ASPP/2024-heraklion-data
8
1
Fork 20
Code Issues 7 Pull requests 2 Actions Packages Projects Releases Wiki Activity
2024-heraklion-data/exercises/tabular_join/.ipynb_checkpoints/tabular_join_solution-checkpoint.ipynb

1087 lines
34 KiB
Plaintext
Raw Permalink Normal View History

ASPP 2024 material
2024-08-27 14:27:53 +02:00
{
"cells": [
{
"cell_type": "markdown",
"id": "f11a76bf",
"metadata": {},
"source": [
"# Exercise: Add experiment information to electrophysiology data"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "b6f2742b",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"# Set some Pandas options: maximum number of rows/columns it's going to display\n",
"pd.set_option('display.max_rows', 1000)\n",
"pd.set_option('display.max_columns', 100)"
]
},
{
"cell_type": "markdown",
"id": "2967c84e",
"metadata": {},
"source": [
"# Load electrophysiology data"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "ed626ee3",
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv('../../data/QC_passed_2024-07-04_collected.csv')\n",
"info = pd.read_csv('../../data/op_info.csv')"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "48d5375f",
"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>OP</th>\n",
" <th>filename</th>\n",
" <th>slice</th>\n",
" <th>cell_ch</th>\n",
" <th>cell_ID</th>\n",
" <th>day</th>\n",
" <th>treatment</th>\n",
" <th>hrs_incubation</th>\n",
" <th>repatch</th>\n",
" <th>hrs_after_OP</th>\n",
" <th>Rs</th>\n",
" <th>Rin</th>\n",
" <th>resting_potential</th>\n",
" <th>max_spikes</th>\n",
" <th>Rheobase</th>\n",
" <th>AP_heigth</th>\n",
" <th>TH</th>\n",
" <th>max_depol</th>\n",
" <th>max_repol</th>\n",
" <th>membra_time_constant_tau</th>\n",
" <th>capacitance</th>\n",
" <th>comments</th>\n",
" <th>rheo_ramp</th>\n",
" <th>AP_halfwidth</th>\n",
" <th>Rheobse_ramp</th>\n",
" <th>Unnamed: 27</th>\n",
" <th>rheos_ramp</th>\n",
" <th>comment</th>\n",
" <th></th>\n",
" <th>high K concentration</th>\n",
" <th>RMP_from_char</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>OP230420</td>\n",
" <td>23420003.abf</td>\n",
" <td>S1</td>\n",
" <td>1</td>\n",
" <td>23420S1c1</td>\n",
" <td>D1</td>\n",
" <td>TTX</td>\n",
" <td>0.0</td>\n",
" <td>no</td>\n",
" <td>10.416389</td>\n",
" <td>6.675643</td>\n",
" <td>39.025301</td>\n",
" <td>-74.285889</td>\n",
" <td>24</td>\n",
" <td>200.0</td>\n",
" <td>80.749512</td>\n",
" <td>-35.278320</td>\n",
" <td>336.181641</td>\n",
" <td>-60.791016</td>\n",
" <td>19.40</td>\n",
" <td>510.601767</td>\n",
" <td>0</td>\n",
" <td>753.380113</td>\n",
" <td>1.151009</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8 mM</td>\n",
" <td>-61.828554</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>OP230420</td>\n",
" <td>23420003.abf</td>\n",
" <td>S1</td>\n",
" <td>3</td>\n",
" <td>23420S1c3</td>\n",
" <td>D1</td>\n",
" <td>TTX</td>\n",
" <td>0.0</td>\n",
" <td>no</td>\n",
" <td>10.416389</td>\n",
" <td>7.867174</td>\n",
" <td>48.728367</td>\n",
" <td>-69.573975</td>\n",
" <td>26</td>\n",
" <td>300.0</td>\n",
" <td>78.448486</td>\n",
" <td>-32.043457</td>\n",
" <td>350.097656</td>\n",
" <td>-67.138672</td>\n",
" <td>17.30</td>\n",
" <td>393.397918</td>\n",
" <td>1</td>\n",
" <td>585.102837</td>\n",
" <td>1.006321</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8 mM</td>\n",
