Data model to understand recovery phase on epilepsy patients

Data Driven approach

Data Scientist: Dr. Juan Ignacio Barrios, MD MSc,

Doctoral Thesis by Susana Lara . Germany -Barcelona 2021

# Importing Python libraries needed for data analysis 
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import os
import math
import plotly.io as pio
pio.renderers.default='notebook'
from sklearn.cluster import KMeans
import scipy.cluster.hierarchy as sch
from sklearn.cluster import AgglomerativeClustering
%matplotlib inline

# reading dataset 
dataset = pd.read_excel('filename.xlsx').iloc[:,:-1]

! python --version

Python 3.7.12

dataset.shape

(189, 46)

# fixing columns spaces 
cols=[]
for col in dataset.columns:
    if col.startswith('Unnamed'):
        cols.append(cols[-1])
    else:
        cols.append(col.strip())
dataset.columns=cols
dataset.columns=[i+'--'+str(z).strip() for i,z in zip(dataset.columns,dataset.iloc[0,:].fillna('').values)]
dataset.columns=[col.strip('--') for col in dataset.columns]

# Data transforming 
dataset['Consciousness Time']=pd.to_numeric(dataset['Consciousness Time'],errors='coerce')
dataset.drop(0,inplace=True)
dataset.dropna(inplace=True)
dataset.reset_index(inplace=True,drop=True)
dataset.columns 

Index(['Nr', 'Location', 'Sex', 'Age', 'Age onset', 'Years with ES',
       'Seizure Type', 'Laterality', 'Behavior before', 'Same day ES before',
       'ES before', 'Ictal Seconds', 'Ictal signs and symtoms--MA',
       'Ictal signs and symtoms--OA', 'Ictal signs and symtoms--SMA',
       'Ictal signs and symtoms--Laughing',
       'Ictal signs and symtoms--Coughing', 'Ictal signs and symtoms--NRR',
       'Ictal signs and symtoms--NRL', 'Ictal signs and symtoms--Vo',
       'Ictal signs and symtoms--Gaze', 'Ictal signs and symtoms--VA',
       'Ictal signs and symtoms--Hiccup', 'Consciousness Time',
       'Postictal signs and symptoms--MA', 'Postictal signs and symptoms--OA',
       'Postictal signs and symptoms--NRR',
       'Postictal signs and symptoms--NRL',
       'Postictal signs and symptoms--Smacking',
       'Postictal signs and symptoms--Smile',
       'Postictal signs and symptoms--Laughing',
       'Postictal signs and symptoms--Coughing',
       'Postictal signs and symptoms--Vo',
       'Postictal signs and symptoms--Gape',
       'Postictal signs and symptoms--Hipcup',
       'Postictal signs and symptoms--Motor restless',
       'Postictal signs and symptoms--Speaks incomprehensible',
       'Postictal signs and symptoms--Cloni Arm',
       'Postictal signs and symptoms--Stand up', 'Level of Consciousness',
       'Coughing Time seconds--Coughing #1',
       'Coughing Time seconds--Coughing #2',
       'Coughing Time seconds--Coughing #3',
       'Coughing Time seconds--Coughing #4', 'Disnomia seconds', 'Aphasia TT'],
      dtype='object')

