Decision Tree in Machine Learning

Program 1

Machine Learning Dataset

import pandas as pd
import numpy as np


df_salary=df_salary=pd.read_csv("D://scikit_data/tree/salaries.csv")


df_salary.head()


df_salary.shape

df_salary.isnull().sum()


# Independed Columns
df_input=df_salary.drop('salary_more_then_100k',axis='columns')


df_input


#Depended Columns
df_output=df_salary['salary_more_then_100k']


df_output


from sklearn.preprocessing import LabelEncoder


lb_company=LabelEncoder()
lb_job=LabelEncoder()
lb_degree=LabelEncoder()


df_input['company_new']=lb_company.fit_transform(df_input['company'])

df_input


df_input['job_new']=lb_job.fit_transform(df_input['job'])
df_input['degree_new']=lb_job.fit_transform(df_input['degree'])


df_input


df_input.drop(['company','job','degree'],axis='columns')


df_input.drop('job_degree',axis='columns')


df_input


df_input1=df_input.drop(['company','job','degree','job_degree'],axis='columns')


df_input1


from sklearn import tree


model=tree.DecisionTreeClassifier()


model.fit(df_input1,df_output)


model.predict([[2,0,1]])


df_output


model.score(df_input1,df_output)


model.predict([[0,0,1]])