOAL_WORDS = 2_200_000
 CATEGORY_GOAL = 1_100_000
 
@@ -33,17 +27,9 @@ TEAM_COLORS = {
 # Cache file location (persists between runs)
 CACHE_FILE = Path(".cache.pkl")
 
-# =============================================================================
-# Setup
-# =============================================================================
-
 st.set_page_config(page_title="Annotation Progress", page_icon="📊", layout="wide")
 
 
-# =============================================================================
-# Data Loading
-# =============================================================================
-
 def fetch_project_data(proj, url, headers):
     """Fetch data from one project (for parallel execution)."""
     pid, name, task_count = proj["id"], proj.get("title", f"Project {proj['id']}"), proj.get("task_number", 0)
@@ -52,12 +38,7 @@ def fetch_project_data(proj, url, headers):
     rows = []
     page = 1
     while True:
-        resp = requests.get(
-            f"{url}/api/projects/{pid}/tasks",
-            headers=headers,
-            params={"page": page, "page_size": 100},
-            timeout=30
-        )
+        resp = requests.get(f"{url}/api/projects/{pid}/tasks", headers=headers, params={"page": page, "page_size": 100}, timeout=30)
         resp.raise_for_status()
         data = resp.json()
         tasks = data if isinstance(data, list) else data.get("tasks", [])
@@ -72,11 +53,17 @@ def fetch_project_data(proj, url, headers):
 
             annots = [a for a in task.get("annotations", []) if not a.get("was_cancelled")]
             if not annots:
-                rows.append({
-                    "project_id": pid, "project": name, "project_group": group,
-                    "date": None, "state": "Not Annotated",
-                    "words": int(words), "category": category
-                })
+                rows.append(
+                    {
+                        "project_id": pid,
+                        "project": name,
+                        "project_group": group,
+                        "date": None,
+                        "state": "Not Annotated",
+                        "words": int(words),
+                        "category": category,
+                    }
+                )
                 continue
 
             ann = annots[0]
@@ -98,11 +85,9 @@ def fetch_project_data(proj, url, headers):
             else:
                 state = "Acceptable"
 
-            rows.append({
-                "project_id": pid, "project": name, "project_group": group,
-                "date": date, "state": state,
-                "words": int(words), "category": category
-            })
+            rows.append(
+                {"project_id": pid, "project": name, "project_group": group, "date": date, "state": state, "words": int(words), "category": category}
+            )
 
         if isinstance(data, list) and len(data) < 100:
             break
@@ -188,10 +173,6 @@ def load_data():
     return df
 
 
-# =============================================================================
-# Helper Functions
-# =============================================================================
-
 def anonymize(name):
     """Convert '26 [Name Lastname]' to 'N.L. (26)'"""
     if name == "Others":
@@ -205,10 +186,6 @@ def anonymize(name):
     return name
 
 
-# =============================================================================
-# Main App
-# =============================================================================
-
 st.title("📊 Annotation Progress Dashboard")
 st.markdown("---")
 
@@ -223,7 +200,7 @@ progress = total / GOAL_WORDS * 100
 
 col1, col2 = st.columns(2)
 col1.metric("Progress toward 2.2M", f"{total:,}", f"{progress:.1f}%")
-col2.metric("Remaining", f"{remaining:,}", f"{100-progress:.1f}%")
+col2.metric("Remaining", f"{remaining:,}", f"{100 - progress:.1f}%")
 
 st.markdown("---")
 
@@ -239,15 +216,10 @@ with tab1:
     # Filter data - use GOAL_STATES to match progress metrics
     df_week = df[df["is_goal_state"] & df["date"].notna()].copy()
     df_week["week_start"] = df_week["date"] - pd.to_timedelta(df_week["date"].dt.dayofweek, unit="d")
-    df_week["member"] = df_week.apply(
-        lambda r: anonymize(r["project"]) if r["project_group"] == "Our Team" else "Others",
-        axis=1
-    )
+    df_week["member"] = df_week.apply(lambda r: anonymize(r["project"]) if r["project_group"] == "Our Team" else "Others", axis=1)
 
     # Weekly pivot (all data)
-    weekly_all = df_week.pivot_table(
-        index="week_start", columns="member", values="words", aggfunc="sum", fill_value=0
-    ).astype(int)
+    weekly_all = df_week.pivot_table(index="week_start", columns="member", values="words", aggfunc="sum", fill_value=0).astype(int)
 
     # Split into before and after cutoff
     weekly_before = weekly_all[weekly_all.index < cutoff_date]
@@ -275,10 +247,7 @@ with tab1:
 
