10/17/24, 4:05 PM Assignment1

In [1]: #Pranav Kulkarni(T512004)

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

In [3]: dataFrame=pd.read_csv('heart.csv')

In [5]: dataFrame.shape

Out[5]: (303, 15)

In [7]: dataFrame.head()

Out[7]: Unnamed:
Age Sex ChestPain RestBP Chol Fbs RestECG MaxHR ExAng O
0

0 1 63 1 typical 145 233 1 2 150 0

1 2 67 1 asymptomatic 160 286 0 2 108 1

2 3 67 1 asymptomatic 120 229 0 2 129 1

3 4 37 1 nonanginal 130 250 0 0 187 0

4 5 41 0 nontypical 130 204 0 2 172 0

In [9]: dataFrame.tail()

Out[9]: Unnamed:
Age Sex ChestPain RestBP Chol Fbs RestECG MaxHR ExAng
0

298 299 45 1 typical 110 264 0 0 132 0

299 300 68 1 asymptomatic 144 193 1 0 141 0

300 301 57 1 asymptomatic 130 131 0 0 115 1

301 302 57 0 nontypical 130 236 0 2 174 0

302 303 38 1 nonanginal 138 175 0 0 173 0

In [11]: dataFrame=dataFrame.drop("Unnamed: 0",axis =1)

In [13]: dataFrame.dtypes

file:///C:/Users/Student/Downloads/Assignment1 (5).html 1/10

10/17/24, 4:05 PM Assignment1

Out[13]: Age int64

Sex int64
ChestPain object
RestBP int64
Chol int64
Fbs int64
RestECG int64
MaxHR int64
ExAng int64
Oldpeak float64
Slope int64
Ca float64
Thal object
AHD object
dtype: object

In [15]: dataFrame.describe()

Out[15]: Age Sex RestBP Chol Fbs RestECG Max

count 303.000000 303.000000 303.000000 303.000000 303.000000 303.000000 303.0000

mean 54.438944 0.679868 131.689769 246.693069 0.148515 0.990099 149.6072

std 9.038662 0.467299 17.599748 51.776918 0.356198 0.994971 22.8750

min 29.000000 0.000000 94.000000 126.000000 0.000000 0.000000 71.0000

25% 48.000000 0.000000 120.000000 211.000000 0.000000 0.000000 133.5000

50% 56.000000 1.000000 130.000000 241.000000 0.000000 1.000000 153.0000

75% 61.000000 1.000000 140.000000 275.000000 0.000000 2.000000 166.0000

max 77.000000 1.000000 200.000000 564.000000 1.000000 2.000000 202.0000

In [17]: dataFrame.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 303 entries, 0 to 302
Data columns (total 14 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Age 303 non-null int64
1 Sex 303 non-null int64
2 ChestPain 303 non-null object
3 RestBP 303 non-null int64
4 Chol 303 non-null int64
5 Fbs 303 non-null int64
6 RestECG 303 non-null int64
7 MaxHR 303 non-null int64
8 ExAng 303 non-null int64
9 Oldpeak 303 non-null float64
10 Slope 303 non-null int64
11 Ca 299 non-null float64
12 Thal 301 non-null object
13 AHD 303 non-null object
dtypes: float64(2), int64(9), object(3)
memory usage: 33.3+ KB

file:///C:/Users/Student/Downloads/Assignment1 (5).html 2/10

10/17/24, 4:05 PM Assignment1

In [19]: dataFrame.Ca.value_counts()

Out[19]: Ca
0.0 176
1.0 65
2.0 38
3.0 20
Name: count, dtype: int64

In [21]: dataFrame.Sex.value_counts()

Out[21]: Sex
1 206
0 97
Name: count, dtype: int64

In [23]: dataFrame.isnull()

Out[23]: Age Sex ChestPain RestBP Chol Fbs RestECG MaxHR ExAng Oldpeak S

0 False False False False False False False False False False

1 False False False False False False False False False False

2 False False False False False False False False False False

3 False False False False False False False False False False

4 False False False False False False False False False False

... ... ... ... ... ... ... ... ... ... ...

