Notes

import pandas as pd
import numpy as np
dataset = pd.read_csv('C:/Users/ACER/Downloads/employees.csv')
X = dataset.iloc[:,:-1].values
Y = dataset.iloc[:, -1].values
dataset.head()
#to display rows and columns
print(dataset.shape)
#checks dataset have null values or not
dataset.isnull().sum()
dataset.isna().sum()
#Encoding categorical data values
from sklearn.preprocessing import LabelEncoder
labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y)
#split dataset
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.20, random_state=1)
#Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
#perform different algorithms
#Using Logistic Regression Algorithm to the Training Set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state = 0)
classifier.fit(X_train, Y_train)
#Using KNeighborsClassifier Method of neighbors class to use Nearest Neighbor algorithm
from sklearn.neighbors import KNeighborsClassifier
classifier = KNeighborsClassifier(n_neighbors = 5, metric = 'minkowski', p = 2)
classifier.fit(X_train, Y_train)
#Using SVC method of svm class to use Support Vector Machine Algorithm
from sklearn.svm import SVC
classifier = SVC(kernel = 'linear', random_state = 0)
classifier.fit(X_train, Y_train)
#Using SVC method of svm class to use Kernel SVM Algorithm
from sklearn.svm import SVC
classifier = SVC(kernel = 'rbf', random_state = 0)
classifier.fit(X_train, Y_train)
#Using GaussianNB method of naïve_bayes class to use Naïve Bayes Algorithm
from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
classifier.fit(X_train, Y_train)
#Using DecisionTreeClassifier of tree class to use Decision Tree Algorithm
from sklearn.tree import DecisionTreeClassifier
classifier = DecisionTreeClassifier(criterion = 'entropy', random_state = 0)
classifier.fit(X_train, Y_train)
#Using RandomForestClassifier method of ensemble class to use Random Forest Classification
algorithm
from sklearn.ensemble import RandomForestClassifier
classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 0)
classifier.fit(X_train, Y_train)
#check accuracy of each algorithm
Y_pred = classifier.predict(X_test)
#create confusion matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(Y_test, Y_pred)
c = print(cm[0, 0] + cm[1, 1])