" <td>-60.460298</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>OP230420</td>\n",
" <td>23420003.abf</td>\n",
" <td>S1</td>\n",
" <td>6</td>\n",
" <td>23420S1c6</td>\n",
" <td>D1</td>\n",
" <td>TTX</td>\n",
" <td>0.0</td>\n",
" <td>no</td>\n",
" <td>10.416389</td>\n",
" <td>8.820134</td>\n",
" <td>35.971082</td>\n",
" <td>-54.956055</td>\n",
" <td>22</td>\n",
" <td>300.0</td>\n",
" <td>76.660156</td>\n",
" <td>-29.827881</td>\n",
" <td>270.629883</td>\n",
" <td>-52.246094</td>\n",
" <td>14.85</td>\n",
" <td>426.098774</td>\n",
" <td>3</td>\n",
" <td>173.915797</td>\n",
" <td>1.266335</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8 mM</td>\n",
" <td>-59.615979</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>OP230420</td>\n",
" <td>23420003.abf</td>\n",
" <td>S1</td>\n",
" <td>7</td>\n",
" <td>23420S1c7</td>\n",
" <td>D1</td>\n",
" <td>TTX</td>\n",
" <td>0.0</td>\n",
" <td>yes</td>\n",
" <td>10.416389</td>\n",
" <td>7.269195</td>\n",
" <td>39.186101</td>\n",
" <td>-69.268799</td>\n",
" <td>24</td>\n",
" <td>300.0</td>\n",
" <td>75.030518</td>\n",
" <td>-29.699707</td>\n",
" <td>242.553711</td>\n",
" <td>-71.411133</td>\n",
" <td>17.15</td>\n",
" <td>478.273362</td>\n",
" <td>4</td>\n",
" <td>598.079936</td>\n",
" <td>0.994396</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8 mM</td>\n",
" <td>-61.173839</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>OP230420</td>\n",
" <td>23420003.abf</td>\n",
" <td>S1</td>\n",
" <td>8</td>\n",
" <td>23420S1c8</td>\n",
" <td>D1</td>\n",
" <td>TTX</td>\n",
" <td>0.0</td>\n",
" <td>yes</td>\n",
" <td>10.416389</td>\n",
" <td>6.000400</td>\n",
" <td>31.599917</td>\n",
" <td>-70.550537</td>\n",
" <td>22</td>\n",
" <td>350.0</td>\n",
" <td>81.011963</td>\n",
" <td>-33.068848</td>\n",
" <td>309.448242</td>\n",
" <td>-61.401367</td>\n",
" <td>16.65</td>\n",
" <td>575.513924</td>\n",
" <td>5</td>\n",
" <td>786.927898</td>\n",
" <td>1.182830</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8 mM</td>\n",
" <td>-60.956350</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" OP filename slice cell_ch cell_ID day treatment \\\n",
"0 OP230420 23420003.abf S1 1 23420S1c1 D1 TTX \n",
"1 OP230420 23420003.abf S1 3 23420S1c3 D1 TTX \n",
"2 OP230420 23420003.abf S1 6 23420S1c6 D1 TTX \n",
"3 OP230420 23420003.abf S1 7 23420S1c7 D1 TTX \n",
"4 OP230420 23420003.abf S1 8 23420S1c8 D1 TTX \n",
"\n",
" hrs_incubation repatch hrs_after_OP Rs Rin \\\n",
"0 0.0 no 10.416389 6.675643 39.025301 \n",
"1 0.0 no 10.416389 7.867174 48.728367 \n",
"2 0.0 no 10.416389 8.820134 35.971082 \n",
"3 0.0 yes 10.416389 7.269195 39.186101 \n",
"4 0.0 yes 10.416389 6.000400 31.599917 \n",
"\n",
" resting_potential max_spikes Rheobase AP_heigth TH max_depol \\\n",
"0 -74.285889 24 200.0 80.749512 -35.278320 336.181641 \n",
"1 -69.573975 26 300.0 78.448486 -32.043457 350.097656 \n",
"2 -54.956055 22 300.0 76.660156 -29.827881 270.629883 \n",
"3 -69.268799 24 300.0 75.030518 -29.699707 242.553711 \n",
"4 -70.550537 22 350.0 81.011963 -33.068848 309.448242 \n",
"\n",
" max_repol membra_time_constant_tau capacitance comments rheo_ramp \\\n",
"0 -60.791016 19.40 510.601767 0 753.380113 \n",
"1 -67.138672 17.30 393.397918 1 585.102837 \n",
"2 -52.246094 14.85 426.098774 3 173.915797 \n",
"3 -71.411133 17.15 478.273362 4 598.079936 \n",