     # Format weekly data for display
     display = weekly_after.reset_index()
-    display["Week"] = (
-        display["week_start"].dt.strftime("%Y-%m-%d") + " - " +
-        (display["week_start"] + pd.Timedelta(days=6)).dt.strftime("%Y-%m-%d")
-    )
+    display["Week"] = display["week_start"].dt.strftime("%Y-%m-%d") + " - " + (display["week_start"] + pd.Timedelta(days=6)).dt.strftime("%Y-%m-%d")
     display = display.drop("week_start", axis=1)
     display = display[["Week"] + list(totals.index) + ["Total"]]
 
@@ -331,18 +300,20 @@ with tab2:
     total_fixing = mok_fixing + zin_fixing
     total_all = total_ready + total_fixing
 
-    cat_df = pd.DataFrame({
-        "Category": ["mokslinis", "ziniasklaida", "TOTAL"],
-        "Ready": [f"{mok_ready:,}", f"{zin_ready:,}", f"{total_ready:,}"],
-        "Needs Fixing": [f"{mok_fixing:,}", f"{zin_fixing:,}", f"{total_fixing:,}"],
-        "Total": [f"{mok_total:,}", f"{zin_total:,}", f"{total_all:,}"],
-        "Goal": [f"{CATEGORY_GOAL:,}", f"{CATEGORY_GOAL:,}", f"{GOAL_WORDS:,}"],
-        "Progress": [
-            f"{mok_total/CATEGORY_GOAL*100:.1f}%",
-            f"{zin_total/CATEGORY_GOAL*100:.1f}%",
-            f"{total_all/GOAL_WORDS*100:.1f}%"
-        ]
-    })
+    cat_df = pd.DataFrame(
+        {
+            "Category": ["mokslinis", "ziniasklaida", "TOTAL"],
+            "Ready": [f"{mok_ready:,}", f"{zin_ready:,}", f"{total_ready:,}"],
+            "Needs Fixing": [f"{mok_fixing:,}", f"{zin_fixing:,}", f"{total_fixing:,}"],
+            "Total": [f"{mok_total:,}", f"{zin_total:,}", f"{total_all:,}"],
+            "Goal": [f"{CATEGORY_GOAL:,}", f"{CATEGORY_GOAL:,}", f"{GOAL_WORDS:,}"],
+            "Progress": [
+                f"{mok_total / CATEGORY_GOAL * 100:.1f}%",
+                f"{zin_total / CATEGORY_GOAL * 100:.1f}%",
+                f"{total_all / GOAL_WORDS * 100:.1f}%",
+            ],
+        }
+    )
     st.dataframe(cat_df, hide_index=True, use_container_width=True)
 
     st.markdown("---")
@@ -350,10 +321,7 @@ with tab2:
 
     # Cumulative data
     df_cum = df[df["is_goal_state"] & df["date"].notna()].copy()
-    df_cum["member"] = df_cum.apply(
-        lambda r: anonymize(r["project"]) if r["project_group"] == "Our Team" else "Others",
-        axis=1
-    )
+    df_cum["member"] = df_cum.apply(lambda r: anonymize(r["project"]) if r["project_group"] == "Our Team" else "Others", axis=1)
 
     daily = df_cum.groupby(["date", "member"])["words"].sum().reset_index()
     pivot = daily.pivot_table(index="date", columns="member", values="words", fill_value=0)
@@ -380,61 +348,68 @@ with tab2:
     fig = go.Figure()
 
     # Goal lines
-    fig.add_hline(y=1_100_000, line_dash="dot", line_color="orange",
-                  annotation_text="Midpoint: 1.1M", annotation_position="top left")
-    fig.add_hline(y=GOAL_WORDS, line_dash="dot", line_color="red",
-                  annotation_text="Goal: 2.2M", annotation_position="top left")
+    fig.add_hline(y=1_100_000, line_dash="dot", line_color="orange", annotation_text="Midpoint: 1.1M", annotation_position="top left")
+    fig.add_hline(y=GOAL_WORDS, line_dash="dot", line_color="red", annotation_text="Goal: 2.2M", annotation_position="top left")
 
