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 +431 -37
2 changed files with 431 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

269
exercises/tabular_join/tabular_join.ipynb
View file

@ -326,12 +326,24 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 6,
"id": "861ac334-14ce-490a-b3c4-877b32789f3e", "id": "861ac334-14ce-490a-b3c4-877b32789f3e",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"data": {
"text/plain": [
"(6324, 16)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"## your code here\n" "## your code here\n",
"df.shape"
] ]
}, },
{ {
@ -344,12 +356,24 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 7,
"id": "14f57842-5722-4953-88d6-d7cf3070400c", "id": "14f57842-5722-4953-88d6-d7cf3070400c",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"data": {
"text/plain": [
"(6287, 3)"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"## your code here\n" "## your code here\n",
"info.shape"
] ]
}, },
{ {
@ -364,14 +388,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 10,
"id": "35e19a53", "id": "35e19a53",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"## your code here\n", "## your code here\n",
"\n", "data_diet = pd.merge(df, info, how='inner', left_on=['location-id', 'patient-id'], right_on=['location-id', 'patient-id'])"
"\n"
] ]
}, },
{ {
@ -388,7 +411,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 9,
"id": "36ce0688-d421-4a07-b00e-0e9b3201f0e0", "id": "36ce0688-d421-4a07-b00e-0e9b3201f0e0",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -456,7 +479,7 @@
"4 5 Malaga" "4 5 Malaga"
] ]
}, },
"execution_count": 8, "execution_count": 9,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -469,12 +492,195 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 11,
"id": "b636dde4-129a-4dd1-8cbf-c539c9c8a5f2", "id": "b636dde4-129a-4dd1-8cbf-c539c9c8a5f2",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"## your code here:\n" "## your code here:\n",
"data_diet_loc = pd.merge(data_diet, locations, how='inner', left_on='location-id', right_on='location-id')"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "e4579355-bdde-40a3-8969-1c27c7bb0eb7",
"metadata": {},
"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></th>\n",
" <th>patient-id</th>\n",
" <th>location-id</th>\n",
" <th>sex</th>\n",
" <th>age</th>\n",
" <th>smoke</th>\n",
" <th>bmi</th>\n",
" <th>waist</th>\n",
" <th>wth</th>\n",
" <th>htn</th>\n",
" <th>diab</th>\n",
" <th>hyperchol</th>\n",
" <th>famhist</th>\n",
" <th>hormo</th>\n",
" <th>p14</th>\n",
" <th>toevent</th>\n",
" <th>event</th>\n",
" <th>group</th>\n",
" <th>City</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>436</td>\n",
" <td>4</td>\n",
" <td>Male</td>\n",
" <td>58</td>\n",
" <td>Former</td>\n",
" <td>33.53</td>\n",
" <td>122</td>\n",
" <td>0.753086</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>10</td>\n",
" <td>5.374401</td>\n",
" <td>Yes</td>\n",
" <td>Control</td>\n",
" <td>Bilbao</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1130</td>\n",
" <td>4</td>\n",
" <td>Male</td>\n",
" <td>77</td>\n",
" <td>Current</td>\n",
" <td>31.05</td>\n",
" <td>119</td>\n",
" <td>0.730061</td>\n",
" <td>Yes</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>10</td>\n",
" <td>6.097194</td>\n",
" <td>No</td>\n",
" <td>Control</td>\n",
" <td>Bilbao</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1131</td>\n",
" <td>4</td>\n",
" <td>Female</td>\n",
" <td>72</td>\n",
" <td>Former</td>\n",
" <td>30.86</td>\n",
" <td>106</td>\n",
" <td>0.654321</td>\n",
" <td>No</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>8</td>\n",
" <td>5.946612</td>\n",
" <td>No</td>\n",
" <td>MedDiet + VOO</td>\n",
" <td>Bilbao</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1132</td>\n",
" <td>4</td>\n",
" <td>Male</td>\n",
" <td>71</td>\n",
" <td>Former</td>\n",
" <td>27.68</td>\n",
" <td>118</td>\n",
" <td>0.694118</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>8</td>\n",
" <td>2.907598</td>\n",
" <td>Yes</td>\n",
" <td>MedDiet + Nuts</td>\n",
" <td>Bilbao</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>1111</td>\n",
" <td>2</td>\n",
" <td>Female</td>\n",
" <td>79</td>\n",
" <td>Never</td>\n",
" <td>35.94</td>\n",
" <td>129</td>\n",
" <td>0.806250</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>Yes</td>\n",
" <td>No</td>\n",
" <td>No</td>\n",
" <td>9</td>\n",
" <td>4.761123</td>\n",
" <td>No</td>\n",
" <td>MedDiet + VOO</td>\n",