"4 -61.401367 16.65 575.513924 5 786.927898 \n",
"\n",
" AP_halfwidth Rheobse_ramp Unnamed: 27 rheos_ramp comment \\\n",
"0 1.151009 NaN NaN NaN NaN NaN \n",
"1 1.006321 NaN NaN NaN NaN NaN \n",
"2 1.266335 NaN NaN NaN NaN NaN \n",
"3 0.994396 NaN NaN NaN NaN NaN \n",
"4 1.182830 NaN NaN NaN NaN NaN \n",
"\n",
" high K concentration RMP_from_char \n",
"0 8 mM -61.828554 \n",
"1 8 mM -60.460298 \n",
"2 8 mM -59.615979 \n",
"3 8 mM -61.173839 \n",
"4 8 mM -60.956350 "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "47191528",
"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>OP</th>\n",
" <th>tissue_source</th>\n",
" <th>area</th>\n",
" <th>patient_age</th>\n",
" <th>patcher</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>OP201027</td>\n",
" <td>Mitte</td>\n",
" <td>temporal</td>\n",
" <td>33</td>\n",
" <td>Rosie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>OP201029</td>\n",
" <td>Mitte</td>\n",
" <td>temporal</td>\n",
" <td>47</td>\n",
" <td>Rosie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>OP210323</td>\n",
" <td>Virchow</td>\n",
" <td>temporal</td>\n",
" <td>10</td>\n",
" <td>Rosie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>OP210615</td>\n",
" <td>Virchow</td>\n",
" <td>temporal</td>\n",
" <td>19</td>\n",
" <td>Rosie</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>OP211123</td>\n",
" <td>Bielefeld</td>\n",
" <td>temporal</td>\n",
" <td>68</td>\n",
" <td>Rosie</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" OP tissue_source area patient_age patcher\n",
"0 OP201027 Mitte temporal 33 Rosie\n",
"1 OP201029 Mitte temporal 47 Rosie\n",
"2 OP210323 Virchow temporal 10 Rosie\n",
"3 OP210615 Virchow temporal 19 Rosie\n",
"4 OP211123 Bielefeld temporal 68 Rosie"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"info.head()"
]
},
{
"cell_type": "markdown",
"id": "2fef4d37",
"metadata": {},
"source": [
"# 1. Add experiment information to the electrophysiology results\n",
"\n",
"* Is there information for every experiment?\n",
"* How many experiments did each patcher perform? (i.e., individual OPs, or rows in `info`)\n",
"* How many samples did each patcher analyze? (i.e., individual rows in `df`)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "35e19a53",
"metadata": {},
"outputs": [],
"source": [
"df_with_info = df.merge(info, on='OP', how='left')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "eac1244f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"OP 827\n",
"filename 827\n",
"slice 827\n",
"cell_ch 827\n",
"cell_ID 827\n",
"day 827\n",
"treatment 827\n",
"hrs_incubation 827\n",
"repatch 827\n",
"hrs_after_OP 827\n",
"Rs 827\n",
"Rin 827\n",
"resting_potential 827\n",
"max_spikes 827\n",
"Rheobase 824\n",
"AP_heigth 824\n",
"TH 824\n",
"max_depol 824\n",
"max_repol 824\n",
"membra_time_constant_tau 827\n",
"capacitance 827\n",
"comments 742\n",
"rheo_ramp 120\n",
"AP_halfwidth 820\n",
"Rheobse_ramp 160\n",
"Unnamed: 27 0\n",
"rheos_ramp 32\n",
"comment 5\n",
" 37\n",
"high K concentration 827\n",
"RMP_from_char 827\n",
"tissue_source 800\n",
"area 800\n",
"patient_age 800\n",
"patcher 800\n",
"dtype: int64"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_with_info.count()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "2f6724ce",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Verji 35\n",