DESCRIPTIVE ANALYTICS

# Examining the dataframe 
dataset.head(25) 

	Nr	Location	Sex	Age	Age onset	Years with ES	Seizure Type	Laterality	Behavior before	Same day ES before	...	Postictal signs and symptoms--Speaks incomprehensible	Postictal signs and symptoms--Cloni Arm	Postictal signs and symptoms--Stand up	Level of Consciousness	Coughing Time seconds--Coughing #1	Coughing Time seconds--Coughing #2	Coughing Time seconds--Coughing #3	Coughing Time seconds--Coughing #4	Disnomia seconds	Aphasia TT
0	1.0	TR	2.0	20.0	9.0	11.0	4.0	1.0	1.0	2.0	...	0	0	0	2.0	0	0	0	0	0.0	0.0
1	2.0	TR	1.0	25.0	22.0	3.0	9.0	1.0	1.0	3.0	...	0	0	0	5.0	0	0	0	0	0.0	0.0
2	3.0	TR	2.0	28.0	6.0	22.0	10.0	1.0	2.0	0.0	...	0	0	0	2.0	39	0	0	0	0.0	0.0
3	4.0	TR	2.0	42.0	1.0	41.0	11.0	1.0	1.0	2.0	...	0	0	0	5.0	0	0	0	0	0.0	0.0
4	5.0	TR	2.0	35.0	10.0	25.0	4.0	1.0	1.0	0.0	...	0	0	0	2.0	0	0	0	0	0.0	0.0
5	6.0	TR	2.0	29.0	20.0	9.0	4.0	2.0	2.0	0.0	...	0	0	0	4.0	0	0	0	0	0.0	0.0
6	7.0	TR	1.0	57.0	3.0	54.0	4.0	1.0	1.0	0.0	...	0	0	0	2.0	0	0	0	0	0.0	0.0
7	8.0	TR	1.0	24.0	4.0	20.0	2.0	1.0	1.0	2.0	...	0	0	0	2.0	0	0	0	0	0.0	0.0
8	9.0	TR	1.0	34.0	7.0	27.0	2.0	1.0	1.0	4.0	...	0	0	0	2.0	0	0	0	0	0.0	0.0
9	10.0	TR	2.0	42.0	1.0	41.0	2.0	1.0	1.0	4.0	...	0	1	0	5.0	0	0	0	0	0.0	0.0
10	11.0	TR	1.0	22.0	13.0	9.0	2.0	1.0	2.0	0.0	...	0	0	0	2.0	0	0	0	0	0.0	0.0
11	12.0	TR	2.0	20.0	10.0	10.0	2.0	1.0	2.0	1.0	...	0	0	0	2.0	2	0	0	0	0.0	0.0
12	13.0	TR	1.0	19.0	14.0	5.0	2.0	1.0	2.0	1.0	...	0	0	0	2.0	0	0	0	0	0.0	0.0
13	14.0	TR	2.0	21.0	10.0	11.0	6.0	2.0	1.0	1.0	...	0	0	0	2.0	0	0	0	0	0.0	0.0
14	15.0	TR	1.0	43.0	16.0	27.0	7.0	2.0	1.0	0.0	...	0	0	0	4.0	0	0	0	0	0.0	0.0
15	16.0	TR	2.0	20.0	10.0	10.0	3.0	1.0	1.0	0.0	...	0	0	0	10.0	0	0	0	0	0.0	0.0
16	18.0	TR	1.0	61.0	30.0	31.0	1.0	1.0	2.0	2.0	...	0	0	0	2.0	0	0	0	0	46.0	0.0
17	19.0	TR	2.0	20.0	9.0	11.0	1.0	1.0	1.0	5.0	...	0	0	0	5.0	0	0	0	0	0.0	60.0
18	20.0	TR	1.0	24.0	23.0	1.0	1.0	1.0	2.0	6.0	...	0	0	0	2.0	0	0	0	0	0.0	0.0
19	21.0	TR	2.0	30.0	16.0	14.0	1.0	1.0	1.0	1.0	...	0	0	0	4.0	0	0	0	0	0.0	0.0
20	24.0	TR	2.0	18.0	16.0	2.0	1.0	1.0	1.0	1.0	...	0	0	0	2.0	0	0	0	0	0.0	0.0
21	25.0	TR	2.0	53.0	51.0	2.0	1.0	1.0	1.0	1.0	...	0	0	0	2.0	7	0	0	0	0.0	0.0
22	26.0	TR	1.0	24.0	22.0	2.0	1.0	1.0	1.0	1.0	...	0.083333	0.125	0.166667	2.0	0	0	0	0	0.0	0.0
23	27.0	TR	2.0	53.0	14.0	39.0	1.0	1.0	2.0	0.0	...	1	0	0	2.0	0	0	0	0	0.0	0.0
24	28.0	TR	1.0	52.0	1.0	51.0	1.0	3.0	1.0	1.0	...	0	0	0	4.0	0	0	0	0	0.0	0.0

25 rows × 46 columns

Distribution analysis CT with respect to sex and age

# scatterplot graph , features transforming 
df1=dataset.loc[:,'Sex':'Ictal Seconds']
for col in df1.columns[1:-1]:
    df1[col]=df1[col].astype(int).astype(str)
df1['Age']=df1['Age'].astype(int)
df1['Consciousness Time']=pd.to_numeric(dataset['Consciousness Time'])
sns.set(rc={'figure.figsize':(20,20)})
g = sns.FacetGrid(df1, col="Sex", height=8.27, aspect=11.7/8.27)
g.map(sns.scatterplot, 'Consciousness Time', 'Age', alpha=.7)
g.add_legend()

<seaborn.axisgrid.FacetGrid at 0x1d080c16fa0>

Distribution analysis CT with respect to laterality

g = sns.FacetGrid(df1, col="Laterality", height=4, aspect=.5)
g.map(sns.barplot, "Sex", "Consciousness Time")

C:\Users\tommy\anaconda3\lib\site-packages\seaborn\axisgrid.py:670: UserWarning:

Using the barplot function without specifying `order` is likely to produce an incorrect plot.

<seaborn.axisgrid.FacetGrid at 0x1d0814e39a0>

Distribution analysis CT with respect to Behavior before

g = sns.FacetGrid(df1, col="Behavior before", height=4, aspect=.5)
g.map(sns.barplot, "Sex", "Consciousness Time")

C:\Users\tommy\anaconda3\lib\site-packages\seaborn\axisgrid.py:670: UserWarning:

Using the barplot function without specifying `order` is likely to produce an incorrect plot.

<seaborn.axisgrid.FacetGrid at 0x1d08198d520>

Distribution analysis CT with respect to sex

##age wise distribution plot
g = sns.FacetGrid(df1, row="Sex",
                  height=1.7, aspect=4,)
g.map(sns.kdeplot, "Consciousness Time")

<seaborn.axisgrid.FacetGrid at 0x1d0819a0bb0>

Correlation comparison for main features

df=dataset.loc[:,'Sex':'Consciousness Time']

corr_df=df.corr()
fig = px.imshow(corr_df)
fig.update_layout(title='Correlation comparion for main features',width=1000,height=1000
 )
fig.show()
# fig.write_html(r'D:\Machine learning\Epilepsia SUSANA\correlacion.html')
#with open("correlacion.html", "r", encoding='utf-8') as f:
#    text= f.read()
import codecs
# f = codecs.open("correlacion.html", 'r', 'utf-8')