Skip to content

FIX: Fix error in report when sklearnex has more parameters than sklearn #171

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
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

FIX: Fix error in report when sklearnex has more parameters than sklearn #171

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
16 changes: 14 additions & 2 deletions sklbench/report/implementation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,8 +16,10 @@

import argparse
import json
from functools import reduce
from typing import Dict, List

import numpy as np
import openpyxl as xl
import pandas as pd
from openpyxl.formatting.rule import ColorScaleRule
Expand Down Expand Up @@ -165,7 +167,12 @@ def select_comparison(i, j, diffs_selection):
df = input_df.set_index(index_columns)
unique_indices = df.index.unique()
splitted_dfs = split_df_by_columns(input_df, diff_columns)
splitted_dfs = {key: df.set_index(index_columns) for key, df in splitted_dfs.items()}
common_cols = reduce(np.intersect1d, [df.columns for df in splitted_dfs.values()])
df_specific_cols = np.setdiff1d(index_columns, common_cols)
splitted_dfs = {
key: df.assign(**{col: None for col in df_specific_cols}).set_index(index_columns)
for key, df in splitted_dfs.items()
}

# drop results with duplicated indices (keep first entry only)
for key, splitted_df in splitted_dfs.items():
Expand All @@ -181,6 +188,9 @@ def select_comparison(i, j, diffs_selection):
# compared values
for i, (key_ith, df_ith) in enumerate(splitted_dfs.items()):
for j, (key_jth, df_jth) in enumerate(splitted_dfs.items()):
common_indexes = np.intersect1d(df_ith.index, df_jth.index)
df_ith = df_ith.loc[common_indexes]
df_jth = df_jth.loc[common_indexes]
if select_comparison(i, j, diffs_selection):
comparison_name = f"{key_jth} vs {key_ith}"
for column in df_ith.columns:
Expand All @@ -196,7 +206,9 @@ def select_comparison(i, j, diffs_selection):
df[f"{comparison_name}\n{column} is equal"] = (
df_ith[column] == df_jth[column]
)
df = df.reset_index()
if len(df_specific_cols):
df.index = df.index.droplevel(list(df_specific_cols))
df = df.dropna(axis=0, how="all", ignore_index=False).reset_index()
# move to multi-index
df = df[reorder_columns(list(df.columns))]
df.columns = [
Expand Down
Loading