     # Members
     members = [c for c in cumulative.columns if c not in ["Total", "Others"]]
     members = sorted(members, key=lambda x: cumulative[x].iloc[-1], reverse=True)
 
     if "Others" in cumulative.columns:
-        fig.add_trace(go.Scatter(
-            x=cumulative.index, y=cumulative["Others"],
-            name=f"Others: {cumulative['Others'].iloc[-1]:,.0f}",
-            mode="lines", line=dict(width=2, color="#7f8c8d")
-        ))
+        fig.add_trace(
+            go.Scatter(
+                x=cumulative.index,
+                y=cumulative["Others"],
+                name=f"Others: {cumulative['Others'].iloc[-1]:,.0f}",
+                mode="lines",
+                line=dict(width=2, color="#7f8c8d"),
+            )
+        )
 
     for m in members:
         color = TEAM_COLORS.get(m, "#34495e")
-        fig.add_trace(go.Scatter(
-            x=cumulative.index, y=cumulative[m],
-            name=f"{m}: {cumulative[m].iloc[-1]:,.0f}",
-            mode="lines", line=dict(width=2, color=color)
-        ))
+        fig.add_trace(
+            go.Scatter(x=cumulative.index, y=cumulative[m], name=f"{m}: {cumulative[m].iloc[-1]:,.0f}", mode="lines", line=dict(width=2, color=color))
+        )
 
     # Total
-    fig.add_trace(go.Scatter(
-        x=cumulative.index, y=cumulative["Total"],
-        name=f"Total: {cumulative['Total'].iloc[-1]:,.0f}",
-        mode="lines", line=dict(width=3, color="#d4af37"),
-        fill="tozeroy", fillcolor="rgba(212, 175, 55, 0.1)"
-    ))
+    fig.add_trace(
+        go.Scatter(
+            x=cumulative.index,
+            y=cumulative["Total"],
+            name=f"Total: {cumulative['Total'].iloc[-1]:,.0f}",
+            mode="lines",
+            line=dict(width=3, color="#d4af37"),
+            fill="tozeroy",
+            fillcolor="rgba(212, 175, 55, 0.1)",
+        )
+    )
 
     # Projection
     if completion:
         proj_dates = pd.date_range(last_date, completion, freq="D")
         proj_vals = current + rate * (proj_dates - last_date).days
-        fig.add_trace(go.Scatter(
-            x=proj_dates, y=proj_vals,
-            name=f"Projection ({int(weekly_rate):,}/wk)",
-            mode="lines", line=dict(width=3, color="#d4af37", dash="dot")
-        ))
-        fig.add_trace(go.Scatter(
-            x=[completion], y=[GOAL_WORDS],
-            mode="markers+text", marker=dict(size=14, color="#d4af37", symbol="diamond"),
-            text=[completion.strftime("%b %d")], textposition="top center",
-            showlegend=False
-        ))
+        fig.add_trace(
+            go.Scatter(
+                x=proj_dates, y=proj_vals, name=f"Projection ({int(weekly_rate):,}/wk)", mode="lines", line=dict(width=3, color="#d4af37", dash="dot")
+            )
+        )
+        fig.add_trace(
+            go.Scatter(
+                x=[completion],
+                y=[GOAL_WORDS],
+                mode="markers+text",
+                marker=dict(size=14, color="#d4af37", symbol="diamond"),
+                text=[completion.strftime("%b %d")],
+                textposition="top center",
+                showlegend=False,
+            )
+        )
         title = f"Cumulative Progress → Est. {completion.strftime('%B %d, %Y')}"
     else:
         title = "Cumulative Progress"
 
-    fig.update_layout(
-        title=title, xaxis_title="Date", yaxis_title="Cumulative Words",
-        height=600, hovermode="x unified", template="plotly_white"
-    )
+    fig.update_layout(title=title, xaxis_title="Date", yaxis_title="Cumulative Words", height=600, hovermode="x unified", template="plotly_white")
     fig.update_yaxes(tickformat=".2s")
 
     st.plotly_chart(fig, use_container_width=True)
@@ -444,12 +419,9 @@ with tab2:
         st.markdown("### Pacing Estimates")
         c1, c2, c3 = st.columns(3)
         c1.metric("Per Week Rate", f"{int(weekly_rate):,} words")
-        c2.metric("Weeks Remaining", f"{days_left/7:.1f} weeks")
+        c2.metric("Weeks Remaining", f"{days_left / 7:.1f} weeks")
         c3.metric("Est. Completion", completion.strftime("%Y-%m-%d"))
 
 # Footer
 st.markdown("---")
-st.caption(
-    f"Updated: {pd.Timestamp.now(tz='Europe/Vilnius').strftime('%Y-%m-%d %H:%M:%S')} | "
-    "Auto-refresh: 5 min | Press 'R' to refresh"
-)
+st.caption(f"Updated: {pd.Timestamp.now(tz='Europe/Vilnius').strftime('%Y-%m-%d %H:%M:%S')} | Auto-refresh: 5 min | Press 'R' to refresh")