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

splitapplycombine

Browse source
This commit is contained in:
ASPP Student 2025-09-24 13:48:49 +03:00
parent 874f984bd5
commit 6085c2def3
1 changed files with 139 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

160
exercises/tabular_split_apply_combine/split_apply_combine.ipynb
View file

@ -10,7 +10,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 7,
"id": "8f9bc8b1", "id": "8f9bc8b1",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -31,7 +31,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 8,
"id": "d2dfebd3", "id": "d2dfebd3",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -41,7 +41,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 9,
"id": "09554c84", "id": "09554c84",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -51,7 +51,7 @@
"(6245, 18)" "(6245, 18)"
] ]
}, },
"execution_count": 3, "execution_count": 9,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -62,7 +62,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 10,
"id": "df95a10b", "id": "df95a10b",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -233,7 +233,7 @@
"4 No Yes No No 9 2.746064 No Control Madrid " "4 No Yes No No 9 2.746064 No Control Madrid "
] ]
}, },
"execution_count": 4, "execution_count": 10,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -257,7 +257,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 11,
"id": "99b21627-1b48-44ee-bda2-312b0718bd59", "id": "99b21627-1b48-44ee-bda2-312b0718bd59",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -275,12 +275,28 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 18,
"id": "00bb9eb1", "id": "00bb9eb1",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"data": {
"text/plain": [
"group\n",
"Control 96\n",
"MedDiet + Nuts 69\n",
"MedDiet + VOO 83\n",
"Name: event, dtype: int64"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"# your code here:\n" "# your code here:\n",
"df.groupby('group')['event'].sum()"
] ]
}, },
{ {
@ -293,12 +309,28 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 17,
"id": "db946d0f-8204-43a3-853c-41981a9811f4", "id": "db946d0f-8204-43a3-853c-41981a9811f4",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"data": {
"text/plain": [
"group\n",
"Control 2016\n",
"MedDiet + Nuts 2077\n",
"MedDiet + VOO 2152\n",
"Name: event, dtype: int64"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"# your code here:\n" "# your code here:\n",
"df.groupby('group').count()['event']"
] ]
}, },
{ {
@ -313,12 +345,28 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 19,
"id": "13ad4130-2094-4e7a-a416-f0fd6e810413", "id": "13ad4130-2094-4e7a-a416-f0fd6e810413",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"data": {
"text/plain": [
"group\n",
"Control 4.761905\n",
"MedDiet + Nuts 3.322099\n",
"MedDiet + VOO 3.856877\n",
"Name: event, dtype: float64"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"# your code here:\n" "# your code here:\n",
"df.groupby('group')['event'].mean()*100"
] ]
}, },
{ {
@ -352,12 +400,81 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 29,
"id": "5ab4e70e-6261-4a26-8ad9-14eae15be09c", "id": "5ab4e70e-6261-4a26-8ad9-14eae15be09c",
"metadata": {}, "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>4.92</td>\n",
" <td>8.04</td>\n",
" <td>3.47</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MedDiet + Nuts</th>\n",
" <td>5.15</td>\n",
" <td>3.71</td>\n",
" <td>2.73</td>\n",
" </tr>\n",
" <tr>\n",
" <th>MedDiet + VOO</th>\n",
" <td>6.90</td>\n",
" <td>5.46</td>\n",
" <td>2.55</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"smoke Current Former Never\n",
"group \n",
"Control 4.92 8.04 3.47\n",
"MedDiet + Nuts 5.15 3.71 2.73\n",
"MedDiet + VOO 6.90 5.46 2.55"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"# your code here\n" "# your code here\n",
"(df.pivot_table(index='group', columns='smoke', values='event')*100).round(2)"
] ]
}, },
{ {
@ -392,7 +509,8 @@
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# your code here:\n" "# your code here:\n",
"df.pivot_table(index='group', columns='smoke', values='age')"
] ]
} }
], ],
@ -412,7 +530,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.5" "version": "3.13.6"
} }
}, },
"nbformat": 4, "nbformat": 4,