"Rosie 8\n",
"Anna 2\n",
"Name: patcher, dtype: int64"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"info['patcher'].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "8f996049",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Verji 594\n",
"Rosie 206\n",
"Name: patcher, dtype: int64"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_with_info['patcher'].value_counts()"
]
},
{
"cell_type": "markdown",
"id": "44031178",
"metadata": {},
"source": [
"# 2. Remove outliers from the table\n",
"\n",
"1. Load the list of outliers in `outliers.csv`\n",
"2. Use an anti-join to remove the outliers from the table\n",
"3. How many samples (rows) are left in the data?"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "d1d4cc27",
"metadata": {},
"outputs": [],
"source": [
"outliers = pd.read_csv('outliers.csv')"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "fbebbd97",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(134, 2)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"outliers.shape"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "8a3c7943",
"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>OP</th>\n",
" <th>cell_ID</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>OP240201</td>\n",
" <td>24201S2c2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>OP210323</td>\n",
" <td>2021_03_25_0S4_D2c6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>OP230808</td>\n",
" <td>23808S2c6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>OP240503</td>\n",
" <td>24503S1c6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>OP230109</td>\n",
" <td>2311S3c2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" OP cell_ID\n",
"0 OP240201 24201S2c2\n",
"1 OP210323 2021_03_25_0S4_D2c6\n",
"2 OP230808 23808S2c6\n",
"3 OP240503 24503S1c6\n",
"4 OP230109 2311S3c2"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"outliers.head()"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "573687e7",
"metadata": {},
"outputs": [],
"source": [
"temp = df_with_info.merge(outliers, on=['OP', 'cell_ID'], how='outer', indicator=True)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "a4a6574b",
"metadata": {},
"outputs": [],
"source": [
"df_without_outliers = temp[temp['_merge'] == 'left_only'].drop('_merge', axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "8fd89a40",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(659, 35)"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_without_outliers.shape"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "07f4776a",
"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>OP</th>\n",
" <th>filename</th>\n",
" <th>slice</th>\n",
" <th>cell_ch</th>\n",
" <th>cell_ID</th>\n",
" <th>day</th>\n",
" <th>treatment</th>\n",
" <th>hrs_incubation</th>\n",
" <th>repatch</th>\n",
" <th>hrs_after_OP</th>\n",
" <th>Rs</th>\n",
" <th>Rin</th>\n",
" <th>resting_potential</th>\n",
" <th>max_spikes</th>\n",
" <th>Rheobase</th>\n",
" <th>AP_heigth</th>\n",
" <th>TH</th>\n",
" <th>max_depol</th>\n",
" <th>max_repol</th>\n",
" <th>membra_time_constant_tau</th>\n",
" <th>capacitance</th>\n",
" <th>comments</th>\n",
" <th>rheo_ramp</th>\n",
" <th>AP_halfwidth</th>\n",
" <th>Rheobse_ramp</th>\n",
" <th>Unnamed: 27</th>\n",
" <th>rheos_ramp</th>\n",
" <th>comment</th>\n",