298 False False False False False False False False False False

299 False False False False False False False False False False

300 False False False False False False False False False False

301 False False False False False False False False False False

302 False False False False False False False False False False

303 rows × 14 columns

In [25]: dataFrame.isnull().sum()

file:///C:/Users/Student/Downloads/Assignment1 (5).html 3/10

10/17/24, 4:05 PM Assignment1

Out[25]: Age 0
Sex 0
ChestPain 0
RestBP 0
Chol 0
Fbs 0
RestECG 0
MaxHR 0
ExAng 0
Oldpeak 0
Slope 0
Ca 4
Thal 2
AHD 0
dtype: int64

In [27]: dataFrame.Age.mean()

Out[27]: 54.43894389438944

In [29]: dataFrame.describe()

Out[29]: Age Sex RestBP Chol Fbs RestECG Max

count 303.000000 303.000000 303.000000 303.000000 303.000000 303.000000 303.0000

mean 54.438944 0.679868 131.689769 246.693069 0.148515 0.990099 149.6072

std 9.038662 0.467299 17.599748 51.776918 0.356198 0.994971 22.8750

min 29.000000 0.000000 94.000000 126.000000 0.000000 0.000000 71.0000

25% 48.000000 0.000000 120.000000 211.000000 0.000000 0.000000 133.5000

50% 56.000000 1.000000 130.000000 241.000000 0.000000 1.000000 153.0000

75% 61.000000 1.000000 140.000000 275.000000 0.000000 2.000000 166.0000

max 77.000000 1.000000 200.000000 564.000000 1.000000 2.000000 202.0000

In [31]: dataFrame["Age"].mean(axis=0)

Out[31]: 54.43894389438944

In [33]: var=dataFrame.loc[:,['Age','Sex','ChestPain','RestBP','Chol']]

In [35]: var

file:///C:/Users/Student/Downloads/Assignment1 (5).html 4/10

10/17/24, 4:05 PM Assignment1

Out[35]: Age Sex ChestPain RestBP Chol

0 63 1 typical 145 233

1 67 1 asymptomatic 160 286

2 67 1 asymptomatic 120 229

3 37 1 nonanginal 130 250

4 41 0 nontypical 130 204

... ... ... ... ... ...

298 45 1 typical 110 264

299 68 1 asymptomatic 144 193

300 57 1 asymptomatic 130 131

301 57 0 nontypical 130 236

302 38 1 nonanginal 138 175

303 rows × 5 columns

In [37]: from sklearn.model_selection import train_test_split

X_train, X_test = train_test_split(var, test_size = 0.25, random_state = 42)

X_train.shape, X_test.shape

Out[37]: ((227, 5), (76, 5))

In [39]: tp=90
fp=11
fn=19
tn=40
acc=(tp+tn)/(tp+fp+fn+tn)
pre=tp/(tp+fp)
rec=tp/(tp+fn)
print("Accuracy is : {}".format(acc))
print("Precision is : {}".format(pre))
print("Recall is : {}".format(rec))
print("F1-Score is : {}".format((2*pre*rec)/(pre+rec)))

Accuracy is : 0.8125
Precision is : 0.8910891089108911
Recall is : 0.8256880733944955
F1-Score is : 0.8571428571428572

In [43]: dataFrame.plot();

file:///C:/Users/Student/Downloads/Assignment1 (5).html 5/10

10/17/24, 4:05 PM Assignment1

In [45]: dataFrame.hist(bins = 10,figsize = (15,11));

In [47]: sns.pairplot(var);

file:///C:/Users/Student/Downloads/Assignment1 (5).html 6/10

10/17/24, 4:05 PM Assignment1

In [49]: labels=['Male','Female']
dataFrame.Sex.value_counts().plot(kind= "pie",labels =labels,startangle=90,shado
explode=(0,0),autopct='%1.1f%%' );

file:///C:/Users/Student/Downloads/Assignment1 (5).html 7/10

10/17/24, 4:05 PM Assignment1

In [51]: plt.hist(dataFrame["Age"],bins=15,label="Age Count")

plt.title("Age Histogram")
plt.xlabel("Age range")
plt.ylabel("Count according to Age")
plt.legend(loc="upper left");

In [53]: sns.barplot(x = "Slope", y = "Age", hue = "Sex", data = dataFrame)

plt.title("Slope Group - Count Bar Plot Grouped by Sex")

file:///C:/Users/Student/Downloads/Assignment1 (5).html 8/10

10/17/24, 4:05 PM Assignment1

plt.show()

In [55]: sns.barplot(x = "Ca", y = "Chol", hue = "Slope", data = dataFrame)

plt.title("Ca Group - Count Bar Plot Grouped by Slope")
plt.show()

file:///C:/Users/Student/Downloads/Assignment1 (5).html 9/10

10/17/24, 4:05 PM Assignment1

In [57]: plt.scatter(dataFrame["RestBP"],dataFrame["Age"],label="BP level according to Ag

plt.title("BP vs Age Scatterplot")
plt.xlabel("Rest BP level")
plt.ylabel("Age")
plt.legend(loc="lower right");

In [ ]:

file:///C:/Users/Student/Downloads/Assignment1 (5).html 10/10