Logistic regression in Python

 Code1

(.env) [boris@fedora34server NUMPY]$ cat logistRegression.py

import pandas as pd

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LogisticRegression

from sklearn import metrics

import seaborn as sn

import matplotlib.pyplot as plt

candidates = {'gmat': [780,750,690,710,680,730,690,720,740,690,610,690,710,680,770,610,580,650,540,590,620,600,550,550,570,670,660,580,650,660,640,620,660,660,680,650,670,580,590,690],'gpa': [4,3.9,3.3,3.7,3.9,3.7,2.3,3.3,3.3,1.7,2.7,3.7,3.7,3.3,3.3,3,2.7,3.7,2.7,2.3,3.3,2,2.3,2.7,3,3.3,3.7,2.3,3.7,3.3,3,2.7,4,3.3,3.3,2.3,2.7,3.3,1.7,3.7],'work_experience': [3,4,3,5,4,6,1,4,5,1,3,5,6,4,3,1,4,6,2,3,2,1,4,1,2,6,4,2,6,5,1,2,4,6,5,1,2,1,4,5],'admitted': [1,1,0,1,0,1,0,1,1,0,0,1,1,0,1,0,0,1,0,0,1,0,0,0,0,1,1,0,1,1,0,0,1,1,1,0,0,0,0,1]

 }

df = pd.DataFrame(candidates,columns= ['gmat', 'gpa','work_experience','admitted'])

X = df[['gmat', 'gpa','work_experience']]

y = df['admitted']

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25,random_state=0)

logistic_regression= LogisticRegression()

logistic_regression.fit(X_train,y_train)

y_pred=logistic_regression.predict(X_test)

confusion_matrix = pd.crosstab(y_test, y_pred, rownames=['Actual'], colnames=['Predicted'])

sn.heatmap(confusion_matrix, annot=True)

print('Accuracy: ',metrics.accuracy_score(y_test, y_pred))

plt.show()

===============

Code2

(.env) [boris@fedora34server NUMPY]$ cat logistRegression1.py

import pandas as pd

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LogisticRegression

candidates = {'gmat': [780,750,690,710,680,730,690,720,740,690,610,690,710,680,770,610,580,650,540,590,620,600,550,550,570,670,660,580,650,660,640,620,660,660,680,650,670,580,590,690],'gpa': [4,3.9,3.3,3.7,3.9,3.7,2.3,3.3,3.3,1.7,2.7,3.7,3.7,3.3,3.3,3,2.7,3.7,2.7,2.3,3.3,2,2.3,2.7,3,3.3,3.7,2.3,3.7,3.3,3,2.7,4,3.3,3.3,2.3,2.7,3.3,1.7,3.7],'work_experience': [3,4,3,5,4,6,1,4,5,1,3,5,6,4,3,1,4,6,2,3,2,1,4,1,2,6,4,2,6,5,1,2,4,6,5,1,2,1,4,5],'admitted': [1,1,0,1,0,1,0,1,1,0,0,1,1,0,1,0,0,1,0,0,1,0,0,0,0,1,1,0,1,1,0,0,1,1,1,0,0,0,0,1]

              }

df = pd.DataFrame(candidates,columns= ['gmat', 'gpa','work_experience','admitted'])

X = df[['gmat', 'gpa','work_experience']]

y = df['admitted']  

#train is based on 75% of the dataset, test is based on 25% of dataset

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25,random_state=0)  

logistic_regression= LogisticRegression()

logistic_regression.fit(X_train,y_train)

y_pred=logistic_regression.predict(X_test)

print (X_test) #test dataset

print (y_pred) #predicted values

==============

Code3

(.env) [boris@fedora34server NUMPY]$ cat logistRegression2.py

import pandas as pd

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LogisticRegression

candidates = {'gmat': [780,750,690,710,680,730,690,720,740,690,610,690,710,680,770,610,580,650,540,590,620,600,550,550,570,670,660,580,650,660,640,620,660,660,680,650,670,580,590,690],'gpa': [4,3.9,3.3,3.7,3.9,3.7,2.3,3.3,3.3,1.7,2.7,3.7,3.7,3.3,3.3,3,2.7,3.7,2.7,2.3,3.3,2,2.3,2.7,3,3.3,3.7,2.3,3.7,3.3,3,2.7,4,3.3,3.3,2.3,2.7,3.3,1.7,3.7],'work_experience': [3,4,3,5,4,6,1,4,5,1,3,5,6,4,3,1,4,6,2,3,2,1,4,1,2,6,4,2,6,5,1,2,4,6,5,1,2,1,4,5],'admitted': [1,1,0,1,0,1,0,1,1,0,0,1,1,0,1,0,0,1,0,0,1,0,0,0,0,1,1,0,1,1,0,0,1,1,1,0,0,0,0,1]

              }

df = pd.DataFrame(candidates,columns= ['gmat', 'gpa','work_experience','admitted'])

X = df[['gmat', 'gpa','work_experience']]

y = df['admitted']

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.25,random_state=0)  #in this case, you may choose to set the test_size=0. You should get the same prediction here

logistic_regression= LogisticRegression()

logistic_regression.fit(X_train,y_train)

new_candidates = {'gmat': [590,740,680,610,710],

                  'gpa': [2,3.7,3.3,2.3,3],

                  'work_experience': [3,4,6,1,5]

                  }

df2 = pd.DataFrame(new_candidates,columns= ['gmat', 'gpa','work_experience'])

y_pred=logistic_regression.predict(df2)

print (df2)

print (y_pred)