" <th></th>\n",
" <th>high K concentration</th>\n",
" <th>RMP_from_char</th>\n",
" <th>tissue_source</th>\n",
" <th>area</th>\n",
" <th>patient_age</th>\n",
" <th>patcher</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>OP230420</td>\n",
" <td>23420003.abf</td>\n",
" <td>S1</td>\n",
" <td>1</td>\n",
" <td>23420S1c1</td>\n",
" <td>D1</td>\n",
" <td>TTX</td>\n",
" <td>0.0</td>\n",
" <td>no</td>\n",
" <td>10.416389</td>\n",
" <td>6.675643</td>\n",
" <td>39.025301</td>\n",
" <td>-74.285889</td>\n",
" <td>24</td>\n",
" <td>200.0</td>\n",
" <td>80.749512</td>\n",
" <td>-35.278320</td>\n",
" <td>336.181641</td>\n",
" <td>-60.791016</td>\n",
" <td>19.40</td>\n",
" <td>510.601767</td>\n",
" <td>0</td>\n",
" <td>753.380113</td>\n",
" <td>1.151009</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8 mM</td>\n",
" <td>-61.828554</td>\n",
" <td>Bielefeld</td>\n",
" <td>temporal</td>\n",
" <td>13.0</td>\n",
" <td>Verji</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>OP230420</td>\n",
" <td>23420003.abf</td>\n",
" <td>S1</td>\n",
" <td>3</td>\n",
" <td>23420S1c3</td>\n",
" <td>D1</td>\n",
" <td>TTX</td>\n",
" <td>0.0</td>\n",
" <td>no</td>\n",
" <td>10.416389</td>\n",
" <td>7.867174</td>\n",
" <td>48.728367</td>\n",
" <td>-69.573975</td>\n",
" <td>26</td>\n",
" <td>300.0</td>\n",
" <td>78.448486</td>\n",
" <td>-32.043457</td>\n",
" <td>350.097656</td>\n",
" <td>-67.138672</td>\n",
" <td>17.30</td>\n",
" <td>393.397918</td>\n",
" <td>1</td>\n",
" <td>585.102837</td>\n",
" <td>1.006321</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8 mM</td>\n",
" <td>-60.460298</td>\n",
" <td>Bielefeld</td>\n",
" <td>temporal</td>\n",
" <td>13.0</td>\n",
" <td>Verji</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>OP230420</td>\n",
" <td>23420003.abf</td>\n",
" <td>S1</td>\n",
" <td>6</td>\n",
" <td>23420S1c6</td>\n",
" <td>D1</td>\n",
" <td>TTX</td>\n",
" <td>0.0</td>\n",
" <td>no</td>\n",
" <td>10.416389</td>\n",
" <td>8.820134</td>\n",
" <td>35.971082</td>\n",
" <td>-54.956055</td>\n",
" <td>22</td>\n",
" <td>300.0</td>\n",
" <td>76.660156</td>\n",
" <td>-29.827881</td>\n",
" <td>270.629883</td>\n",
" <td>-52.246094</td>\n",
" <td>14.85</td>\n",
" <td>426.098774</td>\n",
" <td>3</td>\n",
" <td>173.915797</td>\n",
" <td>1.266335</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8 mM</td>\n",
" <td>-59.615979</td>\n",
" <td>Bielefeld</td>\n",
" <td>temporal</td>\n",
" <td>13.0</td>\n",
" <td>Verji</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>OP230420</td>\n",
" <td>23420003.abf</td>\n",
" <td>S1</td>\n",
" <td>8</td>\n",
" <td>23420S1c8</td>\n",
" <td>D1</td>\n",
" <td>TTX</td>\n",
" <td>0.0</td>\n",
" <td>yes</td>\n",
" <td>10.416389</td>\n",
" <td>6.000400</td>\n",
" <td>31.599917</td>\n",
" <td>-70.550537</td>\n",
" <td>22</td>\n",
" <td>350.0</td>\n",
" <td>81.011963</td>\n",
" <td>-33.068848</td>\n",
" <td>309.448242</td>\n",
" <td>-61.401367</td>\n",
" <td>16.65</td>\n",
" <td>575.513924</td>\n",
" <td>5</td>\n",
" <td>786.927898</td>\n",
" <td>1.182830</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8 mM</td>\n",
" <td>-60.956350</td>\n",
" <td>Bielefeld</td>\n",
" <td>temporal</td>\n",
" <td>13.0</td>\n",
" <td>Verji</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>OP230420</td>\n",
" <td>23420061.abf</td>\n",
" <td>S1_D2</td>\n",
