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

Draft
Copilot wants to merge 2 commits into
base: sess1
Choose a base branch
from
Draft

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

Changes from all commits
Commits
Show all changes
2 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
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
18 changes: 8 additions & 10 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 @@ -53,11 +53,9 @@ def select_variables_and_clean(df):
assert set(keys) & set(columns) == set(
keys
), f"Missing columns {set(keys) - 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
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 @@ -72,13 +70,13 @@ def compute_oracle(table, cible):
columns="Session",
values=cible,
)
# .dropna(axis=0) # fails
.dropna(axis=0)
.sort_index()
)
return mean_absolute_error(piv[2025], piv[2024])


def split_train_test(table, cuble):
def split_train_test(table, cible):
X, y = table.drop(cible, axis=1), table[cible]

train_test = X["Session"] < 2025
Expand All @@ -87,13 +85,13 @@ def split_train_test(table, cuble):

train_X = X[train_test].drop(drop, axis=1)
train_y = y[train_test]
test_X = X[train_test].drop(drop, axis=1)
test_y = y[train_test]
test_X = X[~train_test].drop(drop, axis=1)
test_y = y[~train_test]
return train_X, test_X, train_y, test_y


def make_pipeline(table, cible):
vars = [c for c in table.columns if c != "cible"]
vars = [c for c in table.columns if c != cible]
num_cols = ["Capacité de l’établissement par formation"]
cat_cols = [c for c in vars if c not in num_cols]

Expand Down