Skip to content

Commit 85f32be

Browse files
martinhronecmartinhronec
committed
Add AdvancedPandas lecture
1 parent 4d96cb9 commit 85f32be

File tree

5 files changed

+31088
-218
lines changed

5 files changed

+31088
-218
lines changed

Diff for: ‎04_pandas/04_PandasMatplotlib.ipynb

+2-218
Original file line numberDiff line numberDiff line change
@@ -13,7 +13,7 @@
1313
},
1414
{
1515
"cell_type": "code",
16-
"execution_count": 7,
16+
"execution_count": 2,
1717
"metadata": {},
1818
"outputs": [],
1919
"source": [
@@ -5374,222 +5374,6 @@
53745374
"(df.isnull().sum()/df.shape[0]).sort_values().plot.bar(ylim=(0,1),grid=True)"
53755375
]
53765376
},
5377-
{
5378-
"cell_type": "markdown",
5379-
"metadata": {},
5380-
"source": [
5381-
"## Data ex\n",
5382-
"\n",
5383-
"https://web.archive.org/web/20180506061559/http://lisp.vse.cz/pkdd99/Challenge/chall.htm"
5384-
]
5385-
},
5386-
{
5387-
"cell_type": "code",
5388-
"execution_count": 8,
5389-
"metadata": {},
5390-
"outputs": [],
5391-
"source": [
5392-
"import os"
5393-
]
5394-
},
5395-
{
5396-
"cell_type": "code",
5397-
"execution_count": 10,
5398-
"metadata": {},
5399-
"outputs": [],
5400-
"source": [
5401-
"files = os.listdir('auxiliary/data_ex')"
5402-
]
5403-
},
5404-
{
5405-
"cell_type": "code",
5406-
"execution_count": 11,
5407-
"metadata": {},
5408-
"outputs": [
5409-
{
5410-
"data": {
5411-
"text/plain": [
5412-
"['account.asc',\n",
5413-
" 'card.asc',\n",
5414-
" 'client.asc',\n",
5415-
" 'disp.asc',\n",
5416-
" 'district.asc',\n",
5417-
" 'loan.asc',\n",
5418-
" 'order.asc',\n",
5419-
" 'trans.asc']"
5420-
]
5421-
},
5422-
"execution_count": 11,
5423-
"metadata": {},
5424-
"output_type": "execute_result"
5425-
}
5426-
],
5427-
"source": [
5428-
"files"
5429-
]
5430-
},
5431-
{
5432-
"cell_type": "code",
5433-
"execution_count": 14,
5434-
"metadata": {},
5435-
"outputs": [
5436-
{
5437-
"name": "stderr",
5438-
"output_type": "stream",
5439-
"text": [
5440-
"C:\\Users\\Martin Hronec\\AppData\\Local\\Temp\\ipykernel_22912\\2341300206.py:3: DtypeWarning: Columns (8) have mixed types. Specify dtype option on import or set low_memory=False.\n",
5441-
" data[file_name.split('.')[0]] = pd.read_table('auxiliary/data_ex/' + file_name, sep = ';')\n"
5442-
]
5443-
}
5444-
],
5445-
"source": [
5446-
"data = {}\n",
5447-
"for file_name in files: \n",
5448-
" data[file_name.split('.')[0]] = pd.read_table('auxiliary/data_ex/' + file_name, sep = ';')\n",
5449-
" "
5450-
]
5451-
},
5452-
{
5453-
"cell_type": "code",
5454-
"execution_count": 16,
5455-
"metadata": {},
5456-
"outputs": [
5457-
{
5458-
"data": {
5459-
"text/html": [
5460-
"<div>\n",
5461-
"<style scoped>\n",
5462-
" .dataframe tbody tr th:only-of-type {\n",
5463-
" vertical-align: middle;\n",
5464-
" }\n",
5465-
"\n",
5466-
" .dataframe tbody tr th {\n",
5467-
" vertical-align: top;\n",
5468-
" }\n",
5469-
"\n",
5470-
" .dataframe thead th {\n",
5471-
" text-align: right;\n",
5472-
" }\n",
5473-
"</style>\n",
5474-
"<table border=\"1\" class=\"dataframe\">\n",
5475-
" <thead>\n",
5476-
" <tr style=\"text-align: right;\">\n",
5477-
" <th></th>\n",
5478-
" <th>account_id</th>\n",
5479-
" <th>district_id</th>\n",
5480-
" <th>frequency</th>\n",
5481-
" <th>date</th>\n",
