From 36ea5ab9f05d3f35e7594a6c75d396365cbb6b70 Mon Sep 17 00:00:00 2001
From: Ritwik <rm02120@surrey.ac.uk>
Date: Mon, 14 Apr 2025 21:54:25 +0100
Subject: [PATCH] removed few lines unrequired
---
.../regression/Regression_Preprocessed.ipynb | 286 +-----------------
1 file changed, 1 insertion(+), 285 deletions(-)
diff --git a/notebooks/regression/Regression_Preprocessed.ipynb b/notebooks/regression/Regression_Preprocessed.ipynb
index 72737ca..95b389b 100644
--- a/notebooks/regression/Regression_Preprocessed.ipynb
+++ b/notebooks/regression/Regression_Preprocessed.ipynb
@@ -357,291 +357,6 @@
"df.info()"
]
},
- {
- "cell_type": "code",
- "execution_count": 264,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "\n",
- "🔹 Value counts for 'date':\n",
- "3/11/2015 24\n",
- "1/31/2015 24\n",
- "1/11/2015 23\n",
- "1/12/2015 23\n",
- "3/10/2015 23\n",
- "1/24/2015 23\n",
- "1/8/2015 22\n",
- "1/10/2015 22\n",
- "3/9/2015 22\n",
- "3/3/2015 22\n",
- "1/13/2015 22\n",
- "1/7/2015 22\n",
- "1/5/2015 22\n",
- "1/22/2015 22\n",
- "3/8/2015 22\n",
- "2/26/2015 21\n",
- "3/4/2015 21\n",
- "2/25/2015 21\n",
- "1/25/2015 21\n",
- "1/6/2015 21\n",
- "1/3/2015 21\n",
- "1/4/2015 21\n",
- "2/28/2015 21\n",
- "1/14/2015 21\n",
- "1/28/2015 21\n",
- "1/17/2015 21\n",
- "2/18/2015 21\n",
- "1/27/2015 21\n",
- "3/1/2015 20\n",
- "3/2/2015 20\n",
- "2/17/2015 20\n",
- "2/22/2015 20\n",
- "2/19/2015 20\n",
- "1/29/2015 20\n",
- "3/5/2015 19\n",
- "2/4/2015 19\n",
- "2/8/2015 19\n",
- "3/7/2015 19\n",
- "1/19/2015 19\n",
- "2/7/2015 19\n",
- "1/21/2015 19\n",
- "2/2/2015 19\n",
- "2/23/2015 19\n",
- "1/1/2015 19\n",
- "2/11/2015 19\n",
- "2/24/2015 19\n",
- "1/18/2015 19\n",
- "2/15/2015 19\n",
- "2/10/2015 19\n",
- "1/15/2015 19\n",
- "2/3/2015 19\n",
- "1/26/2015 19\n",
- "2/1/2015 19\n",
- "2/12/2015 19\n",
- "2/5/2015 18\n",
- "2/16/2015 18\n",
- "2/9/2015 18\n",
- "2/14/2015 17\n",
- "1/20/2015 15\n",
- "Name: date, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'quarter':\n",
- "Quarter1 360\n",
- "Quarter2 335\n",
- "Quarter4 248\n",
- "Quarter3 210\n",
- "Quarter5 44\n",
- "Name: quarter, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'department':\n",
- "sweing 691\n",
- "finishing 257\n",
- "finishing 249\n",
- "Name: department, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'day':\n",
- "Wednesday 208\n",
- "Sunday 203\n",
- "Tuesday 201\n",
- "Thursday 199\n",
- "Monday 199\n",
- "Saturday 187\n",
- "Name: day, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'team':\n",
- "8 109\n",
- "2 109\n",
- "4 105\n",
- "1 105\n",
- "9 104\n",
- "10 100\n",
- "12 99\n",
- "7 96\n",
- "3 95\n",
- "6 94\n",
- "5 93\n",
- "11 88\n",
- "Name: team, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'targeted_productivity':\n",
- "0.80 540\n",
- "0.70 242\n",
- "0.75 216\n",
- "0.65 63\n",
- "0.60 57\n",
- "0.50 49\n",
- "0.35 27\n",
- "0.40 2\n",
- "0.07 1\n",
- "Name: targeted_productivity, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'smv':\n",
