Skip encryption step for pages that might be broken (#86)

Author: choldgraf

.github/workflows/deploy.yml

@@ -86,8 +86,16 @@ jobs:
       # Encrypt pages that are only meant for team consumption
       - name: Encrypt some pages
         run: |
-          staticrypt book/_build/dirhtml/people/index.html -p ${{ secrets.STATICRYPT_PASSWORD }} -d book/_build/dirhtml/people/ --short --template-color-primary "#1D4EF5" --template-title "Only for the 2i2c team!" --template-instructions "Check the team BitWarden for the password...";
-          staticrypt book/_build/dirhtml/finances/index.html -p ${{ secrets.STATICRYPT_PASSWORD }} -d book/_build/dirhtml/finances/ --short --template-color-primary "#1D4EF5" --template-title "Only for the 2i2c team!" --template-instructions "Check the team BitWarden for the password...";
+          if [ -f book/_build/dirhtml/people/index.html ]; then
+            staticrypt book/_build/dirhtml/people/index.html -p ${{ secrets.STATICRYPT_PASSWORD }} -d book/_build/dirhtml/people/ --short --template-color-primary "#1D4EF5" --template-title "Only for the 2i2c team!" --template-instructions "Check the team BitWarden for the password...";
+          else
+            echo "Skipping people encryption; missing book/_build/dirhtml/people/index.html"
+          fi
+          if [ -f book/_build/dirhtml/finances/index.html ]; then
+            staticrypt book/_build/dirhtml/finances/index.html -p ${{ secrets.STATICRYPT_PASSWORD }} -d book/_build/dirhtml/finances/ --short --template-color-primary "#1D4EF5" --template-title "Only for the 2i2c team!" --template-instructions "Check the team BitWarden for the password...";
+          else
+            echo "Skipping finances encryption; missing book/_build/dirhtml/finances/index.html"
+          fi
 