" <td>8</td>\n",
" <td>23420S1c8</td>\n",
" <td>D2</td>\n",
" <td>TTX</td>\n",
" <td>19.0</td>\n",
" <td>yes</td>\n",
" <td>29.633333</td>\n",
" <td>8.271614</td>\n",
" <td>30.607259</td>\n",
" <td>-70.745850</td>\n",
" <td>1</td>\n",
" <td>1300.0</td>\n",
" <td>48.883057</td>\n",
" <td>-20.855713</td>\n",
" <td>100.952148</td>\n",
" <td>-27.465820</td>\n",
" <td>13.25</td>\n",
" <td>864.892430</td>\n",
" <td>29</td>\n",
" <td>565.938865</td>\n",
" <td>1.504127</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>8 mM</td>\n",
" <td>-61.283967</td>\n",
" <td>Bielefeld</td>\n",
" <td>temporal</td>\n",
" <td>13.0</td>\n",
" <td>Verji</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" OP filename slice cell_ch cell_ID day treatment \\\n",
"0 OP230420 23420003.abf S1 1 23420S1c1 D1 TTX \n",
"1 OP230420 23420003.abf S1 3 23420S1c3 D1 TTX \n",
"2 OP230420 23420003.abf S1 6 23420S1c6 D1 TTX \n",
"5 OP230420 23420003.abf S1 8 23420S1c8 D1 TTX \n",
"6 OP230420 23420061.abf S1_D2 8 23420S1c8 D2 TTX \n",
"\n",
" hrs_incubation repatch hrs_after_OP Rs Rin \\\n",
"0 0.0 no 10.416389 6.675643 39.025301 \n",
"1 0.0 no 10.416389 7.867174 48.728367 \n",
"2 0.0 no 10.416389 8.820134 35.971082 \n",
"5 0.0 yes 10.416389 6.000400 31.599917 \n",
"6 19.0 yes 29.633333 8.271614 30.607259 \n",
"\n",
" resting_potential max_spikes Rheobase AP_heigth TH max_depol \\\n",
"0 -74.285889 24 200.0 80.749512 -35.278320 336.181641 \n",
"1 -69.573975 26 300.0 78.448486 -32.043457 350.097656 \n",
"2 -54.956055 22 300.0 76.660156 -29.827881 270.629883 \n",
"5 -70.550537 22 350.0 81.011963 -33.068848 309.448242 \n",
"6 -70.745850 1 1300.0 48.883057 -20.855713 100.952148 \n",
"\n",
" max_repol membra_time_constant_tau capacitance comments rheo_ramp \\\n",
"0 -60.791016 19.40 510.601767 0 753.380113 \n",
"1 -67.138672 17.30 393.397918 1 585.102837 \n",
"2 -52.246094 14.85 426.098774 3 173.915797 \n",
"5 -61.401367 16.65 575.513924 5 786.927898 \n",
"6 -27.465820 13.25 864.892430 29 565.938865 \n",
"\n",
" AP_halfwidth Rheobse_ramp Unnamed: 27 rheos_ramp comment \\\n",
"0 1.151009 NaN NaN NaN NaN NaN \n",
"1 1.006321 NaN NaN NaN NaN NaN \n",
"2 1.266335 NaN NaN NaN NaN NaN \n",
"5 1.182830 NaN NaN NaN NaN NaN \n",
"6 1.504127 NaN NaN NaN NaN NaN \n",
"\n",
" high K concentration RMP_from_char tissue_source area patient_age \\\n",
"0 8 mM -61.828554 Bielefeld temporal 13.0 \n",
"1 8 mM -60.460298 Bielefeld temporal 13.0 \n",
"2 8 mM -59.615979 Bielefeld temporal 13.0 \n",
"5 8 mM -60.956350 Bielefeld temporal 13.0 \n",
"6 8 mM -61.283967 Bielefeld temporal 13.0 \n",
"\n",
" patcher \n",
"0 Verji \n",
"1 Verji \n",
"2 Verji \n",
"5 Verji \n",
"6 Verji "
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_without_outliers.head()"
]
},
{
"cell_type": "markdown",
"id": "84270332",
"metadata": {},
"source": [
"# 3. Save final result in `processed_QC_passed_2024-07-04_collected_v1.csv`\n",
"\n",
"1. Using the `.to_csv` method of Pandas DataFrames"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "85902eea",
"metadata": {},
"outputs": [],
"source": [
"df_without_outliers.to_csv('processed_QC_passed_2024-07-04_collected_v1.csv', index=None)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c7bcff45",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in a new issue Copy permalink