Skip to content

Fix four bugs in plot_template_data.py causing compute_oracle and pipeline to fail #90

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sdpython merged 3 commits into from
Apr 12, 2026
Merged

Fix four bugs in plot_template_data.py causing compute_oracle and pipeline to fail #90

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d02ce9a
Initial plan
Copilot Feb 26, 2026
220e337
Fix multiple bugs in plot_template_data.py
Copilot Feb 26, 2026
5c17e93
Merge branch 'sess1' into copilot/sub-pr-89
sdpython Apr 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 6 additions & 9 deletions _doc/examples/ml/plot_template_data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,12 +52,10 @@ def select_variables_and_clean(df):
columns = set(df.columns)
assert set(keys) & set(columns) == set(
keys
), f"Missing columns {set(keys) - set(columns)} in {sorted(df.columns)}"
groups = df[[*keys, cible]].groupby(keys).count()
filtered = groups[groups[cible] > 1].reset_index(drop=False)

mask = filtered.duplicated(subset=keys, keep=False)
return filtered[~mask][[*keys, cible]], cible
), f"Missing columns {set(keys) - set(keys) & set(columns)} in {sorted(df.columns)}"
subset = df[[*keys, cible]]
mask = subset.duplicated(subset=keys, keep=False)
return subset[~mask].reset_index(drop=True), cible


def compute_oracle(table, cible):
Expand All @@ -72,6 +70,7 @@ def compute_oracle(table, cible):
columns="Session",
values=cible,
)
.dropna(axis=0)
.sort_index()
)
# Keep only rows where both 2024 and 2025 have non-missing values
Expand Down Expand Up @@ -99,9 +98,7 @@ def split_train_test(table, cible):

def make_pipeline(table, cible):
vars = [c for c in table.columns if c != cible]
# Candidate numeric feature; include it only if it exists in the table to avoid KeyError.
numeric_feature = "Capacité de l’établissement par formation"
num_cols = [numeric_feature] if numeric_feature in table.columns else []
num_cols = ["Capacité de l’établissement par formation"]
cat_cols = [c for c in vars if c not in num_cols]

transformers = []
Expand Down
Loading