       # Upload artifact for looking at later
       - uses: actions/upload-artifact@v4

book/cloud.md

@@ -115,7 +115,7 @@ slideshow:
 tags: [remove-cell]
 ---
 # The latest number of unique hubs and clusters
-n_hubs = int(np.ceil(unique_hubs.query("date > @last_week").groupby("cluster").mean("hubs")["hubs"].sum()))
+n_hubs = int(np.ceil(unique_hubs.query("date > @last_week").groupby("cluster")["hubs"].mean().sum()))
 n_clusters = unique_hubs.query("date > @last_week")["cluster"].nunique()
 ```
 
@@ -150,7 +150,7 @@ slideshow:
 tags: [full-width, remove-input]
 ---
 # Sort the clusters by most to least hubs
-sorted_clusters = unique_hubs.groupby("cluster").max("hubs").sort_values("hubs", ascending=False).index.values
+sorted_clusters = unique_hubs.groupby("cluster")["hubs"].max().sort_values(ascending=False).index.values
 
 px.area(unique_hubs, x="date", y="hubs", color="cluster", title="Number of active hubs by cluster", category_orders={"cluster": sorted_clusters})
 ```
@@ -206,7 +206,7 @@ for ix, irow in communities.iterrows():
     hubs = df.query("clusterhub in @clusterhub and timescale == 'monthly'")
     # Average across time for each hub, and then add across all hubs
     hubs = df.query("clusterhub in @clusterhub and timescale == 'monthly'")
-    n_users = hubs.groupby("clusterhub").mean("users")["users"].sum().round()
+    n_users = hubs.groupby("clusterhub")["users"].mean().sum().round()
     communities.loc[ix, "users"] = n_users
 ```
 
@@ -356,14 +356,14 @@ slideshow:
 tags: [remove-cell]
 ---
 # Sum by cluster so we avoid having too many categories
-df_clusters = df.groupby(["cluster", "date", "timescale"]).sum("users").reset_index()
+df_clusters = df.groupby(["cluster", "date", "timescale"])["users"].sum().reset_index()
 
 # Add logusers
 df_clusters = df_clusters.query("users > 0")
 df_clusters["logusers"] = df_clusters["users"].map(np.log10)
 
 # List of clusters sorted by size
-sorted_clusters = df_clusters.groupby("cluster").mean("users").sort_values("users", ascending=False).index.values
+sorted_clusters = df_clusters.groupby("cluster")["users"].mean().sort_values("users", ascending=False).index.values
 ```
 
 `````{code-cell} ipython3
@@ -384,7 +384,7 @@ grid = """
 scale_ordering = ["daily", "monthly"]
 interior = []
 for scale in scale_ordering:
-    users = df_clusters.query("timescale == @scale").groupby("cluster").mean("users")["users"].sum()
+    users = df_clusters.query("timescale == @scale").groupby("cluster")["users"].mean().sum()
     interior.append(dedent("""\
     ```{grid-item-card} %s
     %s
@@ -438,13 +438,12 @@ slideshow:
 tags: [remove-cell]
 ---
 # Mean users for each hub
-df_sums = df.groupby(["clusterhub", "timescale"]).mean("users")
+df_sums = df.groupby(["clusterhub", "timescale"])["users"].mean().reset_index()
 
 # Calculate bins and add it to data for plotting 
 bins = [0, 5, 10, 25, 50, 100, 250, 500, 1000, 2500, 5000, 10000]
 labels = [f"{bins[ii]}-{bins[ii+1]}" for ii in range(len(bins)-1)]
 df_sums["bin"] = pd.cut(df_sums["users"], bins, labels=labels, right=False)
-df_sums = df_sums.reset_index()
 max_y_bins = df_sums.groupby(["timescale", "bin"]).count()["users"].max() + 10
 max_y_users = df_sums.groupby(["timescale", "bin"]).sum()["users"].max() + 100
 ```
@@ -502,6 +501,7 @@ display(alt.hconcat(*chs_perc, title=f"% {scale} Total Active Users by community
 When the number of Monthly Active Users (MAUs) >= 5, assume the community is actively using the their hub.
 
 ```{code-cell} ipython3
+:tags: remove-cell
 df['date'] = pd.to_datetime(df['date'])
 
 # Define cutoff = one year ago
@@ -542,6 +542,7 @@ result = result[['cluster', 'hub', 'first_value_date']]
 ```
 
 ```{code-cell} ipython3
+:tags: remove-input
 import ipywidgets as widgets
 from IPython.display import display
 

book/people.md

@@ -168,7 +168,7 @@ df["assignees"] = df["assignees"].map(extract_assignee)
 # Limit last day to the last day of the year
 date_cols = ["first day", "last day"]
 for col in date_cols:
-    df.loc[:, col] = pd.to_datetime(df[col])
+    df[col] = pd.to_datetime(df[col], errors="coerce")
 df["last day"] = df["last day"].map(lambda a: np.min([a, end_cal]))
 
 # Drop entries with missing dates
@@ -382,61 +382,3 @@ fig.add_vline(ANNUAL_EXPECTED_DAYS_OFF, line_dash="dash")
 ```
 
 +++ {"editable": true, "slideshow": {"slide_type": ""}}
-
-### Accumulated time off in the last six months
-
-This shows time off accumulated over the last six months, rather than the last calendar year.
-This gives us an idea for how we're accumulating time off more recently in general.
-
-```{code-cell} ipython3
----
-editable: true
-slideshow:
-  slide_type: ''
-tags: [remove-cell]
----
-# Three month window in the past/future
-start_win = today - timedelta(30 * 6)
-end_win = today + timedelta(30 * 1)
-
-# 6 month window so expected days is 40 / 2
-expected_n_days_in_win = 20
-# Calculate the "burn rate" of time off we'd expect if team members were hitting their 40 day target.
-expected = pd.DataFrame(
-    [{"day": start_win, "amount": 0}, {"day": today, "amount": expected_n_days_in_win}],
-)
-expected["day"] = pd.to_datetime(expected["day"])
-```
-
-```{code-cell} ipython3
----
-editable: true
-slideshow:
-  slide_type: ''
-tags: [remove-input]
----
-# Visualize over time
-fig = px.line(
-    cumulative.query("`first day` >= @start_win"),
-    x="first day",
-    y="cumulative",
-    color="person",
-    line_shape="hv",
-    height=700,
-    hover_data=["last day", "days_off"],
-    color_discrete_sequence=colormap,
-    title="Accumulated time off in a 6-month window",
-)
-fig.add_vline(pd.Timestamp.today(), line_dash="dash")
-fig.add_trace(
-    px.line(
-        expected,
-        x="day",
-        y="amount",
-        line_dash_sequence=["dot"],
-        color_discrete_sequence=["black"],
-    ).data[0]
-)
-fig.update_xaxes(range=[start_win, end_win])
-fig.update_yaxes(range=[0, 35])
-```