In [ ]:
#Heartdisease
In [2]:
import warnings
warnings.filterwarnings('ignore')
import numpy as np 
import pandas as pd 
import seaborn as sns
import matplotlib.pyplot as plt
In [3]:
df = pd.read_csv("C:\\Users\MNLVBPV\heart_disease_uci.csv")
In [4]:
df
Out[4]:
id age sex dataset cp trestbps chol fbs restecg thalch exang oldpeak slope ca thal num
0 1 63 Male Cleveland typical angina 145.0 233.0 True lv hypertrophy 150.0 False 2.3 downsloping 0.0 fixed defect 0
1 2 67 Male Cleveland asymptomatic 160.0 286.0 False lv hypertrophy 108.0 True 1.5 flat 3.0 normal 2
2 3 67 Male Cleveland asymptomatic 120.0 229.0 False lv hypertrophy 129.0 True 2.6 flat 2.0 reversable defect 1
3 4 37 Male Cleveland non-anginal 130.0 250.0 False normal 187.0 False 3.5 downsloping 0.0 normal 0
4 5 41 Female Cleveland atypical angina 130.0 204.0 False lv hypertrophy 172.0 False 1.4 upsloping 0.0 normal 0
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
915 916 54 Female VA Long Beach asymptomatic 127.0 333.0 True st-t abnormality 154.0 False 0.0 NaN NaN NaN 1
916 917 62 Male VA Long Beach typical angina NaN 139.0 False st-t abnormality NaN NaN NaN NaN NaN NaN 0
917 918 55 Male VA Long Beach asymptomatic 122.0 223.0 True st-t abnormality 100.0 False 0.0 NaN NaN fixed defect 2
918 919 58 Male VA Long Beach asymptomatic NaN 385.0 True lv hypertrophy NaN NaN NaN NaN NaN NaN 0
919 920 62 Male VA Long Beach atypical angina 120.0 254.0 False lv hypertrophy 93.0 True 0.0 NaN NaN NaN 1