- "3.94 192\n",
- "2.90 108\n",
- "22.52 103\n",
- "30.10 79\n",
- "4.15 76\n",
- " ... \n",
- "20.20 1\n",
- "20.55 1\n",
- "50.89 1\n",
- "26.87 1\n",
- "42.41 1\n",
- "Name: smv, Length: 70, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'wip':\n",
- "NaN 506\n",
- "1039.0 5\n",
- "1282.0 4\n",
- "968.0 3\n",
- "1144.0 3\n",
- " ... \n",
- "1186.0 1\n",
- "891.0 1\n",
- "1498.0 1\n",
- "551.0 1\n",
- "1239.0 1\n",
- "Name: wip, Length: 549, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'over_time':\n",
- "960 129\n",
- "1440 111\n",
- "6960 61\n",
- "6840 48\n",
- "1200 39\n",
- " ... \n",
- "5580 1\n",
- "13800 1\n",
- "8970 1\n",
- "7680 1\n",
- "2040 1\n",
- "Name: over_time, Length: 143, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'incentive':\n",
- "0 604\n",
- "50 113\n",
- "63 61\n",
- "45 54\n",
- "30 52\n",
- "23 38\n",
- "38 29\n",
- "60 28\n",
- "40 27\n",
- "75 24\n",
- "113 21\n",
- "88 19\n",
- "34 17\n",
- "56 14\n",
- "26 9\n",
- "55 7\n",
- "81 7\n",
- "100 7\n",
- "69 6\n",
- "65 6\n",
- "70 6\n",
- "960 5\n",
- "35 5\n",
- "94 4\n",
- "44 4\n",
- "90 3\n",
- "46 2\n",
- "24 2\n",
- "27 2\n",
- "119 2\n",
- "49 2\n",
- "98 1\n",
- "21 1\n",
- "1200 1\n",
- "62 1\n",
- "25 1\n",
- "1080 1\n",
- "93 1\n",
- "29 1\n",
- "1440 1\n",
- "32 1\n",
- "33 1\n",
- "2880 1\n",
- "54 1\n",
- "37 1\n",
- "138 1\n",
- "53 1\n",
- "3600 1\n",
- "Name: incentive, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'idle_time':\n",
- "0.0 1179\n",
- "3.5 3\n",
- "4.0 2\n",
- "4.5 2\n",
- "8.0 2\n",
- "5.0 2\n",
- "2.0 2\n",
- "270.0 1\n",
- "150.0 1\n",
- "6.5 1\n",
- "300.0 1\n",
- "90.0 1\n",
- "Name: idle_time, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'idle_men':\n",
- "0 1179\n",
- "30 3\n",
- "20 3\n",
- "15 3\n",
- "10 3\n",
- "35 2\n",
- "45 1\n",
- "40 1\n",
- "37 1\n",
- "25 1\n",
- "Name: idle_men, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'no_of_style_change':\n",
- "0 1050\n",
- "1 114\n",
- "2 33\n",
- "Name: no_of_style_change, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'no_of_workers':\n",
- "8.0 262\n",
- "58.0 114\n",
- "57.0 109\n",
- "59.0 75\n",
- "10.0 60\n",
- " ... \n",
- "29.5 1\n",
- "11.0 1\n",
- "21.0 1\n",
- "6.0 1\n",
- "33.5 1\n",
- "Name: no_of_workers, Length: 61, dtype: int64\n",
- "\n",
- "🔹 Value counts for 'actual_productivity':\n",
- "0.800402 24\n",
- "0.971867 12\n",
- "0.850137 12\n",
- "0.750651 11\n",
- "0.850502 11\n",
- " ..\n",
- "0.460579 1\n",
- "0.852794 1\n",
- "0.585316 1\n",
- "1.000457 1\n",
- "0.700888 1\n",
- "Name: actual_productivity, Length: 879, dtype: int64\n"
- ]
- }
- ],
- "source": [
- "for col in df.columns:\n",
- " print(f\"\\n🔹 Value counts for '{col}':\")\n",
- " print(df[col].value_counts(dropna=False)) # This shows all values\n"
- ]
- },
{
"cell_type": "code",
"execution_count": 265,
@@ -684,6 +399,7 @@
}
],
"source": [
+ "#checking for any existing null values\n",
"df.isnull().sum()"
]
},
--
GitLab