How to Write Summary of a Research Paper

Paper Summary should contain the following points:

1. What problem author’s solved?

2. What are the motivations for that problem?

3. Why is it important to solve this problem?

4. What challenges did the author face to solve this problem?

5. Author's contribution in that paper or which method they have used to solve that problem?

6. How did authors validate their solution? 

7. How did the authors do the experiment?

8. What are the limitations of work?

Support Vector Machine in Python

At first download the Heart Disease Dataset from Kaggle:  https://www.kaggle.com/ronitf/heart-disease-uci.  Following, you should put the dataset in google drive. Then Using Google Colab you can run the following Support Vector Machine code:

!pip install -U -q PyDrive 

from pydrive.auth import GoogleAuth 

from pydrive.drive import GoogleDrive 

from google.colab import auth 

from oauth2client.client import GoogleCredentials 

# Authenticate and create the PyDrive client. 

auth.authenticate_user() 

gauth = GoogleAuth() 

gauth.credentials = GoogleCredentials.get_application_default() 

drive = GoogleDrive(gauth)

link =

'https://drive.google.com/file/d/1OglM8GvGIiVMMUXAchljXc86RtOq9K02

/view?usp=sharing'

import pandas as pd 

import numpy as np

# to get the id part of the file 

id = link.split("/")[-2] 

downloaded = drive.CreateFile({'id':id}) 

downloaded.GetContentFile('heart.csv') 

df = pd.read_csv('heart.csv') 

X = df.drop('target', axis=1)

y = df['target']

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y,

 test_size = 0.30)

from sklearn.svm import SVC

svclassifier = SVC(kernel='linear')

svclassifier.fit(X_train, y_train)

y_pred = svclassifier.predict(X_test)

from sklearn.metrics import confusion_matrix, classification_report

print(confusion_matrix(y_test,y_pred))

print(classification_report(y_test,y_pred))

from sklearn import metrics

print("Accuracy:",

metrics.accuracy_score(y_test, y_pred))

print("Precision:",

metrics.precision_score(y_test, y_pred))

print("Recall:",

metrics.recall_score(y_test, y_pred))

print("F1 Score:",metrics.f1_score(y_test, y_pred))

print('Mean Absolute Error:',

 metrics.mean_absolute_error(y_test, y_pred))

print('Mean Squared Error:', 

metrics.mean_squared_error(y_test, y_pred))

print('Root Mean Squared Error:', 

np.sqrt(metrics.mean_squared_error(y_test, y_pred)))

Output:

Python Custom Module Create

 

Let's say we want to create our own module which have some functions like add, sub, mult, and div.

1st step:

Let's create arithmetic.ipynb file :

Code: 

def add(n1, n2):

    return n1 + n2

def sub(n1, n2):

    return n1 - n2

def mult(n1, n2):

    return n1 * n2

def div(n1, n2):

    return n1 / n2

Sample Image:

2nd Step:

Now, download as a .py file ( arithmetic.py) . Then create test.ipynb file:

As Google Colab run in another virtual machine instead of google drive we need to upload the arithmetic.py file in to Colab. So in test.ipynb we will write:

Code:

from google.colab import files

files.upload()

Then , upload the arithmetic.py file. 

3rd Step:  

After uploading, import your custom module arithmetic and call the function add(). Give two input numbers and see the addition result.

Code:

import arithmetic as ar

ar.add(5,6) 

Sample Image: