From 04809033433737a1c31689c78358dfc9611597fd Mon Sep 17 00:00:00 2001
From: Manon Blanco <blanco@teklia.com>
Date: Wed, 11 Oct 2023 12:43:55 +0000
Subject: [PATCH] Round mean values calculated during data analysis
---
dan/datasets/analyze/statistics.py | 26 ++++++++++++++++++--------
1 file changed, 18 insertions(+), 8 deletions(-)
diff --git a/dan/datasets/analyze/statistics.py b/dan/datasets/analyze/statistics.py
index efdc0ef6..d6a716ed 100644
--- a/dan/datasets/analyze/statistics.py
+++ b/dan/datasets/analyze/statistics.py
@@ -1,6 +1,7 @@
# -*- coding: utf-8 -*-
import logging
from collections import Counter, defaultdict
+from functools import partial
from pathlib import Path
from typing import Dict, List, Optional
@@ -32,23 +33,32 @@ def create_table(
operations = []
if count:
- operations.append(("Count", len))
+ operations.append(("Count", len, None))
operations.extend(
[
- ("Min", np.min),
- ("Max", np.max),
- ("Mean", np.mean),
- ("Median", np.median),
+ ("Min", np.min, None),
+ ("Max", np.max, None),
+ ("Mean", np.mean, 2),
+ ("Median", np.median, 2),
]
)
if total:
- operations.append(("Total", np.sum))
+ operations.append(("Total", np.sum, None))
statistics.add_rows(
[
- [col_name, *list(map(operator, data.values()))]
- for col_name, operator in operations
+ [
+ col_name,
+ *list(
+ map(
+ # Round values if needed
+ partial(round, ndigits=digits),
+ map(operator, data.values()),
+ )
+ ),
+ ]
+ for col_name, operator, digits in operations
]
)
--
GitLab