User_dataset

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn import metrics

data = {
'User ID': [1, 2, 3, 4, 5],
'Gender': ['Male', 'Female', 'Male', 'Female', 'Male'],
'Age': [25, 30, 35, 40, 45],
'Estimated Salary': [30000, 40000, 50000, 60000, 70000],
'Purchased': [0, 1, 1, 1, 0] # 0 for not purchased, 1 for purchased
}

df = pd.DataFrame(data)

x = np.array(df[['Estimated Salary']])
y = np.array(df['Purchased'])

x_train, x_test,y_train,y_test = train_test_split(x,y,test_size=0.25)

model = LogisticRegression()
model.fit(x_train,y_train)
y_pred = model.predict(x_test)

print("Accuracy " , metrics.accuracy_score(y_test,y_pred)*100,"%")
def getText(num):
if num == 0:
return "\tNo"
return "\tYes"

print("Salary\tActual\tPredicted")
for [salary ,actual, predicted] in zip(x_test,y_test,y_pred):
print(salary[0] ,getText(actual),getText(predicted))