920 rows × 16 columns

In [5]:
df.head(5)
Out[5]:
id age sex dataset cp trestbps chol fbs restecg thalch exang oldpeak slope ca thal num
0 1 63 Male Cleveland typical angina 145.0 233.0 True lv hypertrophy 150.0 False 2.3 downsloping 0.0 fixed defect 0
1 2 67 Male Cleveland asymptomatic 160.0 286.0 False lv hypertrophy 108.0 True 1.5 flat 3.0 normal 2
2 3 67 Male Cleveland asymptomatic 120.0 229.0 False lv hypertrophy 129.0 True 2.6 flat 2.0 reversable defect 1
3 4 37 Male Cleveland non-anginal 130.0 250.0 False normal 187.0 False 3.5 downsloping 0.0 normal 0
4 5 41 Female Cleveland atypical angina 130.0 204.0 False lv hypertrophy 172.0 False 1.4 upsloping 0.0 normal 0
In [6]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 920 entries, 0 to 919
Data columns (total 16 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   id        920 non-null    int64  
 1   age       920 non-null    int64  
 2   sex       920 non-null    object 
 3   dataset   920 non-null    object 
 4   cp        920 non-null    object 
 5   trestbps  861 non-null    float64
 6   chol      890 non-null    float64
 7   fbs       830 non-null    object 
 8   restecg   918 non-null    object 
 9   thalch    865 non-null    float64
 10  exang     865 non-null    object 
 11  oldpeak   858 non-null    float64
 12  slope     611 non-null    object 
 13  ca        309 non-null    float64
 14  thal      434 non-null    object 
 15  num       920 non-null    int64  
dtypes: float64(5), int64(3), object(8)
memory usage: 115.1+ KB
In [7]:
df.shape
Out[7]:
(920, 16)
In [8]:
df.columns
Out[8]:
Index(['id', 'age', 'sex', 'dataset', 'cp', 'trestbps', 'chol', 'fbs',
       'restecg', 'thalch', 'exang', 'oldpeak', 'slope', 'ca', 'thal', 'num'],
      dtype='object')
In [9]:
df['cp'].value_counts()
Out[9]:
asymptomatic       496
non-anginal        204
atypical angina    174
typical angina      46
Name: cp, dtype: int64
In [10]:
df.isna().sum()
Out[10]:
id            0
age           0
sex           0
dataset       0
cp            0
trestbps     59
chol         30
fbs          90
restecg       2
thalch       55
exang        55
oldpeak      62
slope       309
ca          611
thal        486
num           0
dtype: int64
In [11]:
df.columns= ['id', 'age', 'sex', 'study_location', 'chest_pain_type', 'resting_bloodpressure',
            'cholestrol', 'fasting_bloodsugar', 'resting_ecg', 'maximum_heartrate_achieved', 
            'exercise_induced angina',
            'st_depression', 'slope', 'major_vessel_colored', 'thal','target']
In [12]:
df.head(5)
Out[12]:
id age sex study_location chest_pain_type resting_bloodpressure cholestrol fasting_bloodsugar resting_ecg maximum_heartrate_achieved exercise_induced angina st_depression slope major_vessel_colored thal target
0 1 63 Male Cleveland typical angina 145.0 233.0 True lv hypertrophy 150.0 False 2.3 downsloping 0.0 fixed defect 0
1 2 67 Male Cleveland asymptomatic 160.0 286.0 False lv hypertrophy 108.0 True 1.5 flat 3.0 normal 2
2 3 67 Male Cleveland asymptomatic 120.0 229.0 False lv hypertrophy 129.0 True 2.6 flat 2.0 reversable defect 1
3 4 37 Male Cleveland non-anginal 130.0 250.0 False normal 187.0 False 3.5 downsloping 0.0 normal 0
4 5 41 Female Cleveland atypical angina 130.0 204.0 False lv hypertrophy 172.0 False 1.4 upsloping 0.0 normal 0
In [13]:
df.describe()
Out[13]:
id age resting_bloodpressure cholestrol maximum_heartrate_achieved st_depression major_vessel_colored target
count 920.000000 920.000000 861.000000 890.000000 865.000000 858.000000 309.000000 920.000000
mean 460.500000 53.510870 132.132404 199.130337 137.545665 0.878788 0.676375 0.995652
std 265.725422 9.424685 19.066070 110.780810 25.926276 1.091226 0.935653 1.142693
min 1.000000 28.000000 0.000000 0.000000 60.000000 -2.600000 0.000000 0.000000
25% 230.750000 47.000000 120.000000 175.000000 120.000000 0.000000 0.000000 0.000000
50% 460.500000 54.000000 130.000000 223.000000 140.000000 0.500000 0.000000 1.000000
75% 690.250000 60.000000 140.000000 268.000000 157.000000 1.500000 1.000000 2.000000
max 920.000000 77.000000 200.000000 603.000000 202.000000 6.200000 3.000000 4.000000
In [14]:
df.describe(include=[np.object])
Out[14]:
sex study_location chest_pain_type fasting_bloodsugar resting_ecg exercise_induced angina slope thal
count 920 920 920 830 918 865 611 434
unique 2 4 4 2 3 2 3 3
top Male Cleveland asymptomatic False normal False flat normal
freq 726 304 496 692 551 528 345 196
In [15]:
df.dropna(inplace=True)
In [16]:
df.isnull().sum()
Out[16]:
id                            0
age                           0
sex                           0
study_location                0
chest_pain_type               0
resting_bloodpressure         0
cholestrol                    0
fasting_bloodsugar            0
resting_ecg                   0
maximum_heartrate_achieved    0
exercise_induced angina       0
st_depression                 0
slope                         0
major_vessel_colored          0
thal                          0
target                        0
dtype: int64
In [17]:
df.shape
Out[17]:
(299, 16)
In [18]:
df['target'].value_counts()
Out[18]:
0    160
1     56
2     35
3     35
4     13
Name: target, dtype: int64
In [19]:
plt.figure(figsize=(18,12))
plt.subplot(221)
df['sex'].value_counts().plot.pie(autopct = '%1.0f%%', colors = sns.color_palette('prism',5),
                                  startangle = 900, labels =['Male','Female'],
                                  wedgeprops = {'linewidth':2, 'edgecolor':'w'},
                                  explode = [.1,.1], shadow = True)
plt.title('Distribution of Gender')
plt.subplot(222)
ax = sns.distplot(df['age'], rug = True)
plt.title('Age wise distribution')
plt.show()
In [23]:
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.neighbors import KNeighborsClassifier
knn_clf = KNeighborsClassifier()
In [28]:
y = df['id'] 
X = df.drop(['id'],axis=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=30)
In [29]:
df
Out[29]:
id age sex study_location chest_pain_type resting_bloodpressure cholestrol fasting_bloodsugar resting_ecg maximum_heartrate_achieved exercise_induced angina st_depression slope major_vessel_colored thal target
0 1 63 Male Cleveland typical angina 145.0 233.0 True lv hypertrophy 150.0 False 2.3 downsloping 0.0 fixed defect 0
1 2 67 Male Cleveland asymptomatic 160.0 286.0 False lv hypertrophy 108.0 True 1.5 flat 3.0 normal 2
2 3 67 Male Cleveland asymptomatic 120.0 229.0 False lv hypertrophy 129.0 True 2.6 flat 2.0 reversable defect 1
3 4 37 Male Cleveland non-anginal 130.0 250.0 False normal 187.0 False 3.5 downsloping 0.0 normal 0
4 5 41 Female Cleveland atypical angina 130.0 204.0 False lv hypertrophy 172.0 False 1.4 upsloping 0.0 normal 0
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
299 300 68 Male Cleveland asymptomatic 144.0 193.0 True normal 141.0 False 3.4 flat 2.0 reversable defect 2
300 301 57 Male Cleveland asymptomatic 130.0 131.0 False normal 115.0 True 1.2 flat 1.0 reversable defect 3
301 302 57 Female Cleveland atypical angina 130.0 236.0 False lv hypertrophy 174.0 False 0.0 flat 1.0 normal 1
508 509 47 Male Hungary asymptomatic 150.0 226.0 False normal 98.0 True 1.5 flat 0.0 reversable defect 1
748 749 56 Male VA Long Beach asymptomatic 120.0 100.0 False normal 120.0 True 1.5 flat 0.0 reversable defect 1

299 rows × 16 columns

In [ ]: