137 KiB
137 KiB
import kaggle
import os
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
def downloadCSV():
kaggle.api.authenticate()
kaggle.api.dataset_download_files('fedesoriano/stroke-prediction-dataset', path='.', unzip=True)
data = pd.read_csv('healthcare-dataset-stroke-data.csv')
def dropNaN():
data = pd.read_csv('healthcare-dataset-stroke-data.csv')
data = data.dropna()
return data
def NormalizeData(data):
data = data.astype({"age": np.int64})
for col in data.columns:
if data[col].dtype == object: # STRINGS TO LOWERCASE
data[col] = data[col].str.lower()
if data[col].dtype == np.float64: # FLOATS TO VALUES IN [ 0, 1]
dataReshaped = data[col].values.reshape(-1,1)
scaler = MinMaxScaler(feature_range=(0, 1))
data[col] = scaler.fit_transform(dataReshaped)
if col == 'ever_married': # YES/NO TO 1/0
data[col] = data[col].map(dict(yes=1, no=0))
if col == 'smoking_status':
data[col] = data[col].str.replace(" ", "_")
if col == 'work_type':
data[col] = data[col].str.replace("-", "_")
return data
def saveToCSV(data1,data2,data3):
data1.to_csv("data_train.csv", index=False)
data2.to_csv("data_test.csv",index=False)
data3.to_csv("data_val.csv",index=False)
def describeDataset(dt, dt2, dv):
data = pd.read_csv('healthcare-dataset-stroke-data.csv')
print("Whole dataset size: ", data.size)
print("Train dataset size: ", dt.size)
print("Test dataset size: ", dt2.size)
print("Validate dataset size: ", dv.size)
print(data.describe(include='all'))
# downloadCSV()
data = dropNaN()
data = NormalizeData(data)
data_train, data_test = train_test_split(data, test_size=0.2, random_state=1)
data_train, data_val = train_test_split(data_train, test_size=0.25, random_state=1) ## Twice to get 0.6, 0.2, 0.2
saveToCSV(data_train,data_test,data_val)
describeDataset(data_train,data_test,data_val)
Whole dataset size: 61320
Train dataset size: 35340
Test dataset size: 11784
Validate dataset size: 11784
id gender age hypertension heart_disease \
count 5110.000000 5110 5110.000000 5110.000000 5110.000000
unique NaN 3 NaN NaN NaN
top NaN Female NaN NaN NaN
freq NaN 2994 NaN NaN NaN
mean 36517.829354 NaN 43.226614 0.097456 0.054012
std 21161.721625 NaN 22.612647 0.296607 0.226063
min 67.000000 NaN 0.080000 0.000000 0.000000
25% 17741.250000 NaN 25.000000 0.000000 0.000000
50% 36932.000000 NaN 45.000000 0.000000 0.000000
75% 54682.000000 NaN 61.000000 0.000000 0.000000
max 72940.000000 NaN 82.000000 1.000000 1.000000
ever_married work_type Residence_type avg_glucose_level bmi \
count 5110 5110 5110 5110.000000 4909.000000
unique 2 5 2 NaN NaN
top Yes Private Urban NaN NaN
freq 3353 2925 2596 NaN NaN
mean NaN NaN NaN 106.147677 28.893237
std NaN NaN NaN 45.283560 7.854067
min NaN NaN NaN 55.120000 10.300000
25% NaN NaN NaN 77.245000 23.500000
50% NaN NaN NaN 91.885000 28.100000
75% NaN NaN NaN 114.090000 33.100000
max NaN NaN NaN 271.740000 97.600000
smoking_status stroke
count 5110 5110.000000
unique 4 NaN
top never smoked NaN
freq 1892 NaN
mean NaN 0.048728
std NaN 0.215320
min NaN 0.000000
25% NaN 0.000000
50% NaN 0.000000
75% NaN 0.000000
max NaN 1.000000
pd.unique(data['work_type'])array(['private', 'self_employed', 'govt_job', 'children', 'never_worked'],
dtype=object)data_orginal = pd.read_csv('healthcare-dataset-stroke-data.csv')
data_orginal['work_type'].value_counts().plot(kind="bar")
<AxesSubplot:>
data_orginal['stroke'].value_counts().plot(kind="bar")
<AxesSubplot:>
data_orginal['heart_disease'].value_counts().plot(kind="bar")
<AxesSubplot:>
data_orginal['smoking_status'].value_counts().plot(kind="bar")
<AxesSubplot:>
data_orginal['Residence_type'].value_counts().plot(kind="bar")<AxesSubplot:>