5482-
" </tr>\n",
5483-
" </thead>\n",
5484-
" <tbody>\n",
5485-
" <tr>\n",
5486-
" <th>0</th>\n",
5487-
" <td>576</td>\n",
5488-
" <td>55</td>\n",
5489-
" <td>POPLATEK MESICNE</td>\n",
5490-
" <td>930101</td>\n",
5491-
" </tr>\n",
5492-
" <tr>\n",
5493-
" <th>1</th>\n",
5494-
" <td>3818</td>\n",
5495-
" <td>74</td>\n",
5496-
" <td>POPLATEK MESICNE</td>\n",
5497-
" <td>930101</td>\n",
5498-
" </tr>\n",
5499-
" <tr>\n",
5500-
" <th>2</th>\n",
5501-
" <td>704</td>\n",
5502-
" <td>55</td>\n",
5503-
" <td>POPLATEK MESICNE</td>\n",
5504-
" <td>930101</td>\n",
5505-
" </tr>\n",
5506-
" <tr>\n",
5507-
" <th>3</th>\n",
5508-
" <td>2378</td>\n",
5509-
" <td>16</td>\n",
5510-
" <td>POPLATEK MESICNE</td>\n",
5511-
" <td>930101</td>\n",
5512-
" </tr>\n",
5513-
" <tr>\n",
5514-
" <th>4</th>\n",
5515-
" <td>2632</td>\n",
5516-
" <td>24</td>\n",
5517-
" <td>POPLATEK MESICNE</td>\n",
5518-
" <td>930102</td>\n",
5519-
" </tr>\n",
5520-
" <tr>\n",
5521-
" <th>...</th>\n",
5522-
" <td>...</td>\n",
5523-
" <td>...</td>\n",
5524-
" <td>...</td>\n",
5525-
" <td>...</td>\n",
5526-
" </tr>\n",
5527-
" <tr>\n",
5528-
" <th>4495</th>\n",
5529-
" <td>124</td>\n",
5530-
" <td>55</td>\n",
5531-
" <td>POPLATEK MESICNE</td>\n",
5532-
" <td>971228</td>\n",
5533-
" </tr>\n",
5534-
" <tr>\n",
5535-
" <th>4496</th>\n",
5536-
" <td>3958</td>\n",
5537-
" <td>59</td>\n",
5538-
" <td>POPLATEK MESICNE</td>\n",
5539-
" <td>971228</td>\n",
5540-
" </tr>\n",
5541-
" <tr>\n",
5542-
" <th>4497</th>\n",
5543-
" <td>777</td>\n",
5544-
" <td>30</td>\n",
5545-
" <td>POPLATEK MESICNE</td>\n",
5546-
" <td>971228</td>\n",
5547-
" </tr>\n",
5548-
" <tr>\n",
5549-
" <th>4498</th>\n",
5550-
" <td>1573</td>\n",
5551-
" <td>63</td>\n",
5552-
" <td>POPLATEK MESICNE</td>\n",
5553-
" <td>971229</td>\n",
5554-
" </tr>\n",
5555-
" <tr>\n",
5556-
" <th>4499</th>\n",
5557-
" <td>3276</td>\n",
5558-
" <td>1</td>\n",
5559-
" <td>POPLATEK MESICNE</td>\n",
5560-
" <td>971229</td>\n",
5561-
" </tr>\n",
5562-
" </tbody>\n",
5563-
"</table>\n",
5564-
"<p>4500 rows × 4 columns</p>\n",
5565-
"</div>"
5566-
],
5567-
"text/plain": [
5568-
" account_id district_id frequency date\n",
5569-
"0 576 55 POPLATEK MESICNE 930101\n",
5570-
"1 3818 74 POPLATEK MESICNE 930101\n",
5571-
"2 704 55 POPLATEK MESICNE 930101\n",
5572-
"3 2378 16 POPLATEK MESICNE 930101\n",
5573-
"4 2632 24 POPLATEK MESICNE 930102\n",
5574-
"... ... ... ... ...\n",
5575-
"4495 124 55 POPLATEK MESICNE 971228\n",
5576-
"4496 3958 59 POPLATEK MESICNE 971228\n",
5577-
"4497 777 30 POPLATEK MESICNE 971228\n",
5578-
"4498 1573 63 POPLATEK MESICNE 971229\n",
5579-
"4499 3276 1 POPLATEK MESICNE 971229\n",
5580-
"\n",
5581-
"[4500 rows x 4 columns]"
5582-
]
5583-
},
5584-
"execution_count": 16,
5585-
"metadata": {},
5586-
"output_type": "execute_result"
5587-
}
5588-
],
5589-
"source": [
5590-
"data['account']"
5591-
]
5592-
},
55935377
{
55945378
"cell_type": "markdown",
55955379
"metadata": {
@@ -5810,7 +5594,7 @@
58105594
"name": "python",
58115595
"nbconvert_exporter": "python",
58125596
"pygments_lexer": "ipython3",
5813-
"version": "3.10.7"
5597+
"version": "0.0.0"
58145598
},
58155599
"microsoft": {
58165600
"ms_spell_check": {

0 commit comments

Comments
 (0)