" <td>Valencia</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" patient-id location-id sex age smoke bmi waist wth htn \\\n",
"0 436 4 Male 58 Former 33.53 122 0.753086 No \n",
"1 1130 4 Male 77 Current 31.05 119 0.730061 Yes \n",
"2 1131 4 Female 72 Former 30.86 106 0.654321 No \n",
"3 1132 4 Male 71 Former 27.68 118 0.694118 Yes \n",
"4 1111 2 Female 79 Never 35.94 129 0.806250 Yes \n",
"\n",
" diab hyperchol famhist hormo p14 toevent event group City \n",
"0 No Yes No No 10 5.374401 Yes Control Bilbao \n",
"1 Yes No No No 10 6.097194 No Control Bilbao \n",
"2 Yes No Yes No 8 5.946612 No MedDiet + VOO Bilbao \n",
"3 No Yes No No 8 2.907598 Yes MedDiet + Nuts Bilbao \n",
"4 No Yes No No 9 4.761123 No MedDiet + VOO Valencia "
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data_diet_loc.head()"
] ]
}, },
{ {
@ -492,7 +698,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 13,
"id": "d1d4cc27", "id": "d1d4cc27",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -502,7 +708,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 14,
"id": "fbebbd97", "id": "fbebbd97",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -512,7 +718,7 @@
"(42, 2)" "(42, 2)"
] ]
}, },
"execution_count": 11, "execution_count": 14,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -523,7 +729,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 15,
"id": "8a3c7943", "id": "8a3c7943",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -591,7 +797,7 @@
"4 4 541" "4 4 541"
] ]
}, },
"execution_count": 12, "execution_count": 15,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -602,12 +808,20 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 13, "execution_count": 21,
"id": "573687e7", "id": "573687e7",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# your code here\n" "# your code here\n",
"data_diet_loc_drop = pd.merge(\n",
" data_diet_loc, \n",
" dropped, \n",
" how='left', \n",
" left_on=['location-id', 'patient-id'], \n",
" right_on=['location-id', 'patient-id'], \n",
" indicator=True\n",
").query('_merge != \"both\"').drop(columns='_merge')"
] ]
}, },
{ {
@ -622,15 +836,24 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 14, "execution_count": 22,
"id": "85902eea", "id": "85902eea",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"fname = 'processed_data_predimed.csv'\n", "fname = 'processed_data_predimed.csv'\n",
"\n", "\n",
"# your code here\n" "# your code here\n",
"data_diet_loc_drop.to_csv(fname)"
] ]
},
{
"cell_type": "code",
"execution_count": null,
"id": "38e88726-287a-4448-a250-f8616362d070",
"metadata": {},
"outputs": [],
"source": []
} }
], ],
"metadata": { "metadata": {
@ -649,7 +872,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.5" "version": "3.13.7"
} }
}, },
"nbformat": 4, "nbformat": 4,

199
exercises/tabular_split_apply_combine/split_apply_combine.ipynb
View file

@ -275,12 +275,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 12,
"id": "00bb9eb1", "id": "00bb9eb1",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# your code here:\n" "# your code here:\n",
"event_by_group = df.groupby('group')['event'].sum()"
] ]
}, },
{ {
@ -293,12 +294,13 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 13,
"id": "db946d0f-8204-43a3-853c-41981a9811f4", "id": "db946d0f-8204-43a3-853c-41981a9811f4",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"# your code here:\n" "# your code here:\n",
"group_size = df.groupby('group').size()"
] ]
}, },
{ {
@ -313,12 +315,28 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 15,
"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",
"dtype: float64"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"# your code here:\n" "# your code here:\n",
"event_by_group / group_size * 100"
] ]
}, },
{ {
@ -352,12 +370,81 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 20,
"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>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": [ "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", "cell_type": "code",
"execution_count": 10, "execution_count": 22,
"id": "196fd111-72bc-4b87-b8fb-293547a8c83d", "id": "196fd111-72bc-4b87-b8fb-293547a8c83d",
"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 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": [ "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", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.5" "version": "3.13.7"
} }
}, },
"nbformat": 4, "nbformat": 4,