Machine Learning Project – Titanic Movie in Decision Tree Part 1

Program 1

Titanic Dataset

# Libraries
import pandas as pd 
import numpy as np
from sklearn import tree
from sklearn.preprocessing import LabelEncoder



df_titanic=pd.read_csv("D://scikit_data/titanicData/titanic.csv")


df_titanic


df_titanic.shape


df_titanic.info()


df_titanic.isnull().sum()


df_titanic=df_titanic.dropna()


df_titanic.isnull().sum()


df_titanic.shape


df_titanic.head()


# Encoding
le=LabelEncoder()
df_titanic['Sex_new']=le.fit_transform(df_titanic['Sex'])


df_titanic


df_titanic=df_titanic.drop('Sex',axis='columns')


df_titanic


# Independed variables
df_input=df_titanic.drop('Survived',axis='columns')


df_input


df_output=df_titanic.drop(['Pclass','Age','Fare','Sex_new'],axis='columns')


df_output

# Model Creation
model=tree.DecisionTreeClassifier()


type(model)


# Training of Model
model.fit(df_input,df_output)


model.predict([[1,0,38,71.2833]])


model.predict([[3,1,35,8.05]])


model.predict([[2,1,23,3.22]])


model.score(df_input,df_output)