ASPP/2025-plovdiv-data
0
0
Fork 15
Code Issues 6 Pull requests 12 Projects Releases Packages Wiki Activity Actions

tabsplit #19

Open
julioro wants to merge 2 commits from julioro/2025-plovdiv-data:tabsplit into main
pull from: julioro/2025-plovdiv-data:tabsplit
merge into: ASPP:main
Conversation 0 Commits 2 Files changed 2 +185 -14
1 changed files with 185 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files
Showing only changes of commit 82d1b357b8 - Show all commits

199
exercises/tabular_split_apply_combine/split_apply_combine.ipynb
View file

@ -275,12 +275,13 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 12,
"id": "00bb9eb1",
"metadata": {},
"outputs": [],
"source": [
"# your code here:\n"
"# your code here:\n",
"event_by_group = df.groupby('group')['event'].sum()"
]
},
{
@ -293,12 +294,13 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 13,
"id": "db946d0f-8204-43a3-853c-41981a9811f4",
"metadata": {},
"outputs": [],
"source": [
"# your code here:\n"
"# your code here:\n",
"group_size = df.groupby('group').size()"
]
},
{
@ -313,12 +315,28 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 15,
"id": "13ad4130-2094-4e7a-a416-f0fd6e810413",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"group\n",
"Control 4.761905\n",
"MedDiet + Nuts 3.322099\n",
"MedDiet + VOO 3.856877\n",
"dtype: float64"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# your code here:\n"
"# your code here:\n",
"event_by_group / group_size * 100"
]
},
{
@ -352,12 +370,81 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 20,
"id": "5ab4e70e-6261-4a26-8ad9-14eae15be09c",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>smoke</th>\n",
" <th>Current</th>\n",
" <th>Former</th>\n",
" <th>Never</th>\n",
" </tr>\n",
" <tr>\n",
" <th>group</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Control</th>\n",
" <td>13</td>\n",
" <td>39</td>\n",
" <td>44</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MedDiet + Nuts</th>\n",
" <td>15</td>\n",
" <td>20</td>\n",
" <td>34</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MedDiet + VOO</th>\n",
" <td>20</td>\n",
" <td>29</td>\n",
" <td>34</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"smoke Current Former Never\n",
"group \n",
"Control 13 39 44\n",
"MedDiet + Nuts 15 20 34\n",
"MedDiet + VOO 20 29 34"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# your code here\n"
"# your code here\n",
"df.pivot_table(index='group', columns='smoke', values='event',aggfunc='sum')"
]
},
{
@ -387,12 +474,96 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 22,
"id": "196fd111-72bc-4b87-b8fb-293547a8c83d",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead tr th {\n",
" text-align: left;\n",
" }\n",
"\n",
" .dataframe thead tr:last-of-type th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th colspan=\"2\" halign=\"left\">mean</th>\n",
" <th colspan=\"2\" halign=\"left\">std</th>\n",
" </tr>\n",
" <tr>\n",
" <th>sex</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" <th>Female</th>\n",
" <th>Male</th>\n",
" </tr>\n",
" <tr>\n",
" <th>group</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>Control</th>\n",
" <td>68.009046</td>\n",
" <td>66.400000</td>\n",
" <td>5.979313</td>\n",
" <td>6.605266</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MedDiet + Nuts</th>\n",
" <td>67.414591</td>\n",
" <td>65.822665</td>\n",
" <td>5.580050</td>\n",
" <td>6.403373</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MedDiet + VOO</th>\n",
" <td>67.668775</td>\n",
" <td>66.080045</td>\n",
" <td>5.816703</td>\n",
" <td>6.621440</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" mean std \n",
"sex Female Male Female Male\n",
"group \n",
"Control 68.009046 66.400000 5.979313 6.605266\n",
"MedDiet + Nuts 67.414591 65.822665 5.580050 6.403373\n",
"MedDiet + VOO 67.668775 66.080045 5.816703 6.621440"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# your code here:\n"
"# your code here:\n",
"df.pivot_table(index='group', columns='sex', values='age', aggfunc=['mean','std'])\n"
]
}
],
@ -412,7 +583,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.5"
"version": "3.13.7"
}
},
"nbformat": 4,