Skip to content
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

MAINT: use build-in round for df instead of ours #174

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

MAINT: use build-in round for df instead of ours #174

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
20 changes: 0 additions & 20 deletions rampwf/utils/scoring.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,23 +117,3 @@ def score_matrix(score_types, ground_truth, predictions):
score_type.score_function(ground_truth[step], predictions[step])
for score_type in score_types] for step in ground_truth]
return score_matrix_from_scores(score_types, steps, scoress)


def round_df_scores(df_scores, score_types):
"""Round scores to the precision set in the score type.

Parameters
----------
df_scores : pd.DataFrame
the score dataframe
score_types : list of score types

Returns
-------
df_scores : the dataframe with rounded scores
"""
df_scores_copy = df_scores.copy()
for column, score_type in zip(df_scores_copy, score_types):
df_scores_copy[column] = [round(score, score_type.precision)
for score in df_scores_copy[column]]
return df_scores_copy
13 changes: 9 additions & 4 deletions rampwf/utils/submission.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
from .io import save_y_pred, set_state, print_submission_exception
from .combine import get_score_cv_bags
from .pretty_print import print_title, print_df_scores, print_warning
from .scoring import score_matrix, round_df_scores, reorder_df_scores
from .scoring import score_matrix, reorder_df_scores


def save_submissions(problem, y_pred, data_path='.', output_path='.',
Expand Down Expand Up @@ -286,7 +286,8 @@ def run_submission_on_full_train(problem, module_path, X_train, y_train,
predictions=OrderedDict([('train', predictions_train),
('test', predictions_test)]),
)
df_scores_rounded = round_df_scores(df_scores, score_types)
map_score_precision = {st.name: st.precision for st in score_types}
df_scores_rounded = df_scores.round(map_score_precision)
print_df_scores(df_scores_rounded, indent='\t')

if save_output:
Expand All @@ -302,7 +303,8 @@ def run_submission_on_full_train(problem, module_path, X_train, y_train,
ground_truth=OrderedDict([('train', ground_truth_train)]),
predictions=OrderedDict([('train', predictions_train)]),
)
df_scores_rounded = round_df_scores(df_scores, score_types)
map_score_precision = {st.name: st.precision for st in score_types}
df_scores_rounded = df_scores.round(map_score_precision)
print_df_scores(df_scores_rounded, indent='\t')

if save_output:
Expand Down Expand Up @@ -396,7 +398,10 @@ def bag_submissions(problem, cv, y_train, y_test, predictions_valid_list,
df_scores = df_scores.loc[(slice(None), highest_level), :]
df_scores.index = df_scores.index.droplevel('n_bag')
df_scores = reorder_df_scores(df_scores, score_types)
df_scores = round_df_scores(df_scores, score_types)

# round the dataframe
map_score_precision = {st.name: st.precision for st in score_types}
df_scores = df_scores.round(map_score_precision)
print_df_scores(df_scores, indent='\t')


Expand Down
5 changes: 3 additions & 2 deletions rampwf/utils/testing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@
from .io import load_y_pred, set_state
from .pretty_print import print_title, print_df_scores
from .notebook import execute_notebook, convert_notebook
from .scoring import round_df_scores, mean_score_matrix
from .scoring import mean_score_matrix
from .submission import (bag_submissions, run_submission_on_cv_fold,
run_submission_on_full_train)

Expand Down Expand Up @@ -124,7 +124,8 @@ def assert_submission(ramp_kit_dir='.', ramp_data_dir='.',
if save_output:
filename = os.path.join(fold_output_path, 'scores.csv')
df_scores.to_csv(filename)
df_scores_rounded = round_df_scores(df_scores, score_types)
map_score_precision = {st.name: st.precision for st in score_types}
df_scores_rounded = df_scores.round(map_score_precision)
print_df_scores(df_scores_rounded, indent='\t')

# saving predictions for CV bagging after the CV loop
Expand Down